diff --git a/antigen_scoring/notebooks/SARS_proteins_co-occurence.ipynb b/antigen_scoring/notebooks/SARS_proteins_co-occurence.ipynb index 6da03f9..71ae659 100644 --- a/antigen_scoring/notebooks/SARS_proteins_co-occurence.ipynb +++ b/antigen_scoring/notebooks/SARS_proteins_co-occurence.ipynb @@ -29,7 +29,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 46, "metadata": {}, "outputs": [], "source": [ @@ -43,7 +43,9 @@ "import os\n", "import json\n", "import numpy as np\n", - "import collections" + "import collections\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns" ] }, { @@ -55,7 +57,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 65, "metadata": {}, "outputs": [], "source": [ @@ -101,7 +103,15 @@ " \n", " result_dic = dict(c)\n", " \n", - " return result_dic" + " return result_dic\n", + "\n", + "#https://www.kaggle.com/rtatman/co-occurrence-matrix-plot-in-python\n", + "def df_co_occurrance(df, strain_group):\n", + " strains_df = df.copy() \n", + " for i in strain_group:\n", + " eval_match = df.SARS_COV.str.contains(i)\n", + " strains_df[i] = eval_match\n", + " return strains_df" ] }, { @@ -113,7 +123,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 3, "metadata": { "scrolled": true }, @@ -122,20 +132,20 @@ "name": "stderr", "output_type": "stream", "text": [ - "100%|██████████| 913/913 [00:03<00:00, 259.59it/s]\n", - "100%|██████████| 9123/9123 [01:08<00:00, 134.00it/s]\n", - "100%|██████████| 16959/16959 [10:24<00:00, 27.17it/s] \n", - "100%|██████████| 2358/2358 [05:57<00:00, 6.60it/s] \n" + "100%|██████████| 1342/1342 [00:04<00:00, 312.19it/s]\n", + "100%|██████████| 9365/9365 [01:39<00:00, 93.95it/s] \n", + "100%|██████████| 23152/23152 [17:13<00:00, 22.39it/s] \n", + "100%|██████████| 2377/2377 [00:08<00:00, 271.22it/s]\n" ] } ], "source": [ "#load all files\n", "dirs = [\n", - " 'data/scibitelabs/biorxiv_medrxiv/biorxiv_medrxiv/',\n", - " 'data/scibitelabs/comm_use_subset/comm_use_subset/',\n", - " 'data/scibitelabs/custom_license/custom_license/',\n", - " 'data/scibitelabs/noncomm_use_subset/noncomm_use_subset/' \n", + " 'data/cord-19_annotated/biorxiv_medrxiv/biorxiv_medrxiv/pdf_json/',\n", + " 'data/cord-19_annotated/comm_use_subset/comm_use_subset/pdf_json/',\n", + " 'data/cord-19_annotated/custom_license/custom_license/pdf_json/',\n", + " 'data/cord-19_annotated/noncomm_use_subset/noncomm_use_subset/pdf_json/'\n", "]\n", "\n", "files_stack = []\n", @@ -146,14 +156,14 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "100%|██████████| 4/4 [00:49<00:00, 9.42s/it]\n" + "100%|██████████| 4/4 [01:16<00:00, 15.12s/it]\n" ] } ], @@ -178,7 +188,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -196,14 +206,14 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "100%|██████████| 4/4 [01:27<00:00, 17.75s/it]\n" + "100%|██████████| 4/4 [02:51<00:00, 34.21s/it]\n" ] }, { @@ -352,7 +362,7 @@ "4 None None " ] }, - "execution_count": 27, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -408,7 +418,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -425,34 +435,7 @@ }, { "cell_type": "code", - "execution_count": 73, - "metadata": {}, - "outputs": [], - "source": [ - "def get_cat_vocab(cat):\n", - " df_cat = df[cat]\n", - " items = df_cat.dropna().tolist()\n", - "\n", - " vocab_list = []\n", - "\n", - " for element in items:\n", - " item = element.split(\",\")\n", - " for e in item:\n", - " vocab_list.append(e)\n", - " \n", - " c = collections.Counter()\n", - "\n", - " for word in vocab_list:\n", - " c[word] += 1\n", - " \n", - " result_dic = dict(c)\n", - " \n", - " return result_dic" - ] - }, - { - "cell_type": "code", - "execution_count": 74, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -461,132 +444,137 @@ }, { "cell_type": "code", - "execution_count": 75, + "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "{'retroviral integrase activity': 554,\n", - " \"retroviral 3' processing activity\": 24,\n", - " 'viral life cycle': 20547,\n", - " 'virion maturation': 355,\n", - " 'transmission of virus': 44020,\n", - " 'Severe acute respiratory syndrome coronavirus 2': 9419,\n", - " 'incubation period': 18425,\n", - " 'virus receptor activity': 2101,\n", - " 'viral release from host cell': 3860,\n", - " 'SARS coronavirus': 25300,\n", - " 'viral genome': 8785,\n", - " 'transport of virus': 878,\n", - " 'human-to-human viral transmission': 2505,\n", - " 'viral nucleocapsid': 4590,\n", - " 'virion attachment to host cell': 123,\n", - " 'modulation by virus of host morphology or physiology': 302,\n", - " 'viral process': 166,\n", - " 'viral membrane': 1398,\n", - " 'virion membrane': 1398,\n", - " 'virus maturation': 339,\n", - " 'viral strain': 4857,\n", - " 'viral gene expression': 717,\n", - " 'virion assembly': 1912,\n", - " 'SARS-CoV genome': 608,\n", - " 'viral transcription': 524,\n", - " 'SARS coronavirus NS-1': 2803,\n", - " 'SARS coronavirus Tor2': 254,\n", - " 'RNA viral genome': 312,\n", - " 'viral translation': 879,\n", - " '': 1313,\n", - " 'viral capsid': 1318,\n", - " 'viral entry into host cell': 490,\n", - " 'zoonotic viral transmission': 947,\n", - " 'Bat SARS-like coronavirus': 47,\n", - " 'viral envelope': 2827,\n", - " 'SARS coronavirus Urbani': 480,\n", - " 'SARS coronavirus CUHK-W1': 43,\n", - " 'SARS coronavirus MA15': 286,\n", - " 'SARS coronavirus ZS-C': 7,\n", - " 'SARS coronavirus Sino1-11': 10,\n", + "{'retroviral integrase activity': 666,\n", + " \"retroviral 3' processing activity\": 28,\n", + " 'viral life cycle': 26007,\n", + " 'virion maturation': 420,\n", + " 'Severe acute respiratory syndrome coronavirus 2': 15294,\n", + " 'SARS coronavirus': 32512,\n", + " '': 4365,\n", + " 'transmission of virus': 52614,\n", + " 'incubation period': 22303,\n", + " 'virus receptor activity': 2684,\n", + " 'viral release from host cell': 4666,\n", + " 'viral genome': 10635,\n", + " 'transport of virus': 1018,\n", + " 'viral nucleocapsid': 6408,\n", + " 'human-to-human viral transmission': 3031,\n", + " 'virion attachment to host cell': 1946,\n", + " 'modulation by virus of host morphology or physiology': 383,\n", + " 'viral process': 223,\n", + " 'viral membrane': 1797,\n", + " 'virion membrane': 330,\n", + " 'virus maturation': 402,\n", + " 'viral envelope': 3532,\n", + " 'viral gene expression': 911,\n", + " 'virion assembly': 2399,\n", + " 'SARS-CoV genome': 852,\n", + " 'viral transcription': 642,\n", + " 'viral capsid': 1646,\n", + " 'SARS coronavirus NS-1': 3402,\n", + " 'provirus': 567,\n", + " 'viral latency': 265,\n", + " 'viral strain': 6034,\n", + " 'SARS coronavirus Tor2': 343,\n", + " 'RNA viral genome': 381,\n", + " 'zoonotic viral transmission': 1124,\n", + " 'viral translation': 1103,\n", + " 'viral entry into host cell': 598,\n", + " 'Severe acute respiratory syndrome-related coronavirus': 84,\n", + " 'SARS coronavirus MA15': 380,\n", + " 'SARS coronavirus ZS-C': 8,\n", + " 'SARS coronavirus Sino1-11': 11,\n", + " 'SARS coronavirus GZ02': 71,\n", + " 'Bat SARS-like coronavirus': 58,\n", + " 'SARS coronavirus Urbani': 689,\n", + " 'SARS coronavirus BJ01': 230,\n", + " 'SARS coronavirus CUHK-W1': 50,\n", " 'ribosomal skipping': 2,\n", " 'viral budding from Golgi membrane': 1,\n", - " 'Severe acute respiratory syndrome-related coronavirus': 67,\n", - " 'viral DNA genome replication': 310,\n", - " 'viral genome replication': 399,\n", - " 'SARS coronavirus HSR 1': 27,\n", - " 'viral procapsid maturation': 12,\n", + " 'viral DNA genome replication': 366,\n", + " 'viral genome replication': 499,\n", + " 'SARS coronavirus TW3': 6,\n", + " 'SARS coronavirus TW2': 8,\n", + " 'SARS coronavirus HSR 1': 26,\n", + " 'viral procapsid maturation': 15,\n", + " 'viral budding': 819,\n", + " 'transformation of host cell by virus': 38,\n", " 'positive sense viral genome': 7,\n", - " 'holin activity': 17,\n", + " 'holin activity': 18,\n", " 'Bat SARS-like coronavirus WIV1': 1,\n", - " 'virus tail': 7,\n", - " 'ssRNA viral genome': 16,\n", - " 'cap snatching': 161,\n", - " 'viral budding': 656,\n", - " 'transmission period': 39,\n", - " 'SARS coronavirus ZJ01': 44,\n", - " 'SARS coronavirus GZ02': 60,\n", - " 'SARS coronavirus LC3': 1183,\n", - " 'uncoating of virus': 1120,\n", - " 'viral latency': 217,\n", - " 'SARS coronavirus Frankfurt 1': 122,\n", - " 'viral exocytosis': 4,\n", + " 'virus tail': 8,\n", + " 'ssRNA viral genome': 17,\n", + " 'cap snatching': 203,\n", + " 'transmission period': 50,\n", + " 'SARS coronavirus ZJ01': 52,\n", + " 'SARS coronavirus LC3': 1864,\n", + " 'uncoating of virus': 1330,\n", + " 'SARS coronavirus Frankfurt 1': 143,\n", + " 'viral exocytosis': 6,\n", " 'SARS bat coronavirus': 1,\n", - " 'viral outer capsid': 293,\n", - " 'icosahedral viral capsid': 13,\n", - " 'provirus': 498,\n", - " 'SARS coronavirus HC/SZ/61/03': 13,\n", - " 'maintenance of viral latency': 7,\n", - " 'exit of virus from host cell nucleus by nuclear egress': 24,\n", - " 'viral protein processing': 17,\n", + " 'viral outer capsid': 340,\n", + " 'SARS coronavirus HKU-39849': 134,\n", + " 'SARS coronavirus GDH-BJH01': 1,\n", + " 'capsomere': 249,\n", + " 'icosahedral viral capsid': 17,\n", + " 'viral tegument': 45,\n", + " 'SARS coronavirus HC/SZ/61/03': 19,\n", + " 'latency-replication decision': 85,\n", + " 'maintenance of viral latency': 9,\n", + " 'exit of virus from host cell nucleus by nuclear egress': 35,\n", + " 'viral protein processing': 21,\n", " 'superinfection exclusion': 38,\n", - " 'SARS coronavirus AS': 13,\n", - " 'establishment of viral latency': 3,\n", - " 'capsomere': 216,\n", - " 'viral inner capsid': 135,\n", - " 'transformation of host cell by virus': 34,\n", + " 'SARS coronavirus AS': 21,\n", + " 'establishment of viral latency': 4,\n", + " 'viral inner capsid': 143,\n", " 'negative sense viral genome': 7,\n", " 'SARS coronavirus CUHK-Su10': 20,\n", - " 'DNA viral genome': 58,\n", + " 'DNA viral genome': 69,\n", " 'SARS coronavirus TW5': 3,\n", " 'SARS coronavirus TW10': 2,\n", - " 'viral genome integration into host DNA': 9,\n", - " 'SARS coronavirus GZ50': 47,\n", - " 'latency-replication decision': 66,\n", - " 'dsRNA viral genome': 10,\n", - " 'retroviral strand transfer activity': 5,\n", - " 'viral RNA genome replication': 16,\n", - " 'SARS coronavirus LC5': 6,\n", - " 'viral capsid assembly': 13,\n", - " 'SARS coronavirus BJ04': 33,\n", - " 'SARS coronavirus GD03T0013': 23,\n", + " 'viral genome integration into host DNA': 11,\n", + " 'SARS coronavirus GZ50': 66,\n", + " 'dsRNA viral genome': 13,\n", + " 'retroviral strand transfer activity': 10,\n", + " 'viral RNA genome replication': 18,\n", + " 'SARS coronavirus LC5': 7,\n", + " 'viral capsid assembly': 20,\n", + " 'viral genome packaging': 20,\n", + " 'SARS coronavirus BJ04': 37,\n", + " 'SARS coronavirus GD03T0013': 30,\n", " 'establishment of integrated proviral latency': 14,\n", " 'non-segmented viral genome': 3,\n", - " 'viral mRNA cap methylation': 4,\n", - " 'SARS coronavirus GD01': 71,\n", - " 'SARS coronavirus HKU-39849': 113,\n", - " 'SARS coronavirus BJ02': 24,\n", - " 'SARS coronavirus ShanghaiQXC1': 6,\n", + " 'viral mRNA cap methylation': 6,\n", + " 'SARS coronavirus GD01': 88,\n", + " 'SARS coronavirus BJ02': 30,\n", + " 'SARS coronavirus ShanghaiQXC1': 7,\n", " 'SARS coronavirus GZ-C': 21,\n", " 'SARS coronavirus GZ-B': 6,\n", " 'SARS coronavirus CUHK-AG01': 9,\n", " 'SARS coronavirus HZS2-Fb': 4,\n", " 'SARS coronavirus LC1': 13,\n", - " 'SARS coronavirus Sin2748': 28,\n", - " 'SARS coronavirus PUMC01': 21,\n", + " 'SARS coronavirus Sin2748': 36,\n", + " 'SARS coronavirus PUMC01': 37,\n", " 'fusion of virus membrane with host plasma membrane': 1,\n", " 'receptor-mediated virion attachment to host cell': 2,\n", " 'viral DNA genome packaging': 2,\n", " 'nuclear capsid assembly': 2,\n", - " 'SARS coronavirus Sin2774': 32,\n", + " 'SARS coronavirus Sin2774': 50,\n", " 'SARS coronavirus Sin3725V': 1,\n", - " 'SARS coronavirus Sin0409': 1,\n", - " 'SARS coronavirus Sin_WNV': 1,\n", - " 'SARS coronavirus Sin2500': 27,\n", - " 'SARS coronavirus Sin2677': 23,\n", - " 'SARS coronavirus Sin2679': 20,\n", - " 'viral scaffold': 3,\n", - " 'induction by virus of host cell-cell fusion': 6,\n", - " 'viral tegument': 35,\n", - " 'non-lytic viral release': 11,\n", + " 'SARS coronavirus Sin0409': 9,\n", + " 'SARS coronavirus Sin_WNV': 3,\n", + " 'SARS coronavirus Sin2500': 36,\n", + " 'SARS coronavirus Sin2677': 32,\n", + " 'SARS coronavirus Sin2679': 26,\n", + " 'viral scaffold': 18,\n", + " 'induction by virus of host cell-cell fusion': 8,\n", + " 'non-lytic viral release': 12,\n", " 'SARS coronavirus Sin846': 3,\n", " 'SARS coronavirus Sin847': 4,\n", " 'SARS coronavirus Sin842': 5,\n", @@ -595,23 +583,22 @@ " 'SARS coronavirus Sin848': 9,\n", " 'SARS coronavirus Sin850': 5,\n", " 'SARS coronavirus Sin849': 11,\n", - " 'intracellular transport of virus': 14,\n", + " 'intracellular transport of virus': 17,\n", " 'early viral transcription': 4,\n", - " 'virion part': 13,\n", - " 'SARS coronavirus B012': 1,\n", - " 'SARS coronavirus LC2': 8,\n", + " 'virion part': 15,\n", + " 'SARS coronavirus B012': 2,\n", + " 'SARS coronavirus LC2': 9,\n", " 'SARS coronavirus ExoN1': 36,\n", - " 'SARS coronavirus C025': 15,\n", + " 'SARS coronavirus C025': 16,\n", " 'nosocomial viral transmission': 9,\n", " 'viral genome circularization': 1,\n", - " 'SARS coronavirus PUMC03': 7,\n", + " 'SARS coronavirus PUMC03': 8,\n", " 'segmented viral genome': 14,\n", " 'SARS coronavirus wtic-MB': 1,\n", - " 'SARS coronavirus TW2': 6,\n", - " 'SARS coronavirus GZ0402': 13,\n", + " 'SARS coronavirus GZ0402': 14,\n", " 'SARS coronavirus BJ182-12': 2,\n", " 'SARS coronavirus HSZ-Cb': 4,\n", - " 'SARS coronavirus A022': 2,\n", + " 'SARS coronavirus A022': 3,\n", " 'SARS coronavirus SZ1': 8,\n", " 'fusion of viral membrane with host outer nuclear membrane': 1,\n", " 'viral capsid secondary envelopment': 1,\n", @@ -619,62 +606,66 @@ " 'viral genome ejection through host cell envelope': 1,\n", " ' headful': 1,\n", " 'receptor-mediated endocytosis of virus by host cell': 2,\n", - " 'viral genome packaging': 13,\n", - " 'SARS coronavirus TW1': 58,\n", + " 'SARS coronavirus TW1': 77,\n", " 'SARS coronavirus Sin3408': 3,\n", " 'SARS coronavirus BJ302': 5,\n", - " 'SARS coronavirus WH20': 1,\n", - " 'SARS coronavirus SoD': 10,\n", - " 'SARS coronavirus ShanghaiQXC2': 5,\n", + " 'SARS coronavirus WH20': 8,\n", + " 'SARS coronavirus SoD': 11,\n", + " 'SARS coronavirus ShanghaiQXC2': 6,\n", " 'suppression by virus of host translation': 1,\n", - " 'SARS coronavirus BJ01': 174,\n", " 'SARS coronavirus TW4': 5,\n", " 'latent virus replication': 1,\n", " 'SARS coronavirus LC4': 5,\n", " 'multipartite viral genome': 4,\n", " 'cytolysis by virus of host cell': 1,\n", " 'viral penetration into host nucleus': 1,\n", + " 'SARS coronavirus BJ202': 19,\n", " 'single stranded viral RNA replication via double stranded DNA intermediate': 1,\n", - " 'SARS coronavirus BJ03': 22,\n", - " 'SARS coronavirus BJ202': 15,\n", " 'SARS coronavirus JMD': 1,\n", + " 'SARS coronavirus BJ03': 25,\n", + " 'viral transmission by vector': 1,\n", " 'SARS coronavirus ES191': 1,\n", " 'viral extrusion': 2,\n", + " 'SARS coronavirus Taiwan TC2': 3,\n", + " 'SARS coronavirus Taiwan TC3': 3,\n", + " 'SARS coronavirus Taiwan TC1': 5,\n", " 'viral budding from ER membrane': 1,\n", " 'evasion or tolerance by virus of host immune response': 1,\n", - " 'SARS coronavirus PUMC02': 7,\n", + " 'SARS coronavirus PUMC02': 8,\n", " 'viral head-tail joining': 1,\n", + " 'late viral transcription': 3,\n", + " 'viral budding from plasma membrane': 1,\n", " 'SARS coronavirus TWC2': 6,\n", " 'SARS coronavirus TWC3': 9,\n", - " 'SARS coronavirus Taiwan TC2': 1,\n", - " 'SARS coronavirus Taiwan TC3': 1,\n", - " 'SARS coronavirus Taiwan TC1': 3,\n", " 'SARS coronavirus ZMY 1': 15,\n", - " 'SARS coronavirus GZ43': 17,\n", + " 'SARS coronavirus GZ43': 18,\n", + " 'SARS coronavirus FRA': 1,\n", + " 'SARS coronavirus HGZ8L2': 3,\n", + " 'SARS coronavirus HGZ8L1-A': 5,\n", + " 'SARS coronavirus GZ0401': 3,\n", + " 'SARS coronavirus CUHK-AG02': 5,\n", + " 'SARS coronavirus CUHK-AG03': 5,\n", + " 'viral genome maturation': 1,\n", " 'SARS coronavirus SZ13': 7,\n", " 'SARS coronavirus CUHK-L2': 1,\n", " 'SARS coronavirus HSZ-A': 1,\n", " 'SARS coronavirus HKU-65806': 1,\n", " 'SARS coronavirus ZS-B': 4,\n", " 'SARS coronavirus TW6': 2,\n", - " 'SARS coronavirus TW3': 3,\n", " 'SARS coronavirus GD69': 6,\n", " 'SARS coronavirus TW11': 5,\n", - " 'SARS coronavirus HGZ8L1-A': 4,\n", " 'SARS coronavirus Sino3-11': 4,\n", - " 'SARS coronavirus CUHK-AG02': 5,\n", - " 'SARS coronavirus CUHK-AG03': 5,\n", " 'SARS coronavirus TW9': 1,\n", " 'SARS coronavirus TW8': 2,\n", " 'SARS coronavirus TW7': 1,\n", - " 'late viral transcription': 1,\n", - " 'viral genome maturation': 1,\n", " 'SARS coronavirus LLJ-2004': 2,\n", " 'SARS coronavirus GZ60': 11,\n", - " 'pore-mediated entry of viral genome into host cell': 1,\n", + " 'pore-mediated entry of viral genome into host cell': 2,\n", + " 'viral procapsid': 1,\n", + " 'BtRs-BetaCoV/YN2013': 1,\n", + " 'BtRs-BetaCoV/GX2013': 2,\n", " 'viral intermediate capsid': 11,\n", - " 'SARS coronavirus Rs_672/2006': 1,\n", - " 'SARS coronavirus GZ0401': 2,\n", + " 'SARS coronavirus Rs_672/2006': 2,\n", " 'SARS coronavirus HZS2-C': 3,\n", " 'SARS coronavirus HZS2-Fc': 3,\n", " 'SARS coronavirus GZ-A': 1,\n", @@ -683,41 +674,56 @@ " 'BtRf-BetaCoV/SX2013': 1,\n", " 'BtRf-BetaCoV/HeB2013': 1,\n", " 'ambisense viral genome': 1,\n", - " 'SARS coronavirus A030': 2,\n", - " 'SARS coronavirus A013': 1,\n", + " 'SARS coronavirus A030': 3,\n", + " 'SARS coronavirus A001': 4,\n", + " 'SARS coronavirus A013': 2,\n", + " 'bipartite viral genome': 1,\n", " 'viral RNA editing': 2,\n", " 'virion nucleoid': 2,\n", - " 'SARS coronavirus B039': 1,\n", + " 'SARS coronavirus B039': 2,\n", " 'SARS coronavirus PC4-227': 3,\n", " 'SARS coronavirus PC4-136': 2,\n", - " 'SARS coronavirus civet020': 2,\n", - " 'SARS coronavirus civet010': 1,\n", + " 'SARS coronavirus civet020': 3,\n", + " 'SARS coronavirus civet010': 2,\n", " 'SARS coronavirus PC4-13': 2,\n", " 'SARS coronavirus HSZ-Bc': 3,\n", " 'SARS coronavirus HSZ-Bb': 3,\n", " 'SARS coronavirus HSZ-Cc': 3,\n", - " 'viral transmission by vector': 1,\n", - " 'SARS coronavirus C028': 2,\n", - " 'SARS coronavirus A001': 1,\n", - " 'SARS coronavirus B024': 1,\n", + " 'SARS coronavirus C028': 3,\n", + " 'SARS coronavirus B024': 2,\n", " 'immortalization of host cell by virus': 2,\n", " 'SARS coronavirus civet014': 1,\n", " 'SARS coronavirus ZS-A': 4,\n", + " 'SARS coronavirus PC4-199': 1,\n", + " 'SARS coronavirus PC4-241': 1,\n", + " 'SARS coronavirus A031': 1,\n", + " 'SARS coronavirus A021': 1,\n", + " 'SARS coronavirus B033': 1,\n", + " 'SARS coronavirus B029': 1,\n", + " 'SARS coronavirus C014': 1,\n", + " 'SARS coronavirus PC4-205': 1,\n", + " 'SARS coronavirus C017': 1,\n", + " 'SARS coronavirus B040': 1,\n", + " 'SARS coronavirus C013': 1,\n", + " 'SARS coronavirus PC4-137': 1,\n", + " 'SARS coronavirus PC4-127': 1,\n", + " 'SARS coronavirus C018': 1,\n", + " 'SARS coronavirus C019': 1,\n", " 'viral translational readthrough': 1,\n", " 'SARS coronavirus TWC': 1,\n", " 'SARS coronavirus PC4-115': 1,\n", + " 'SARS coronavirus GD322': 1,\n", " 'SARS coronavirus SinP2': 6,\n", " 'SARS coronavirus Sin3408L': 4,\n", " 'SARS coronavirus SinP5': 2,\n", " 'SARS coronavirus SinP3': 4,\n", " 'SARS coronavirus SinP4': 2,\n", " 'SARS coronavirus HSZ2-A': 2,\n", - " 'SARS coronavirus HGZ8L2': 2,\n", " 'SARS coronavirus HZS2-E': 2,\n", " 'SARS coronavirus HZS2-D': 2}" ] }, - "execution_count": 75, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -728,18 +734,25 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": true - }, + "execution_count": 13, + "metadata": {}, "outputs": [], "source": [ - "sars = ['SARS coronavirus']\n", "covid_19 = ['Severe acute respiratory syndrome coronavirus 2']\n", "\n", - "sars_sin_strains = [\n", - " 'SARS coronavirus Sin2748',\n", - " 'SARS coronavirus Sin2774',\n", + " \n", + "sars_genome = [\n", + " 'SARS coronavirus',\n", + " 'SARS-CoV genome'\n", + "] \n", + " \n", + "sars_strain_sin = [\n", + " 'SARS coronavirus SinP2',\n", + " 'SARS coronavirus Sin3408L',\n", + " 'SARS coronavirus SinP5',\n", + " 'SARS coronavirus SinP3',\n", + " 'SARS coronavirus SinP4',\n", + " 'SARS coronavirus Sin3408',\n", " 'SARS coronavirus Sin3725V',\n", " 'SARS coronavirus Sin0409',\n", " 'SARS coronavirus Sin_WNV',\n", @@ -754,154 +767,214 @@ " 'SARS coronavirus Sin848',\n", " 'SARS coronavirus Sin850',\n", " 'SARS coronavirus Sin849',\n", - " 'SARS coronavirus Sin3408',\n", - " 'SARS coronavirus SinP2',\n", - " 'SARS coronavirus Sin3408L',\n", - " 'SARS coronavirus SinP5',\n", - " 'SARS coronavirus SinP3',\n", - " 'SARS coronavirus SinP4',\n", + " 'SARS coronavirus Sino3-11',\n", + " 'SARS coronavirus Sin2748',\n", + " 'SARS coronavirus Sin2774',\n", "]\n", "\n", - "sars_betacov_strains = [\n", - " 'BtRf-BetaCoV/JL2012',\n", - " 'BtRf-BetaCoV/SX2013',\n", - " 'BtRf-BetaCoV/HeB2013',\n", + "\n", + "sars_strain_a = [\n", + " 'SARS coronavirus A031',\n", + " 'SARS coronavirus A021',\n", + " 'SARS coronavirus A030',\n", + " 'SARS coronavirus A001',\n", + " 'SARS coronavirus A013',\n", + " 'SARS coronavirus A022',\n", "]\n", "\n", - "sars_tw_strains = [\n", + "\n", + "sars_strain_tw = [\n", " 'SARS coronavirus TW1',\n", - " 'SARS coronavirus TW2',\n", - " 'SARS coronavirus TW4',\n", - " 'SARS coronavirus TW5',\n", - " 'SARS coronavirus TW10',\n", - " 'SARS coronavirus TWC2',\n", - " 'SARS coronavirus TWC3',\n", + " 'SARS coronavirus TW11',\n", " 'SARS coronavirus TW9',\n", " 'SARS coronavirus TW8',\n", " 'SARS coronavirus TW7',\n", - " 'SARS coronavirus TW6',\n", " 'SARS coronavirus TW3',\n", + " 'SARS coronavirus TW2',\n", + " 'SARS coronavirus TW6',\n", " 'SARS coronavirus TW4',\n", + " 'SARS coronavirus TW5',\n", + " 'SARS coronavirus TW10',\n", "]\n", "\n", - "sars_shanghai_strains = [\n", - " 'SARS coronavirus ShanghaiQXC1',\n", - " 'SARS coronavirus ShanghaiQXC2',\n", + "\n", + "sars_strain_pc4 = [\n", + " 'SARS coronavirus PC4-199',\n", + " 'SARS coronavirus PC4-241',\n", + " 'SARS coronavirus PC4-115',\n", + " 'SARS coronavirus PC4-227',\n", + " 'SARS coronavirus PC4-136',\n", + " 'SARS coronavirus PC4-205',\n", + " 'SARS coronavirus PC4-13',\n", + " 'SARS coronavirus PC4-137',\n", + " 'SARS coronavirus PC4-127',\n", "]\n", "\n", - "sars_gz_strains = [\n", - " 'SARS coronavirus GZ02',\n", - " 'SARS coronavirus GZ-C',\n", - " 'SARS coronavirus GZ-B',\n", - " 'SARS coronavirus GZ50',\n", - " 'SARS coronavirus GZ0402',\n", + "\n", + "sars_strain_hzs2 = [\n", + " 'SARS coronavirus HZS2-C',\n", + " 'SARS coronavirus HZS2-Fc',\n", + " 'SARS coronavirus HSZ-Bc',\n", + " 'SARS coronavirus HSZ-Bb',\n", + " 'SARS coronavirus HSZ-Cc',\n", + " 'SARS coronavirus HSZ2-A',\n", + " 'SARS coronavirus HZS2-E',\n", + " 'SARS coronavirus HZS2-D',\n", + " 'SARS coronavirus HSZ-A',\n", + " 'SARS coronavirus HZS2-C',\n", + " 'SARS coronavirus HZS2-Fc',\n", "]\n", "\n", - "sars_bj_stains = [\n", - " 'SARS coronavirus BJ04',\n", + "\n", + "sars_strain_b = [\n", + " 'SARS coronavirus B033',\n", + " 'SARS coronavirus B029',\n", + " 'SARS coronavirus B040',\n", + " 'SARS coronavirus B039',\n", + " 'SARS coronavirus B024',\n", + " 'SARS coronavirus B012',\n", + "]\n", + "\n", + "sars_strain_btrf = [\n", + " 'BtRf-BetaCoV/JL2012',\n", + " 'BtRf-BetaCoV/SX2013',\n", + " 'BtRf-BetaCoV/HeB2013',\n", + " 'BtRs-BetaCoV/YN2013',\n", + " 'BtRs-BetaCoV/GX2013',\n", + " 'BtRf-BetaCoV/JL2012',\n", + " 'BtRf-BetaCoV/SX2013',\n", + " 'BtRf-BetaCoV/HeB2013',\n", + "] \n", + "\n", + "sars_strain_c = [\n", + " 'SARS coronavirus C014',\n", + " 'SARS coronavirus C017',\n", + " 'SARS coronavirus C013',\n", + " 'SARS coronavirus C018',\n", + " 'SARS coronavirus C019',\n", + " 'SARS coronavirus C028',\n", + " 'SARS coronavirus C025',\n", + "]\n", + "\n", + "sars_strain_bj = [\n", " 'SARS coronavirus BJ302',\n", - " 'SARS coronavirus BJ01',\n", - " 'SARS coronavirus BJ182-12',\n", - " 'SARS coronavirus BJ02',\n", " 'SARS coronavirus BJ03',\n", " 'SARS coronavirus BJ202',\n", + " 'SARS coronavirus BJ02',\n", + " 'SARS coronavirus