From c43bc1d7d4b291d293bd95fa111c986922e0ffb4 Mon Sep 17 00:00:00 2001 From: bsantan <70932395+bsantan@users.noreply.github.com> Date: Fri, 23 Aug 2024 12:32:53 -0600 Subject: [PATCH 1/6] create all graphs for paper --- Makefile | 33 ++++++++------------------------- 1 file changed, 8 insertions(+), 25 deletions(-) diff --git a/Makefile b/Makefile index 3b01a45..1634806 100644 --- a/Makefile +++ b/Makefile @@ -1,29 +1,12 @@ -# download-transforms: +kg-microbe-core: + poetry run kg merge -m duckdb -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa" -# wget "XXX" -O data/raw/merged-kg_nodes.tsv +kg-microbe-function: + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa, uniprot_functional_microbes" -# merge-kg-microbe-function: -# PWD=$(pwd) -# poetry run kg merge -y $(PWD)/merged_yamls/kg_base_merge.yaml -# poetry run kg duckdb_merge -base-n $(PWD)/data/merged/merged-kg_nodes.tsv -subset-n $(PWD)/data/transformed/nodes.tsv -base-e $(PWD)/data/merged/merged-kg_edges.tsv -subset-e $(PWD)/data/transformed/edges.tsv +kg-microbe-biomedical: + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_human" -# merge-kg-microbe-biomedical: -# PWD=$(pwd) -# poetry run kg merge -y $(PWD)/merged_yamls/kg_biomedical_merge.yaml - -# merge-kg-microbe-biomedical-function: -# PWD=$(pwd) -# poetry run kg merge -y $(PWD)/merged_yamls/kg_biomedical_merge.yaml -# poetry run kg duckdb_merge -base-n $(PWD)/data/merged/merged-kg_nodes.tsv -subset-n $(PWD)/data/transformed/nodes.tsv -base-e $(PWD)/data/merged/merged-kg_edges.tsv -subset-e $(PWD)/data/transformed/edges.tsv - -# !For testing -# merge-kg-microbe-biomedical-function: -# poetry run kg merge -y merge_yamls/merge.yaml -m duckdb -base-n '/Users/brooksantangelo/Documents/LozuponeLab/FRMS_2024/duckdb/merged-kg_kg-microbe-base/merged-kg_nodes.tsv' -base-e '/Users/brooksantangelo/Documents/LozuponeLab/FRMS_2024/duckdb/merged-kg_kg-microbe-base/merged-kg_edges.tsv' -subset-n '/Users/brooksantangelo/Documents/Repositories/kg-microbe/data/transformed/uniprot_genome_features/nodes.tsv' -subset-e '/Users/brooksantangelo/Documents/Repositories/kg-microbe/data/transformed/uniprot_genome_features/edges.tsv' - -datamodel: - poetry run gen-python kg_microbe_merge/schema/merge_schema.yaml > kg_microbe_merge/schema/merge_datamodel.py - - -subset-merge: - poetry run kg merge -m duckdb -s "bacdive, bactotraits, chebi, ncbitaxon" \ No newline at end of file +kg-microbe-biomedical-function-merge: + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_functional_microbes, uniprot_human" \ No newline at end of file From 954de6864deccb5a0d699dad62eca3d025b8a90b Mon Sep 17 00:00:00 2001 From: bsantan <70932395+bsantan@users.noreply.github.com> Date: Mon, 26 Aug 2024 16:37:07 -0600 Subject: [PATCH 2/6] add datamodel back into Makefile --- Makefile | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Makefile b/Makefile index 1634806..eb26c0f 100644 --- a/Makefile +++ b/Makefile @@ -1,4 +1,7 @@ +datamodel: + poetry run gen-python kg_microbe_merge/schema/merge_schema.yaml > kg_microbe_merge/schema/merge_datamodel.py + kg-microbe-core: poetry run kg merge -m duckdb -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa" From 8598e91c3fbd9d409eb59b2e61e91981933a6c06 Mon Sep 17 00:00:00 2001 From: bsantan <70932395+bsantan@users.noreply.github.com> Date: Fri, 30 Aug 2024 13:09:56 -0600 Subject: [PATCH 3/6] Add merge labels --- Makefile | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/Makefile b/Makefile index eb26c0f..4111957 100644 --- a/Makefile +++ b/Makefile @@ -3,13 +3,13 @@ datamodel: poetry run gen-python kg_microbe_merge/schema/merge_schema.yaml > kg_microbe_merge/schema/merge_datamodel.py kg-microbe-core: - poetry run kg merge -m duckdb -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa" + poetry run kg merge -m duckdb -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa" --merge-tool $@ kg-microbe-function: - poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa, uniprot_functional_microbes" + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa, uniprot_functional_microbes" --merge-tool $@ kg-microbe-biomedical: - poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_human" + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_human" --merge-tool $@ kg-microbe-biomedical-function-merge: - poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_functional_microbes, uniprot_human" \ No newline at end of file + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_functional_microbes, uniprot_human" --merge-tool $@ \ No newline at end of file From 659914ffd398190510fe2ccc2920cf8e2a75a05a Mon Sep 17 00:00:00 2001 From: bsantan <70932395+bsantan@users.noreply.github.com> Date: Fri, 30 Aug 2024 15:12:59 -0600 Subject: [PATCH 4/6] fix Makefile --- Makefile | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/Makefile b/Makefile index 4111957..09d62f7 100644 --- a/Makefile +++ b/Makefile @@ -3,13 +3,13 @@ datamodel: poetry run gen-python kg_microbe_merge/schema/merge_schema.yaml > kg_microbe_merge/schema/merge_datamodel.py kg-microbe-core: - poetry run kg merge -m duckdb -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa" --merge-tool $@ + poetry run kg merge -m duckdb -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa" --merge-tool $@ kg-microbe-function: - poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa, uniprot_functional_microbes" --merge-tool $@ + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa, uniprot_functional_microbes" --merge-tool $@ kg-microbe-biomedical: - poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_human" --merge-tool $@ + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_human" --merge-tool $@ kg-microbe-biomedical-function-merge: - poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rheamappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_functional_microbes, uniprot_human" --merge-tool $@ \ No newline at end of file + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_functional_microbes, uniprot_human" --merge-tool $@ \ No newline at end of file From 8ed26362b776455a1f53775d0b1138c4e49cf096 Mon Sep 17 00:00:00 2001 From: bsantan <70932395+bsantan@users.noreply.github.com> Date: Tue, 3 Sep 2024 12:26:45 -0600 Subject: [PATCH 5/6] Update Makefile --- Makefile | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/Makefile b/Makefile index 09d62f7..db906e3 100644 --- a/Makefile +++ b/Makefile @@ -3,13 +3,13 @@ datamodel: poetry run gen-python kg_microbe_merge/schema/merge_schema.yaml > kg_microbe_merge/schema/merge_datamodel.py kg-microbe-core: - poetry run kg merge -m duckdb -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa" --merge-tool $@ + poetry run kg merge -m duckdb -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa" --merge-label $@ kg-microbe-function: - poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa, uniprot_functional_microbes" --merge-tool $@ + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa, uniprot_functional_microbes" --merge-label $@ kg-microbe-biomedical: - poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_human" --merge-tool $@ + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_human" --merge-label $@ kg-microbe-biomedical-function-merge: - poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_functional_microbes, uniprot_human" --merge-tool $@ \ No newline at end of file + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_functional_microbes, uniprot_human" --merge-label $@ \ No newline at end of file From b9989d53c801fd4b2cd9ccb9abdd76903c35d7bb Mon Sep 17 00:00:00 2001 From: bsantan <70932395+bsantan@users.noreply.github.com> Date: Tue, 3 Sep 2024 12:32:39 -0600 Subject: [PATCH 6/6] reformat makefile --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index db906e3..42b4a24 100644 --- a/Makefile +++ b/Makefile @@ -9,7 +9,7 @@ kg-microbe-function: poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa, uniprot_functional_microbes" --merge-label $@ kg-microbe-biomedical: - poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_human" --merge-label $@ + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa, hp, mondo, ctd, wallen_etal, uniprot_human" --merge-label $@ kg-microbe-biomedical-function-merge: - poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, ctd, wallen_etal, chebi, ec, envo, go, hp, mondo, ncbitaxon, upa, uniprot_functional_microbes, uniprot_human" --merge-label $@ \ No newline at end of file + poetry run kg merge -m duckdb -n 1000000 -e 100000 -s "bacdive, mediadive, madin_etal, rhea_mappings, bactotraits, chebi, ec, envo, go, ncbitaxon, upa, hp, mondo, ctd, wallen_etal, uniprot_human, uniprot_functional_microbes" --merge-label $@ \ No newline at end of file