BJ04',\n", + " 'SARS coronavirus BJ182-12',\n", + "]\n", + "\n", + "sars_strain_civet = [\n", + " 'SARS coronavirus civet014',\n", + " 'SARS coronavirus civet020',\n", + " 'SARS coronavirus civet010',\n", + "]\n", + "\n", + "sars_strain_hku = [\n", + " 'SARS coronavirus HKU-39849',\n", + " 'SARS coronavirus HKU-65806',\n", "]\n", "\n", - "sars_lc_stains = [\n", + "sars_strain_lc = [\n", + " 'SARS coronavirus LC4',\n", " 'SARS coronavirus LC3',\n", + " 'SARS coronavirus LC1',\n", " 'SARS coronavirus LC2',\n", " 'SARS coronavirus LC5',\n", - " 'SARS coronavirus LC1',\n", + " \n", "]\n", "\n", - "sars_other_strains = [\n", - " 'SARS coronavirus NS-1',\n", - " 'SARS coronavirus Tor2',\n", - " 'Bat SARS-like coronavirus',\n", - " 'SARS coronavirus Urbani',\n", - " 'SARS coronavirus CUHK-W1',\n", - " 'SARS coronavirus MA15',\n", - " 'SARS coronavirus ZS-C',\n", - " 'SARS coronavirus Sino1-11',\n", - " 'SARS coronavirus HSR 1',\n", - " 'Bat SARS-like coronavirus WIV1',\n", - " 'SARS coronavirus ZJ01',\n", + "sars_strain_twc = [\n", + " 'SARS coronavirus TWC',\n", + " 'SARS coronavirus TWC2',\n", + " 'SARS coronavirus TWC3',\n", + " 'SARS coronavirus Taiwan TC2',\n", + " 'SARS coronavirus Taiwan TC3',\n", + " 'SARS coronavirus Taiwan TC1',\n", + " \n", + "]\n", + "\n", + "\n", + "sars_strain_gz = [\n", + " 'SARS coronavirus GZ60',\n", + " 'SARS coronavirus GZ0401',\n", + " 'SARS coronavirus GZ43',\n", + " 'SARS coronavirus GZ-A',\n", + " 'SARS coronavirus GZ50',\n", + " 'SARS coronavirus GZ-C',\n", + " 'SARS coronavirus GZ-B',\n", + " 'SARS coronavirus GZ0402', \n", + "]\n", + "\n", + "sars_strain_frankfurt = [\n", " 'SARS coronavirus Frankfurt 1',\n", - " 'SARS coronavirus HC/SZ/61/03',\n", - " 'SARS coronavirus AS',\n", - " 'SARS coronavirus GD03T0013',\n", - " 'SARS coronavirus GD01': 71,\n", - " 'SARS coronavirus HKU-39849',\n", + " 'SARS coronavirus FRA',\n", + "]\n", + "\n", + "sars_strain_cuhk = [\n", + " 'SARS coronavirus CUHK-AG02',\n", + " 'SARS coronavirus CUHK-AG03',\n", + " 'SARS coronavirus CUHK-L2',\n", + " 'SARS coronavirus CUHK-Su10',\n", " 'SARS coronavirus CUHK-AG01',\n", - " 'SARS coronavirus HZS2-Fb',\n", + "]\n", + "\n", + "sars_strain_gd = [\n", + " 'SARS coronavirus GD03T0013',\n", + " 'SARS coronavirus GD01',\n", + " 'SARS coronavirus GD69',\n", + " 'SARS coronavirus GD322', \n", + "] \n", + "\n", + "\n", + "sars_strain_pumc = [\n", " 'SARS coronavirus PUMC01',\n", - " 'SARS coronavirus B012',\n", - " 'SARS coronavirus ExoN1',\n", - " 'SARS coronavirus C025',\n", " 'SARS coronavirus PUMC03',\n", - " 'SARS coronavirus wtic-MB',\n", - " 'SARS coronavirus HSZ-Cb',\n", - " 'SARS coronavirus A022',\n", - " 'SARS coronavirus SZ1',\n", + " 'SARS coronavirus PUMC02', \n", + "]\n", + "\n", + "sars_strain_zj = [\n", + " 'SARS coronavirus ZJ01', \n", + "]\n", + "\n", + "sars_strain_other = [\n", + " 'SARS coronavirus ZS-A',\n", " 'SARS coronavirus WH20',\n", " 'SARS coronavirus SoD',\n", - " 'SARS coronavirus BJ01': 174,\n", - " 'SARS coronavirus LC4': 5,\n", - " 'SARS coronavirus JMD': 1,\n", - " 'SARS coronavirus ES191': 1,\n", - " 'SARS coronavirus PUMC02': 7,\n", - " 'SARS coronavirus Taiwan TC2': 1,\n", - " 'SARS coronavirus Taiwan TC3': 1,\n", - " 'SARS coronavirus Taiwan TC1': 3,\n", - " 'SARS coronavirus ZMY 1': 15,\n", - " 'SARS coronavirus GZ43': 17,\n", - " 'SARS coronavirus SZ13': 7,\n", - " 'SARS coronavirus CUHK-L2': 1,\n", - " 'SARS coronavirus HSZ-A': 1,\n", - " 'SARS coronavirus HKU-65806': 1,\n", - " 'SARS coronavirus ZS-B': 4,\n", - " 'SARS coronavirus GD69': 6,\n", - " 'SARS coronavirus TW11': 5,\n", - " 'SARS coronavirus HGZ8L1-A': 4,\n", - " 'SARS coronavirus Sino3-11': 4,\n", - " 'SARS coronavirus CUHK-AG02': 5,\n", - " 'SARS coronavirus CUHK-AG03': 5,\n", - " 'SARS coronavirus LLJ-2004': 2,\n", - " 'SARS coronavirus GZ60': 11,\n", - " 'SARS coronavirus Rs_672/2006': 1,\n", - " 'SARS coronavirus GZ0401': 2,\n", - " 'SARS coronavirus HZS2-C': 3,\n", - " 'SARS coronavirus HZS2-Fc': 3,\n", - " 'SARS coronavirus GZ-A': 1,\n", - " 'SARS Coronavirus CDC#200301157': 2,\n", - " 'SARS coronavirus A030': 2,\n", - " 'SARS coronavirus A013': 1,\n", - " 'SARS coronavirus B039': 1,\n", - " 'SARS coronavirus PC4-227': 3,\n", - " 'SARS coronavirus PC4-136': 2,\n", - " 'SARS coronavirus civet020': 2,\n", - " 'SARS coronavirus civet010': 1,\n", - " 'SARS coronavirus PC4-13': 2,\n", - " 'SARS coronavirus HSZ-Bc': 3,\n", - " 'SARS coronavirus HSZ-Bb': 3,\n", - " 'SARS coronavirus HSZ-Cc': 3,\n", - " 'SARS coronavirus C028': 2,\n", - " 'SARS coronavirus A001': 1,\n", - " 'SARS coronavirus B024': 1,\n", - " 'SARS coronavirus civet014': 1,\n", - " 'SARS coronavirus ZS-A': 4,\n", - " 'SARS coronavirus TWC': 1,\n", - " 'SARS coronavirus PC4-115': 1,\n", - " 'SARS coronavirus HSZ2-A': 2,\n", - " 'SARS coronavirus HGZ8L2': 2,\n", - " 'SARS coronavirus HZS2-E': 2,\n", - " 'SARS coronavirus HZS2-D': 2\n", - "]" + " 'SARS coronavirus ShanghaiQXC1',\n", + " 'SARS coronavirus ShanghaiQXC2',\n", + " 'SARS coronavirus ExoN1',\n", + " 'SARS coronavirus JMD',\n", + " 'SARS coronavirus ES191',\n", + " 'SARS coronavirus ZMY 1',\n", + " 'SARS coronavirus HGZ8L2',\n", + " 'SARS coronavirus HGZ8L1-A',\n", + " 'SARS coronavirus HSZ-Cb',\n", + " 'SARS coronavirus HZS2-Fb', \n", + " 'SARS coronavirus ZS-B',\n", + " 'SARS coronavirus LLJ-2004',\n", + " 'SARS coronavirus Rs_672/2006',\n", + " 'SARS coronavirus Rs_672/2006',\n", + " 'SARS Coronavirus CDC#200301157',\n", + " 'SARS Coronavirus CDC#200301157'\n", + " 'SARS coronavirus HSR 1',\n", + " 'Bat SARS-like coronavirus WIV1',\n", + " 'SARS bat coronavirus',\n", + " 'SARS coronavirus GDH-BJH01',\n", + " 'SARS coronavirus HC/SZ/61/03',\n", + " 'SARS coronavirus AS',\n", + " 'SARS coronavirus wtic-MB',\n", + " 'SARS coronavirus SZ1',\n", + " 'SARS coronavirus SZ13',\n", + "]\n", + "\n", + "sars = sars_genome + sars_strain_sin + sars_strain_a + sars_strain_tw + sars_strain_pc4 + sars_strain_hzs2 + sars_strain_b + sars_strain_btrf + sars_strain_c + sars_strain_bj +sars_strain_civet + sars_strain_hku + sars_strain_lc + sars_strain_twc + sars_strain_gz + sars_strain_frankfurt + sars_strain_cuhk + sars_strain_gd + sars_strain_pumc + sars_strain_zj + sars_strain_other" ] }, { "cell_type": "code", - "execution_count": 77, + "execution_count": 14, "metadata": {}, "outputs": [], "source": [ @@ -910,30 +983,31 @@ }, { "cell_type": "code", - "execution_count": 78, + "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "{'SPIKE_WCPV': 18610,\n", - " 'R1AB_WCPV': 20633,\n", - " 'NCAP_WCPV': 11323,\n", - " 'R1A_WCPV': 10141,\n", - " 'NS8_WCPV': 558,\n", - " 'VME1_WCPV': 7109,\n", - " 'AP3A_WCPV': 582,\n", - " 'VEMP_WCPV': 5832,\n", - " 'A0A663DJA2_9BETC': 59,\n", - " 'ORF9B_WCPV': 182,\n", - " 'Y14_WCPV': 35,\n", - " 'NS6_WCPV': 498,\n", - " '': 933,\n", - " 'NS7B_WCPV': 132,\n", - " 'NS7A_WCPV': 113}" + "{'SPIKE_CVHSA': 10329,\n", + " 'NCAP_CVHSA': 4960,\n", + " 'VME1_CVHSA': 2230,\n", + " 'AP3A_CVHSA': 349,\n", + " 'VEMP_CVHSA': 2258,\n", + " 'Y14_CVHSA': 25,\n", + " 'ORF9B_CVHSA': 165,\n", + " 'R1A_CVHSA': 2993,\n", + " 'R1AB_CVHSA': 3095,\n", + " 'NS6_CVHSA': 255,\n", + " '': 21,\n", + " 'NS7B_CVHSA': 67,\n", + " 'NS3B_CVHSA': 90,\n", + " 'NS7A_CVHSA': 93,\n", + " 'NS8A_CVHSA': 33,\n", + " 'NS8B_CVHSA': 20}" ] }, - "execution_count": 78, + "execution_count": 15, "metadata": {}, "output_type": "execute_result" } @@ -944,7 +1018,7 @@ }, { "cell_type": "code", - "execution_count": 80, + "execution_count": 16, "metadata": {}, "outputs": [], "source": [ @@ -953,186 +1027,240 @@ }, { "cell_type": "code", - "execution_count": 82, + "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "{'PC4 and SFRS1 interacting protein 1': 24,\n", - " 'ATP/GTP binding protein like 1': 90,\n", - " 'double homeobox 4': 61,\n", - " 'tumor protein p53': 1734,\n", + "{'PC4 and SFRS1 interacting protein 1': 27,\n", + " 'ATP/GTP binding protein like 1': 144,\n", + " 'angiotensin I converting enzyme 2': 6575,\n", + " 'transmembrane protease': 1477,\n", + " ' serine 2': 823,\n", + " 'dipeptidyl peptidase 4': 2908,\n", + " 'ST6 beta-galactoside alpha-2': 135,\n", + " '6-sialyltransferase 1': 149,\n", + " 'cathepsin L': 844,\n", + " 'alanyl aminopeptidase': 1541,\n", + " ' membrane': 1541,\n", + " 'ST3 beta-galactoside alpha-2': 75,\n", + " '3-sialyltransferase 4': 16,\n", + " 'furin': 1381,\n", + " ' paired basic amino acid cleaving enzyme': 1381,\n", + " 'cathepsin B': 807,\n", + " ' serine 11D': 101,\n", + " 'DNA topoisomerase II alpha': 39,\n", + " 'achaete-scute family bHLH transcription factor 3': 3,\n", + " 'keratin 5': 62,\n", + " 'achaete-scute family bHLH transcription factor 1': 11,\n", + " 'G protein subunit gamma 13': 4,\n", + " 'TYRO protein tyrosine kinase binding protein': 157,\n", + " 'G protein subunit gamma 8': 3,\n", + " \"5\\\\'-nucleotidase ecto\": 91,\n", + " 'inositol 1': 103,\n", + " '4': 106,\n", + " '5-trisphosphate receptor type 3': 34,\n", + " 'forkhead box L1': 3,\n", + " 'transient receptor potential cation channel subfamily M member 5': 4,\n", + " 'cystic fibrosis transmembrane conductance regulator': 652,\n", + " 'carcinoembryonic antigen related cell adhesion molecule 1': 1048,\n", + " 'basigin (Ok blood group)': 484,\n", + " 'triggering receptor expressed on myeloid cells 2': 153,\n", + " 'SRY-box 11': 9,\n", + " 'C-X-C motif chemokine ligand 14': 38,\n", + " 'fatty acid binding protein 7': 9,\n", + " 'proteolipid protein 1': 263,\n", + " 'lumican': 5,\n", + " 'tyrosine kinase with immunoglobulin like and EGF like domains 1': 4,\n", + " 'kinase insert domain receptor': 187,\n", + " 'myosin light chain 9': 8,\n", + " 'maternally expressed 3 (non-protein coding)': 27,\n", + " 'cytochrome P450 family 2 subfamily J member 2': 1,\n", + " 'glutathione peroxidase 3': 16,\n", + " 'forkhead box I1': 1,\n", + " 'cytochrome P450 family 2 subfamily A member 13': 13,\n", + " 'SRY-box 9': 42,\n", + " 'tumor protein p63': 92,\n", + " 'double homeobox 4': 60,\n", + " 'tumor protein p53': 2009,\n", " 'structural maintenance of chromosomes flexible hinge domain containing 1': 4,\n", - " 'paired box 7': 15,\n", - " 'paired box 3': 11,\n", - " 'MDM2 proto-oncogene': 228,\n", - " 'tripartite motif containing 24': 21,\n", - " 'platelet derived growth factor receptor alpha': 100,\n", - " 'integrin subunit alpha 7': 11,\n", - " 'matrix metallopeptidase 8': 86,\n", - " 'fibroblast growth factor 2': 290,\n", - " 'angiotensin I converting enzyme 2': 4253,\n", - " 'furin': 1142,\n", - " ' paired basic amino acid cleaving enzyme': 1142,\n", - " 'CD4 molecule': 8998,\n", - " 'angiotensin I converting enzyme': 820,\n", - " 'C-reactive protein': 2924,\n", - " '': 2370,\n", - " 'nucleophosmin 1': 178,\n", - " 'exportin 1': 254,\n", - " 'heterogeneous nuclear ribonucleoprotein A1': 232,\n", - " 'nuclear factor kappa B subunit 1': 1763,\n", - " 'dipeptidyl peptidase 4': 2134,\n", - " 'inhibitor of nuclear factor kappa B kinase subunit beta': 231,\n", - " 'glycogen synthase kinase 3 beta': 164,\n", - " 'SMAD family member 3': 131,\n", - " 'poly(ADP-ribose) polymerase 1': 704,\n", - " 'estrogen receptor 1': 267,\n", + " 'paired box 7': 34,\n", + " 'paired box 3': 19,\n", + " 'MDM2 proto-oncogene': 277,\n", + " 'tripartite motif containing 24': 38,\n", + " 'platelet derived growth factor receptor alpha': 149,\n", + " 'integrin subunit alpha 7': 10,\n", + " 'matrix metallopeptidase 8': 115,\n", + " 'fibroblast growth factor 2': 380,\n", + " 'CD4 molecule': 11503,\n", + " 'angiotensin I converting enzyme': 1217,\n", + " 'C-reactive protein': 3620,\n", + " '': 2734,\n", + " 'mitochondrially encoded transcription terminator': 57,\n", + " 'nucleophosmin 1': 183,\n", + " 'exportin 1': 289,\n", + " 'heterogeneous nuclear ribonucleoprotein A1': 295,\n", + " 'nuclear factor kappa B subunit 1': 2146,\n", + " 'inhibitor of nuclear factor kappa B kinase subunit beta': 346,\n", + " 'glycogen synthase kinase 3 beta': 223,\n", + " 'SMAD family member 3': 196,\n", + " 'poly(ADP-ribose) polymerase 1': 907,\n", + " 'estrogen receptor 1': 321,\n", " 'eukaryotic translation initiation factor 3 subunit I': 29,\n", - " 'eukaryotic translation initiation factor 3 subunit E': 27,\n", - " 'eukaryotic translation initiation factor 3 subunit F': 67,\n", - " 'ribosomal protein L19': 17,\n", - " 'chromosome 11 open reading frame 74': 19,\n", - " 'solute carrier family 10 member 1': 86,\n", - " 'mechanistic target of rapamycin kinase': 851,\n", - " 'poly(A) binding protein cytoplasmic 1': 106,\n", - " 'BCL2 like 1': 374,\n", - " 'nuclear receptor subfamily 3 group C member 2': 28,\n", - " 'DNA topoisomerase II alpha': 33,\n", - " 'DNA topoisomerase II beta': 7,\n", - " 'podoplanin': 85,\n", - " 'Jun proto-oncogene': 405,\n", - " ' AP-1 transcription factor subunit': 736,\n", - " 'interleukin 6': 7185,\n", - " 'angiotensinogen': 861,\n", - " 'mitochondrial antiviral signaling protein': 1433,\n", - " 'poliovirus receptor': 128,\n", - " 'nectin cell adhesion molecule 2': 128,\n", - " 'apolipoprotein E': 380,\n", - " 'amyloid beta precursor protein': 556,\n", - " 'apolipoprotein A1': 126,\n", - " 'ATP binding cassette subfamily A member 7': 10,\n", - " 'CD33 molecule': 100,\n", - " 'reelin': 23,\n", - " 'galectin 3': 98,\n", - " 'interferon gamma': 9226,\n", - " 'interleukin 1 beta': 3638,\n", - " 'mannose receptor C-type 1': 163,\n", + " 'eukaryotic translation initiation factor 3 subunit E': 39,\n", + " 'eukaryotic translation initiation factor 3 subunit F': 83,\n", + " 'ribosomal protein L19': 18,\n", + " 'chromosome 11 open reading frame 74': 36,\n", + " 'solute carrier family 10 member 1': 96,\n", + " 'mechanistic target of rapamycin kinase': 1171,\n", + " 'poly(A) binding protein cytoplasmic 1': 126,\n", + " 'BCL2 like 1': 503,\n", + " 'nuclear receptor subfamily 3 group C member 2': 38,\n", + " 'DNA topoisomerase II beta': 10,\n", + " 'podoplanin': 109,\n", + " 'Jun proto-oncogene': 537,\n", + " ' AP-1 transcription factor subunit': 927,\n", + " 'interleukin 6': 8919,\n", + " 'coagulation factor II': 1321,\n", + " ' thrombin': 1321,\n", + " 'Purkinje cell protein 2': 58,\n", + " 'angiotensinogen': 1341,\n", + " 'mitochondrial antiviral signaling protein': 1821,\n", + " 'zinc finger protein 292': 2,\n", + " 'poliovirus receptor': 152,\n", + " 'nectin cell adhesion molecule 2': 143,\n", + " 'apolipoprotein E': 504,\n", + " 'amyloid beta precursor protein': 690,\n", + " 'apolipoprotein A1': 167,\n", + " 'ATP binding cassette subfamily A member 7': 11,\n", + " 'CD33 molecule': 128,\n", + " 'reelin': 25,\n", + " 'galectin 3': 128,\n", + " 'interferon gamma': 12162,\n", + " 'interleukin 1 beta': 4474,\n", + " 'mannose receptor C-type 1': 208,\n", " 'chitinase 3 like 2': 2,\n", - " 'chitinase 3 like 1': 41,\n", - " 'NLR family apoptosis inhibitory protein': 19,\n", - " 'NLR family pyrin domain containing 3': 456,\n", - " 'NLR family pyrin domain containing 1': 53,\n", - " 'retinoic acid receptor responder 2': 17,\n", - " 'retinoic acid receptor responder 3': 461,\n", + " 'chitinase 3 like 1': 68,\n", + " 'NLR family apoptosis inhibitory protein': 26,\n", + " 'NLR family pyrin domain containing 3': 559,\n", + " 'NLR family pyrin domain containing 1': 77,\n", + " 'retinoic acid receptor responder 2': 22,\n", + " 'retinoic acid receptor responder 3': 594,\n", " 'S100 calcium binding protein A4': 15,\n", - " 'S100 calcium binding protein A9': 158,\n", - " 'advanced glycosylation end-product specific receptor': 74,\n", - " 'toll like receptor 4': 2005,\n", - " 'S100 calcium binding protein A8': 85,\n", - " 'S100 calcium binding protein A12': 90,\n", - " 'S100 calcium binding protein B': 50,\n", - " 'toll like receptor 3': 1839,\n", - " 'S100 calcium binding protein A11': 10,\n", - " 'toll like receptor 2': 1331,\n", + " 'S100 calcium binding protein A9': 170,\n", + " 'advanced glycosylation end-product specific receptor': 114,\n", + " 'toll like receptor 4': 2591,\n", + " 'S100 calcium binding protein A8': 100,\n", + " 'S100 calcium binding protein A12': 94,\n", + " 'S100 calcium binding protein B': 52,\n", + " 'toll like receptor 3': 2490,\n", + " 'S100 calcium binding protein A11': 11,\n", + " 'toll like receptor 2': 1684,\n", " 'glucosamine-6-phosphate deaminase 1': 1,\n", - " 'interleukin 10': 4643,\n", - " 'chemokine (C-X-C motif) ligand 8': 3107,\n", - " 'interleukin 2 receptor subunit alpha': 1379,\n", - " 'tumor necrosis factor': 7835,\n", - " 'ectonucleoside triphosphate diphosphohydrolase 1': 52,\n", - " 'CD38 molecule': 209,\n", - " 'C-C motif chemokine receptor 6': 116,\n", - " 'C-C motif chemokine receptor 4': 135,\n", - " 'interleukin 17A': 1372,\n", - " 'major histocompatibility complex': 1561,\n", - " ' class I': 1099,\n", - " ' A': 671,\n", - " 'beta-secretase 1': 93,\n", - " 'albumin': 2423,\n", - " 'glutamic--pyruvic transaminase': 592,\n", - " 'mucin 4': 57,\n", - " ' cell surface associated': 310,\n", + " 'interleukin 10': 5834,\n", + " 'chemokine (C-X-C motif) ligand 8': 3893,\n", + " 'interleukin 2 receptor subunit alpha': 1653,\n", + " 'tumor necrosis factor': 9579,\n", + " 'ectonucleoside triphosphate diphosphohydrolase 1': 72,\n", + " 'CD38 molecule': 251,\n", + " 'C-C motif chemokine receptor 6': 166,\n", + " 'C-C motif chemokine receptor 4': 196,\n", + " 'interleukin 17A': 1762,\n", + " 'beta-secretase 1': 135,\n", + " 'albumin': 2802,\n", + " 'glutamic--pyruvic transaminase': 679,\n", + " 'mucin 4': 58,\n", + " ' cell surface associated': 405,\n", " 'negative regulator of reactive oxygen species': 3,\n", " 'immunoglobulin like domain containing receptor 1': 1,\n", - " 'poly(ADP-ribose) polymerase family member 14': 72,\n", + " 'poly(ADP-ribose) polymerase family member 14': 129,\n", " 'SEC22 homolog A': 1,\n", " ' vesicle trafficking protein': 1,\n", - " 'mucin 1': 202,\n", - " '6-phosphogluconolactonase': 26,\n", - " 'cytochrome c': 529,\n", - " ' somatic': 529,\n", - " 'potassium voltage-gated channel subfamily H member 2': 44,\n", - " \"5\\\\'-3\\\\' exoribonuclease 1\": 346,\n", - " 'SRY-box 9': 32,\n", + " 'mucin 1': 287,\n", + " 'protease': 305,\n", + " 'epithelial cell adhesion molecule': 144,\n", + " 'tumor associated calcium signal transducer 2': 5,\n", + " 'keratin 19': 30,\n", + " 'keratin 18': 95,\n", + " 'asialoglycoprotein receptor 1': 97,\n", + " 'hes family bHLH transcription factor 1': 28,\n", + " 'mucin 6': 5,\n", + " ' oligomeric mucus/gel-forming': 399,\n", + " 'cytochrome c': 637,\n", + " ' somatic': 637,\n", + " 'potassium voltage-gated channel subfamily H member 2': 58,\n", + " \"5\\\\'-3\\\\' exoribonuclease 1\": 547,\n", " 'SRY-box 15': 8,\n", " 'LIM domains containing 1': 48,\n", - " 'ribonuclease A family member 1': 576,\n", - " ' pancreatic': 576,\n", - " \"DIS3 like 3\\\\'-5\\\\' exoribonuclease 2\": 16,\n", - " 'islet amyloid polypeptide': 54,\n", - " 'interleukin 4': 3076,\n", - " 'CD86 molecule': 717,\n", - " 'colony stimulating factor 2': 1316,\n", - " 'surfactant protein A1': 85,\n", - " 'prion protein': 517,\n", - " 'growth arrest specific 6': 46,\n", - " 'annexin A1': 114,\n", - " 'zinc finger CCCH-type containing': 91,\n", - " ' antiviral 1': 91,\n", - " 'complement factor properdin': 165,\n", - " 'epidermal growth factor receptor': 1006,\n", - " 'nucleolin': 325,\n", - " 'neuroplastin': 4,\n", - " 'vimentin': 642,\n", - " 'hepatitis A virus cellular receptor 1': 77,\n", + " 'ribonuclease A family member 1': 702,\n", + " ' pancreatic': 702,\n", + " \"DIS3 like 3\\\\'-5\\\\' exoribonuclease 2\": 26,\n", + " 'SH2 domain containing 3C': 2161,\n", + " 'islet amyloid polypeptide': 69,\n", + " 'interleukin 4': 3815,\n", + " 'CD86 molecule': 928,\n", + " 'colony stimulating factor 2': 1632,\n", + " 'surfactant protein A1': 135,\n", + " 'prion protein': 600,\n", + " 'growth arrest specific 6': 65,\n", + " 'annexin A1': 118,\n", + " 'zinc finger CCCH-type containing': 118,\n", + " ' antiviral 1': 118,\n", + " 'complement factor properdin': 175,\n", + " 'epidermal growth factor receptor': 1229,\n", + " 'nucleolin': 372,\n", + " 'neuroplastin': 5,\n", + " 'vimentin': 719,\n", + " 'hepatitis A virus cellular receptor 1': 89,\n", " 'fermitin family member 2': 1,\n", - " 'bone marrow stromal cell antigen 2': 635,\n", - " 'transferrin': 756,\n", + " 'bone marrow stromal cell antigen 2': 764,\n", + " 'transferrin': 924,\n", " 'zyxin': 11,\n", - " 'endothelial cell adhesion molecule': 12,\n", + " 'endothelial cell adhesion molecule': 14,\n", " 'fermitin family member 3': 3,\n", - " 'PTEN induced putative kinase 1': 50,\n", - " 'parkin RBR E3 ubiquitin protein ligase': 10,\n", - " 'mitogen-activated protein kinase 3': 877,\n", - " 'eukaryotic translation elongation factor 1 alpha 1': 379,\n", - " 'dopa decarboxylase': 17,\n", - " 'mitofusin 2': 69,\n", - " 'OPA1': 37,\n", - " ' mitochondrial dynamin like GTPase': 37,\n", + " 'PTEN induced putative kinase 1': 78,\n", + " 'parkin RBR E3 ubiquitin protein ligase': 13,\n", + " 'mitogen-activated protein kinase 3': 1059,\n", + " 'eukaryotic translation elongation factor 1 alpha 1': 478,\n", + " 'dopa decarboxylase': 21,\n", + " 'mitofusin 2': 89,\n", + " 'OPA1': 43,\n", + " ' mitochondrial dynamin like GTPase': 43,\n", " 'ubiquinol-cytochrome c reductase core protein 1': 12,\n", - " 'coagulation factor XII': 361,\n", - " 'mitogen-activated protein kinase 1': 900,\n", - " 'GC': 182,\n", - " ' vitamin D binding protein': 182,\n", - " 'glycoprotein hormone alpha 2': 5,\n", + " 'coagulation factor XII': 431,\n", + " 'mitogen-activated protein kinase 1': 1099,\n", + " 'GC': 214,\n", + " ' vitamin D binding protein': 214,\n", + " 'glycoprotein hormone alpha 2': 6,\n", " 'alpha-N-acetylgalactosaminidase': 11,\n", - " 'MAF bZIP transcription factor': 62,\n", - " 'membrane palmitoylated protein 5': 43,\n", - " 'beta-2-microglobulin': 308,\n", - " 'myomesin 2': 1999,\n", - " 'caspase 9': 431,\n", - " 'mitogen-activated protein kinase 8': 1198,\n", - " 'caspase 8': 596,\n", - " 'caspase 3': 1463,\n", - " 'signal transducer and activator of transcription 1': 2118,\n", - " 'karyopherin subunit alpha 2': 71,\n", - " 'C-C motif chemokine ligand 5': 1514,\n", - " 'sperm antigen with calponin homology and coiled-coil domains 1': 664,\n", - " 'SH2 domain containing 3A': 1751,\n", - " 'SH2 domain containing 3C': 1734,\n", - " 'peptidylprolyl isomerase D': 81,\n", - " 'prohibitin 2': 41,\n", - " 'interferon regulatory factor 3': 2597,\n", - " 'RB transcriptional corepressor 1': 324,\n", - " 'methyltransferase like 3': 20,\n", + " 'MAF bZIP transcription factor': 80,\n", + " 'membrane palmitoylated protein 5': 58,\n", + " 'major histocompatibility complex': 2015,\n", + " ' class I': 1462,\n", + " ' A': 863,\n", + " 'beta-2-microglobulin': 376,\n", + " 'myomesin 2': 2662,\n", + " 'caspase 9': 548,\n", + " 'mitogen-activated protein kinase 8': 1449,\n", + " 'caspase 8': 725,\n", + " 'caspase 3': 1871,\n", + " 'signal transducer and activator of transcription 1': 2768,\n", + " 'karyopherin subunit alpha 2': 110,\n", + " 'C-C motif chemokine ligand 5': 1991,\n", + " 'SH2 domain containing 3A': 2237,\n", + " 'sperm antigen with calponin homology and coiled-coil domains 1': 824,\n", + " 'peptidylprolyl isomerase D': 121,\n", + " 'prohibitin 2': 52,\n", + " 'interferon regulatory factor 3': 3474,\n", + " 'RB transcriptional corepressor 1': 372,\n", + " 'methyltransferase like 3': 28,\n", " 'enkurin': 34,\n", " ' TRPC channel interacting protein': 34,\n", - " 'polycystin 1': 28,\n", - " ' transient receptor potential channel interacting': 29,\n", - " 'RAB8A': 39,\n", - " ' member RAS oncogene family': 1384,\n", + " 'polycystin 1': 29,\n", + " ' transient receptor potential channel interacting': 31,\n", + " 'RAB8A': 64,\n", + " ' member RAS oncogene family': 1748,\n", " 'coiled-coil domain containing 63': 1,\n", " 'cilia and flagella associated protein 57': 2,\n", " 'coiled-coil domain containing 113': 1,\n", @@ -1142,827 +1270,773 @@ " 'chromosome 4 open reading frame 22': 1,\n", " 'cilia and flagella associated protein 100': 1,\n", " 'coiled-coil domain containing 170': 1,\n", - " 'peptidylprolyl cis/trans isomerase': 96,\n", - " ' NIMA-interacting 1': 82,\n", + " 'peptidylprolyl cis/trans isomerase': 112,\n", + " ' NIMA-interacting 1': 98,\n", " 'sperm-tail PG-rich repeat containing 2': 1,\n", " 'zinc finger MYND-type containing 12': 1,\n", - " 'transient receptor potential cation channel subfamily M member 3': 7,\n", + " 'transient receptor potential cation channel subfamily M member 3': 8,\n", " 'Ellis van Creveld syndrome 2': 3,\n", " 'IQ motif containing E': 1,\n", " 'EF-hand calcium binding domain 7': 1,\n", - " 'arrestin beta 1': 61,\n", - " 'opioid receptor mu 1': 31,\n", - " 'arrestin beta 2': 20,\n", - " 'transient receptor potential cation channel subfamily M member 2': 22,\n", + " 'arrestin beta 1': 87,\n", + " 'opioid receptor mu 1': 38,\n", + " 'arrestin beta 2': 40,\n", + " 'transient receptor potential cation channel subfamily M member 2': 25,\n", " 'enkurin domain containing 1': 2,\n", - " 'polycystin 2': 44,\n", - " ' transient receptor potential cation channel': 79,\n", - " 'nodal growth differentiation factor': 7,\n", - " 'intraflagellar transport 81': 7,\n", - " 'tubulin beta class I': 211,\n", + " 'polycystin 2': 54,\n", + " ' transient receptor potential cation channel': 96,\n", + " 'nodal growth differentiation factor': 8,\n", + " 'intraflagellar transport 81': 9,\n", + " 'tubulin beta class I': 239,\n", " 'intraflagellar transport 172': 2,\n", " 'tektin 1': 1,\n", " 'intraflagellar transport 122': 1,\n", " 'intraflagellar transport 80': 1,\n", " 'intraflagellar transport 57': 1,\n", " 'sperm associated antigen 17': 1,\n", - " 'serpin family E member 2': 28,\n", + " 'serpin family E member 2': 34,\n", " 'HYDIN': 5,\n", " ' axonemal central pair apparatus protein': 5,\n", - " 'RAB28': 1,\n", - " 'NIMA related kinase 9': 2,\n", - " 'ubiquitin C': 66,\n", - " 'hydroxymethylbilane synthase': 81,\n", - " 'left-right determination factor 2': 15,\n", - " 'caspase 7': 248,\n", + " 'RAB28': 2,\n", + " 'NIMA related kinase 9': 3,\n", + " 'ubiquitin C': 68,\n", + " 'hydroxymethylbilane synthase': 85,\n", + " 'left-right determination factor 2': 16,\n", + " 'caspase 7': 325,\n", " 'solute carrier family 7 member 11': 13,\n", - " 'Pancreatic beta cell': 50,\n", - " ' agenesis of': 50,\n", - " 'activating transcription factor 4': 339,\n", - " 'nuclear factor': 347,\n", - " ' erythroid 2 like 2': 321,\n", - " 'GS homeobox 2': 3,\n", - " 'hypoxia inducible factor 1 alpha subunit': 221,\n", - " 'eukaryotic translation initiation factor 2 alpha kinase 4': 108,\n", - " 'ribosomal protein S6 kinase B1': 118,\n", - " 'glyceraldehyde-3-phosphate dehydrogenase': 2414,\n", - " 'eukaryotic translation initiation factor 2A': 955,\n", - " 'eukaryotic translation initiation factor 2-alpha kinase 3': 260,\n", - " 'endoplasmic reticulum to nucleus signaling 1': 661,\n", - " 'kelch like ECH associated protein 1': 67,\n", - " 'ferritin heavy chain 1': 36,\n", - " 'heme oxygenase 1': 111,\n", + " 'Pancreatic beta cell': 51,\n", + " ' agenesis of': 51,\n", + " 'activating transcription factor 4': 417,\n", + " 'nuclear factor': 416,\n", + " ' erythroid 2 like 2': 381,\n", + " 'GS homeobox 2': 4,\n", + " 'hypoxia inducible factor 1 alpha subunit': 335,\n", + " 'eukaryotic translation initiation factor 2 alpha kinase 4': 148,\n", + " 'ribosomal protein S6 kinase B1': 145,\n", + " 'glyceraldehyde-3-phosphate dehydrogenase': 2963,\n", + " 'eukaryotic translation initiation factor 2A': 1241,\n", + " 'eukaryotic translation initiation factor 2-alpha kinase 3': 327,\n", + " 'endoplasmic reticulum to nucleus signaling 1': 766,\n", + " 'kelch like ECH associated protein 1': 76,\n", + " 'ferritin heavy chain 1': 45,\n", + " 'heme oxygenase 1': 144,\n", " 'glutamate-cysteine ligase catalytic subunit': 16,\n", " 'glutamate-cysteine ligase modifier subunit': 8,\n", - " 'glutathione peroxidase 4': 6,\n", - " 'insulin': 1929,\n", - " 'vascular endothelial growth factor A': 102,\n", - " 'renin': 529,\n", - " 'spleen associated tyrosine kinase': 80,\n", - " 'AP2 associated kinase 1': 17,\n", - " 'Janus kinase 2': 259,\n", - " 'Janus kinase 1': 307,\n", - " 'galanin and GMAP prepropeptide': 87,\n", - " 'interferon beta 1': 4196,\n", - " \"2\\\\'-5\\\\'-oligoadenylate synthetase 2\": 215,\n", - " 'ISG15 ubiquitin-like modifier': 1491,\n", - " 'interferon induced protein with tetratricopeptide repeats 1': 774,\n", - " 'TANK binding kinase 1': 1019,\n", - " 'interferon regulatory factor 7': 1221,\n", - " 'inhibitor of nuclear factor kappa B kinase subunit epsilon': 471,\n", - " 'SRC proto-oncogene': 592,\n", - " ' non-receptor tyrosine kinase': 839,\n", - " 'tripartite motif containing 25': 424,\n", - " 'lin-28 homolog A': 25,\n", - " 'tripartite motif containing 71': 13,\n", - " 'ring finger protein 13': 6,\n", - " 'tripartite motif containing 56': 122,\n", + " 'glutathione peroxidase 4': 8,\n", + " 'suppression of tumorigenicity 14': 162,\n", + " 'transcription factor AP-2 epsilon': 1,\n", + " 'zinc finger DHHC-type containing 5': 8,\n", + " 'golgin A7': 2,\n", + " 'histone deacetylase 2': 62,\n", + " 'tRNA methyltransferase 1': 2,\n", + " 'NLR family member X1': 108,\n", + " 'TANK binding kinase 1': 1407,\n", + " 'inhibitor of nuclear factor kappa B kinase subunit epsilon': 726,\n", + " 'Nedd4 family interacting protein 2': 1,\n", + " 'conserved helix-loop-helix ubiquitous kinase': 417,\n", + " 'ring finger protein 41': 10,\n", + " 'mindbomb E3 ubiquitin protein ligase 1': 13,\n", + " 'F2R like trypsin receptor 1': 120,\n", + " 'TBK1 binding protein 1': 72,\n", + " 'tripartite motif containing 59': 3,\n", + " 'eukaryotic translation initiation factor 4A2': 624,\n", + " 'eukaryotic translation initiation factor 4A1': 428,\n", + " 'La ribonucleoprotein domain family member 1': 7,\n", + " 'G3BP stress granule assembly factor 1': 518,\n", + " 'G3BP stress granule assembly factor 2': 76,\n", + " 'eukaryotic translation initiation factor 2 alpha kinase 2': 501,\n", + " 'nucleoporin 98': 75,\n", + " 'ribonucleic acid export 1': 63,\n", + " 'zyg-11 family member B': 2,\n", + " ' cell cycle regulator': 6,\n", + " 'cullin 2': 28,\n", + " 'neural precursor cell expressed': 554,\n", + " ' developmentally down-regulated 8': 201,\n", + " 'bromodomain containing 2': 37,\n", + " 'bromodomain containing 4': 48,\n", + " 'histone cluster 2 H2A family member c': 11,\n", + " 'sigma non-opioid intracellular receptor 1': 62,\n", + " 'centrosomal protein 250': 9,\n", + " 'inosine monophosphate dehydrogenase 2': 16,\n", + " 'FK506 binding protein 7': 1,\n", + " 'peptidylprolyl isomerase A': 328,\n", + " 'mitochondrial ribosomal protein S27': 1,\n", + " 'mitochondrial ribosomal protein S25': 7,\n", + " 'mitochondrial ribosomal protein S2': 1,\n", + " 'mitochondrial ribosomal protein S5': 1,\n", + " 'solute carrier family 6 member 15': 3,\n", + " 'zyg-11 family member A': 1,\n", + " 'DAN domain BMP antagonist family member 5': 9,\n", + " 'cytokine receptor like factor 2': 18,\n", + " 'insulin': 2277,\n", + " 'vascular endothelial growth factor A': 146,\n", + " 'renin': 873,\n", + " 'spleen associated tyrosine kinase': 116,\n", + " 'AP2 associated kinase 1': 26,\n", + " 'Janus kinase 2': 319,\n", + " 'Janus kinase 1': 464,\n", + " 'galanin and GMAP prepropeptide': 53,\n", + " 'interferon beta 1': 5391,\n", + " \"2\\\\'-5\\\\'-oligoadenylate synthetase 2\": 278,\n", + " 'ISG15 ubiquitin-like modifier': 2024,\n", + " 'interferon induced protein with tetratricopeptide repeats 1': 953,\n", + " 'interferon regulatory factor 7': 1642,\n", + " 'SRC proto-oncogene': 708,\n", + " ' non-receptor tyrosine kinase': 989,\n", + " 'tripartite motif containing 25': 541,\n", + " 'lin-28 homolog A': 26,\n", + " 'tripartite motif containing 71': 14,\n", + " 'ring finger protein 13': 8,\n", + " 'tripartite motif containing 56': 136,\n", " 'microRNA let-7a-1': 27,\n", - " 'MYC proto-oncogene': 1700,\n", - " ' bHLH transcription factor': 1782,\n", - " 'ubiquitin conjugating enzyme E2 D3': 19,\n", - " 'ubiquitin like modifier activating enzyme 1': 42,\n", - " 'tripartite motif containing 5': 195,\n", - " 'tripartite motif containing 27': 21,\n", - " 'tripartite motif containing 21': 159,\n", - " 'tripartite motif containing 65': 13,\n", - " 'ring finger and CCCH-type domains 1': 9,\n", + " 'MYC proto-oncogene': 2028,\n", + " ' bHLH transcription factor': 2119,\n", + " 'ubiquitin conjugating enzyme E2 D3': 26,\n", + " 'ubiquitin like modifier activating enzyme 1': 69,\n", + " 'tripartite motif containing 5': 287,\n", + " 'tripartite motif containing 27': 22,\n", + " 'tripartite motif containing 21': 244,\n", + " 'tripartite motif containing 65': 14,\n", + " 'ring finger and CCCH-type domains 1': 10,\n", " 'mex-3 RNA binding family member B': 2,\n", - " 'DExD/H-box helicase 58': 721,\n", - " 'small nucleolar RNA': 69,\n", - " ' C/D box 1A': 13,\n", - " 'ubiquitin like modifier activating enzyme 7': 163,\n", - " 'DM1 protein kinase': 26,\n", - " 'DExH-box helicase 9': 117,\n", + " 'DExD/H-box helicase 58': 933,\n", + " 'small nucleolar RNA': 87,\n", + " ' C/D box 1A': 20,\n", + " 'ubiquitin like modifier activating enzyme 7': 249,\n", + " 'DM1 protein kinase': 39,\n", + " 'DExH-box helicase 9': 138,\n", " 'cubilin': 5,\n", " 'solute carrier family 13 member 3': 32,\n", " 'solute carrier family 22 member 8': 8,\n", - " 'interferon alpha 1': 2653,\n", - " 'interferon alpha 2': 2844,\n", + " 'deoxyribonuclease 1': 805,\n", + " 'C-C motif chemokine receptor 5 (gene/pseudogene)': 1903,\n", + " 'interferon alpha 1': 3665,\n", + " 'interferon alpha 2': 3888,\n", + " 'coagulation factor III': 489,\n", + " ' tissue factor': 489,\n", " 'centromere protein E': 10,\n", - " 'centromere protein F': 24,\n", + " 'centromere protein F': 26,\n", " 'dynactin subunit 1': 19,\n", - " 'centromere protein C': 7,\n", + " 'centromere protein C': 8,\n", " 'zwilch kinetochore protein': 14,\n", - " 'spindle apparatus coiled-coil protein 1': 9,\n", + " 'spindle apparatus coiled-coil protein 1': 10,\n", " 'BUB1 mitotic checkpoint serine/threonine kinase B': 16,\n", " 'DSN1 homolog': 4,\n", " ' MIS12 kinetochore complex component': 6,\n", " 'BUB3': 28,\n", " ' mitotic checkpoint protein': 28,\n", - " 'BUB1 mitotic checkpoint serine/threonine kinase': 36,\n", + " 'BUB1 mitotic checkpoint serine/threonine kinase': 35,\n", " 'kinetochore scaffold 1': 16,\n", " 'zw10 kinetochore protein': 1,\n", - " 'cyclin dependent kinase 1': 275,\n", + " 'cyclin dependent kinase 1': 301,\n", " 'NDC80': 6,\n", " ' kinetochore complex component': 21,\n", - " 'polo like kinase 1': 82,\n", + " 'polo like kinase 1': 122,\n", " 'inner centromere protein': 3,\n", " 'kinetochore associated 1': 17,\n", - " 'oligodendrocyte transcription factor 1': 10,\n", - " 'integrin subunit alpha M': 1155,\n", - " 'Fc fragment of IgG receptor IIIa': 729,\n", - " 'protein tyrosine phosphatase': 1565,\n", - " ' receptor type C': 1131,\n", - " 'Fc fragment of IgG receptor IIIb': 645,\n", - " 'CD19 molecule': 637,\n", - " 'CD14 molecule': 947,\n", - " 'carcinoembryonic antigen related cell adhesion molecule 8': 83,\n", - " 'ribonuclease A family member 3': 164,\n", - " 'ribonuclease A family member 2': 46,\n", - " 'granzyme B': 306,\n", - " 'elastase': 283,\n", - " ' neutrophil expressed': 283,\n", + " 'oligodendrocyte transcription factor 1': 30,\n", + " 'integrin subunit alpha M': 1484,\n", + " 'Fc fragment of IgG receptor IIIa': 902,\n", + " 'protein tyrosine phosphatase': 2136,\n", + " ' receptor type C': 1579,\n", + " 'Fc fragment of IgG receptor IIIb': 812,\n", + " 'CD19 molecule': 899,\n", + " 'CD14 molecule': 1230,\n", + " 'carcinoembryonic antigen related cell adhesion molecule 8': 99,\n", + " 'ribonuclease A family member 3': 222,\n", + " 'ribonuclease A family member 2': 61,\n", + " 'granzyme B': 419,\n", + " 'elastase': 322,\n", + " ' neutrophil expressed': 322,\n", " 'mitochondrial methionyl-tRNA formyltransferase': 1,\n", " 'RNA binding motif protein 47': 2,\n", - " 'STEAP3 metalloreductase': 1,\n", + " 'STEAP3 metalloreductase': 2,\n", " 'serpin family B member 13': 2,\n", " 'solute carrier family 44 member 1': 9,\n", " 'IQ motif containing GTPase activating protein 3': 1,\n", - " 'GABA type A receptor-associated protein': 51,\n", - " 'leukotriene B4 receptor': 36,\n", - " 'ribosomal protein L6': 1,\n", - " 'placenta specific 8': 9,\n", + " 'GABA type A receptor-associated protein': 88,\n", + " 'leukotriene B4 receptor': 38,\n", + " 'ribosomal protein L6': 2,\n", + " 'placenta specific 8': 10,\n", " 'nicastrin': 13,\n", " 'helicase like transcription factor': 3,\n", " 'methyltransferase like 7B': 1,\n", - " 'glucuronidase beta': 118,\n", - " 'membrane palmitoylated protein 1': 4,\n", - " 'STN1': 7,\n", - " ' CST complex subunit': 7,\n", + " 'glucuronidase beta': 142,\n", + " 'membrane palmitoylated protein 1': 6,\n", + " 'STN1': 8,\n", + " ' CST complex subunit': 8,\n", " 'serpin family B member 1': 7,\n", - " 'Sad1 and UNC84 domain containing 1': 3,\n", - " 'serpin family B member 2': 6,\n", + " 'Sad1 and UNC84 domain containing 1': 2,\n", + " 'serpin family B member 2': 7,\n", " 'zinc finger protein 185 with LIM domain': 1,\n", " 'Ral GTPase activating protein catalytic alpha subunit 1': 3,\n", " 'transmembrane protein 50A': 1,\n", - " 'lysozyme': 26,\n", + " 'lysozyme': 29,\n", " 'laccase (multicopper oxidoreductase) domain containing 1': 2,\n", - " 'Ras like without CAAX 1': 2,\n", - " 'solute carrier family 7 member 6': 4,\n", - " 'versican': 34,\n", + " 'Ras like without CAAX 1': 3,\n", + " 'solute carrier family 7 member 6': 6,\n", + " 'versican': 37,\n", " 'G protein subunit alpha q': 9,\n", " 'ninjurin 1': 14,\n", - " 'integrin subunit alpha 5': 56,\n", + " 'integrin subunit alpha 5': 66,\n", " 'late endosomal/lysosomal adaptor': 8,\n", " ' MAPK and MTOR activator 4': 1,\n", - " 'RAD9 checkpoint clamp component A': 6,\n", - " 'ATP binding cassette subfamily C member 8': 60,\n", - " 'sigma non-opioid intracellular receptor 1': 49,\n", - " 'CD47 molecule': 67,\n", - " 'dicer 1': 624,\n", - " ' ribonuclease III': 624,\n", - " 'argonaute RISC catalytic component 1': 47,\n", - " 'argonaute RISC catalytic component 2': 209,\n", + " 'RAD9 checkpoint clamp component A': 7,\n", + " 'ATP binding cassette subfamily C member 8': 68,\n", + " 'CD47 molecule': 84,\n", + " 'dicer 1': 823,\n", + " ' ribonuclease III': 823,\n", + " 'argonaute RISC catalytic component 1': 61,\n", + " 'argonaute RISC catalytic component 2': 301,\n", " 'SID1 transmembrane family member 1': 8,\n", - " 'drosha ribonuclease III': 185,\n", + " 'drosha ribonuclease III': 243,\n", " 'homeobox B4': 1,\n", - " 'homeobox B5': 1,\n", - " 'DS cell adhesion molecule': 11,\n", - " 'protein phosphatase 1 catalytic subunit alpha': 643,\n", - " 'sterol regulatory element binding transcription factor 1': 81,\n", - " 'ribosomal protein L12': 25,\n", - " 'ribosomal protein L7': 21,\n", - " 'TIA1 cytotoxic granule associated RNA binding protein like 1': 133,\n", - " 'TIA1 cytotoxic granule associated RNA binding protein': 184,\n", - " 'RAS p21 protein activator 1': 27,\n", - " 'G3BP stress granule assembly factor 1': 409,\n", - " 'DnaJ heat shock protein family (Hsp40) member C3': 12,\n", - " 'protein phosphatase 1 regulatory subunit 15A': 228,\n", + " 'homeobox B5': 2,\n", + " 'DS cell adhesion molecule': 15,\n", + " 'period circadian regulator 2': 204,\n", + " 'period circadian regulator 3': 96,\n", + " 'sterol regulatory element binding transcription factor 1': 96,\n", + " 'TIA1 cytotoxic granule associated RNA binding protein like 1': 188,\n", + " 'TIA1 cytotoxic granule associated RNA binding protein': 286,\n", + " 'RAS p21 protein activator 1': 35,\n", + " 'DnaJ heat shock protein family (Hsp40) member C3': 15,\n", + " 'protein phosphatase 1 regulatory subunit 15A': 260,\n", " 'protein phosphatase 5 catalytic subunit': 37,\n", - " 'cell division cycle 37': 7,\n", - " 'heat shock protein family A (Hsp70) member 8': 207,\n", - " 'GNAS complex locus': 36,\n", + " 'cell division cycle 37': 13,\n", + " 'heat shock protein family A (Hsp70) member 8': 302,\n", + " 'GNAS complex locus': 48,\n", " 'glucosamine-phosphate N-acetyltransferase 1': 3,\n", - " 'actin beta': 2003,\n", - " 'seryl-tRNA synthetase 2': 144,\n", - " ' mitochondrial': 429,\n", - " 'heat shock protein 90 alpha family class B member 1': 56,\n", - " 'heat shock protein 90 alpha family class A member 1': 52,\n", - " 'heat shock protein 90 beta family member 1': 190,\n", - " 'secretoglobin family 1A member 1': 48,\n", - " 'forkhead box J1': 11,\n", - " 'keratin 5': 41,\n", - " 'mucin 5AC': 178,\n", - " ' oligomeric mucus/gel-forming': 332,\n", - " 'transforming growth factor beta 1': 1856,\n", - " 'epidermal growth factor': 438,\n", - " 'Wnt family member 3A': 24,\n", - " 'noggin': 23,\n", + " 'actin beta': 2393,\n", + " 'seryl-tRNA synthetase 2': 189,\n", + " ' mitochondrial': 509,\n", + " 'heat shock protein 90 alpha family class B member 1': 63,\n", + " 'heat shock protein 90 alpha family class A member 1': 61,\n", + " 'heat shock protein 90 beta family member 1': 206,\n", + " 'secretoglobin family 1A member 1': 68,\n", + " 'forkhead box J1': 17,\n", + " 'mucin 5AC': 217,\n", + " 'transforming growth factor beta 1': 2451,\n", + " 'epidermal growth factor': 523,\n", + " 'Wnt family member 3A': 42,\n", + " 'noggin': 47,\n", " 'gastrin': 210,\n", - " 'leucine rich repeat containing G protein-coupled receptor 5': 58,\n", - " 'ribonuclease H2 subunit C': 398,\n", - " 'endogenous retrovirus group K member 6': 457,\n", - " ' envelope': 666,\n", - " 'ribonuclease H2 subunit B': 397,\n", - " 'ribonuclease H1': 359,\n", - " 'ribonuclease H2 subunit A': 359,\n", - " 'mucin 2': 75,\n", - " 'nitric oxide synthase 2': 1075,\n", - " 'TNF receptor superfamily member 1A': 303,\n", - " 'retinoid X receptor alpha': 44,\n", - " 'peroxisome proliferator activated receptor alpha': 215,\n", - " 'C-C motif chemokine ligand 11': 242,\n", + " 'leucine rich repeat containing G protein-coupled receptor 5': 65,\n", + " 'ribonuclease H2 subunit C': 503,\n", + " 'endogenous retrovirus group K member 6': 567,\n", + " ' envelope': 795,\n", + " 'ribonuclease H2 subunit B': 500,\n", + " 'ribonuclease H1': 459,\n", + " 'ribonuclease H2 subunit A': 459,\n", + " 'mucin 2': 89,\n", + " 'nitric oxide synthase 2': 1339,\n", + " 'TNF receptor superfamily member 1A': 375,\n", + " 'retinoid X receptor alpha': 58,\n", + " 'peroxisome proliferator activated receptor alpha': 235,\n", + " 'C-C motif chemokine ligand 11': 315,\n", " 'aquaporin 10': 6,\n", - " 'fatty acid binding protein 1': 14,\n", - " 'interleukin 22 receptor subunit alpha 1': 20,\n", - " 'meprin A subunit beta': 4,\n", - " 'meprin A subunit alpha': 3,\n", - " 'APC': 26,\n", - " ' WNT signaling pathway regulator': 50,\n", - " 'interferon alpha inducible protein 27': 81,\n", + " 'fatty acid binding protein 1': 23,\n", + " 'interleukin 22 receptor subunit alpha 1': 21,\n", + " 'meprin A subunit beta': 5,\n", + " 'meprin A subunit alpha': 4,\n", + " 'APC': 30,\n", + " ' WNT signaling pathway regulator': 54,\n", + " 'interferon alpha inducible protein 27': 98,\n", " 'caldesmon 1': 8,\n", " 'mucin 16': 16,\n", " 'mucin 19': 4,\n", " ' oligomeric': 4,\n", " 'macrophage expressed 1': 7,\n", - " 'cystic fibrosis transmembrane conductance regulator': 561,\n", - " 'lactotransferrin': 491,\n", - " 'F2R like trypsin receptor 1': 103,\n", - " 'interleukin 13': 1034,\n", - " 'tryptase delta 1': 3,\n", + " 'lactotransferrin': 610,\n", + " 'troponin I3': 96,\n", + " ' cardiac type': 311,\n", + " 'ribonuclease P/MRP subunit p30': 15,\n", + " 'tRNA methyltransferase 5': 9,\n", + " 'interleukin 13': 1345,\n", + " 'tryptase delta 1': 4,\n", " 'tryptase alpha/beta 1': 3,\n", - " 'adrenoceptor beta 2': 123,\n", - " 'tryptase gamma 1': 12,\n", - " 'transforming growth factor beta 2': 130,\n", - " 'coagulation factor II': 1079,\n", - " ' thrombin': 1079,\n", - " 'exonuclease 1': 64,\n", - " 'DNA topoisomerase III alpha': 6,\n", - " 'caspase recruitment domain family member 16': 6,\n", - " 'colony stimulating factor 3': 541,\n", - " 'pyrin and HIN domain family member 1': 40,\n", - " 'interleukin 27': 260,\n", - " 'interleukin 2': 3033,\n", - " 'par-6 family cell polarity regulator alpha': 5,\n", - " 'interleukin 7': 330,\n", - " 'C-C motif chemokine ligand 3': 673,\n", - " 'C-C motif chemokine ligand 2': 2092,\n", - " 'interleukin 6 receptor': 81,\n", - " 'interferon gamma receptor 1': 153,\n", - " 'TNF receptor superfamily member 9': 85,\n", - " 'CD69 molecule': 406,\n", - " 'TNF receptor superfamily member 4': 97,\n", - " 'CD44 molecule (Indian blood group)': 487,\n", - " 'hepatitis A virus cellular receptor 2': 152,\n", - " 'phosphatase and tensin homolog': 194,\n", - " 'proprotein convertase subtilisin/kexin type 9': 69,\n", - " 'AKT serine/threonine kinase 1': 1332,\n", + " 'adrenoceptor beta 2': 166,\n", + " 'tryptase gamma 1': 27,\n", + " 'transforming growth factor beta 2': 143,\n", + " 'exonuclease 1': 73,\n", + " 'caspase recruitment domain family member 16': 7,\n", + " 'colony stimulating factor 3': 741,\n", + " 'pyrin and HIN domain family member 1': 49,\n", + " 'interleukin 27': 370,\n", + " 'interleukin 2': 3845,\n", + " 'par-6 family cell polarity regulator alpha': 4,\n", + " 'interleukin 7': 446,\n", + " 'C-C motif chemokine ligand 3': 911,\n", + " 'C-C motif chemokine ligand 2': 2824,\n", + " 'interleukin 6 receptor': 105,\n", + " 'interferon gamma receptor 1': 210,\n", + " 'TNF receptor superfamily member 9': 105,\n", + " 'CD69 molecule': 493,\n", + " 'TNF receptor superfamily member 4': 146,\n", + " 'CD44 molecule (Indian blood group)': 620,\n", + " 'hepatitis A virus cellular receptor 2': 219,\n", + " 'phosphatase and tensin homolog': 236,\n", + " 'proprotein convertase subtilisin/kexin type 9': 95,\n", + " 'AKT serine/threonine kinase 1': 1662,\n", " 'cytochrome P450 family 8 subfamily B member 1': 7,\n", - " 'fatty acid synthase': 96,\n", - " 'serum amyloid A1': 303,\n", - " 'CAS1 domain containing 1': 75,\n", - " 'sialophorin': 98,\n", - " 'deleted in malignant brain tumors 1': 23,\n", - " 'Fc fragment of IgG receptor IIa': 388,\n", - " 'Fc fragment of IgG receptor IIb': 335,\n", - " 'CD22 molecule': 157,\n", - " 'complement C3d receptor 2': 340,\n", - " 'CD93 molecule': 17,\n", - " 'selectin L': 453,\n", - " 'glycophorin A (MNS blood group)': 56,\n", - " 'transferrin receptor': 493,\n", - " 'toll like receptor 5': 319,\n", - " 'myeloid differentiation primary response 88': 1062,\n", - " 'toll like receptor 6': 196,\n", - " 'interleukin 1 receptor associated kinase 4': 102,\n", - " 'toll like receptor 9': 1144,\n", - " 'conserved helix-loop-helix ubiquitous kinase': 264,\n", - " 'mitogen-activated protein kinase 9': 142,\n", - " 'toll like receptor 7': 1403,\n", - " 'sialic acid binding Ig like lectin 9': 10,\n", - " 'deoxyribonuclease 1': 656,\n", - " 'IK cytokine': 38,\n", - " 'peptidylprolyl isomerase A': 259,\n", - " 'proteolipid protein 2': 408,\n", + " 'fatty acid synthase': 112,\n", + " 'serum amyloid A1': 341,\n", + " 'CAS1 domain containing 1': 76,\n", + " 'sialophorin': 108,\n", + " 'deleted in malignant brain tumors 1': 26,\n", + " 'Fc fragment of IgG receptor IIa': 497,\n", + " 'Fc fragment of IgG receptor IIb': 426,\n", + " 'CD22 molecule': 196,\n", + " 'complement C3d receptor 2': 381,\n", + " 'CD93 molecule': 19,\n", + " 'selectin L': 582,\n", + " 'glycophorin A (MNS blood group)': 71,\n", + " 'transferrin receptor': 636,\n", + " 'toll like receptor 5': 394,\n", + " 'myeloid differentiation primary response 88': 1455,\n", + " 'toll like receptor 6': 265,\n", + " 'interleukin 1 receptor associated kinase 4': 145,\n", + " 'toll like receptor 9': 1650,\n", + " 'mitogen-activated protein kinase 9': 166,\n", + " 'toll like receptor 7': 1976,\n", + " 'sialic acid binding Ig like lectin 9': 17,\n", + " 'IK cytokine': 44,\n", + " 'proteolipid protein 2': 522,\n", " 'testis specific serine kinase 6': 3,\n", - " 'KH RNA binding domain containing': 183,\n", - " ' signal transduction associated 3': 159,\n", - " 'regulatory associated protein of MTOR complex 1': 52,\n", - " ' C': 159,\n", - " ' class II': 459,\n", - " ' DR beta 1': 211,\n", - " 'heat shock protein family A (Hsp70) member 14': 115,\n", - " 'heat shock protein family D (Hsp60) member 1': 268,\n", - " ' DR beta 5': 31,\n", + " 'KH RNA binding domain containing': 207,\n", + " ' signal transduction associated 3': 173,\n", + " 'regulatory associated protein of MTOR complex 1': 79,\n", + " ' C': 247,\n", + " ' class II': 549,\n", + " ' DR beta 1': 244,\n", + " 'heat shock protein family A (Hsp70) member 14': 176,\n", + " 'heat shock protein family D (Hsp60) member 1': 342,\n", + " ' DR beta 5': 33,\n", " ' DR beta 3': 10,\n", " ' DP alpha 1': 13,\n", " 'neurocalcin delta': 1,\n", - " 'cyclic nucleotide gated channel beta 3': 3,\n", - " 'cell division cycle 5 like': 13,\n", + " 'cyclic nucleotide gated channel beta 3': 4,\n", + " 'cell division cycle 5 like': 14,\n", + " 'glutamate ionotropic receptor delta type subunit 1': 7,\n", + " 'BBX': 3,\n", + " ' HMG-box containing': 3,\n", " 'A-Raf proto-oncogene': 7,\n", - " ' serine/threonine kinase': 288,\n", - " 'serine peptidase inhibitor': 131,\n", - " ' Kunitz type 2': 67,\n", - " 'suppression of tumorigenicity 14': 101,\n", - " 'kallikrein related peptidase 5': 33,\n", - " 'plasminogen': 345,\n", - " 'kallikrein related peptidase 12': 18,\n", - " 'transmembrane protease': 1160,\n", - " ' serine 2': 673,\n", + " ' serine/threonine kinase': 309,\n", + " 'serine peptidase inhibitor': 151,\n", + " ' Kunitz type 2': 71,\n", + " 'kallikrein related peptidase 5': 37,\n", + " 'plasminogen': 463,\n", + " 'kallikrein related peptidase 12': 20,\n", " 'kallikrein related peptidase 8': 10,\n", - " 'kallikrein related peptidase 10': 14,\n", - " 'kallikrein related peptidase 2': 5,\n", - " 'protease': 221,\n", - " ' serine 3': 56,\n", - " 'kallikrein related peptidase 7': 9,\n", - " ' serine 4': 93,\n", - " ' serine 13': 66,\n", - " ' serine 11D': 81,\n", + " 'kallikrein related peptidase 10': 17,\n", + " 'kallikrein related peptidase 2': 10,\n", + " ' serine 3': 77,\n", + " 'kallikrein related peptidase 7': 11,\n", + " ' serine 4': 113,\n", + " ' serine 13': 76,\n", " ' Kunitz type 3': 1,\n", - " 'SUMO1/sentrin/SMT3 specific peptidase 3': 29,\n", - " ' Kunitz type 1': 11,\n", - " 'alanyl aminopeptidase': 1179,\n", - " ' membrane': 1179,\n", - " 'ceruloplasmin': 396,\n", + " 'SUMO1/sentrin/SMT3 specific peptidase 3': 100,\n", + " ' Kunitz type 1': 18,\n", + " 'cell division cycle 6': 34,\n", + " 'orosomucoid 1': 9,\n", + " 'ceruloplasmin': 442,\n", " 'PAK1 interacting protein 1': 1,\n", " 'MAK16 homolog': 4,\n", " 'WD repeat domain 61': 3,\n", " 'exosome component 4': 12,\n", " 'N(alpha)-acetyltransferase 50': 3,\n", " ' NatE catalytic subunit': 3,\n", - " 'N(alpha)-acetyltransferase 30': 3,\n", - " ' NatC catalytic subunit': 3,\n", + " 'N(alpha)-acetyltransferase 30': 4,\n", + " ' NatC catalytic subunit': 4,\n", " 'male germ cell associated kinase': 6,\n", " 'N(alpha)-acetyltransferase 35': 2,\n", " ' NatC auxiliary subunit': 3,\n", " 'N(alpha)-acetyltransferase 38': 1,\n", - " 'Ski2 like RNA helicase': 25,\n", - " 'DNA topoisomerase I': 59,\n", - " 'lipocalin 2': 93,\n", - " 'KIT proto-oncogene receptor tyrosine kinase': 505,\n", - " 'KRAS proto-oncogene': 196,\n", - " ' GTPase': 449,\n", - " 'methylmalonyl-CoA mutase': 55,\n", - " 'interferon alpha 5': 50,\n", + " 'Ski2 like RNA helicase': 28,\n", + " 'DNA topoisomerase I': 74,\n", + " 'lipocalin 2': 141,\n", + " 'KIT proto-oncogene receptor tyrosine kinase': 599,\n", + " 'KRAS proto-oncogene': 193,\n", + " ' GTPase': 484,\n", + " 'methylmalonyl-CoA mutase': 72,\n", + " 'interferon alpha 5': 57,\n", " 'transfer RNA selenocysteine 1 (anticodon UCA)': 11,\n", " ' H/ACA box 38': 1,\n", - " 'Pvt1 oncogene (non-protein coding)': 5,\n", + " 'Pvt1 oncogene (non-protein coding)': 6,\n", " ' C/D box 112': 2,\n", " 'small Cajal body-specific RNA 7': 1,\n", " ' H/ACA box 48': 1,\n", - " 'T-box 5': 11,\n", - " 'X (inactive)-specific transcript (non-protein coding)': 69,\n", - " 'MX dynamin like GTPase 1': 415,\n", + " 'T-box 5': 14,\n", + " 'X (inactive)-specific transcript (non-protein coding)': 82,\n", + " 'MX dynamin like GTPase 1': 551,\n", " 'semaphorin 3G': 3,\n", - " 'plasminogen activator': 397,\n", - " ' tissue type': 184,\n", - " 'epithelial cell adhesion molecule': 111,\n", - " 'angiopoietin 1': 698,\n", - " 'angiopoietin 2': 938,\n", - " 'endonuclease': 211,\n", - " ' poly(U) specific': 211,\n", + " 'plasminogen activator': 539,\n", + " ' tissue type': 238,\n", + " 'cyclin dependent kinase inhibitor 1A': 149,\n", + " 'zinc metallopeptidase STE24': 12,\n", + " 'marker of proliferation Ki-67': 363,\n", + " 'myeloperoxidase': 359,\n", + " 'Sp8 transcription factor': 96,\n", + " 'galactosidase beta 1': 532,\n", + " 'chromobox 5': 9,\n", + " 'lamin A/C': 84,\n", + " 'lamin B1': 58,\n", + " 'dopachrome tautomerase': 21,\n", + " 'cyclin dependent kinase inhibitor 2A': 205,\n", + " 'polo like kinase 3': 4,\n", + " 'angiopoietin 1': 1229,\n", + " 'angiopoietin 2': 1565,\n", + " 'DNA topoisomerase III beta': 19,\n", + " 'tudor domain containing 3': 17,\n", + " 'cadherin EGF LAG seven-pass G-type receptor 2': 4,\n", + " 'DNA topoisomerase III alpha': 7,\n", + " 'Fas ligand': 590,\n", + " 'protein phosphatase 1 catalytic subunit alpha': 863,\n", + " 'endonuclease': 234,\n", + " ' poly(U) specific': 234,\n", " 'immunoglobulin binding protein 1': 7,\n", - " 'interleukin 1 receptor antagonist': 300,\n", - " 'interleukin 15': 558,\n", - " 'interleukin 1 receptor type 1': 441,\n", - " 'myeloperoxidase': 309,\n", + " 'interleukin 1 receptor antagonist': 364,\n", + " 'interleukin 15': 749,\n", + " 'interleukin 1 receptor type 1': 548,\n", " 'mitogen-activated protein kinase kinase kinase kinase 2': 6,\n", - " 'T-cell immunoreceptor with Ig and ITIM domains': 24,\n", + " 'T-cell immunoreceptor with Ig and ITIM domains': 55,\n", " 'collagen type XVII alpha 1 chain': 25,\n", - " 'collagen type XII alpha 1 chain': 3,\n", - " 'laminin subunit alpha 3': 9,\n", - " 'tight junction protein 1': 81,\n", - " 'gap junction protein alpha 1': 30,\n", - " 'C-type lectin domain family 4 member E': 32,\n", - " 'CD55 molecule (Cromer blood group)': 124,\n", - " 'period circadian regulator 3': 81,\n", - " 'C-X-C motif chemokine ligand 10': 1363,\n", - " 'MOB kinase activator 1A': 1,\n", - " 'sphingomyelin synthase 1': 20,\n", - " 'C-X-C motif chemokine receptor 3': 482,\n", - " 'GLI family zinc finger 2': 715,\n", - " 'RELA proto-oncogene': 240,\n", - " ' NF-kB subunit': 331,\n", - " 'vitamin D receptor': 92,\n", - " 'autophagy related 16 like 1': 135,\n", - " 'phosphatidylinositol 3-kinase catalytic subunit type 3': 143,\n", - " 'microtubule associated protein 1 light chain 3 beta': 205,\n", - " 'autophagy related 5': 598,\n", - " 'CD274 molecule': 431,\n", - " 'programmed cell death 1': 279,\n", - " 'poly(ADP-ribose) polymerase family member 10': 94,\n", - " 'ADP-ribosyltransferase 3': 13,\n", - " 'poly(ADP-ribose) polymerase family member 12': 49,\n", - " 'TCDD inducible poly(ADP-ribose) polymerase': 32,\n", - " 'tankyrase': 44,\n", - " 'Sp6 transcription factor': 251,\n", - " 'coagulation factor III': 427,\n", - " ' tissue factor': 427,\n", - " 'interleukin 7 receptor': 189,\n", - " 'C-type lectin domain family 4 member M': 662,\n", + " 'collagen type XII alpha 1 chain': 5,\n", + " 'laminin subunit alpha 3': 10,\n", + " 'tight junction protein 1': 90,\n", + " 'gap junction protein alpha 1': 39,\n", + " 'C-type lectin domain family 4 member E': 52,\n", + " 'CD55 molecule (Cromer blood group)': 137,\n", + " 'sialic acid binding Ig like lectin 1': 224,\n", + " 'perforin 1': 699,\n", + " 'CD68 molecule': 395,\n", + " 'GLI family zinc finger 2': 832,\n", + " 'C-X-C motif chemokine ligand 10': 2033,\n", + " 'MOB kinase activator 1A': 2,\n", + " 'sphingomyelin synthase 1': 22,\n", + " 'C-X-C motif chemokine receptor 3': 763,\n", + " 'RELA proto-oncogene': 311,\n", + " ' NF-kB subunit': 435,\n", + " 'vitamin D receptor': 126,\n", + " 'autophagy related 16 like 1': 276,\n", + " 'phosphatidylinositol 3-kinase catalytic subunit type 3': 231,\n", + " 'microtubule associated protein 1 light chain 3 beta': 263,\n", + " 'autophagy related 5': 1021,\n", + " 'CD274 molecule': 516,\n", + " 'programmed cell death 1': 348,\n", + " 'poly(ADP-ribose) polymerase family member 10': 133,\n", + " 'ADP-ribosyltransferase 3': 18,\n", + " 'poly(ADP-ribose) polymerase family member 12': 81,\n", + " 'TCDD inducible poly(ADP-ribose) polymerase': 60,\n", + " 'tankyrase': 74,\n", + " 'Sp6 transcription factor': 308,\n", + " 'interleukin 7 receptor': 262,\n", + " 'cystatin C': 265,\n", + " 'CD3-TCR complex': 1,\n", + " ' omega polypeptide': 1,\n", + " 'interleukin 34': 36,\n", + " 'C-type lectin domain family 4 member M': 950,\n", " 'calcium voltage-gated channel subunit alpha1 A': 11,\n", - " 'calcium voltage-gated channel subunit alpha1 D': 7,\n", - " 'distal-less homeobox 4': 4,\n", + " 'calcium voltage-gated channel subunit alpha1 D': 8,\n", + " 'distal-less homeobox 4': 5,\n", " 'gamma-aminobutyric acid type A receptor alpha2 subunit': 8,\n", " 'coenzyme Q3': 1,\n", " ' methyltransferase': 1,\n", - " 'immunoglobulin superfamily member 8': 6,\n", + " 'immunoglobulin superfamily member 8': 8,\n", " 'gamma-aminobutyric acid type A receptor beta1 subunit': 3,\n", " ' receptor type R': 2,\n", " 'sodium/potassium transporting ATPase interacting 3': 1,\n", - " 'potassium voltage-gated channel subfamily J member 10': 10,\n", + " 'potassium voltage-gated channel subfamily J member 10': 14,\n", " 'gamma-aminobutyric acid type A receptor alpha5 subunit': 2,\n", - " 'ATPase Na+/K+ transporting subunit alpha 2': 8,\n", + " 'ATPase Na+/K+ transporting subunit alpha 2': 9,\n", " 'Rap guanine nucleotide exchange factor 6': 3,\n", - " 'signaling lymphocytic activation molecule family member 1': 114,\n", + " 'signaling lymphocytic activation molecule family member 1': 137,\n", " 'gamma-aminobutyric acid type A receptor gamma1 subunit': 1,\n", " 'solute carrier family 16 member 14': 18,\n", - " 'DnaJ heat shock protein family (Hsp40) member B1': 93,\n", - " 'protein kinase cAMP-activated catalytic subunit alpha': 44,\n", - " 'activating transcription factor 2': 135,\n", - " 'SRY-box 1': 15,\n", - " 'hepatocyte nuclear factor 4 alpha': 31,\n", - " 'MYB proto-oncogene': 26,\n", - " ' transcription factor': 61,\n", + " 'DnaJ heat shock protein family (Hsp40) member B1': 149,\n", + " 'protein kinase cAMP-activated catalytic subunit alpha': 48,\n", + " 'activating transcription factor 2': 179,\n", + " 'SRY-box 1': 22,\n", + " 'hepatocyte nuclear factor 4 alpha': 52,\n", + " 'MYB proto-oncogene': 30,\n", + " ' transcription factor': 70,\n", " 'E2F transcription factor 6': 1,\n", " 'hes family bHLH transcription factor 2': 1,\n", - " 'homer scaffolding protein 1': 55,\n", + " 'homer scaffolding protein 1': 58,\n", " 'FOS like 2': 26,\n", - " 'FOS like 1': 15,\n", - " 'cAMP responsive element binding protein 1': 31,\n", - " 'activating transcription factor 3': 112,\n", + " 'FOS like 1': 16,\n", + " 'cAMP responsive element binding protein 1': 35,\n", + " 'activating transcription factor 3': 127,\n", " 'trinucleotide repeat containing 6C': 2,\n", " 'carbonic anhydrase 12': 12,\n", " 'family with sequence similarity 19 member A5': 7,\n", " ' C-C motif chemokine like': 8,\n", - " 'ornithine aminotransferase': 12,\n", + " 'ornithine aminotransferase': 13,\n", " 'transmembrane protein 163': 3,\n", " 'tescalcin': 4,\n", - " 'beta-site APP-cleaving enzyme 2': 10,\n", - " 'collagen type IV alpha 1 chain': 8,\n", - " 'interferon regulatory factor 4': 89,\n", + " 'beta-site APP-cleaving enzyme 2': 14,\n", + " 'collagen type IV alpha 1 chain': 10,\n", + " 'interferon regulatory factor 4': 113,\n", " 'kinesin family member 26B': 1,\n", - " 'heat shock protein family A (Hsp70) member 1B': 27,\n", - " 'frizzled class receptor 10': 2,\n", + " 'heat shock protein family A (Hsp70) member 1B': 30,\n", + " 'frizzled class receptor 10': 3,\n", " 'ribosomal protein S6 kinase A2': 15,\n", " 'ATPase Na+/K+ transporting subunit beta 1': 11,\n", " 'protein kinase cAMP-activated catalytic subunit beta': 2,\n", - " 'bromodomain containing 4': 33,\n", - " 'R-spondin 1': 10,\n", - " 'ribosomal protein S9': 26,\n", + " 'R-spondin 1': 15,\n", + " 'ribosomal protein S9': 31,\n", " 'epiphycan': 3,\n", " 'ISL LIM homeobox 2': 5,\n", " 'myosin heavy chain 15': 13,\n", - " 'lymphoid enhancer binding factor 1': 18,\n", - " 'CD1d molecule': 73,\n", - " 'CD1c molecule': 57,\n", - " 'cystatin F': 17,\n", - " 'CD3d molecule': 24,\n", - " 'CD8a molecule': 241,\n", - " 'C-C motif chemokine ligand 4': 447,\n", - " 'lymphotoxin beta': 49,\n", - " 'C-type lectin domain containing 9A': 39,\n", - " 'thrombomodulin': 135,\n", - " 'T cell receptor alpha locus': 104,\n", - " 'interferon': 1905,\n", - " ' type 1': 941,\n", - " ' cluster': 941,\n", - " 'interferon induced transmembrane protein 3': 1753,\n", - " 'interferon induced transmembrane protein 1': 995,\n", - " 'Fos proto-oncogene': 236,\n", - " 'AXL receptor tyrosine kinase': 75,\n", - " 'JunB proto-oncogene': 20,\n", - " 'sialic acid binding Ig like lectin 6': 9,\n", - " 'interleukin 37': 89,\n", - " 'Epstein-Barr virus induced 3': 206,\n", - " 'interleukin 12A': 2344,\n", - " 'interleukin 1 alpha': 499,\n", - " 'Aural atresia': 28,\n", - " ' congenital': 36,\n", - " 'grancalcin': 31,\n", - " 'glucosidase alpha': 43,\n", - " ' acid': 42,\n", - " 'preferentially expressed antigen in melanoma': 84,\n", - " 'C-type lectin domain containing 5A': 64,\n", - " 'TATA-box binding protein like 2': 11,\n", - " 'telomeric repeat binding factor 1': 22,\n", - " 'transfer RNA serine 2 (anticodon AGA)': 39,\n", - " 'BCL2': 1191,\n", - " ' apoptosis regulator': 1761,\n", - " 'BCL2 associated X': 570,\n", - " 'secretory leukocyte peptidase inhibitor': 110,\n", - " 'peptidase inhibitor 3': 32,\n", - " 'radical S-adenosyl methionine domain containing 2': 330,\n", - " 'mannose binding lectin 2': 150,\n", + " 'lymphoid enhancer binding factor 1': 27,\n", + " 'CD1d molecule': 108,\n", + " 'CD1c molecule': 68,\n", + " 'cystatin F': 19,\n", + " 'CD3d molecule': 25,\n", + " 'CD8a molecule': 292,\n", + " 'C-C motif chemokine ligand 4': 603,\n", + " 'lymphotoxin beta': 83,\n", + " 'C-type lectin domain containing 9A': 52,\n", + " 'thrombomodulin': 166,\n", + " 'T cell receptor alpha locus': 151,\n", + " 'interferon': 2550,\n", + " ' type 1': 1280,\n", + " ' cluster': 1280,\n", + " 'interferon induced transmembrane protein 3': 2206,\n", + " 'interferon induced transmembrane protein 1': 1204,\n", + " 'Fos proto-oncogene': 274,\n", + " 'AXL receptor tyrosine kinase': 90,\n", + " 'JunB proto-oncogene': 30,\n", + " 'sialic acid binding Ig like lectin 6': 11,\n", + " 'interleukin 37': 90,\n", + " 'Epstein-Barr virus induced 3': 290,\n", + " 'interleukin 12A': 2972,\n", + " 'interleukin 1 alpha': 616,\n", + " 'Aural atresia': 32,\n", + " ' congenital': 39,\n", + " 'grancalcin': 28,\n", + " 'glucosidase alpha': 55,\n", + " ' acid': 54,\n", + " 'preferentially expressed antigen in melanoma': 89,\n", + " 'C-type lectin domain containing 5A': 74,\n", + " 'TATA-box binding protein like 2': 13,\n", + " 'telomeric repeat binding factor 1': 25,\n", + " 'transfer RNA serine 2 (anticodon AGA)': 44,\n", + " 'BCL2': 1556,\n", + " ' apoptosis regulator': 2225,\n", + " 'BCL2 associated X': 669,\n", + " 'secretory leukocyte peptidase inhibitor': 122,\n", + " 'peptidase inhibitor 3': 52,\n", + " 'radical S-adenosyl methionine domain containing 2': 397,\n", + " 'mannose binding lectin 2': 172,\n", + " 'molybdenum cofactor sulfurase': 4,\n", " 'coiled-coil domain containing 92': 2,\n", " 'ribosomal protein lateral stalk subunit P1': 7,\n", " 'homocysteine inducible ER protein with ubiquitin like domain 1': 19,\n", " 'RNA polymerase II subunit A': 51,\n", " 'ChaC glutathione specific gamma-glutamylcyclotransferase 1': 35,\n", - " 'eukaryotic translation initiation factor 2B subunit gamma': 1,\n", - " 'X-box binding protein 1': 473,\n", - " 'heat shock protein family A (Hsp70) member 5': 508,\n", + " 'eukaryotic translation initiation factor 2B subunit gamma': 2,\n", + " 'X-box binding protein 1': 551,\n", + " 'heat shock protein family A (Hsp70) member 5': 594,\n", " 'gamma-glutamylcyclotransferase': 6,\n", - " 'ribosomal protein S21': 3,\n", - " 'carcinoembryonic antigen related cell adhesion molecule 1': 753,\n", - " 'cell adhesion molecule 1': 44,\n", - " 'CD40 molecule': 606,\n", - " 'C-X3-C motif chemokine ligand 1': 132,\n", - " 'C-X-C motif chemokine ligand 5': 135,\n", - " 'cathepsin S': 72,\n", - " 'C-X-C motif chemokine ligand 16': 63,\n", - " 'interferon induced with helicase C domain 1': 1842,\n", + " 'ribosomal protein S21': 4,\n", + " 'cell adhesion molecule 1': 55,\n", + " 'CD40 molecule': 837,\n", + " 'C-X3-C motif chemokine ligand 1': 179,\n", + " 'C-X-C motif chemokine ligand 5': 194,\n", + " 'cathepsin S': 91,\n", + " 'C-X-C motif chemokine ligand 16': 82,\n", + " 'interferon induced with helicase C domain 1': 2549,\n", " 'cathepsin O': 2,\n", - " 'cyclin D1': 285,\n", - " 'caspase 10': 37,\n", - " 'interleukin 15 receptor subunit alpha': 19,\n", - " 'poly(ADP-ribose) polymerase family member 3': 36,\n", - " 'integrin subunit alpha 2': 115,\n", - " 'TNF receptor associated factor 1': 48,\n", - " 'laminin subunit alpha 1': 7,\n", - " 'interleukin 2 receptor subunit gamma': 110,\n", - " 'C-C motif chemokine ligand 7': 142,\n", - " 'VPS11': 41,\n", - " ' CORVET/HOPS core subunit': 93,\n", - " 'BCL2 antagonist/killer 1': 25,\n", - " 'signal transducer and activator of transcription 2': 687,\n", - " 'vascular endothelial growth factor C': 33,\n", - " 'CASP8 and FADD-like apoptosis regulator': 37,\n", - " 'promyelocytic leukemia': 139,\n", + " 'cyclin D1': 338,\n", + " 'caspase 10': 57,\n", + " 'interleukin 15 receptor subunit alpha': 30,\n", + " 'poly(ADP-ribose) polymerase family member 3': 47,\n", + " 'integrin subunit alpha 2': 139,\n", + " 'TNF receptor associated factor 1': 61,\n", + " 'laminin subunit alpha 1': 9,\n", + " 'interleukin 2 receptor subunit gamma': 151,\n", + " 'C-C motif chemokine ligand 7': 216,\n", + " 'VPS11': 49,\n", + " ' CORVET/HOPS core subunit': 108,\n", + " 'BCL2 antagonist/killer 1': 27,\n", + " 'signal transducer and activator of transcription 2': 923,\n", + " 'vascular endothelial growth factor C': 39,\n", + " 'CASP8 and FADD-like apoptosis regulator': 54,\n", + " 'promyelocytic leukemia': 178,\n", " 'G protein subunit beta 4': 7,\n", - " 'transmembrane protein 173': 212,\n", - " 'suppressor of cytokine signaling 3': 318,\n", - " 'suppressor of cytokine signaling 1': 245,\n", - " 'carcinoembryonic antigen related cell adhesion molecule 5': 96,\n", - " 'carcinoembryonic antigen related cell adhesion molecule 6': 75,\n", - " 'annexin A5': 557,\n", - " 'iduronate 2-sulfatase': 48,\n", - " 'neural cell adhesion molecule 1': 460,\n", - " 'myoglobin': 175,\n", - " 'troponin I3': 80,\n", - " ' cardiac type': 272,\n", - " 'glutathione-disulfide reductase': 52,\n", - " 'glutamate ionotropic receptor NMDA type subunit 2A': 16,\n", - " 'glutamate ionotropic receptor NMDA type subunit 2B': 26,\n", - " 'profilin 1': 30,\n", - " 'huntingtin': 88,\n", - " 'interleukin 33': 250,\n", - " 'interleukin 18': 952,\n", - " 'ADAM metallopeptidase domain 17': 396,\n", - " 'mitogen-activated protein kinase 14': 236,\n", - " 'interleukin 5': 1018,\n", - " 'lymphotoxin alpha': 111,\n", - " 'interleukin 20': 35,\n", - " 'interleukin 17B': 37,\n", - " 'signal transducer and activator of transcription 4': 122,\n", - " 'mitogen-activated protein kinase-activated protein kinase 2': 36,\n", - " 'mitogen-activated protein kinase 15': 3,\n", - " 'signal transducer and activator of transcription 6': 195,\n", - " 'natural cytotoxicity triggering receptor 1': 169,\n", - " 'natural cytotoxicity triggering receptor 2': 41,\n", - " 'killer cell lectin like receptor K1': 116,\n", - " 'ribonuclease L': 1137,\n", + " 'transmembrane protein 173': 295,\n", + " 'suppressor of cytokine signaling 3': 364,\n", + " 'suppressor of cytokine signaling 1': 286,\n", + " 'carcinoembryonic antigen related cell adhesion molecule 5': 122,\n", + " 'carcinoembryonic antigen related cell adhesion molecule 6': 124,\n", + " 'annexin A5': 692,\n", + " 'iduronate 2-sulfatase': 56,\n", + " 'myoglobin': 210,\n", + " 'glutathione-disulfide reductase': 60,\n", + " 'glutamate ionotropic receptor NMDA type subunit 2A': 40,\n", + " 'glutamate ionotropic receptor NMDA type subunit 2B': 45,\n", + " 'profilin 1': 29,\n", + " 'huntingtin': 144,\n", + " 'interleukin 33': 315,\n", + " 'interleukin 18': 1171,\n", + " 'ADAM metallopeptidase domain 17': 496,\n", + " 'mitogen-activated protein kinase 14': 315,\n", + " 'interleukin 5': 1236,\n", + " 'lymphotoxin alpha': 131,\n", + " 'interleukin 20': 37,\n", + " 'interleukin 17B': 39,\n", + " 'signal transducer and activator of transcription 4': 164,\n", + " 'mitogen-activated protein kinase-activated protein kinase 2': 44,\n", + " 'mitogen-activated protein kinase 15': 6,\n", + " 'signal transducer and activator of transcription 6': 255,\n", + " 'neural cell adhesion molecule 1': 573,\n", + " 'natural cytotoxicity triggering receptor 1': 220,\n", + " 'natural cytotoxicity triggering receptor 2': 77,\n", + " 'killer cell lectin like receptor K1': 183,\n", + " 'ribonuclease L': 1484,\n", " 'zinc finger protein 221': 1,\n", - " 'kallikrein related peptidase 6': 31,\n", - " 'protein C': 359,\n", - " ' inactivator of coagulation factors Va and VIIIa': 359,\n", - " ' DR alpha': 37,\n", + " 'kallikrein related peptidase 6': 38,\n", + " 'protein C': 426,\n", + " ' inactivator of coagulation factors Va and VIIIa': 426,\n", + " 'coagulation factor X': 280,\n", + " 'caspase 1': 708,\n", + " ' DR alpha': 38,\n", " 'glucokinase': 20,\n", - " 'ATP binding cassette subfamily A member 1': 75,\n", - " 'apolipoprotein A2': 37,\n", - " 'apolipoprotein C3': 35,\n", - " 'cholesteryl ester transfer protein': 17,\n", - " 'scavenger receptor class B member 1': 117,\n", - " 'paraoxonase 1': 62,\n", - " 'lipoprotein lipase': 73,\n", - " 'lecithin-cholesterol acyltransferase': 24,\n", + " 'ATP binding cassette subfamily A member 1': 106,\n", + " 'apolipoprotein A2': 43,\n", + " 'apolipoprotein C3': 36,\n", + " 'cholesteryl ester transfer protein': 19,\n", + " 'scavenger receptor class B member 1': 163,\n", + " 'paraoxonase 1': 73,\n", + " 'lipoprotein lipase': 85,\n", + " 'lecithin-cholesterol acyltransferase': 27,\n", " 'lipase C': 13,\n", " ' hepatic type': 13,\n", " 'lipase G': 5,\n", " ' endothelial type': 5,\n", - " 'serum amyloid A2': 93,\n", + " 'serum amyloid A2': 98,\n", " 'protein phosphatase 1 catalytic subunit gamma': 22,\n", - " 'apolipoprotein C2': 22,\n", - " 'integrin subunit beta 3': 111,\n", + " 'apolipoprotein C2': 28,\n", + " 'integrin subunit beta 3': 154,\n", " 'fetuin B': 3,\n", - " 'apolipoprotein B': 129,\n", - " 'integrin subunit beta 1': 260,\n", - " 'serum amyloid A4': 10,\n", - " ' constitutive': 10,\n", - " 'complement component 4 binding protein alpha': 37,\n", - " 'adhesion G protein-coupled receptor E5': 20,\n", - " 'phospholipid transfer protein': 6,\n", - " 'apolipoprotein A4': 25,\n", - " 'apolipoprotein A5': 9,\n", - " 'apolipoprotein C1': 31,\n", + " 'apolipoprotein B': 178,\n", + " 'integrin subunit beta 1': 329,\n", + " 'serum amyloid A4': 12,\n", + " ' constitutive': 12,\n", + " 'complement component 4 binding protein alpha': 68,\n", + " 'adhesion G protein-coupled receptor E5': 22,\n", + " 'phospholipid transfer protein': 7,\n", + " 'apolipoprotein A4': 32,\n", + " 'apolipoprotein A5': 10,\n", + " 'apolipoprotein C1': 37,\n", " 'insulin like growth factor binding protein acid labile subunit': 2,\n", - " 'glycosylphosphatidylinositol specific phospholipase D1': 5,\n", - " 'apolipoprotein D': 114,\n", + " 'glycosylphosphatidylinositol specific phospholipase D1': 7,\n", + " 'apolipoprotein D': 147,\n", " 'paraoxonase 3': 2,\n", - " 'tissue factor pathway inhibitor': 30,\n", - " 'clusterin': 122,\n", - " 'complement C4B (Chido blood group)': 27,\n", - " 'apolipoprotein M': 15,\n", - " 'apolipoprotein H': 34,\n", - " 'fibrinogen beta chain': 18,\n", - " 'fibrinogen alpha chain': 20,\n", + " 'tissue factor pathway inhibitor': 39,\n", + " 'clusterin': 157,\n", + " 'complement C4B (Chido blood group)': 30,\n", + " 'apolipoprotein M': 16,\n", + " 'apolipoprotein H': 44,\n", + " 'fibrinogen beta chain': 21,\n", + " 'fibrinogen alpha chain': 23,\n", " 'napsin A aspartic peptidase': 6,\n", - " 'alpha 2-HS glycoprotein': 61,\n", + " 'alpha 2-HS glycoprotein': 78,\n", " 'apolipoprotein C4': 6,\n", " 'retinol binding protein 4': 41,\n", - " 'platelet factor 4': 75,\n", - " 'immunoglobulin heavy constant mu': 36,\n", - " 'platelet factor 4 variant 1': 33,\n", - " ' serine 1': 110,\n", - " 'Sp1 transcription factor': 207,\n", - " 'hemoglobin subunit beta': 251,\n", - " 'H2B histone family member M': 25,\n", - " 'PPARG coactivator 1 alpha': 59,\n", - " 'cyclin dependent kinase inhibitor 1B': 130,\n", - " 'eukaryotic translation initiation factor 4A2': 510,\n", - " 'eukaryotic translation initiation factor 4A1': 351,\n", - " 'eukaryotic translation initiation factor 2 alpha kinase 2': 356,\n", - " 'peroxiredoxin 2': 72,\n", - " 'eukaryotic translation initiation factor 4E': 654,\n", - " 'eukaryotic translation initiation factor 4B': 71,\n", - " 'eukaryotic translation initiation factor 4 gamma 1': 647,\n", - " 'forkhead box O3': 66,\n", - " 'tripartite motif containing 33': 10,\n", - " 'TNF alpha induced protein 3': 50,\n", - " 'C-X-C motif chemokine ligand 2': 300,\n", - " 'interferon induced protein with tetratricopeptide repeats 2': 400,\n", - " \"2\\\\'-5\\\\'-oligoadenylate synthetase like\": 161,\n", - " 'inner mitochondrial membrane peptidase subunit 1': 7,\n", - " 'inositol monophosphatase 1': 13,\n", - " 'histocompatibility minor 13': 15,\n", - " 'insulin like growth factor 2 mRNA binding protein 1': 18,\n", - " 'insulin like growth factor 1': 448,\n", - " 'galactosidase beta 1': 427,\n", + " 'platelet factor 4': 89,\n", + " 'immunoglobulin heavy constant mu': 39,\n", + " 'platelet factor 4 variant 1': 35,\n", + " ' serine 1': 127,\n", + " 'hemoglobin subunit beta': 309,\n", + " 'H2B histone family member M': 38,\n", + " 'PPARG coactivator 1 alpha': 66,\n", + " 'cyclin dependent kinase inhibitor 1B': 149,\n", + " 'peroxiredoxin 2': 73,\n", + " 'eukaryotic translation initiation factor 4E': 813,\n", + " 'eukaryotic translation initiation factor 4B': 87,\n", + " 'eukaryotic translation initiation factor 4 gamma 1': 808,\n", + " 'forkhead box O3': 89,\n", + " 'tripartite motif containing 33': 22,\n", + " 'TNF alpha induced protein 3': 71,\n", + " 'C-X-C motif chemokine ligand 2': 410,\n", + " 'interferon induced protein with tetratricopeptide repeats 2': 545,\n", + " \"2\\\\'-5\\\\'-oligoadenylate synthetase like\": 207,\n", + " 'plectin': 29,\n", + " 'inner mitochondrial membrane peptidase subunit 1': 6,\n", + " 'inositol monophosphatase 1': 14,\n", + " 'histocompatibility minor 13': 14,\n", + " 'insulin like growth factor 2 mRNA binding protein 1': 20,\n", + " 'O-linked N-acetylglucosamine (GlcNAc) transferase': 34,\n", " 'zinc finger protein 479': 1,\n", - " 'caspase 12': 64,\n", - " 'SR-related CTD associated factor 11': 10,\n", - " 'cholinergic receptor muscarinic 3': 34,\n", - " 'C-X3-C motif chemokine receptor 1': 244,\n", - " 'Sp8 transcription factor': 83,\n", - " 'glial fibrillary acidic protein': 680,\n", + " 'Sp1 transcription factor': 274,\n", + " 'stratifin': 10,\n", + " 'keratin 10': 27,\n", + " 'keratin 6A': 8,\n", + " 'solute carrier family 6 member 19': 24,\n", + " 'caspase 12': 76,\n", + " 'SR-related CTD associated factor 11': 21,\n", + " 'HFM1': 29,\n", + " ' ATP dependent DNA helicase homolog': 29,\n", + " 'cholinergic receptor muscarinic 3': 38,\n", + " 'C-X3-C motif chemokine receptor 1': 320,\n", + " 'glial fibrillary acidic protein': 888,\n", " 'ribosomal protein L13a': 47,\n", - " 'folliculogenesis specific bHLH transcription factor': 12,\n", - " 'purinergic receptor P2Y11': 3,\n", - " 'glutamate metabotropic receptor 1': 13,\n", - " 'glutamate metabotropic receptor 5': 7,\n", - " 'pyrimidinergic receptor P2Y6': 3,\n", - " 'pyrimidinergic receptor P2Y4': 2,\n", - " 'purinergic receptor P2Y2': 8,\n", + " 'folliculogenesis specific bHLH transcription factor': 13,\n", + " 'purinergic receptor P2Y11': 5,\n", + " 'glutamate metabotropic receptor 1': 12,\n", + " 'glutamate metabotropic receptor 5': 8,\n", + " 'pyrimidinergic receptor P2Y6': 10,\n", + " 'pyrimidinergic receptor P2Y4': 3,\n", + " 'purinergic receptor P2Y2': 40,\n", " 'purinergic receptor P2Y1': 7,\n", - " 'olfactory marker protein': 44,\n", - " 'secreted phosphoprotein 1': 112,\n", - " 'ephrin B2': 100,\n", - " 'fission': 18,\n", - " ' mitochondrial 1': 18,\n", - " 'receptor accessory protein 5': 8,\n", - " 'dynamin 1': 26,\n", - " 'cytoskeleton associated protein 4': 14,\n", - " 'kinectin 1': 5,\n", - " 'trichoplein keratin filament binding': 4,\n", - " 'cytochrome b5 type A': 41,\n", - " 'endogenous retrovirus group W member 1': 163,\n", + " 'olfactory marker protein': 50,\n", + " 'secreted phosphoprotein 1': 147,\n", + " 'ephrin B2': 124,\n", + " 'natriuretic peptide B': 97,\n", + " 'angiotensin II receptor type 1': 394,\n", + " 'fission': 21,\n", + " ' mitochondrial 1': 21,\n", + " 'receptor accessory protein 5': 9,\n", + " 'dynamin 1': 32,\n", + " 'cytoskeleton associated protein 4': 15,\n", + " 'kinectin 1': 7,\n", + " 'trichoplein keratin filament binding': 8,\n", + " 'cytochrome b5 type A': 46,\n", + " '6-phosphogluconolactonase': 27,\n", + " 'endogenous retrovirus group W member 1': 179,\n", " 'pyroglutamyl-peptidase I': 25,\n", - " 'amphiphysin': 75,\n", - " 'FCH domain only 1': 28,\n", - " 'FCH domain only 2': 9,\n", - " 'SLIT-ROBO Rho GTPase activating protein 2': 4,\n", + " 'amphiphysin': 84,\n", + " 'FCH domain only 1': 29,\n", + " 'FCH domain only 2': 10,\n", + " 'SLIT-ROBO Rho GTPase activating protein 2': 5,\n", " 'neurofilament medium': 12,\n", - " 'BAI1 associated protein 2': 11,\n", - " 'sorting nexin 9': 6,\n", - " 'dynamin 1 like': 34,\n", - " 'dishevelled segment polarity protein 3': 5,\n", - " 'epsin 1': 20,\n", - " 'isoleucyl-tRNA synthetase': 12,\n", - " 'syndecan binding protein': 88,\n", - " 'discs large MAGUK scaffold protein 4': 113,\n", - " 'interleukin 3': 303,\n", + " 'BAI1 associated protein 2': 10,\n", + " 'sorting nexin 9': 9,\n", + " 'dynamin 1 like': 44,\n", + " 'dishevelled segment polarity protein 3': 7,\n", + " 'epsin 1': 31,\n", + " 'isoleucyl-tRNA synthetase': 16,\n", + " 'syndecan binding protein': 92,\n", + " 'discs large MAGUK scaffold protein 4': 118,\n", + " 'interleukin 3': 392,\n", " 'ariadne RBR E3 ubiquitin protein ligase 2': 5,\n", - " 'DGCR8': 63,\n", - " ' microprocessor complex subunit': 63,\n", - " 'exportin 5': 55,\n", - " 'poly(A)-specific ribonuclease': 16,\n", + " 'DGCR8': 73,\n", + " ' microprocessor complex subunit': 73,\n", + " 'exportin 5': 77,\n", + " 'poly(A)-specific ribonuclease': 25,\n", " 'zinc finger CCHC-type containing 11': 5,\n", " 'zinc finger CCHC-type containing 6': 5,\n", - " 'terminal uridylyl transferase 1': 7,\n", - " ' U6 snRNA-specific': 7,\n", - " 'glutamate-ammonia ligase': 66,\n", - " 'bromodomain containing 2': 32,\n", - " 'E2F transcription factor 1': 61,\n", - " 'SRY-box 4': 7,\n", - " 'ferritin light chain': 11,\n", - " 'ribosomal protein L9': 6,\n", - " 'cysteine rich angiogenic inducer 61': 9,\n", - " 'Kruppel like factor 9': 1,\n", - " 'anti-silencing function 1B histone chaperone': 5,\n", - " 'damage specific DNA binding protein 1': 43,\n", - " 'CD84 molecule': 7,\n", - " 'forkhead box P3': 1068,\n", - " 'myeloid derived growth factor': 316,\n", - " 'CD28 molecule': 645,\n", - " 'insulin receptor': 138,\n", - " 'basal cell adhesion molecule (Lutheran blood group)': 1,\n", - " 'TNF receptor superfamily member 12A': 17,\n", - " 'CD226 molecule': 25,\n", - " 'CD302 molecule': 23,\n", - " 'aryl hydrocarbon receptor': 46,\n", - " 'sonic hedgehog': 185,\n", - " 'period circadian regulator 2': 193,\n", - " 'sucrase-isomaltase': 163,\n", - " 'ribonuclease T2': 11,\n", - " ' G': 89,\n", - " ' B': 39,\n", - " 'C-type lectin domain family 4 member C': 49,\n", - " 'natural cytotoxicity triggering receptor 3': 40,\n", - " 'erb-b2 receptor tyrosine kinase 2': 350,\n", - " 'endogenous retrovirus group K member 5': 60,\n", - " 'serine incorporator 5': 48,\n", - " 'RAB7A': 329,\n", - " 'serine incorporator 3': 12,\n", - " 'NPC intracellular cholesterol transporter 1': 492,\n", - " 'Sp3 transcription factor': 28,\n", - " 'solute carrier family 7 member 9': 93,\n", - " 'solute carrier family 1 member 5': 30,\n", - " 'heterogeneous nuclear ribonucleoprotein A2/B1': 44,\n", - " 'lymphocyte antigen 6 family member E': 103,\n", - " ' urokinase receptor': 53,\n", - " 'vav guanine nucleotide exchange factor 1': 19,\n", - " 'interferon alpha and beta receptor subunit 1': 1562,\n", - " 'C-X-C motif chemokine ligand 9': 452,\n", - " 'DEAD-box helicase 3': 273,\n", - " ' X-linked': 427,\n", - " 'SP110 nuclear body protein': 10,\n", - " 'serpin family E member 1': 241,\n", - " ' lambda receptor 1': 257,\n", - " 'corticotropin releasing hormone receptor 2': 8,\n", - " 'helicase with zinc finger 2': 5,\n", - " ' transcriptional coactivator': 5,\n", - " 'ring finger protein 114': 15,\n", - " 'interferon regulatory factor 2': 81,\n", - " 'spermatogenesis associated serine rich 2 like': 5,\n", - " 'sialic acid binding Ig like lectin 1': 191,\n", - " 'cytohesin 1': 4,\n", - " 'allograft inflammatory factor 1': 75,\n", - " 'colony stimulating factor 1 receptor': 154,\n", - " 'purinergic receptor P2Y12': 266,\n", - " 'transmembrane protein 119': 33,\n", - " 'Rho GTPase activating protein 42': 1,\n", - " 'triggering receptor expressed on myeloid cells 2': 130,\n", - " 'CD74 molecule': 48,\n", - " 'natural killer cell granule protein 7': 6,\n", - " 'marker of proliferation Ki-67': 307,\n", - " 'cyclin A2': 24,\n", - " 'cyclin B2': 7,\n", - " 'C-C motif chemokine receptor 7': 358,\n", - " 'USH1 protein network component harmonin binding protein 1': 4,\n", - " 'mutated in colorectal cancers': 8,\n", - " 'centromere protein A': 10,\n", - " 'MIS12': 15,\n", - " 'aurora kinase B': 28,\n", - " 'telomerase reverse transcriptase': 164,\n", - " 'HFM1': 24,\n", - " ' ATP dependent DNA helicase homolog': 24,\n", - " 'N-methylpurine DNA glycosylase': 10,\n", - " 'proteolipid protein 1': 165,\n", - " 'calnexin': 306,\n", - " 'ALG12': 1,\n", - " ' alpha-1': 13,\n", - " '6-mannosyltransferase': 9,\n", - " 'G protein nucleolar 1 (putative)': 27,\n", - " 'azurocidin 1': 41,\n", - " 'natriuretic peptide B': 81,\n", - " ' serine 7': 11,\n", - " ' serine 11A': 26,\n", - " ' serine 11B': 7,\n", - " 'kallikrein related peptidase 13': 15,\n", - " 'kallikrein related peptidase 14': 5,\n", - " ' serine 12': 4,\n", - " ' serine 11E': 67,\n", - " ' serine 11F': 10,\n", - " ' serine 5': 11,\n", - " ' serine 6': 18,\n", - " 'hepsin': 42,\n", - " ' serine 9': 9,\n", - " 'kallikrein 1': 13,\n", - " 'kallikrein related peptidase 4': 4,\n", - " 'kallikrein related peptidase 3': 149,\n", - " 'kallikrein related peptidase 9': 3,\n", - " 'corin': 29,\n", - " ' serine peptidase': 29,\n", - " 'kallikrein related peptidase 15': 3,\n", - " 'kallikrein related peptidase 11': 120,\n", - " ' serine 15': 102,\n", - " 'kallikrein B1': 27,\n", - " 'glycophorin C (Gerbich blood group)': 165,\n", - " 'coiled-coil domain containing 9': 2,\n", - " 'ribonuclease P/MRP subunit p30': 12,\n", - " 'lysosomal associated membrane protein 1': 600,\n", - " 'VPS39': 34,\n", - " ' HOPS complex subunit': 59,\n", - " 'pancreatic polypeptide': 15,\n", - " 'galectin 8': 14,\n", - " 'nuclear receptor subfamily 3 group C member 1': 112,\n", - " 'Rho GTPase activating protein 9': 2,\n", - " 'dedicator of cytokinesis 4': 4,\n", + " 'terminal uridylyl transferase 1': 8,\n", + " ' U6 snRNA-specific': 8,\n", + " 'glutamate-ammonia ligase': 79,\n", + " 'E2F transcription factor 1': 91,\n", + " 'SRY-box 4': 8,\n", + " 'ferritin light chain': 15,\n", " ...}" ] }, - "execution_count": 82, + "execution_count": 17, "metadata": {}, "output_type": "execute_result" } @@ -1973,7 +2047,7 @@ }, { "cell_type": "code", - "execution_count": 83, + "execution_count": 18, "metadata": {}, "outputs": [], "source": [ @@ -1982,1016 +2056,1016 @@ }, { "cell_type": "code", - "execution_count": 84, + "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "{'Pneumonia': 21615,\n", - " 'Myopathy': 391,\n", - " '': 31364,\n", - " 'Increased reactive oxygen species production': 2214,\n", - " 'Alopecia': 915,\n", - " 'Palpebral edema': 69,\n", - " 'Papilloma': 492,\n", - " 'T-cell lymphoma': 280,\n", - " 'Recurrent lower respiratory tract infections': 2032,\n", - " 'Diarrhea': 21696,\n", - " 'Intermittent diarrhea': 79,\n", - " 'Respiratory tract infection': 9935,\n", - " 'Allergy': 6174,\n", - " 'Fever': 20396,\n", - " 'Elevated hepatic transaminase': 552,\n", - " 'Abnormal liver physiology': 59,\n", - " 'Cough': 11009,\n", - " 'Breathing dysregulation': 206,\n", - " 'Hepatic steatosis': 510,\n", - " 'Nonproductive cough': 788,\n", - " 'Elevated C-reactive protein level': 193,\n", - " 'Myalgia': 2530,\n", - " 'Inflammation of the large intestine': 981,\n", - " 'Hypertension': 2561,\n", - " \"Crohn's disease\": 463,\n", - " 'Respiratory failure': 2603,\n", - " 'Autoimmunity': 6234,\n", - " 'Systemic lupus erythematosus': 667,\n", - " 'Rheumatoid arthritis': 1121,\n", - " 'Breast carcinoma': 1595,\n", - " 'Increased inflammatory response': 142,\n", - " 'Fatigue': 1896,\n", - " 'Dyspnea': 4480,\n", - " 'Phenotypic abnormality': 572,\n", - " 'Joint swelling': 63,\n", - " 'Conjunctival hyperemia': 107,\n", - " 'Edema': 5969,\n", - " 'Arthralgia': 997,\n", - " 'Skin rash': 2946,\n", - " 'Pruritus': 1114,\n", - " 'Microcephaly': 631,\n", - " 'Paralysis': 2433,\n", - " 'Cerebral edema': 370,\n", - " 'Seizures': 2551,\n", - " 'Neoplasm': 16889,\n", - " 'Myocarditis': 1365,\n", - " 'Lymphocytosis': 392,\n", - " 'Rhinorrhea': 2916,\n", - " 'Chest pain': 778,\n", - " 'Immunodeficiency': 1962,\n", - " 'Hypoalbuminemia': 730,\n", - " 'Chronic obstructive pulmonary disease': 2336,\n", - " 'Decrease in T cell count': 109,\n", - " 'Multiple myeloma': 337,\n", - " 'Chronic myelogenous leukemia': 159,\n", - " 'Inflammatory abnormality of the skin': 1639,\n", - " 'Nausea and vomiting': 954,\n", - " 'Acute lymphoblastic leukemia': 166,\n", - " 'Renal cell carcinoma': 227,\n", - " 'Hepatitis': 3791,\n", - " 'Lymphopenia': 1754,\n", - " 'Anxiety': 2348,\n", - " 'Weight loss': 5091,\n", - " 'Respiratory distress': 2428,\n", - " 'Synovial sarcoma': 23,\n", - " 'Pleural effusion': 1625,\n", - " \"Kaposi's sarcoma\": 262,\n", - " 'Neurodegeneration': 1552,\n", - " 'Herpes simplex encephalitis': 52,\n", - " 'Dementia': 620,\n", - " 'Type II diabetes mellitus': 613,\n", - " 'Parkinsonism': 74,\n", - " 'Laryngeal carcinoma': 48,\n", - " 'Abnormality of mitochondrial metabolism': 271,\n", - " 'Lewy bodies': 35,\n", - " 'Neuroblastoma': 433,\n", - " 'Decreased pulmonary function': 258,\n", - " 'Recurrent pneumonia': 1819,\n", - " 'Situs inversus totalis': 35,\n", - " 'Rosette': 259,\n", + "{'Anosmia': 92,\n", + " 'Parageusia': 28,\n", + " 'Respiratory distress': 2956,\n", + " 'Hyposmia': 61,\n", + " '': 37956,\n", + " 'Pneumonia': 24919,\n", + " 'Myopathy': 434,\n", + " 'Increased reactive oxygen species production': 2767,\n", + " 'Alopecia': 944,\n", + " 'Palpebral edema': 66,\n", + " 'Papilloma': 549,\n", + " 'T-cell lymphoma': 306,\n", + " 'Functional respiratory abnormality': 5134,\n", + " 'Recurrent lower respiratory tract infections': 2505,\n", + " 'Diarrhea': 24218,\n", + " 'Intermittent diarrhea': 82,\n", + " 'Respiratory tract infection': 11847,\n", + " 'Allergy': 7061,\n", + " 'Fever': 26441,\n", + " 'Elevated hepatic transaminase': 620,\n", + " 'Abnormal liver physiology': 69,\n", + " 'Cough': 12688,\n", + " 'Productive cough': 1295,\n", + " 'Breathing dysregulation': 243,\n", + " 'Hepatic steatosis': 566,\n", + " 'Nonproductive cough': 960,\n", + " 'Elevated C-reactive protein level': 238,\n", + " 'Myalgia': 2948,\n", + " 'Inflammation of the large intestine': 1145,\n", + " 'Hypertension': 3336,\n", + " \"Crohn's disease\": 653,\n", + " 'Respiratory failure': 3097,\n", + " 'Autoimmunity': 7926,\n", + " 'Systemic lupus erythematosus': 798,\n", + " 'Rheumatoid arthritis': 1371,\n", + " 'Breast carcinoma': 1993,\n", + " 'Increased inflammatory response': 182,\n", + " 'Fatigue': 2296,\n", + " 'Dyspnea': 5902,\n", + " 'Phenotypic abnormality': 1591,\n", + " 'Joint swelling': 74,\n", + " 'Conjunctival hyperemia': 118,\n", + " 'Edema': 6478,\n", + " 'Arthralgia': 1124,\n", + " 'Skin rash': 3228,\n", + " 'Pruritus': 1151,\n", + " 'Microcephaly': 680,\n", + " 'Astigmatism': 26,\n", + " 'Paralysis': 2844,\n", + " 'Ground-glass opacification on pulmonary HRCT': 767,\n", + " 'Cerebral edema': 404,\n", + " 'Seizures': 2794,\n", + " 'Neoplasm': 19391,\n", + " 'Myocarditis': 1634,\n", + " 'Lymphocytosis': 414,\n", + " 'Rhinorrhea': 3458,\n", + " 'Chest pain': 855,\n", + " 'Immunodeficiency': 2338,\n", + " 'Lymphopenia': 2192,\n", + " 'Hypoalbuminemia': 795,\n", + " 'Chronic obstructive pulmonary disease': 2808,\n", + " 'Decrease in T cell count': 155,\n", + " 'Multiple myeloma': 463,\n", + " 'Chronic myelogenous leukemia': 180,\n", + " 'Inflammatory abnormality of the skin': 1726,\n", + " 'Nausea and vomiting': 1086,\n", + " 'Acute lymphoblastic leukemia': 226,\n", + " 'Renal cell carcinoma': 261,\n", + " 'Hepatitis': 4355,\n", + " 'Anxiety': 2836,\n", + " 'Weight loss': 5728,\n", + " 'Synovial sarcoma': 28,\n", + " 'Decreased liver function': 510,\n", + " 'Abnormality of the liver': 639,\n", + " 'Hepatocellular carcinoma': 1243,\n", + " \"Kaposi's sarcoma\": 322,\n", + " 'Neurodegeneration': 2063,\n", + " 'Herpes simplex encephalitis': 63,\n", + " 'Dementia': 795,\n", + " 'Type II diabetes mellitus': 795,\n", + " 'Parkinsonism': 90,\n", + " 'Laryngeal carcinoma': 56,\n", + " 'Abnormality of mitochondrial metabolism': 327,\n", + " 'Lewy bodies': 60,\n", + " 'Neuroblastoma': 567,\n", + " 'Situs inversus totalis': 38,\n", + " 'Rosette': 283,\n", " 'Thoracic dysplasia': 2,\n", " 'Short ribs': 3,\n", " 'Abnormal liver lobulation': 1,\n", - " 'Asplenia': 101,\n", + " 'Asplenia': 115,\n", " 'Abnormal ciliary motility': 5,\n", - " 'Rod-cone dystrophy': 40,\n", - " 'Skeletal dysplasia': 13,\n", - " 'Agitation': 315,\n", - " 'Postural instability': 1361,\n", - " 'Hepatocellular carcinoma': 1061,\n", - " 'Recurrent infections': 1340,\n", - " 'Asthma': 8898,\n", - " 'Type I diabetes mellitus': 360,\n", - " 'Anemia': 3815,\n", - " 'Diabetes mellitus': 1491,\n", - " 'Severe infection': 1193,\n", - " 'Stroke': 1324,\n", - " 'IgA deposition in the glomerulus': 19,\n", - " 'Abnormal heart morphology': 378,\n", - " 'Nephropathy': 899,\n", - " 'Acute kidney injury': 846,\n", - " 'Abnormality of the kidney': 347,\n", - " 'Bladder carcinoma': 166,\n", - " 'Malnutrition': 1108,\n", - " 'Increased T cell count': 119,\n", - " 'Chronic infection': 1853,\n", - " 'Stage 5 chronic kidney disease': 539,\n", - " 'Albuminuria': 81,\n", - " 'Azotemia': 546,\n", - " 'Hypoxemia': 1247,\n", - " 'Abnormal renal physiology': 26,\n", - " 'Sepsis': 5215,\n", - " 'Septic shock': 1552,\n", - " 'Aplasia/hypoplasia of the extremities': 13,\n", - " 'Limb undergrowth': 15,\n", - " 'Hearing impairment': 536,\n", - " 'Prostate cancer': 846,\n", - " 'Metabolic acidosis': 673,\n", - " 'Abnormality of the coagulation cascade': 812,\n", - " 'Chronic lung disease': 815,\n", - " 'Elevated serum creatinine': 162,\n", - " 'Alcoholism': 248,\n", - " 'Vomiting': 4969,\n", - " 'Lung adenocarcinoma': 306,\n", - " 'Colon cancer': 641,\n", - " 'Behavioral abnormality': 657,\n", - " 'Leukemia': 1550,\n", - " 'Renal insufficiency': 1683,\n", - " 'Leukopenia': 1224,\n", - " 'Nausea': 968,\n", - " 'Thrombocytopenia': 2363,\n", - " 'Elevated serum aspartate aminotransferase': 32,\n", - " 'Hyponatremia': 353,\n", - " 'Allergic rhinitis': 963,\n", - " 'Nasal polyposis': 235,\n", - " 'Rhinitis': 1496,\n", - " 'Neoplasm of the pituitary gland': 63,\n", - " 'Vitamin A deficiency': 146,\n", - " 'Blindness': 895,\n", - " 'Headache': 3230,\n", - " 'Vertigo': 412,\n", - " 'Pulmonary fibrosis': 697,\n", - " 'Scaling skin': 412,\n", - " 'Insomnia': 238,\n", - " 'Whooping cough': 223,\n", - " 'Abnormal lung morphology': 436,\n", - " 'Decreased circulating total IgM': 32,\n", - " 'Tachypnea': 1085,\n", - " 'Recurrent upper respiratory tract infections': 1555,\n", - " 'Decreased inflammatory response': 52,\n", - " 'Obesity': 1842,\n", - " 'Growth delay': 638,\n", - " 'Urticaria': 586,\n", - " 'Otitis media': 1216,\n", - " 'Ear pain': 125,\n", - " 'Nasal obstruction': 1028,\n", - " 'Opportunistic infection': 978,\n", - " 'Alzheimer disease': 105,\n", - " 'Congenital stationary cone dysfunction': 4,\n", - " 'Retinal degeneration': 294,\n", - " 'Meningitis': 2871,\n", - " 'Encephalitis': 4502,\n", - " 'Cervix cancer': 805,\n", - " 'Restrictive behavior': 14,\n", - " 'Unusual CNS infection': 858,\n", - " 'Depressivity': 3887,\n", - " 'EEG abnormality': 19,\n", - " 'Pancreatitis': 991,\n", - " 'Atopic dermatitis': 546,\n", - " 'Seborrheic dermatitis': 79,\n", - " 'Bacteremia': 1776,\n", - " 'Colorectal carcinoma': 533,\n", - " 'Psychosis': 144,\n", - " 'Chills': 1205,\n", - " 'Gastroparesis': 118,\n", - " 'Hematochezia': 239,\n", - " 'Pulmonary opacity': 98,\n", - " 'Productive cough': 335,\n", - " 'Scotoma': 38,\n", - " 'Wide nose': 3,\n", - " 'Facial neoplasm': 13,\n", - " 'Overweight': 350,\n", - " 'Crackles': 1053,\n", - " 'Respiratory arrest': 99,\n", - " 'Ulcerative colitis': 417,\n", - " 'Tremor': 731,\n", - " 'Dysphasia': 14,\n", - " 'Dysarthria': 49,\n", - " 'Ptosis': 83,\n", - " 'Tachycardia': 1016,\n", - " 'Generalized muscle weakness': 101,\n", - " 'Anorexia': 3848,\n", - " 'Arrhythmia': 887,\n", - " 'Vitamin D deficiency': 117,\n", - " 'Atherosclerosis': 851,\n", - " 'Hemoptysis': 541,\n", - " 'Interstitial pulmonary abnormality': 1,\n", - " 'Interstitial pneumonitis': 191,\n", - " 'Hydrops fetalis': 42,\n", - " 'Hydrocephalus': 430,\n", - " 'Hydranencephaly': 112,\n", + " 'Rod-cone dystrophy': 57,\n", + " 'Skeletal dysplasia': 20,\n", + " 'Agitation': 355,\n", + " 'Nausea': 1114,\n", + " 'Postural instability': 1570,\n", + " 'Recurrent infections': 1626,\n", + " 'Asthma': 10928,\n", + " 'Type I diabetes mellitus': 478,\n", + " 'Anemia': 4019,\n", + " 'Diabetes mellitus': 1644,\n", + " 'Severe infection': 1407,\n", + " 'Stroke': 1971,\n", + " 'IgA deposition in the glomerulus': 24,\n", + " 'Malnutrition': 1229,\n", + " 'Tachypnea': 1168,\n", + " 'Pulmonary infiltrates': 4039,\n", + " 'Abnormal heart morphology': 472,\n", + " 'Nephropathy': 1090,\n", + " 'Acute kidney injury': 1000,\n", + " 'Abnormality of the kidney': 401,\n", + " 'Bladder carcinoma': 196,\n", + " 'Pleural effusion': 1824,\n", + " 'Stage 5 chronic kidney disease': 593,\n", + " 'Atrial fibrillation': 288,\n", + " 'Arrhythmia': 1014,\n", + " 'Recurrent pneumonia': 2323,\n", + " 'Increased T cell count': 158,\n", + " 'Chronic infection': 2251,\n", + " 'Pharyngitis': 3955,\n", + " 'Albuminuria': 109,\n", + " 'Leukopenia': 1676,\n", + " 'Azotemia': 552,\n", + " 'Hypoxemia': 1381,\n", + " 'Abnormal renal physiology': 28,\n", + " 'Sepsis': 6050,\n", + " 'Septic shock': 1759,\n", + " 'Aplasia/hypoplasia of the extremities': 17,\n", + " 'Limb undergrowth': 20,\n", + " 'Headache': 3684,\n", + " 'Stomach cancer': 574,\n", + " 'Colon cancer': 792,\n", + " 'Renal insufficiency': 1872,\n", + " 'Allergic rhinitis': 1050,\n", + " 'Peritonitis': 1825,\n", + " 'Prostate cancer': 1124,\n", + " 'Metabolic acidosis': 687,\n", + " 'Abnormality of the coagulation cascade': 894,\n", + " 'Chronic lung disease': 1006,\n", + " 'Elevated serum creatinine': 186,\n", + " 'Alcoholism': 279,\n", + " 'Vomiting': 5367,\n", + " 'Lung adenocarcinoma': 345,\n", + " 'Behavioral abnormality': 799,\n", + " 'Risk taking': 63,\n", + " 'Palpitations': 119,\n", + " 'Coronary artery atherosclerosis': 485,\n", + " 'Sinus tachycardia': 93,\n", + " 'Carcinoma': 4071,\n", + " 'Vertigo': 479,\n", + " 'Shivering': 146,\n", + " 'Conjunctivitis': 1986,\n", + " 'Depressivity': 4496,\n", + " 'Agranulocytosis': 108,\n", + " 'Neutrophilia': 822,\n", + " 'Thrombocytopenia': 2648,\n", + " 'Decreased eosinophil count': 17,\n", + " 'Elevated serum aspartate aminotransferase': 35,\n", + " 'Hyponatremia': 375,\n", + " 'Nasal polyposis': 293,\n", + " 'Rhinitis': 2090,\n", + " 'Neoplasm of the pituitary gland': 65,\n", + " 'Vitamin A deficiency': 153,\n", + " 'Hemoptysis': 592,\n", + " 'Increased blood urea nitrogen': 80,\n", + " 'Blindness': 982,\n", + " 'Usual interstitial pneumonia': 44,\n", + " 'Bronchitis': 2287,\n", + " 'Pulmonary edema': 1697,\n", + " 'Germ cell neoplasia': 25,\n", + " 'Pulmonary fibrosis': 886,\n", + " 'Insomnia': 288,\n", + " 'Whooping cough': 263,\n", + " 'Abnormal EKG': 61,\n", + " 'Abnormality of the gastrointestinal tract': 258,\n", + " 'Sinus bradycardia': 35,\n", + " 'Atrioventricular block': 27,\n", + " 'Bradycardia': 457,\n", + " 'First degree atrioventricular block': 3,\n", + " 'Abnormality of coagulation': 595,\n", + " 'Abnormal lung morphology': 528,\n", + " 'Chronic kidney disease': 703,\n", + " 'Subarachnoid hemorrhage': 86,\n", + " 'Congestive heart failure': 2912,\n", + " 'Cerebral hemorrhage': 165,\n", + " 'Peripheral arterial stenosis': 101,\n", + " 'Abdominal aortic aneurysm': 34,\n", + " 'Ischemic stroke': 309,\n", + " 'Myocardial infarction': 920,\n", + " 'Decreased circulating total IgM': 38,\n", + " 'Recurrent upper respiratory tract infections': 1848,\n", + " 'Jaundice': 1466,\n", + " 'Recurrent singultus': 31,\n", + " 'Decreased inflammatory response': 63,\n", + " 'Obesity': 2169,\n", + " 'Pulmonary opacity': 118,\n", + " 'Neoplasm of the lung': 323,\n", + " 'Growth delay': 712,\n", + " 'Urticaria': 595,\n", + " 'Otitis media': 1428,\n", + " 'Ear pain': 142,\n", + " 'Nasal obstruction': 1286,\n", + " 'Opportunistic infection': 1104,\n", + " 'Alzheimer disease': 147,\n", + " 'Congenital stationary cone dysfunction': 6,\n", + " 'Retinal degeneration': 333,\n", + " 'Meningitis': 3148,\n", + " 'Encephalitis': 5466,\n", + " 'Cervix cancer': 992,\n", + " 'Restrictive behavior': 17,\n", + " 'Unusual CNS infection': 1142,\n", + " 'EEG abnormality': 21,\n", + " 'Pancreatitis': 1044,\n", + " 'Cardiac arrest': 654,\n", + " 'Emphysema': 898,\n", + " 'Bronchiectasis': 1109,\n", + " 'Pneumothorax': 832,\n", + " 'Atopic dermatitis': 611,\n", + " 'Seborrheic dermatitis': 81,\n", + " 'Bacteremia': 1915,\n", + " 'Stereotypy': 63,\n", + " 'Abnormality of the hand': 5,\n", + " 'Skeletal muscle atrophy': 460,\n", + " 'Respiratory insufficiency': 321,\n", + " 'Colorectal carcinoma': 623,\n", + " 'Psychosis': 188,\n", + " 'Sneeze': 2421,\n", + " 'Neutropenia': 1624,\n", + " 'Chills': 1364,\n", + " 'Gastroparesis': 120,\n", + " 'Hematochezia': 255,\n", + " 'Increased lactate dehydrogenase activity': 76,\n", + " 'Scotoma': 52,\n", + " 'Wide nose': 4,\n", + " 'Dehydration': 4169,\n", + " 'B Acute Lymphoblastic Leukemia': 17,\n", + " 'Facial neoplasm': 16,\n", + " 'Overweight': 404,\n", + " 'Crackles': 1155,\n", + " 'Chronic metabolic acidosis': 8,\n", + " 'Respiratory arrest': 107,\n", + " 'Ulcerative colitis': 479,\n", + " 'Tremor': 786,\n", + " 'Dysphasia': 15,\n", + " 'Dysarthria': 50,\n", + " 'Ptosis': 85,\n", + " 'Tachycardia': 1100,\n", + " 'Generalized muscle weakness': 102,\n", + " 'Anorexia': 4029,\n", + " 'Vitamin D deficiency': 138,\n", + " 'Scaling skin': 471,\n", + " 'Atherosclerosis': 1136,\n", + " 'Interstitial pulmonary abnormality': 15,\n", + " 'Interstitial pneumonitis': 230,\n", + " 'Hydrops fetalis': 46,\n", + " 'Hydrocephalus': 483,\n", + " 'Hydranencephaly': 113,\n", " 'Generalized myoclonic seizures': 12,\n", - " 'Generalized-onset seizure': 84,\n", + " 'Generalized-onset seizure': 88,\n", " 'Impaired myocardial contractility': 13,\n", - " 'Clonus': 18,\n", - " 'Focal-onset seizure': 72,\n", - " 'Carcinoma': 3569,\n", - " 'Neoplasm of the liver': 203,\n", - " 'Glioblastoma multiforme': 403,\n", - " 'Cholangiocarcinoma': 111,\n", - " 'Hypokalemia': 367,\n", - " 'Ventricular arrhythmia': 117,\n", - " 'Abnormality of the musculature': 42,\n", - " 'Abnormal EKG': 53,\n", - " 'Increased blood urea nitrogen': 80,\n", - " 'Bronchitis': 1965,\n", - " 'Prolonged prothrombin time': 38,\n", - " 'Abdominal pain': 2291,\n", - " 'Hypocalcemia': 454,\n", - " 'Abdominal symptom': 38,\n", - " 'Respiratory insufficiency': 266,\n", - " 'Abnormality of coagulation': 514,\n", - " 'Abnormality of the immune system': 317,\n", - " 'Chronic kidney disease': 596,\n", - " 'Neutrophilia': 715,\n", - " 'Cognitive impairment': 347,\n", - " 'Brain neoplasm': 277,\n", - " 'Astrocytoma': 245,\n", - " 'Hypercoagulability': 88,\n", - " 'Chest tightness': 140,\n", - " 'Pain': 4686,\n", - " 'Congestive heart failure': 2437,\n", - " 'Rhabdomyolysis': 231,\n", - " 'Flushing': 537,\n", - " 'Lymphoma': 2789,\n", - " 'Endometrial carcinoma': 49,\n", - " 'Uterine leiomyoma': 46,\n", - " 'Scarring': 1010,\n", - " 'Insulin resistance': 450,\n", - " 'Insulin insensitivity': 450,\n", - " 'Hypercholesterolemia': 243,\n", - " 'Abnormality of the cardiovascular system': 247,\n", + " 'Clonus': 20,\n", + " 'Focal-onset seizure': 73,\n", + " 'Neoplasm of the liver': 228,\n", + " 'Glioblastoma multiforme': 468,\n", + " 'Cholangiocarcinoma': 114,\n", + " 'Chest tightness': 178,\n", + " 'Hypokalemia': 396,\n", + " 'Ventricular arrhythmia': 136,\n", + " 'Abnormality of the musculature': 50,\n", + " 'Prolonged prothrombin time': 43,\n", + " 'Abdominal pain': 2381,\n", + " 'Hypocalcemia': 461,\n", + " 'Abdominal symptom': 46,\n", + " 'Abnormality of the immune system': 391,\n", + " 'Lethargy': 2347,\n", + " 'Cognitive impairment': 464,\n", + " 'Brain neoplasm': 348,\n", + " 'Astrocytoma': 273,\n", + " 'Hypercoagulability': 96,\n", + " 'Pain': 5149,\n", + " 'Rhabdomyolysis': 253,\n", + " 'Flushing': 590,\n", + " 'Lymphoma': 3113,\n", + " 'Endometrial carcinoma': 50,\n", + " 'Uterine leiomyoma': 49,\n", + " 'Scarring': 1124,\n", + " 'Insulin resistance': 568,\n", + " 'Insulin insensitivity': 568,\n", + " 'Hypercholesterolemia': 270,\n", + " 'Abnormality of the cardiovascular system': 311,\n", + " 'B-cell lymphoma': 542,\n", + " 'Acute promyelocytic leukemia': 126,\n", + " 'Decreased body weight': 702,\n", + " 'Hostility': 104,\n", + " 'Obsessive-compulsive behavior': 46,\n", " 'Heat intolerance': 3,\n", - " 'B-cell lymphoma': 468,\n", - " 'Acute promyelocytic leukemia': 105,\n", - " 'Pulmonary edema': 1521,\n", - " 'Decreased body weight': 613,\n", - " 'Hostility': 82,\n", - " 'Obsessive-compulsive behavior': 37,\n", - " 'Acidosis': 857,\n", - " 'Overgrowth': 722,\n", - " 'Shivering': 142,\n", - " 'Conjunctivitis': 1844,\n", - " 'Impaired social interactions': 8,\n", - " 'immune tolerance': 611,\n", - " 'Decreased proportion of CD4-positive T cells': 64,\n", - " 'Allodynia': 36,\n", - " 'Abnormality of lymphocytes': 19,\n", - " 'Dilatation': 892,\n", - " 'Unhappy demeanor': 65,\n", - " 'Poor appetite': 416,\n", - " 'Recurrent infection of the gastrointestinal tract': 407,\n", - " 'Hypersensitivity pneumonitis': 120,\n", - " 'Coma': 972,\n", - " 'Cirrhosis': 1453,\n", - " 'Coronary artery atherosclerosis': 397,\n", - " 'Gastrointestinal hemorrhage': 264,\n", - " 'Venous thrombosis': 84,\n", - " 'Hyperglycemia': 679,\n", - " 'Renal neoplasm': 59,\n", - " 'Hepatic necrosis': 470,\n", - " 'Amyotrophic lateral sclerosis': 177,\n", - " 'Premature birth': 294,\n", - " 'Cardiac arrest': 612,\n", - " 'Preeclampsia': 135,\n", - " 'Fetal distress': 57,\n", - " 'Spontaneous abortion': 347,\n", - " 'Placental abruption': 26,\n", - " 'Patent ductus arteriosus': 133,\n", - " 'Wheezing': 2726,\n", - " 'Neonatal sepsis': 214,\n", - " 'Neoplasm of the pancreas': 96,\n", - " 'Elevated serum creatine phosphokinase': 92,\n", + " 'Hypothyroidism': 440,\n", + " 'Unilateral facial palsy': 7,\n", + " 'Hyperthyroidism': 390,\n", + " 'Sinusitis': 1454,\n", + " 'Recurrent infection of the gastrointestinal tract': 470,\n", + " 'Anaphylactic shock': 668,\n", + " 'Acute pancreatitis': 287,\n", + " 'Poor appetite': 1455,\n", + " 'Asthenia': 123,\n", + " 'Impaired social interactions': 11,\n", + " 'immune tolerance': 764,\n", + " 'Decreased proportion of CD4-positive T cells': 92,\n", + " 'Allodynia': 42,\n", + " 'Abnormality of lymphocytes': 24,\n", + " 'Acidosis': 914,\n", + " 'Dilatation': 991,\n", + " 'Leukocytosis': 1070,\n", + " 'Unhappy demeanor': 74,\n", + " 'Sleep disturbance': 271,\n", + " 'Decreased red blood cell count': 45,\n", + " 'Cirrhosis': 1635,\n", + " 'Congenital microcephaly': 20,\n", + " 'Hypersensitivity pneumonitis': 136,\n", + " 'Hepatic failure': 654,\n", + " 'Intestinal bleeding': 103,\n", + " 'Pleural thickening': 61,\n", + " 'Atelectasis': 649,\n", + " 'Lymphadenopathy': 1333,\n", + " 'Muscle weakness': 331,\n", + " 'Myositis': 433,\n", + " 'Non-small cell lung carcinoma': 314,\n", + " 'Myelitis': 350,\n", + " 'Bowel incontinence': 84,\n", + " 'Hyporeflexia': 31,\n", + " 'Paresthesia': 134,\n", + " 'Sensory impairment': 122,\n", + " 'Brain atrophy': 48,\n", + " 'Neuropathic pain': 175,\n", + " 'Reduced consciousness/confusion': 243,\n", + " 'Macular edema': 40,\n", + " 'Leukemia': 1823,\n", + " 'Confusion': 410,\n", + " 'Hyperglycemia': 810,\n", + " 'Stomatitis': 575,\n", + " 'Hyperbilirubinemia': 289,\n", + " 'Coma': 1060,\n", + " 'Pleuritis': 624,\n", + " 'Malabsorption': 1140,\n", + " 'Proteinuria': 598,\n", + " 'Gastrointestinal hemorrhage': 286,\n", + " 'Venous thrombosis': 95,\n", + " 'Hepatic necrosis': 506,\n", + " 'Amyotrophic lateral sclerosis': 232,\n", + " 'Premature birth': 361,\n", + " 'Preeclampsia': 173,\n", + " 'Fetal distress': 73,\n", + " 'Spontaneous abortion': 390,\n", + " 'Placental abruption': 29,\n", + " 'Patent ductus arteriosus': 145,\n", + " 'Wheezing': 3382,\n", + " 'Neonatal sepsis': 262,\n", + " 'Abnormality of pulmonary circulation': 640,\n", + " 'Hepatic fibrosis': 466,\n", + " 'Pulmonary arterial hypertension': 125,\n", + " 'Neoplasm of the pancreas': 106,\n", + " 'Elevated serum creatine phosphokinase': 106,\n", " 'Increased NT-proBNP level': 11,\n", - " 'Neural tube defect': 53,\n", - " 'Epiphora': 348,\n", - " 'Osteosarcoma': 322,\n", - " 'Decreased liver function': 452,\n", - " 'Elevated serum alanine aminotransferase': 65,\n", - " 'Abnormality of the liver': 569,\n", - " 'Inertia': 165,\n", - " 'Hepatic failure': 599,\n", - " 'Abnormality of pulmonary circulation': 528,\n", - " 'Hypotension': 1181,\n", - " 'Abnormal glycosylation': 10,\n", - " 'Orchitis': 254,\n", - " 'Cardiomyopathy': 654,\n", - " 'Orthopnea': 54,\n", - " 'Apnea': 484,\n", - " 'Increased body weight': 1434,\n", - " 'Arthritis': 1717,\n", - " 'Frontotemporal dementia': 23,\n", - " 'Progressive neurologic deterioration': 59,\n", - " 'Sarcoma': 556,\n", - " 'Asthenia': 94,\n", - " 'Emphysema': 827,\n", - " 'Tenesmus': 303,\n", - " 'Peripheral demyelination': 2960,\n", - " 'Pulmonary arterial hypertension': 93,\n", - " 'Hepatomegaly': 653,\n", - " 'Hepatic fibrosis': 374,\n", - " 'Acute hepatic failure': 145,\n", - " 'Beta-cell dysfunction': 22,\n", - " 'Pericardial effusion': 242,\n", - " 'Lymphadenopathy': 1230,\n", - " 'Non-small cell lung carcinoma': 275,\n", - " 'Abnormality of the nervous system': 552,\n", - " 'Proteopathy': 423,\n", + " 'Hearing impairment': 636,\n", + " 'Neural tube defect': 55,\n", + " 'Epiphora': 367,\n", + " 'Small for gestational age': 574,\n", + " 'Intrauterine growth retardation': 177,\n", + " 'Secretory diarrhea': 166,\n", + " 'Osteosarcoma': 361,\n", + " 'Elevated serum alanine aminotransferase': 74,\n", + " 'Inertia': 201,\n", + " 'Chronic bronchitis': 670,\n", + " 'Hyperlipidemia': 254,\n", + " 'Abnormality of lipid metabolism': 154,\n", + " 'Hypotension': 1311,\n", + " 'Amenorrhea': 21,\n", + " 'Abnormal glycosylation': 13,\n", + " 'Peripheral neuropathy': 788,\n", + " 'Retinopathy': 272,\n", + " 'Orchitis': 260,\n", + " 'Cardiomyopathy': 739,\n", + " 'Orthopnea': 55,\n", + " 'Apnea': 573,\n", + " 'Acute hepatitis': 511,\n", + " 'Constitutional symptom': 1919,\n", + " 'Myelofibrosis': 98,\n", + " 'Increased body weight': 1585,\n", + " 'Arthritis': 1963,\n", + " 'Frontotemporal dementia': 29,\n", + " 'Progressive neurologic deterioration': 74,\n", + " 'Sarcoma': 586,\n", + " 'No social interaction': 1,\n", + " 'Autistic behavior': 46,\n", + " 'Tenesmus': 308,\n", + " 'Peripheral demyelination': 3916,\n", + " 'Hepatomegaly': 689,\n", + " 'Acute hepatic failure': 171,\n", + " 'Pericardial effusion': 262,\n", + " 'Decreased pulmonary function': 306,\n", + " 'Abnormality of the nervous system': 653,\n", + " 'Intralobular interstitial thickening': 15,\n", + " 'Increased body mass index': 88,\n", + " 'Pulmonary embolism': 328,\n", + " 'Proteopathy': 522,\n", " 'Dilatation of the pancreatic duct': 2,\n", - " 'Chronic pancreatitis': 148,\n", - " 'Hernia': 471,\n", - " 'Constipation': 610,\n", - " 'Syncope': 204,\n", - " 'Sneeze': 367,\n", - " 'Palpitations': 103,\n", - " 'Myocardial infarction': 715,\n", - " 'Atrioventricular block': 24,\n", - " 'Mitral regurgitation': 90,\n", + " 'Chronic pancreatitis': 155,\n", + " 'Overgrowth': 771,\n", + " 'Hernia': 480,\n", + " 'Psoriasiform dermatitis': 473,\n", + " 'Heart block': 34,\n", + " 'Abnormality of vision': 13,\n", + " 'Acne inversa': 6,\n", + " 'Disseminated intravascular coagulation': 656,\n", + " 'Immune dysregulation': 282,\n", + " 'Acute bronchitis': 595,\n", + " 'Constipation': 648,\n", + " 'Syncope': 214,\n", + " 'Low-grade fever': 507,\n", + " 'Prostatitis': 152,\n", + " 'Benign prostatic hyperplasia': 50,\n", + " 'Mitral regurgitation': 98,\n", " 'Aortic regurgitation': 21,\n", " 'Left atrial enlargement': 24,\n", - " 'Abnormality of the respiratory system': 208,\n", - " 'Sinus tachycardia': 83,\n", - " 'Testicular neoplasm': 75,\n", - " 'Male infertility': 80,\n", - " 'Low-grade fever': 475,\n", - " 'Proteinuria': 527,\n", - " 'Hematuria': 449,\n", - " 'Prolonged partial thromboplastin time': 40,\n", - " 'Glomerulonephritis': 506,\n", - " 'Recurrent urinary tract infections': 1064,\n", - " 'T-cell neoplasm': 40,\n", - " 'Melanoma': 1431,\n", + " 'Abnormality of the respiratory system': 248,\n", + " 'Testicular neoplasm': 78,\n", + " 'Male infertility': 89,\n", + " 'Neurological speech impairment': 16,\n", + " 'Self-injurious behavior': 63,\n", + " 'Hematuria': 467,\n", + " 'Prolonged partial thromboplastin time': 46,\n", + " 'Glomerulonephritis': 556,\n", + " 'Recurrent urinary tract infections': 1189,\n", + " 'T-cell neoplasm': 50,\n", + " 'Melanoma': 1762,\n", + " 'Aspiration pneumonia': 582,\n", " 'Proboscis': 61,\n", - " 'Amyloidosis': 365,\n", - " 'Gliosis': 392,\n", - " 'Neuronal loss in central nervous system': 238,\n", - " 'Dilation of lateral ventricles': 15,\n", - " 'Mental deterioration': 96,\n", - " 'Allergic conjunctivitis': 48,\n", - " 'Episodic fever': 96,\n", - " 'Hallucinations': 106,\n", - " 'Schizophrenia': 448,\n", - " 'Delusions': 22,\n", + " 'Amyloidosis': 405,\n", + " 'Gliosis': 448,\n", + " 'Neuronal loss in central nervous system': 306,\n", + " 'Dilation of lateral ventricles': 16,\n", + " 'Mental deterioration': 123,\n", + " 'Allergic conjunctivitis': 47,\n", + " 'Episodic fever': 104,\n", + " 'Hypophosphatemia': 114,\n", + " 'Diabetic ketoacidosis': 64,\n", + " 'Respiratory alkalosis': 52,\n", + " 'Hallucinations': 127,\n", + " 'Schizophrenia': 620,\n", + " 'Delusions': 28,\n", " 'Protruding tongue': 20,\n", - " 'Abnormality of extrapyramidal motor function': 16,\n", - " 'Tardive dyskinesia': 16,\n", - " 'Dystonia': 35,\n", - " 'Stereotypy': 61,\n", - " 'Maceration': 70,\n", - " 'Retinal dystrophy': 13,\n", + " 'Abnormality of extrapyramidal motor function': 17,\n", + " 'Tardive dyskinesia': 19,\n", + " 'Dystonia': 37,\n", + " 'Maceration': 78,\n", + " 'Retinal dystrophy': 15,\n", " 'Medullary thyroid carcinoma': 11,\n", - " 'Central diabetes insipidus': 14,\n", - " 'Nephroblastoma': 77,\n", - " 'Nephrotic syndrome': 234,\n", - " 'Muscle weakness': 295,\n", - " 'Muscle stiffness': 30,\n", - " 'Centrally nucleated skeletal muscle fibers': 14,\n", - " 'Muscular dystrophy': 181,\n", + " 'Central diabetes insipidus': 21,\n", + " 'Nephroblastoma': 94,\n", + " 'Nephrotic syndrome': 253,\n", + " 'Muscle stiffness': 29,\n", + " 'Centrally nucleated skeletal muscle fibers': 15,\n", + " 'Muscular dystrophy': 220,\n", " 'Skeletal muscle fibrosis': 3,\n", + " 'Cyanosis': 770,\n", " 'Speech apraxia': 11,\n", - " 'Perseveration': 3,\n", - " 'Aphasia': 43,\n", - " 'Neurological speech impairment': 10,\n", - " 'Acute pancreatitis': 258,\n", - " 'Dehydration': 3842,\n", - " 'Single naris': 58,\n", - " 'Cyanosis': 736,\n", - " 'Lethargy': 2207,\n", - " 'Abnormality of brain morphology': 75,\n", - " 'Constitutional symptom': 1716,\n", - " 'Abnormality of the placenta': 48,\n", - " 'Functional respiratory abnormality': 336,\n", - " 'Anaphylactic shock': 657,\n", - " 'B Acute Lymphoblastic Leukemia': 10,\n", - " 'Juvenile rheumatoid arthritis': 68,\n", - " 'Abnormality of T cell physiology': 54,\n", - " 'Impaired T cell function': 66,\n", - " 'Uveitis': 1211,\n", + " 'Perseveration': 5,\n", + " 'Aphasia': 56,\n", + " 'Single naris': 64,\n", + " 'Hemolytic anemia': 621,\n", + " 'Abnormality of brain morphology': 83,\n", + " 'Abnormality of the placenta': 56,\n", + " 'Hyperactivity': 292,\n", + " 'Rhonchi': 156,\n", + " 'Juvenile rheumatoid arthritis': 81,\n", + " 'Abnormality of T cell physiology': 67,\n", + " 'Impaired T cell function': 80,\n", + " 'Uveitis': 1247,\n", " 'Band keratopathy': 8,\n", - " 'Elevated erythrocyte sedimentation rate': 57,\n", - " 'Glaucoma': 556,\n", - " 'Antinuclear antibody positivity': 205,\n", - " 'Macular edema': 29,\n", - " 'Cataract': 582,\n", - " 'Anterior uveitis': 383,\n", + " 'Elevated erythrocyte sedimentation rate': 66,\n", + " 'Glaucoma': 585,\n", + " 'Antinuclear antibody positivity': 221,\n", + " 'Cataract': 605,\n", + " 'Anterior uveitis': 387,\n", " 'Vitritis': 23,\n", " 'Oligoarthritis': 17,\n", - " 'Sleep disturbance': 152,\n", - " 'Polycystic ovaries': 12,\n", - " 'Premature rupture of membranes': 18,\n", - " 'Hypothyroidism': 418,\n", - " 'Maternal hypertension': 24,\n", - " 'Neonatal asphyxia': 14,\n", - " 'Small for gestational age': 489,\n", - " 'Red eye': 55,\n", - " 'Atrial fibrillation': 252,\n", - " 'Ataxia': 1487,\n", - " 'Gout': 168,\n", - " 'Glomerulosclerosis': 94,\n", - " 'Acute tubular necrosis': 110,\n", - " 'Hypothermia': 842,\n", - " 'Pulmonary infiltrates': 599,\n", - " 'Absent testis': 5,\n", - " 'Nevus': 134,\n", - " 'Hyperactivity': 249,\n", + " 'Abnormal lymphocyte morphology': 21,\n", + " 'Thrombocytosis': 227,\n", + " 'Paranoia': 35,\n", + " 'B lymphocytopenia': 62,\n", + " 'Polycystic ovaries': 15,\n", + " 'Premature rupture of membranes': 24,\n", + " 'Maternal hypertension': 31,\n", + " 'Neonatal asphyxia': 22,\n", + " 'Red eye': 60,\n", + " 'Abdominal distention': 981,\n", + " 'Reduced factor IX activity': 2,\n", + " 'Abnormality of metabolism/homeostasis': 40,\n", + " 'Coronary artery spasm': 5,\n", + " 'Ataxia': 1550,\n", + " 'Ciliary dyskinesia': 51,\n", + " 'T-cell lymphoma/leukemia': 108,\n", + " 'Hypothermia': 881,\n", + " 'Pulmonary hemorrhage': 343,\n", + " 'Nevus': 144,\n", " 'Abnormal social behavior': 1,\n", - " 'Mania': 85,\n", - " 'Exaggerated startle response': 10,\n", - " 'Bipolar affective disorder': 110,\n", - " 'Aggressive behavior': 574,\n", - " 'Memory impairment': 151,\n", - " 'Hyperkalemia': 296,\n", - " 'Increased IgG level': 93,\n", - " 'Increased IgM level': 20,\n", - " 'Severe viral infections': 119,\n", - " 'Severe viral infection': 119,\n", - " 'Monocytopenia': 47,\n", - " 'Irritability': 363,\n", - " 'Drooling': 238,\n", - " 'Pressure ulcer': 122,\n", - " 'Increased body mass index': 83,\n", - " 'Leukocytosis': 999,\n", - " 'Thyroid nodule': 20,\n", - " 'Stomach cancer': 517,\n", - " 'Glioma': 618,\n", - " 'Blurred vision': 59,\n", - " 'Keratoconjunctivitis sicca': 183,\n", - " 'Keratitis': 562,\n", - " 'Photophobia': 214,\n", - " 'Posterior uveitis': 132,\n", - " 'Iritis': 66,\n", - " 'Abnormality of the eye': 25,\n", - " 'Papule': 435,\n", + " 'Mania': 94,\n", + " 'Exaggerated startle response': 9,\n", + " 'Bipolar affective disorder': 132,\n", + " 'Aggressive behavior': 629,\n", + " 'Memory impairment': 188,\n", + " 'Hyperkalemia': 304,\n", + " 'Increased IgG level': 106,\n", + " 'Increased IgM level': 26,\n", + " 'Severe viral infections': 146,\n", + " 'Severe viral infection': 146,\n", + " 'Monocytopenia': 55,\n", + " 'Diminished ability to concentrate': 58,\n", + " 'Irritability': 410,\n", + " 'Drooling': 242,\n", + " 'Pressure ulcer': 138,\n", + " 'Thyroid nodule': 19,\n", + " 'Ventricular tachycardia': 120,\n", + " 'Supraventricular tachycardia': 39,\n", + " 'Glioma': 706,\n", + " 'Blurred vision': 64,\n", + " 'Keratoconjunctivitis sicca': 188,\n", + " 'Keratitis': 602,\n", + " 'Photophobia': 225,\n", + " 'Posterior uveitis': 141,\n", + " 'Iritis': 69,\n", + " 'Abnormality of the eye': 30,\n", + " 'Hypoglycemia': 1116,\n", + " 'Abnormal blistering of the skin': 249,\n", + " 'Skin vesicle': 269,\n", + " 'Esophageal carcinoma': 93,\n", + " 'Eosinophilia': 1147,\n", + " 'Telangiectasia': 47,\n", + " 'Papule': 446,\n", " 'Macule': 98,\n", - " 'Neoplasm of the breast': 414,\n", - " 'Chronic pain': 147,\n", - " 'Hypocupremia': 105,\n", - " 'Polyphagia': 173,\n", - " 'B lymphocytopenia': 47,\n", + " 'Cachexia': 768,\n", + " 'Left ventricular dysfunction': 119,\n", + " 'Neoplasm of the breast': 461,\n", + " 'Chronic pain': 174,\n", + " 'Hypocupremia': 108,\n", + " 'Polyphagia': 180,\n", " 'Tics': 27,\n", " 'Abnormality of the basal ganglia': 6,\n", - " 'Abnormality of movement': 72,\n", + " 'Abnormality of movement': 85,\n", " 'Abulia': 1,\n", " 'Ovotestis': 4,\n", - " 'Hyporeflexia': 27,\n", - " 'Abnormality of the bladder': 54,\n", - " 'Urinary bladder inflammation': 420,\n", + " 'Pulmonary arteriovenous malformation': 8,\n", + " 'Right-to-left shunt': 28,\n", + " 'Increased hemoglobin': 20,\n", + " 'Abnormal inflammatory response': 40,\n", + " 'Decreased serum testosterone level': 26,\n", + " 'Hypogonadism': 35,\n", + " 'Hypernatremia': 117,\n", + " 'Nephrolithiasis': 106,\n", + " 'Hypercalcemia': 321,\n", + " 'Abnormality of the bladder': 56,\n", + " 'Urinary bladder inflammation': 482,\n", " 'Left ventricular diastolic dysfunction': 3,\n", - " 'Bradycardia': 418,\n", - " 'Urinary retention': 93,\n", - " 'Polyuria': 370,\n", + " 'Urinary retention': 96,\n", + " 'Polyuria': 381,\n", " 'Urinary urgency': 24,\n", - " 'Hypoventilation': 248,\n", - " 'Hyperreflexia': 29,\n", - " 'Mydriasis': 216,\n", - " 'Neuropathic pain': 149,\n", - " 'Hyposmia': 46,\n", - " 'Reduced consciousness/confusion': 231,\n", - " 'Cerebral hemorrhage': 115,\n", - " 'Ischemic stroke': 229,\n", - " 'Rhabdomyosarcoma': 209,\n", - " 'Pneumothorax': 760,\n", - " 'Chronic bronchitis': 610,\n", - " 'Recurrent viral infections': 18,\n", - " 'Bronchiectasis': 1012,\n", - " 'Coronary artery stenosis': 19,\n", + " 'Hypoventilation': 268,\n", + " 'Hyperreflexia': 34,\n", + " 'Mydriasis': 222,\n", + " 'Rhabdomyosarcoma': 243,\n", + " 'Vasculitis': 1729,\n", + " 'Recurrent viral infections': 20,\n", + " 'Coronary artery stenosis': 23,\n", " 'HbC hemoglobin': 4,\n", + " 'Low APGAR score': 25,\n", + " 'Hoarse voice': 271,\n", " 'Infantile spasms': 11,\n", - " 'Epileptic encephalopathy': 8,\n", - " 'Autism': 180,\n", - " 'Osteoporosis': 370,\n", - " 'Lissencephaly': 27,\n", + " 'Epileptic encephalopathy': 10,\n", + " 'Autism': 262,\n", + " 'Osteoporosis': 430,\n", + " 'Lissencephaly': 29,\n", " 'Spina bifida': 68,\n", - " 'Cerebral palsy': 74,\n", - " 'Global developmental delay': 159,\n", - " 'Infertility': 609,\n", - " 'Increased total bilirubin': 77,\n", - " 'Hyperlipidemia': 217,\n", - " 'Benign prostatic hyperplasia': 43,\n", - " 'Mediastinal lymphadenopathy': 47,\n", + " 'Cerebral palsy': 95,\n", + " 'Global developmental delay': 179,\n", + " 'Infertility': 642,\n", + " 'Hypoproteinemia': 577,\n", + " 'Increased total bilirubin': 89,\n", + " 'Acute tubular necrosis': 121,\n", + " 'Glomerulosclerosis': 115,\n", + " 'Tubular atrophy': 43,\n", + " 'Mediastinal lymphadenopathy': 53,\n", " 'Dyspepsia': 179,\n", - " 'Hyperthyroidism': 376,\n", - " 'Neoplasm of the lung': 286,\n", - " 'Peritonitis': 1734,\n", - " 'Closed comedo': 91,\n", - " 'Hypoproteinemia': 569,\n", - " 'Psoriasiform dermatitis': 378,\n", - " 'Scleroderma': 69,\n", - " 'Stuttering': 124,\n", - " 'Colitis': 1630,\n", - " 'Pulmonary embolism': 297,\n", - " 'Deep venous thrombosis': 132,\n", - " 'Ascites': 1409,\n", - " 'Torticollis': 140,\n", - " 'Pancreatic adenocarcinoma': 88,\n", - " 'Tendon rupture': 30,\n", + " 'Scleroderma': 91,\n", + " 'Closed comedo': 110,\n", + " 'Stuttering': 141,\n", + " 'Colitis': 1828,\n", + " 'Deep venous thrombosis': 141,\n", + " 'Ascites': 1535,\n", + " 'Torticollis': 144,\n", + " 'Tendon rupture': 31,\n", " 'Difficulty walking': 35,\n", " 'Ankle swelling': 6,\n", - " 'Rigors': 191,\n", - " 'Low back pain': 59,\n", - " 'Hypoglycemia': 1073,\n", - " 'Abnormal blistering of the skin': 235,\n", - " 'Skin vesicle': 255,\n", - " 'Myelitis': 308,\n", - " 'Axonal loss': 172,\n", - " 'Vasculitis': 1576,\n", - " 'Axonal degeneration': 470,\n", - " 'Morphological abnormality of the central nervous system': 231,\n", - " 'Combined immunodeficiency': 59,\n", + " 'Rigors': 222,\n", + " 'Low back pain': 70,\n", + " 'Axonal loss': 227,\n", + " 'Axonal degeneration': 618,\n", + " 'Morphological abnormality of the central nervous system': 285,\n", + " 'Combined immunodeficiency': 74,\n", " 'Conical tooth': 12,\n", - " 'Ectodermal dysplasia': 17,\n", - " 'Decreased antibody level in blood': 239,\n", - " 'Hepatosplenomegaly': 350,\n", - " 'Chorioretinitis': 273,\n", - " 'Immune dysregulation': 181,\n", - " 'Hepatocellular necrosis': 184,\n", - " 'Acne': 131,\n", - " 'Eosinophilia': 1075,\n", - " 'Limb muscle weakness': 102,\n", - " 'Bronchiolitis': 3500,\n", - " 'Pulmonary eosinophilic infiltration': 71,\n", - " 'Pulmonary hypoplasia': 41,\n", - " 'Aspiration': 272,\n", - " 'Decreased fertility': 96,\n", - " 'Abnormality of metabolism/homeostasis': 36,\n", - " 'Kyphosis': 95,\n", - " 'Increased antibody level in blood': 584,\n", - " 'Anterior open-bite malocclusion': 14,\n", - " 'Inflammatory abnormality of the eye': 84,\n", - " 'CNS demyelination': 115,\n", - " 'Cellulitis': 820,\n", - " 'Recurrent skin infections': 445,\n", - " 'Verrucae': 320,\n", - " 'Stomatitis': 552,\n", - " 'Hemophagocytosis': 100,\n", - " 'Abnormality of the face': 69,\n", - " 'Complement deficiency': 34,\n", - " 'Molluscum contagiosum': 79,\n", - " 'Severe combined immunodeficiency': 167,\n", - " 'Acute hepatitis': 453,\n", - " 'Fulminant hepatitis': 230,\n", - " 'Tricuspid regurgitation': 57,\n", - " 'Encephalopathy': 965,\n", - " 'Bronchospasm': 351,\n", - " 'Status asthmaticus': 53,\n", - " 'Hypomagnesemia': 92,\n", + " 'Ectodermal dysplasia': 20,\n", + " 'Decreased antibody level in blood': 285,\n", + " 'Hepatosplenomegaly': 381,\n", + " 'Chorioretinitis': 280,\n", + " 'Hepatocellular necrosis': 200,\n", + " 'Acne': 150,\n", + " 'Encephalopathy': 1123,\n", + " 'Viral hepatitis': 772,\n", + " 'Chronic hepatitis': 674,\n", + " 'Hepatoblastoma': 45,\n", + " 'Limb muscle weakness': 113,\n", + " 'Bronchiolitis': 4258,\n", + " 'Pulmonary eosinophilic infiltration': 82,\n", + " 'Pulmonary hypoplasia': 48,\n", + " 'Aspiration': 318,\n", + " 'Decreased fertility': 119,\n", + " 'Kyphosis': 106,\n", + " 'Increased antibody level in blood': 633,\n", + " 'Anterior open-bite malocclusion': 15,\n", + " 'Inflammatory abnormality of the eye': 91,\n", + " 'CNS demyelination': 158,\n", + " 'Cellulitis': 887,\n", + " 'Recurrent skin infections': 494,\n", + " 'Verrucae': 338,\n", + " 'Hemophagocytosis': 131,\n", + " 'Abnormality of the face': 74,\n", + " 'Complement deficiency': 41,\n", + " 'Molluscum contagiosum': 88,\n", + " 'Severe combined immunodeficiency': 211,\n", + " 'Fulminant hepatitis': 276,\n", + " 'Tricuspid regurgitation': 59,\n", + " 'Bronchospasm': 393,\n", + " 'Status asthmaticus': 57,\n", + " 'Hypomagnesemia': 101,\n", " 'Hypermagnesemia': 17,\n", " 'Cerebral calcification': 32,\n", - " 'Cerebellar hypoplasia': 179,\n", - " 'Cerebral ischemia': 274,\n", - " 'Emotional lability': 21,\n", + " 'Cerebellar hypoplasia': 180,\n", + " 'Cerebral ischemia': 343,\n", + " 'Emotional lability': 22,\n", " 'Porencephalic cyst': 61,\n", - " 'Arthrogryposis multiplex congenita': 87,\n", - " 'Abdominal distention': 935,\n", - " 'Osteoarthritis': 322,\n", - " 'Jaundice': 1381,\n", - " 'Villous atrophy': 573,\n", + " 'Arthrogryposis multiplex congenita': 89,\n", + " 'Osteoarthritis': 363,\n", + " 'Pancreatic adenocarcinoma': 97,\n", + " 'Villous atrophy': 614,\n", " 'Abnormality of fluid regulation': 14,\n", - " 'Neoplasm of the colon': 68,\n", - " 'Ovarian carcinoma': 419,\n", - " 'Cutaneous T-cell lymphoma': 53,\n", + " 'Neoplasm of the colon': 78,\n", + " 'Ovarian carcinoma': 521,\n", + " 'Cutaneous T-cell lymphoma': 59,\n", " 'Hyposegmentation of neutrophil nuclei': 4,\n", - " 'Neoplasm of the skin': 146,\n", - " 'Pyoderma': 200,\n", - " 'Gingivitis': 302,\n", - " 'Increased intracranial pressure': 190,\n", - " 'Macular degeneration': 108,\n", - " 'Slurred speech': 20,\n", - " 'Brain atrophy': 44,\n", - " 'Abnormal bleeding': 224,\n", - " 'Hepatoblastoma': 31,\n", - " 'Developmental stagnation': 12,\n", - " 'Cachexia': 648,\n", - " 'Pallor': 375,\n", + " 'Neoplasm of the skin': 155,\n", + " 'Pyoderma': 202,\n", + " 'Gingivitis': 342,\n", + " 'Increased intracranial pressure': 197,\n", + " 'Macular degeneration': 156,\n", + " 'Slurred speech': 25,\n", + " 'Abnormal bleeding': 233,\n", + " 'Developmental stagnation': 14,\n", + " 'Pallor': 392,\n", " 'Supernumerary testes': 7,\n", - " 'Viral hepatitis': 668,\n", - " 'Fulminant hepatic failure': 119,\n", - " 'Squamous cell carcinoma': 657,\n", - " 'Atelectasis': 588,\n", - " 'Absent natural killer cells': 35,\n", - " 'Acute respiratory tract infection': 520,\n", - " 'Acute otitis media': 327,\n", - " 'Migraine': 126,\n", - " 'Hypertriglyceridemia': 121,\n", - " 'T-cell lymphoma/leukemia': 70,\n", - " 'Retinitis': 319,\n", - " 'Nephritis': 485,\n", + " 'Fulminant hepatic failure': 131,\n", + " 'Squamous cell carcinoma': 702,\n", + " 'Absent natural killer cells': 42,\n", + " 'Acute respiratory tract infection': 636,\n", + " 'Acute otitis media': 440,\n", + " 'Migraine': 144,\n", + " 'Hypertriglyceridemia': 132,\n", + " 'Retinitis': 369,\n", + " 'Nephritis': 577,\n", " 'Recurrent pharyngitis': 17,\n", - " 'Tonsillitis': 462,\n", - " 'Sinusitis': 1301,\n", - " 'Abnormal glucose tolerance': 40,\n", - " 'Decreased glucose tolerance': 39,\n", - " 'Abnormality of lipid metabolism': 124,\n", - " 'Elevated mean arterial pressure': 55,\n", - " 'Erysipelas': 142,\n", - " 'Endocarditis': 825,\n", - " 'Alkalosis': 83,\n", - " 'Gangrene': 155,\n", - " 'Pharyngitis': 1412,\n", - " 'Enlarged tonsils': 87,\n", - " 'Petechiae': 413,\n", - " 'Hoarse voice': 254,\n", - " 'Mastoiditis': 91,\n", - " 'Lymphadenitis': 488,\n", - " 'Ovarian neoplasm': 236,\n", - " 'Neurofibrillary tangles': 55,\n", - " 'Drowsiness': 142,\n", - " 'Splenomegaly': 782,\n", - " 'Hyperventilation': 194,\n", - " 'Loss of consciousness': 144,\n", - " 'Involuntary movements': 38,\n", - " 'Panic attack': 19,\n", - " 'Hypercapnia': 300,\n", - " 'Arteritis': 308,\n", - " 'Coronary artery aneurysm': 99,\n", - " 'Abnormality of blood and blood-forming tissues': 129,\n", - " 'Thrombocytosis': 205,\n", - " 'Thyroiditis': 85,\n", - " 'Ecchymosis': 206,\n", - " 'Myoclonus': 111,\n", - " 'Pulmonary hemorrhage': 317,\n", - " 'Pleuritis': 591,\n", - " 'Chronic hepatitis': 615,\n", - " 'Hemolytic anemia': 585,\n", - " 'Oophoritis': 37,\n", - " 'Premature ovarian insufficiency': 14,\n", - " 'Bronchiolitis obliterans': 316,\n", - " 'Erectile abnormalities': 26,\n", - " 'Astrocytosis': 90,\n", - " 'CNS hypomyelination': 71,\n", - " 'Absence seizure': 15,\n", - " 'Febrile seizures': 219,\n", - " 'Nasal flaring': 79,\n", - " 'Autoimmune thrombocytopenia': 106,\n", - " 'Decreased circulating IgA level': 122,\n", - " 'Abnormality of neutrophils': 40,\n", - " 'Nasopharyngeal carcinoma': 209,\n", - " 'Hashimoto thyroiditis': 46,\n", - " 'Chronic lymphatic leukemia': 123,\n", - " 'Decreased circulating IgG level': 25,\n", - " 'Aspiration pneumonia': 555,\n", - " 'Risk taking': 59,\n", + " 'Tonsillitis': 498,\n", + " 'Abnormal glucose tolerance': 54,\n", + " 'Decreased glucose tolerance': 50,\n", + " 'Elevated mean arterial pressure': 80,\n", + " 'Erysipelas': 143,\n", + " 'Endocarditis': 862,\n", + " 'Alkalosis': 91,\n", + " 'Gangrene': 169,\n", + " 'Enlarged tonsils': 89,\n", + " 'Petechiae': 434,\n", + " 'Mastoiditis': 100,\n", + " 'Lymphadenitis': 511,\n", + " 'Ovarian neoplasm': 290,\n", + " 'Neurofibrillary tangles': 81,\n", + " 'Drowsiness': 160,\n", + " 'Splenomegaly': 845,\n", + " 'Hyperventilation': 201,\n", + " 'Loss of consciousness': 149,\n", + " 'Involuntary movements': 40,\n", + " 'Panic attack': 21,\n", + " 'Hypercapnia': 323,\n", + " 'Arteritis': 323,\n", + " 'Coronary artery aneurysm': 121,\n", + " 'Abnormality of blood and blood-forming tissues': 140,\n", + " 'Thyroiditis': 90,\n", + " 'Ecchymosis': 213,\n", + " 'Acute encephalopathy': 57,\n", + " 'Cerebral cortical atrophy': 35,\n", + " 'Lymphoproliferative disorder': 434,\n", + " 'Plethora': 13,\n", + " 'Vitamin E deficiency': 83,\n", + " 'Acute necrotizing encephalopathy': 32,\n", + " 'Myoclonus': 118,\n", + " 'Oophoritis': 39,\n", + " 'Premature ovarian insufficiency': 18,\n", + " 'Bronchiolitis obliterans': 418,\n", + " 'Erectile abnormalities': 30,\n", + " 'Astrocytosis': 107,\n", + " 'CNS hypomyelination': 93,\n", + " 'Absence seizure': 17,\n", + " 'Febrile seizures': 255,\n", + " 'Nasal flaring': 95,\n", + " 'Autoimmune thrombocytopenia': 124,\n", + " 'Decreased circulating IgA level': 135,\n", + " 'Abnormality of neutrophils': 42,\n", + " 'Nasopharyngeal carcinoma': 260,\n", + " 'Hashimoto thyroiditis': 58,\n", + " 'Chronic lymphatic leukemia': 150,\n", + " 'Decreased circulating IgG level': 28,\n", " 'Laryngospasm': 47,\n", - " 'Grade I preterm intraventricular hemorrhage': 2,\n", - " 'Intellectual disability': 213,\n", - " 'Perivascular spaces': 198,\n", - " 'Gastrointestinal carcinoma': 39,\n", - " 'Autophagic vacuoles': 107,\n", - " 'Peripheral neuropathy': 712,\n", - " 'Gastritis': 605,\n", - " 'Self-mutilation': 100,\n", - " 'Neutropenia': 1453,\n", - " 'Reduced hematocrit': 49,\n", + " 'Grade I preterm intraventricular hemorrhage': 4,\n", + " 'Intellectual disability': 249,\n", + " 'Perivascular spaces': 277,\n", + " 'Gastrointestinal carcinoma': 45,\n", + " 'Autophagic vacuoles': 213,\n", + " 'Gastritis': 630,\n", + " 'Self-mutilation': 101,\n", + " 'Reduced hematocrit': 52,\n", " 'Thyroid adenoma': 5,\n", - " 'Pleural mesothelioma': 19,\n", + " 'Pleural mesothelioma': 21,\n", " 'Generalized amyotrophy': 11,\n", " 'Generalized limb muscle atrophy': 9,\n", - " 'Cholestasis': 397,\n", - " 'Polycystic kidney dysplasia': 77,\n", - " 'Tubulointerstitial nephritis': 295,\n", - " 'Membranoproliferative glomerulonephritis': 38,\n", + " 'Cholestasis': 431,\n", + " 'Polycystic kidney dysplasia': 80,\n", + " 'Tubulointerstitial nephritis': 314,\n", + " 'Membranoproliferative glomerulonephritis': 51,\n", " 'Parathyroid hyperplasia': 18,\n", - " 'Glossitis': 68,\n", + " 'Glossitis': 78,\n", " 'Parathyroid adenoma': 9,\n", - " 'Pheochromocytoma': 80,\n", - " 'Neoplasm of the thyroid gland': 32,\n", + " 'Pheochromocytoma': 88,\n", + " 'Neoplasm of the thyroid gland': 33,\n", " 'Pituitary carcinoma': 3,\n", - " 'Neuroendocrine neoplasm': 42,\n", - " 'Leukoencephalopathy': 40,\n", - " 'Multiple lipomas': 88,\n", - " 'Myocardial fibrosis': 72,\n", - " 'Increased bone mineral density': 25,\n", - " 'Myelofibrosis': 80,\n", - " 'Thyroid hyperplasia': 9,\n", + " 'Neuroendocrine neoplasm': 44,\n", + " 'Leukoencephalopathy': 50,\n", + " 'Multiple lipomas': 93,\n", + " 'Myocardial fibrosis': 88,\n", + " 'Increased bone mineral density': 27,\n", + " 'Thyroid hyperplasia': 10,\n", " 'Neoplasm of the endocrine system': 27,\n", - " 'Hypertrophic cardiomyopathy': 147,\n", - " 'Secondary hyperparathyroidism': 37,\n", - " 'Genital neoplasm': 7,\n", - " 'B-cell neoplasm': 62,\n", - " 'Malignant mesothelioma': 19,\n", + " 'Hypertrophic cardiomyopathy': 161,\n", + " 'Secondary hyperparathyroidism': 38,\n", + " 'Genital neoplasm': 8,\n", + " 'B-cell neoplasm': 64,\n", + " 'Malignant mesothelioma': 20,\n", " 'Pericardial mesothelioma': 3,\n", - " 'Meningioma': 175,\n", - " 'Hyperparathyroidism': 56,\n", + " 'Meningioma': 173,\n", + " 'Hyperparathyroidism': 60,\n", " 'Primary hyperparathyroidism': 15,\n", - " 'Polydipsia': 292,\n", - " 'Hypercalcemia': 317,\n", - " 'Visual loss': 227,\n", - " 'Confusion': 380,\n", + " 'Polydipsia': 295,\n", + " 'Visual loss': 257,\n", " 'Hyperplasia of the endometrium': 90,\n", - " 'Paranoia': 26,\n", - " 'Ketosis': 144,\n", - " 'Abnormality of the gastrointestinal tract': 233,\n", - " 'Upper airway obstruction': 164,\n", + " 'Ketosis': 143,\n", + " 'Upper airway obstruction': 171,\n", " 'Neoplasm of the lip': 2,\n", - " 'Obstructive sleep apnea': 72,\n", - " 'Acute encephalopathy': 49,\n", - " 'Central apnea': 4,\n", - " 'Cardiogenic shock': 139,\n", - " 'Cervical dysplasia': 13,\n", + " 'Obstructive sleep apnea': 77,\n", + " 'Central apnea': 5,\n", + " 'Cardiogenic shock': 156,\n", + " 'Cervical dysplasia': 14,\n", " 'Reticulocytosis': 69,\n", - " 'Elevated hepcidin level': 2,\n", + " 'Elevated hepcidin level': 3,\n", " 'Decreased hepcidin level': 1,\n", - " 'Abnormality of the vasculature': 71,\n", - " 'Stiff neck': 111,\n", - " 'Increased B cell count': 35,\n", + " 'Abnormality of the vasculature': 92,\n", + " 'Stiff neck': 120,\n", + " 'Increased B cell count': 45,\n", " 'Hyperalbuminemia': 9,\n", - " 'Rhonchi': 135,\n", - " 'Cranial nerve paralysis': 43,\n", + " 'Cranial nerve paralysis': 47,\n", " 'Reduced vital capacity': 10,\n", - " 'Facial edema': 137,\n", - " 'Biliary cirrhosis': 116,\n", - " 'Cholangitis': 380,\n", - " 'Impulsivity': 69,\n", - " 'Enterocolitis': 583,\n", - " 'Open mouth': 128,\n", - " 'Histiocytosis': 94,\n", - " 'Mitochondrial myopathy': 14,\n", - " 'Prostate neoplasm': 65,\n", - " 'Epistaxis': 401,\n", + " 'Facial edema': 134,\n", + " 'Biliary cirrhosis': 147,\n", + " 'Cholangitis': 386,\n", + " 'Impulsivity': 82,\n", + " 'Enterocolitis': 604,\n", + " 'Open mouth': 136,\n", + " 'Histiocytosis': 100,\n", + " 'Mitochondrial myopathy': 17,\n", + " 'Prostate neoplasm': 75,\n", + " 'Epistaxis': 424,\n", " 'Milia': 25,\n", - " 'Axonal regeneration': 59,\n", - " 'Myelodysplasia': 194,\n", - " 'Osteopetrosis': 38,\n", - " 'Acute myeloid leukemia': 263,\n", - " 'Congenital diaphragmatic hernia': 155,\n", - " 'Atherosclerotic lesion': 86,\n", - " 'Foam cells': 256,\n", - " 'Decreased systolic blood pressure': 8,\n", - " 'Left ventricular dysfunction': 83,\n", - " 'Corneal ulceration': 266,\n", - " 'Acute bronchitis': 547,\n", + " 'Axonal regeneration': 68,\n", + " 'Myelodysplasia': 236,\n", + " 'Osteopetrosis': 48,\n", + " 'Acute myeloid leukemia': 335,\n", + " 'Congenital diaphragmatic hernia': 162,\n", + " 'Panniculitis': 150,\n", + " 'Atherosclerotic lesion': 140,\n", + " 'Foam cells': 290,\n", + " 'Decreased systolic blood pressure': 10,\n", + " 'Corneal ulceration': 267,\n", " 'Bladder stones': 15,\n", - " 'Nephrolithiasis': 103,\n", - " 'Back pain': 141,\n", - " 'Non-Hodgkin lymphoma': 229,\n", - " 'Thyroid carcinoma': 113,\n", - " 'Hyperalgesia': 83,\n", - " 'Epigastric pain': 50,\n", - " 'Cholelithiasis': 160,\n", - " 'Peripheral arterial stenosis': 87,\n", - " 'Hemiplegia': 83,\n", - " 'Carious teeth': 376,\n", - " 'Epidermal acanthosis': 114,\n", - " 'Erythema': 1264,\n", - " 'Arthropathy': 228,\n", - " 'Disseminated intravascular coagulation': 597,\n", - " 'Hypovolemic shock': 406,\n", + " 'Back pain': 155,\n", + " 'Non-Hodgkin lymphoma': 297,\n", + " 'Thyroid carcinoma': 108,\n", + " 'Hyperalgesia': 93,\n", + " 'Epigastric pain': 52,\n", + " 'Cholelithiasis': 164,\n", + " 'Hemiplegia': 105,\n", + " 'Carious teeth': 403,\n", + " 'Epidermal acanthosis': 120,\n", + " 'Erythema': 1334,\n", + " 'Arthropathy': 245,\n", + " 'Hypovolemic shock': 438,\n", " 'Skin detachment': 20,\n", - " 'Thromboembolism': 312,\n", + " 'Thromboembolism': 321,\n", " 'Pierre-Robin sequence': 4,\n", - " 'Hypopnea': 21,\n", - " 'Micrognathia': 21,\n", - " 'Failure to thrive': 353,\n", - " 'Feeding difficulties': 112,\n", - " 'Cleft palate': 165,\n", + " 'Hypopnea': 23,\n", + " 'Micrognathia': 27,\n", + " 'Failure to thrive': 380,\n", + " 'Feeding difficulties': 132,\n", + " 'Cleft palate': 177,\n", " 'Glossoptosis': 8,\n", - " 'Hyperhidrosis': 321,\n", - " 'Restlessness': 202,\n", - " 'Stridor': 411,\n", - " 'Sleep apnea': 39,\n", - " 'Snoring': 77,\n", - " 'Pustule': 330,\n", + " 'Hyperhidrosis': 338,\n", + " 'Restlessness': 206,\n", + " 'Stridor': 424,\n", + " 'Sleep apnea': 46,\n", + " 'Snoring': 80,\n", + " 'Pustule': 349,\n", " 'Susceptibility to coronavirus 229e': 2,\n", - " 'Tubulointerstitial fibrosis': 25,\n", - " 'Glucose intolerance': 61,\n", - " 'Abnormal breath sound': 39,\n", + " 'Tubulointerstitial fibrosis': 31,\n", + " 'Glucose intolerance': 82,\n", + " 'Abnormal breath sound': 43,\n", " 'Anaplastic thyroid carcinoma': 6,\n", - " 'IgE-mediated food allergy': 462,\n", - " 'Severe B lymphocytopenia': 36,\n", - " 'Abnormal B cell morphology': 10,\n", - " 'Lymphoproliferative disorder': 396,\n", - " 'Hematemesis': 140,\n", - " 'Melena': 312,\n", - " 'Menorrhagia': 13,\n", - " 'Ocular pain': 63,\n", - " 'Acute sinusitis': 158,\n", - " 'Recurrent respiratory infections': 82,\n", - " 'Aplastic anemia': 198,\n", - " 'Bloody diarrhea': 558,\n", - " 'Helicobacter pylori infection': 84,\n", - " 'Hemolytic-uremic syndrome': 209,\n", + " 'IgE-mediated food allergy': 463,\n", + " 'Severe B lymphocytopenia': 54,\n", + " 'Abnormal B cell morphology': 15,\n", + " 'Hematemesis': 154,\n", + " 'Melena': 319,\n", + " 'Menorrhagia': 15,\n", + " 'Ocular pain': 70,\n", + " 'Acute sinusitis': 169,\n", + " 'Recurrent respiratory infections': 96,\n", + " 'Aplastic anemia': 238,\n", + " 'Bloody diarrhea': 620,\n", + " 'Helicobacter pylori infection': 94,\n", + " 'Hemolytic-uremic syndrome': 227,\n", " 'Hyaline casts': 11,\n", - " 'Lung abscess': 351,\n", - " 'Periodontitis': 441,\n", - " 'Fibrosarcoma': 333,\n", - " 'Retinoblastoma': 169,\n", + " 'Lung abscess': 381,\n", + " 'Periodontitis': 583,\n", + " 'Fibrosarcoma': 358,\n", + " 'Retinoblastoma': 198,\n", " 'Vestibular dysfunction': 77,\n", - " 'Scoliosis': 105,\n", + " 'Scoliosis': 112,\n", " 'Cardiorespiratory arrest': 19,\n", - " 'Spinal muscular atrophy': 48,\n", - " 'Intestinal perforation': 148,\n", - " 'Usual interstitial pneumonia': 38,\n", - " 'Celiac disease': 263,\n", - " 'Aplasia of the nose': 28,\n", - " 'Bone pain': 65,\n", - " 'Impaired antigen-specific response': 13,\n", - " 'Pericarditis': 485,\n", - " 'Increased IgA level': 103,\n", - " 'Peptic ulcer': 141,\n", - " 'Pyelonephritis': 302,\n", - " 'Tetraplegia': 79,\n", - " 'Bilateral lung agenesis': 69,\n", - " 'Keratoconjunctivitis': 271,\n", - " 'Brain abscess': 142,\n", - " 'Neoplasm of head and neck': 10,\n", - " 'Myelopathy': 278,\n", - " 'Cardiomegaly': 182,\n", + " 'Spinal muscular atrophy': 61,\n", + " 'Intestinal perforation': 170,\n", + " 'Celiac disease': 299,\n", + " 'Aplasia of the nose': 30,\n", + " 'Bone pain': 76,\n", + " 'Impaired antigen-specific response': 17,\n", + " 'Pericarditis': 511,\n", + " 'Increased IgA level': 124,\n", + " 'Peptic ulcer': 153,\n", + " 'Pyelonephritis': 350,\n", + " 'Tetraplegia': 91,\n", + " 'Bilateral lung agenesis': 73,\n", + " 'Keratoconjunctivitis': 283,\n", + " 'Brain abscess': 146,\n", + " 'Neoplasm of head and neck': 19,\n", + " 'Myelopathy': 289,\n", + " 'Cardiomegaly': 204,\n", " 'Abnormality of the endocrine system': 39,\n", - " 'Seasonal allergy': 89,\n", - " 'Prostatitis': 151,\n", - " 'Cervicitis': 38,\n", - " 'Septic arthritis': 188,\n", - " 'Gastroesophageal reflux': 288,\n", - " 'Absence of CD8-positive T cells': 19,\n", - " 'Increased circulating cortisol level': 73,\n", - " 'Urinary incontinence': 133,\n", - " 'Neuritis': 96,\n", - " 'Senile plaques': 48,\n", - " 'Upper limb undergrowth': 81,\n", - " 'Night sweats': 117,\n", - " 'Negative affectivity': 7,\n", - " 'Severe short stature': 43,\n", + " 'Seasonal allergy': 87,\n", + " 'Cervicitis': 35,\n", + " 'Septic arthritis': 198,\n", + " 'Gastroesophageal reflux': 308,\n", + " 'Absence of CD8-positive T cells': 24,\n", + " 'Increased circulating cortisol level': 74,\n", + " 'Urinary incontinence': 134,\n", + " 'Neuritis': 109,\n", + " 'Senile plaques': 61,\n", + " 'Upper limb undergrowth': 87,\n", + " 'Night sweats': 127,\n", + " 'Negative affectivity': 9,\n", + " 'Trichodysplasia': 9,\n", + " 'Severe short stature': 51,\n", " 'Chronic tubulointerstitial nephritis': 12,\n", " 'Urethral obstruction': 106,\n", - " 'Cryptococcal meningitis': 83,\n", - " 'Hypogonadism': 31,\n", - " 'Female infertility': 31,\n", - " 'Impotence': 31,\n", - " 'Increased serum testosterone level': 15,\n", + " 'Mask-like facies': 6,\n", + " 'Cryptococcal meningitis': 92,\n", + " 'Female infertility': 33,\n", + " 'Impotence': 35,\n", + " 'Increased serum testosterone level': 16,\n", + " 'Gastrointestinal inflammation': 66,\n", + " 'Skin ulcer': 54,\n", " 'Oropharyngeal squamous cell carcinoma': 10,\n", " 'Sensory ataxia': 23,\n", - " 'Eczema': 340,\n", + " 'Eczema': 389,\n", " 'Pollakisuria': 36,\n", " 'Nocturia': 13,\n", " 'Urinary hesitancy': 2,\n", - " 'Bacteriuria': 131,\n", - " 'Personality changes': 41,\n", + " 'Bacteriuria': 138,\n", + " 'Personality changes': 45,\n", " 'Abnormality of the cell cycle': 5,\n", - " 'Anuria': 111,\n", - " 'Liver abscess': 233,\n", - " 'Cerebral venous thrombosis': 15,\n", + " 'Anuria': 116,\n", + " 'Liver abscess': 242,\n", + " 'Cerebral venous thrombosis': 19,\n", " 'Cutaneous abscess': 52,\n", " 'Mechanical ileus': 4,\n", - " 'Microphthalmia': 107,\n", - " 'Internal hemorrhage': 44,\n", + " 'Microphthalmia': 109,\n", + " 'Internal hemorrhage': 48,\n", " 'Poor coordination': 25,\n", - " 'Incoordination': 306,\n", - " 'Hyperesthesia': 244,\n", - " 'Opisthotonus': 200,\n", + " 'Incoordination': 321,\n", + " 'Hyperesthesia': 250,\n", + " 'Opisthotonus': 201,\n", " 'Fasciculations': 109,\n", - " 'Nystagmus': 350,\n", - " 'Skeletal muscle atrophy': 399,\n", + " 'Nystagmus': 352,\n", " 'Abnormal neuron morphology': 3,\n", - " 'Extramedullary hematopoiesis': 103,\n", + " 'Extramedullary hematopoiesis': 105,\n", " 'Lipid accumulation in hepatocytes': 7,\n", - " 'Iron deficiency anemia': 102,\n", - " 'Hyperinsulinemia': 81,\n", - " 'Panniculitis': 120,\n", - " 'Chronic colitis': 51,\n", + " 'Iron deficiency anemia': 110,\n", + " 'Hyperinsulinemia': 98,\n", + " 'Chronic colitis': 60,\n", + " 'Increased adipose tissue': 115,\n", " 'Musty odor': 2,\n", - " 'Psychomotor retardation': 40,\n", - " 'Intercostal retractions': 55,\n", - " 'Apathy': 127,\n", - " 'Abnormality of cardiovascular system morphology': 99,\n", - " 'Abnormal myelination': 5,\n", - " 'Dilated cardiomyopathy': 238,\n", - " 'Fungal meningitis': 25,\n", - " 'Hyperammonemia': 116,\n", - " 'Hepatic encephalopathy': 253,\n", + " 'Psychomotor retardation': 47,\n", + " 'Intercostal retractions': 60,\n", + " 'Apathy': 133,\n", + " 'Abnormality of cardiovascular system morphology': 115,\n", + " 'Abnormal myelination': 9,\n", + " 'Dilated cardiomyopathy': 296,\n", + " 'Fungal meningitis': 26,\n", + " 'Hyperammonemia': 122,\n", + " 'Hepatic encephalopathy': 266,\n", " 'Abnormality of the skin': 66,\n", " 'Paraproteinemia': 10,\n", - " 'Polyneuritis': 517,\n", - " 'Corneal opacity': 123,\n", - " 'Blue irides': 71,\n", - " 'Ventriculomegaly': 87,\n", + " 'Polyneuritis': 566,\n", + " 'Corneal opacity': 130,\n", + " 'Blue irides': 73,\n", + " 'Ventriculomegaly': 99,\n", " 'Basal ganglia calcification': 3,\n", - " 'Decreased level of thrombomodulin': 24,\n", - " 'Plethora': 11,\n", - " 'Respiratory acidosis': 125,\n", - " 'Capillary leak': 110,\n", - " 'Abnormality of myeloid leukocytes': 19,\n", + " 'Decreased level of thrombomodulin': 29,\n", + " 'Respiratory acidosis': 132,\n", + " 'Capillary leak': 116,\n", + " 'Abnormality of myeloid leukocytes': 20,\n", " 'Increased adiponectin level': 4,\n", " 'Portal fibrosis': 57,\n", - " 'Skin ulcer': 47,\n", - " 'Gastric ulcer': 442,\n", - " 'Dry skin': 61,\n", - " 'Malabsorption': 1087,\n", - " 'Abnormal leukocyte count': 16,\n", - " 'Waddling gait': 20,\n", - " 'Sickled erythrocytes': 99,\n", + " 'Decreased adipose tissue': 45,\n", + " 'Gastric ulcer': 467,\n", + " 'Dry skin': 68,\n", + " 'Abnormal leukocyte count': 19,\n", + " 'Waddling gait': 28,\n", + " 'Sickled erythrocytes': 121,\n", " 'Chronic hemolytic anemia': 13,\n", - " 'Recurrent sinusitis': 18,\n", - " 'Otitis media with effusion': 73,\n", - " 'Recurrent otitis media': 20,\n", - " 'Increased size of nasopharyngeal adenoids': 28,\n", - " 'Myositis': 369,\n", - " 'Epidermoid cyst': 26,\n", + " 'Recurrent sinusitis': 24,\n", + " 'Otitis media with effusion': 94,\n", + " 'Recurrent otitis media': 25,\n", + " 'Increased size of nasopharyngeal adenoids': 39,\n", + " 'Epidermoid cyst': 28,\n", " 'Increased hemoglobin concentration': 15,\n", - " 'Intestinal bleeding': 92,\n", - " 'Platelet antibody positive': 19,\n", - " 'Diffuse alveolar hemorrhage': 52,\n", - " 'Fibroblastic foci': 25,\n", - " 'Angioedema': 375,\n", - " 'Strawberry tongue': 42,\n", - " 'Cerebral vasculitis': 17,\n", - " 'Facial paralysis': 85,\n", - " 'Cerebral atrophy': 19,\n", - " 'Areflexia': 36,\n", - " 'Muscular hypotonia': 75,\n", - " 'Muscle fibrillation': 116,\n", - " 'Generalized edema': 61,\n", - " 'Serositis': 101,\n", - " 'Torsade de pointes': 24,\n", - " 'Ventricular tachycardia': 110,\n", - " 'Ventricular fibrillation': 94,\n", - " 'Abnormal inflammatory response': 32,\n", - " 'Exercise intolerance': 203,\n", - " 'Acute leukemia': 142,\n", + " 'Platelet antibody positive': 26,\n", + " 'Diffuse alveolar hemorrhage': 64,\n", + " 'Fibroblastic foci': 29,\n", + " 'Angioedema': 347,\n", + " 'Strawberry tongue': 47,\n", + " 'Cerebral vasculitis': 21,\n", + " 'Facial paralysis': 87,\n", + " 'Cerebral atrophy': 22,\n", + " 'Areflexia': 40,\n", + " 'Muscular hypotonia': 87,\n", + " 'Muscle fibrillation': 118,\n", + " 'Generalized edema': 62,\n", + " 'Serositis': 109,\n", + " 'Torsade de pointes': 29,\n", + " 'Ventricular fibrillation': 102,\n", + " 'Exercise intolerance': 208,\n", + " 'Acute leukemia': 199,\n", " 'Pelvic organ prolapse': 4,\n", - " 'Autistic behavior': 31,\n", - " 'Neurodevelopmental abnormality': 16,\n", - " 'Abnormality of the autonomic nervous system': 22,\n", - " 'Intussusception': 527,\n", - " 'Recurrent bacterial infections': 66,\n", - " 'Hodgkin lymphoma': 140,\n", - " 'Chondritis': 32,\n", - " 'Preauricular skin tag': 76,\n", - " 'Adenocarcinoma of the colon': 78,\n", - " 'Limb pain': 24,\n", - " 'Abnormality of ion homeostasis': 38,\n", - " 'Intestinal obstruction': 486,\n", - " 'Abnormal trachea morphology': 13,\n", - " 'Meconium ileus': 27,\n", - " 'Exocrine pancreatic insufficiency': 177,\n", - " 'Recurrent bronchitis': 12,\n", - " 'Astigmatism': 23,\n", - " 'Localized skin lesion': 9,\n", - " 'Skin plaque': 1,\n", - " 'Vascular neoplasm': 41,\n", - " 'Arteriosclerosis': 76,\n", - " 'Inguinal hernia': 54,\n", - " 'Hydrocele testis': 19,\n", - " 'Maturity-onset diabetes of the young': 5,\n", - " 'Transient ischemic attack': 24,\n", - " 'Aortic aneurysm': 44,\n", - " 'Aberrant wound healing': 26,\n", - " 'Thoracic aortic aneurysm': 3,\n", - " 'Angina pectoris': 40,\n", - " 'Bicuspid aortic valve': 6,\n", - " 'Mitochondrial swelling': 40,\n", - " 'Decreased superoxide dismutase activity': 4,\n", - " 'Supraventricular tachycardia': 32,\n", - " 'Diabetic ketoacidosis': 62,\n", - " 'Ketoacidosis': 52,\n", - " 'Narcolepsy': 57,\n", - " 'Chronic myelomonocytic leukemia': 17,\n", - " 'Polymicrogyria': 5,\n", - " 'Diminished motivation': 21,\n", - " 'Myopia': 39,\n", - " 'Spinal cord lesion': 131,\n", - " 'Narrow nose': 7,\n", - " 'Pleural rub': 4,\n", - " 'Abnormality of the spinal cord': 87,\n", - " 'Ileus': 467,\n", - " 'Liposarcoma': 24,\n", - " 'Neoplasm of the rectum': 94,\n", - " 'Acute monocytic leukemia': 15,\n", - " 'Morbilliform rash': 10,\n", - " 'Cervical lymphadenopathy': 191,\n", - " 'Rigidity': 78,\n", - " 'Myeloid leukemia': 63,\n", - " 'Heparin-induced thrombocytopenia': 21,\n", - " 'Laryngomalacia': 14,\n", - " 'Unexplained fevers': 83,\n", - " 'Sacroiliac arthritis': 9,\n", - " 'Gait disturbance': 159,\n", - " 'Increased muscle fatiguability': 38,\n", - " 'Hypervolemia': 16,\n", - " 'Secretory diarrhea': 152,\n", - " 'Basal cell carcinoma': 65,\n", - " 'Agammaglobulinemia': 100,\n", - " 'Trichodysplasia': 7,\n", - " 'Squamous cell carcinoma of the skin': 8,\n", - " 'Deeply set eye': 83,\n", - " 'Paresthesia': 121,\n", - " 'Sensory impairment': 23,\n", - " 'Abnormal autonomic nervous system physiology': 166,\n", - " 'Hemiparesis': 97,\n", - " 'Chronic diarrhea': 556,\n", - " 'Clubbing': 59,\n", + " 'Neurodevelopmental abnormality': 17,\n", + " 'Abnormality of the autonomic nervous system': 23,\n", + " 'Intussusception': 535,\n", + " 'Recurrent bacterial infections': 77,\n", + " 'Hodgkin lymphoma': 195,\n", + " 'Chondritis': 42,\n", + " 'Preauricular skin tag': 81,\n", + " 'Adenocarcinoma of the colon': 90,\n", + " 'Limb pain': 27,\n", + " 'Abnormality of ion homeostasis': 40,\n", + " 'Intestinal obstruction': 508,\n", + " 'Abnormal trachea morphology': 14,\n", + " 'Meconium ileus': 30,\n", + " 'Exocrine pancreatic insufficiency': 181,\n", + " 'Recurrent bronchitis': 14,\n", " ...}" ] }, - "execution_count": 84, + "execution_count": 19, "metadata": {}, "output_type": "execute_result" } @@ -3009,7 +3083,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "metadata": {}, "outputs": [], "source": [ @@ -3018,7 +3092,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "metadata": {}, "outputs": [], "source": [ @@ -3027,189 +3101,761 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "#vocab_cvprot per step 2:\n", - "\n", - "vocab_cvprot = ['SPIKE_WCPV', 'R1AB_WCPV',\n", - " 'NCAP_WCPV',\n", - " 'R1A_WCPV',\n", - " 'NS8_WCPV',\n", - " 'VME1_WCPV',\n", - " 'AP3A_WCPV',\n", - " 'VEMP_WCPV',\n", - " 'A0A663DJA2_9BETC',\n", - " 'ORF9B_WCPV',\n", - " 'Y14_WCPV',\n", - " 'NS6_WCPV',\n", - " 'NS7B_WCPV',\n", - " 'NS7A_WCPV']\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "sars_paper_id = {'PAPER_ID': [], 'SARS_COV': [],'SPECIES': [],'CVPROT': []}\n", - "for i in range(0, data.shape[0]):\n", - " row = data.iloc[i]\n", - " prot_field = row[3]\n", - " if prot_field not in vocab_cvprot: continue\n", - " paper_id = row[0]\n", - " SARS_cov = row[9]\n", - " species = row[10]\n", - " sars_paper_id['PAPER_ID'].append(paper_id)\n", - " sars_paper_id['SARS_COV'].append(SARS_cov)\n", - " sars_paper_id['SPECIES'].append(species)\n", - " sars_paper_id['CVPROT'].append(prot_field)\n", - " \n", - "df_cvprot = pd.DataFrame(sars_paper_id, columns=['PAPER_ID', 'SARS_COV', 'SPECIES', 'CVPROT'])\n", - "df_cvprot.head()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## 4. Create Pie Chart, Histogram" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "#check data unique relation - paper ID & protein\n", - "df_paper_id = df_cvprot[\"PAPER_ID\"]\n", - "df_prot = df_cvprot[\"CVPROT\"]\n", - "df_check_unq = pd.concat([df_paper_id, df_prot], axis=1)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "df_check_unq.shape\n", - "df_check_unq = df_check_unq.drop_duplicates()\n", - "df_check_unq.shape" - ] - }, - { - "cell_type": "code", - "execution_count": null, + "execution_count": 22, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "qqqqq 1309117\n", + "SPIKE_CVHSA 7699\n", + "NCAP_CVHSA 2827\n", + "R1A_CVHSA,R1AB_CVHSA 2488\n", + "VEMP_CVHSA 1025\n", + "NCAP_CVHSA,SPIKE_CVHSA 787\n", + "VME1_CVHSA 657\n", + "SPIKE_CVHSA,VME1_CVHSA 341\n", + "NCAP_CVHSA,SPIKE_CVHSA,VME1_CVHSA,VEMP_CVHSA 269\n", + "SPIKE_CVHSA,VEMP_CVHSA 242\n", + "NCAP_CVHSA,VME1_CVHSA 237\n", + "NCAP_CVHSA,SPIKE_CVHSA,VME1_CVHSA 236\n", + "AP3A_CVHSA 159\n", + "NS6_CVHSA 147\n", + "R1AB_CVHSA 145\n", + "VME1_CVHSA,VEMP_CVHSA 141\n", + "NCAP_CVHSA,VEMP_CVHSA 119\n", + "R1A_CVHSA 119\n", + "NCAP_CVHSA,SPIKE_CVHSA,VEMP_CVHSA 113\n", + "SPIKE_CVHSA,VME1_CVHSA,VEMP_CVHSA 102\n", + "R1A_CVHSA,SPIKE_CVHSA,R1AB_CVHSA 78\n", + "ORF9B_CVHSA 78\n", + "R1A_CVHSA,R1AB_CVHSA,SPIKE_CVHSA 67\n", + "NS7A_CVHSA 45\n", + "SPIKE_CVHSA,AP3A_CVHSA 44\n", + "NS3B_CVHSA 42\n", + "AP3A_CVHSA,VEMP_CVHSA 40\n", + "NCAP_CVHSA,VME1_CVHSA,VEMP_CVHSA 40\n", + "NS7B_CVHSA 35\n", + "NCAP_CVHSA,ORF9B_CVHSA 35\n", + " ... \n", + "AP3A_CVHSA,ORF9B_CVHSA 1\n", + "R1A_CVHSA,NS8A_CVHSA,NCAP_CVHSA,SPIKE_CVHSA,R1AB_CVHSA 1\n", + "SPIKE_CVHSA,VME1_CVHSA,NS3B_CVHSA 1\n", + "R1A_CVHSA,SPIKE_CVHSA,NS6_CVHSA 1\n", + "NCAP_CVHSA,VME1_CVHSA,AP3A_CVHSA,VEMP_CVHSA 1\n", + "NCAP_CVHSA,R1AB_CVHSA,VME1_CVHSA 1\n", + "NS8A_CVHSA,VME1_CVHSA,AP3A_CVHSA,VEMP_CVHSA 1\n", + "R1A_CVHSA,SPIKE_CVHSA,R1AB_CVHSA,VEMP_CVHSA 1\n", + "R1A_CVHSA,R1AB_CVHSA,VME1_CVHSA,NS6_CVHSA 1\n", + "NCAP_CVHSA,SPIKE_CVHSA,NS6_CVHSA,VEMP_CVHSA 1\n", + "NCAP_CVHSA,NS6_CVHSA,NS7B_CVHSA 1\n", + "NCAP_CVHSA,NS3B_CVHSA,VEMP_CVHSA 1\n", + "R1AB_CVHSA,SPIKE_CVHSA,NS7A_CVHSA 1\n", + "AP3A_CVHSA,NS3B_CVHSA,NS7A_CVHSA 1\n", + "NS8A_CVHSA,NS8B_CVHSA,NS7B_CVHSA 1\n", + "NCAP_CVHSA,NS7A_CVHSA,VEMP_CVHSA 1\n", + "SPIKE_CVHSA,NS6_CVHSA,VEMP_CVHSA 1\n", + "NCAP_CVHSA,ORF9B_CVHSA,NS7A_CVHSA,VEMP_CVHSA 1\n", + "SPIKE_CVHSA,VME1_CVHSA,AP3A_CVHSA,NS6_CVHSA 1\n", + "AP3A_CVHSA,NS3B_CVHSA,NS7B_CVHSA 1\n", + "NCAP_CVHSA,SPIKE_CVHSA,NS7A_CVHSA 1\n", + "SPIKE_CVHSA,AP3A_CVHSA,NS7A_CVHSA,VEMP_CVHSA 1\n", + "NCAP_CVHSA,R1AB_CVHSA,SPIKE_CVHSA,NS6_CVHSA,VEMP_CVHSA 1\n", + "NS3B_CVHSA,ORF9B_CVHSA 1\n", + "SPIKE_CVHSA,NS8B_CVHSA,VEMP_CVHSA 1\n", + "NCAP_CVHSA,Y14_CVHSA,SPIKE_CVHSA,VME1_CVHSA,ORF9B_CVHSA,VEMP_CVHSA 1\n", + "R1A_CVHSA,SPIKE_CVHSA,VEMP_CVHSA 1\n", + "R1AB_CVHSA,NS6_CVHSA 1\n", + "SPIKE_CVHSA,AP3A_CVHSA,NS3B_CVHSA,VEMP_CVHSA 1\n", + "VME1_CVHSA,NS8B_CVHSA 1\n", + "Name: CVPROT, Length: 222, dtype: int64" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "#Plot piechart for strains groups: percent of papers (not blocks) mentioned each strains group. \n", - "#IMPORTANT: STRAINS or PROTEINS? This is proteins.\n", - "#get count of papers that contain at least one mention of the protein\n", - "prot_counts = df_check_unq.groupby('CVPROT').CVPROT.value_counts()\n", - "prot_counts" + "data['CVPROT'].value_counts()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 26, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "['AP3A_CVHSA',\n", + " 'NCAP_CVHSA',\n", + " 'NS3B_CVHSA',\n", + " 'NS6_CVHSA',\n", + " 'NS7A_CVHSA',\n", + " 'NS7B_CVHSA',\n", + " 'NS8A_CVHSA',\n", + " 'NS8B_CVHSA',\n", + " 'ORF9B_CVHSA',\n", + " 'R1AB_CVHSA',\n", + " 'R1A_CVHSA',\n", + " 'SPIKE_CVHSA',\n", + " 'VEMP_CVHSA',\n", + " 'VME1_CVHSA',\n", + " 'Y14_CVHSA']" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "#get total paper count\n", - "papers = df_cvprot[\"PAPER_ID\"]\n", - "papers.shape[0]\n", - "papers = papers.drop_duplicates()\n", - "papers.shape[0]\n", - "total_papers = papers.shape[0]" + "#create cvprot list\n", + "\n", + "cvprot_list = sorted(list(vocab_cvprot.keys()))\n", + "cvprot_list = cvprot_list[1:] #filter na\n", + "cvprot_list" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 28, "metadata": {}, - "outputs": [], - "source": [ - "#create %s\n", - "A0A663DJA2_9BETC = prot_counts[0]\n", - "AP3A_WCPV = prot_counts[1]\n", - "NCAP_WCPV = prot_counts[2]\n", - "NS6_WCPV = prot_counts[3]\n", - "NS7A_WCPV = prot_counts[4]\n", - "NS7B_WCPV = prot_counts[5]\n", - "ORF9B_WCPV = prot_counts[6]\n", - "R1A_WCPV = prot_counts[7]\n", - "R1AB_WCPV = prot_counts[8]\n", - "SPIKE_WCPV = prot_counts[9]\n", - "VEMP_WCPV = prot_counts[10]\n", - "VME1_WCPV = prot_counts[11]\n", - "Y14_WCPV = prot_counts[12]" + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1328146/1328146 [03:33<00:00, 6224.18it/s]\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PAPER_IDSARS_COVSPECIESCVPROT
07cfaa2540d3c8eea0982b3b1147884f125f67ff2SARS coronavirusSARS Virus,Humans,VirusesSPIKE_CVHSA
19bbfd3d34ee18ea1b9f4669331a6cee9c5992893Severe acute respiratory syndrome coronavirus 2Humans,VirusesSPIKE_CVHSA
29bbfd3d34ee18ea1b9f4669331a6cee9c5992893SARS coronavirus,Severe acute respiratory synd...SARS Virus,VirusesSPIKE_CVHSA
39bbfd3d34ee18ea1b9f4669331a6cee9c5992893Severe acute respiratory syndrome coronavirus 2Coronavirus NL63, HumanSPIKE_CVHSA
4240da1ff435355a853d5c830f78751aff5f51fd1viral genome,Severe acute respiratory syndrome...NucleocapsidNCAP_CVHSA
\n", + "
" + ], + "text/plain": [ + " PAPER_ID \\\n", + "0 7cfaa2540d3c8eea0982b3b1147884f125f67ff2 \n", + "1 9bbfd3d34ee18ea1b9f4669331a6cee9c5992893 \n", + "2 9bbfd3d34ee18ea1b9f4669331a6cee9c5992893 \n", + "3 9bbfd3d34ee18ea1b9f4669331a6cee9c5992893 \n", + "4 240da1ff435355a853d5c830f78751aff5f51fd1 \n", + "\n", + " SARS_COV \\\n", + "0 SARS coronavirus \n", + "1 Severe acute respiratory syndrome coronavirus 2 \n", + "2 SARS coronavirus,Severe acute respiratory synd... \n", + "3 Severe acute respiratory syndrome coronavirus 2 \n", + "4 viral genome,Severe acute respiratory syndrome... \n", + "\n", + " SPECIES CVPROT \n", + "0 SARS Virus,Humans,Viruses SPIKE_CVHSA \n", + "1 Humans,Viruses SPIKE_CVHSA \n", + "2 SARS Virus,Viruses SPIKE_CVHSA \n", + "3 Coronavirus NL63, Human SPIKE_CVHSA \n", + "4 Nucleocapsid NCAP_CVHSA " + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sars_paper_id = {'PAPER_ID': [], 'SARS_COV': [],'STRAINS_GROUP': [],'SPECIES': [],'CVPROT': []}\n", + "for i in tqdm(range(0, data.shape[0])):\n", + " row = data.iloc[i]\n", + " prot_field = row['CVPROT']\n", + " prot_field = str(prot_field)\n", + " prot_field = prot_field.split(',')\n", + " for prot in prot_field:\n", + " if prot in cvprot_list:\n", + " paper_id = row['paper_id']\n", + " SARS_cov = row['SARSCOV']\n", + " species = row['SPECIES']\n", + " sars_paper_id['PAPER_ID'].append(paper_id)\n", + " sars_paper_id['SARS_COV'].append(SARS_cov)\n", + " sars_paper_id['SPECIES'].append(species)\n", + " sars_paper_id['CVPROT'].append(prot)\n", + " \n", + " \n", + "df_cvprot = pd.DataFrame(sars_paper_id, columns=['PAPER_ID', 'SARS_COV', 'SPECIES', 'CVPROT'])\n", + "df_cvprot.head()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 29, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "(26962, 4)" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "SPIKE_WCPV_pt = round(SPIKE_WCPV/total_papers,2)\n", - "R1AB_WCPV_pt = round(R1AB_WCPV/total_papers,2)\n", - "NCAP_WCPV_pt = round(NCAP_WCPV/total_papers,2)\n", - "R1A_WCPV_pt = round(R1A_WCPV/total_papers,2)\n", - "#NS8_WCPV_pt = round(NS8_WCPV/total_papers,2)\n", - "VME1_WCPV_pt = round(VME1_WCPV/total_papers,2)\n", - "AP3A_WCPV_pt = round(AP3A_WCPV/total_papers,2)\n", - "VEMP_WCPV_pt = round(VEMP_WCPV/total_papers,2)\n", - "A0A663DJA2_9BETC_pt = round(A0A663DJA2_9BETC/total_papers,2)\n", - "ORF9B_WCPV_pt = round(ORF9B_WCPV/total_papers,2)\n", - "Y14_WCPV_pt = round(Y14_WCPV/total_papers,2)\n", - "NS6_WCPV_pt = round(NS6_WCPV/total_papers,2)\n", - "NS7B_WCPV_pt = round(NS7B_WCPV/total_papers,2)\n", - "NS7A_WCPV_pt = round(NS7A_WCPV/total_papers,2)" + "df_cvprot.shape" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 30, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "#save data\n", + "df_cvprot.to_csv('data/data_prot.csv')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 4. Create Pie Chart, Histogram" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 31, "metadata": {}, "outputs": [], "source": [ - "print(SPIKE_WCPV_pt,R1AB_WCPV_pt,NCAP_WCPV_pt,R1A_WCPV_pt,NS8_WCPV_pt,VME1_WCPV_pt,AP3A_WCPV_pt,VEMP_WCPV_pt,A0A663DJA2_9BETC_pt,ORF9B_WCPV_pt, Y14_WCPV_pt,NS6_WCPV_pt,NS7B_WCPV_pt,NS7A_WCPV_pt)" + "#check data unique relation - paper ID & protein\n", + "df_paper_id = df_cvprot[\"PAPER_ID\"]\n", + "df_prot = df_cvprot[\"CVPROT\"]\n", + "df_check_unq = pd.concat([df_paper_id, df_prot], axis=1)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "(10404, 2)" + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "#Pie Chart - Adjust labels, sizes & explode after running on full data\n", - "#https://matplotlib.org/3.1.1/gallery/pie_and_polar_charts/pie_features.html" + "df_check_unq.shape\n", + "df_check_unq = df_check_unq.drop_duplicates()\n", + "df_check_unq.shape" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 33, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "CVPROT CVPROT \n", + "AP3A_CVHSA AP3A_CVHSA 134\n", + "NCAP_CVHSA NCAP_CVHSA 2136\n", + "NS3B_CVHSA NS3B_CVHSA 55\n", + "NS6_CVHSA NS6_CVHSA 147\n", + "NS7A_CVHSA NS7A_CVHSA 59\n", + "NS7B_CVHSA NS7B_CVHSA 37\n", + "NS8A_CVHSA NS8A_CVHSA 19\n", + "NS8B_CVHSA NS8B_CVHSA 11\n", + "ORF9B_CVHSA ORF9B_CVHSA 69\n", + "R1AB_CVHSA R1AB_CVHSA 925\n", + "R1A_CVHSA R1A_CVHSA 839\n", + "SPIKE_CVHSA SPIKE_CVHSA 3537\n", + "VEMP_CVHSA VEMP_CVHSA 1129\n", + "VME1_CVHSA VME1_CVHSA 1296\n", + "Y14_CVHSA Y14_CVHSA 11\n", + "Name: CVPROT, dtype: int64" + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "import matplotlib.pyplot as plt\n", + "#Plot piechart for strains groups: percent of papers (not blocks) mentioned each strains group. \n", + "#IMPORTANT: STRAINS or PROTEINS? This is proteins.\n", + "#get count of papers that contain at least one mention of the protein\n", + "prot_counts = df_check_unq.groupby('CVPROT').CVPROT.value_counts()\n", + "prot_counts" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "5352" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#get total paper count\n", + "papers = df_cvprot[\"PAPER_ID\"]\n", + "papers.shape[0]\n", + "papers = papers.drop_duplicates()\n", + "papers.shape[0]\n", + "total_papers = papers.shape[0]\n", + "total_papers" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 AP3A_CVHSA\n", + "1 NCAP_CVHSA\n", + "2 NS3B_CVHSA\n", + "3 NS6_CVHSA\n", + "4 NS7A_CVHSA\n", + "5 NS7B_CVHSA\n", + "6 NS8A_CVHSA\n", + "7 NS8B_CVHSA\n", + "8 ORF9B_CVHSA\n", + "9 R1AB_CVHSA\n", + "10 R1A_CVHSA\n", + "11 SPIKE_CVHSA\n", + "12 VEMP_CVHSA\n", + "13 VME1_CVHSA\n", + "14 Y14_CVHSA\n", + "Name: 0, dtype: object" + ] + }, + "execution_count": 41, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#get sorted listed of proteins\n", + "proteins = df_cvprot.CVPROT.value_counts()\n", + "proteins = list(proteins.index)\n", + "proteins = pd.Series(proteins)\n", + "proteins = proteins.sort_values().reset_index()\n", + "proteins = pd.DataFrame(proteins)\n", + "proteins = proteins.iloc[:,1]\n", + "proteins" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[134, 2136, 55, 147, 59, 37, 19, 11, 69, 925, 839, 3537, 1129, 1296, 11]" + ] + }, + "execution_count": 43, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "protein_counts = prot_counts.values.tolist()\n", + "protein_counts" + ] + }, + { + "cell_type": "code", + "execution_count": 50, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
proteinpercent
11SPIKE_CVHSA66.0
1NCAP_CVHSA40.0
13VME1_CVHSA24.0
12VEMP_CVHSA21.0
9R1AB_CVHSA17.0
10R1A_CVHSA16.0
0AP3A_CVHSA3.0
3NS6_CVHSA3.0
2NS3B_CVHSA1.0
4NS7A_CVHSA1.0
5NS7B_CVHSA1.0
8ORF9B_CVHSA1.0
6NS8A_CVHSA0.0
7NS8B_CVHSA0.0
14Y14_CVHSA0.0
\n", + "
" + ], + "text/plain": [ + " protein percent\n", + "11 SPIKE_CVHSA 66.0\n", + "1 NCAP_CVHSA 40.0\n", + "13 VME1_CVHSA 24.0\n", + "12 VEMP_CVHSA 21.0\n", + "9 R1AB_CVHSA 17.0\n", + "10 R1A_CVHSA 16.0\n", + "0 AP3A_CVHSA 3.0\n", + "3 NS6_CVHSA 3.0\n", + "2 NS3B_CVHSA 1.0\n", + "4 NS7A_CVHSA 1.0\n", + "5 NS7B_CVHSA 1.0\n", + "8 ORF9B_CVHSA 1.0\n", + "6 NS8A_CVHSA 0.0\n", + "7 NS8B_CVHSA 0.0\n", + "14 Y14_CVHSA 0.0" + ] + }, + "execution_count": 50, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pie_chart_input = {'protein': [], 'percent': []}\n", + "for i in range(0,proteins.shape[0]):\n", + " label = proteins.iloc[i]\n", + " value = protein_counts[i]\n", + " percent = round(value/total_papers,2)*100\n", + " pie_chart_input['protein'].append(label)\n", + " pie_chart_input['percent'].append(percent)\n", + "\n", + "pie_chart_input = pd.DataFrame(pie_chart_input)\n", + "pie_chart_input = pie_chart_input.sort_values(by='percent', ascending=False)\n", + "pie_chart_input" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
proteinpercent
11SPIKE_CVHSA66.0
1NCAP_CVHSA40.0
13VME1_CVHSA24.0
12VEMP_CVHSA21.0
9R1AB_CVHSA17.0
10R1A_CVHSA16.0
\n", + "
" + ], + "text/plain": [ + " protein percent\n", + "11 SPIKE_CVHSA 66.0\n", + "1 NCAP_CVHSA 40.0\n", + "13 VME1_CVHSA 24.0\n", + "12 VEMP_CVHSA 21.0\n", + "9 R1AB_CVHSA 17.0\n", + "10 R1A_CVHSA 16.0" + ] + }, + "execution_count": 51, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#use only top 6 for pie chart\n", + "input = pie_chart_input.iloc[0:6]\n", + "input" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['SPIKE_CVHSA',\n", + " 'NCAP_CVHSA',\n", + " 'VME1_CVHSA',\n", + " 'VEMP_CVHSA',\n", + " 'R1AB_CVHSA',\n", + " 'Other']" + ] + }, + "execution_count": 53, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#sum the rest\n", + "labels = list(input.iloc[:,0])\n", + "labels[-1] = 'Other'\n", + "labels" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[66.0, 40.0, 24.0, 21.0, 17.0, 7.0]" + ] + }, + "execution_count": 56, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "other = pie_chart_input.iloc[7:,1].sum()\n", + "sizes = list(input.iloc[:,1])\n", + "sizes[-1] = other\n", + "sizes" + ] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "#Pie Chart - Adjust labels, sizes & explode after running on full data\n", + "#https://matplotlib.org/3.1.1/gallery/pie_and_polar_charts/pie_features.html\n", "\n", "# Pie chart, where the slices will be ordered and plotted counter-clockwise:\n", - "labels = 'SPIKE_WCPV_pt','R1A_WCPV_pt','NCAP_WCPV_pt','VME1_WCPV_pt','VEMP_WCPV_pt','Others'\n", - "sizes = [0.38,0.32,0.27,0.21,0.16,0.02]\n", - "explode = (0.1, 0.0, 0, 0,0,0) # only \"explode\" the 2nd slice (i.e. 'Hogs')\n", + "labels = labels\n", + "sizes = sizes\n", + "explode = (0.1, 0.0, 0, 0,0,0) # only \"explode\" the 1st slice (i.e. 'Hogs')\n", "\n", "fig1, ax1 = plt.subplots()\n", "ax1.pie(sizes, explode=explode, labels=labels, autopct='%1.1f%%',\n", @@ -3217,16 +3863,27 @@ "ax1.axis('equal') # Equal aspect ratio ensures that pie is drawn as a circle.\n", "fig = plt.gcf()\n", "fig.set_size_inches(8,8)\n", - "plt.show()\n" + "plt.show()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 61, "metadata": {}, "outputs": [], "source": [ - "#Do the same for strains?\n" + "#Do the same for strains?\n", + "\n", + "#get sorted listed\n", + "strains = df_cvprot.SARS_COV.value_counts()\n", + "strains = list(strains.index)\n", + "strains = pd.Series(strains)\n", + "strains = proteins.sort_values().reset_index()\n", + "strains = pd.DataFrame(strains)\n", + "strains = strains.iloc[:,1]\n", + "\n", + "strains_counts = df_check_unq.groupby('SARS_COV').SARS_COV.value_counts()\n", + "strains_counts = prot_counts.values.tolist()" ] }, { @@ -3243,7 +3900,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 58, "metadata": {}, "outputs": [], "source": [ @@ -3252,9 +3909,32 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 59, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "Text(0, 0.5, 'protein')" + ] + }, + "execution_count": 59, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], "source": [ "cvprot_counts\n", "top_5 = cvprot_counts[0:5]\n", @@ -3262,7 +3942,7 @@ "top_5.plot(kind='bar')\n", "plt.title('Top 5 Protein Mentions')\n", "plt.xlabel('value')\n", - "plt.ylabel('protein')\n" + "plt.ylabel('protein')" ] }, { @@ -3283,61 +3963,62 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "#https://www.kaggle.com/rtatman/co-occurrence-matrix-plot-in-python" - ] - }, - { - "cell_type": "code", - "execution_count": null, + "execution_count": 63, "metadata": {}, - "outputs": [], - "source": [ - "import seaborn as sns" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "df_cvprot.shape[0], df_cvprot.PAPER_ID.nunique() # " + ] + }, + "execution_count": 67, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], "source": [ "#transform data and create heatmap (repeat for all strain groups)\n", "strains_df.iloc[:,4:] = strains_df.iloc[:,4:].astype(int) \n", @@ -3345,13 +4026,6 @@ "prot_strains_grpd = strains_df.groupby('CVPROT').sum()\n", "sns.heatmap(prot_strains_grpd)" ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] } ], "metadata": { @@ -3370,7 +4044,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.4" + "version": "3.6.8" } }, "nbformat": 4,