fixup: update dataset to incorporate fixes

* Use reconstructed roots for serotype-level and genotype-level datasets
* Update the all dataset with root and gap penalty
* Update the dengue/all dataset README.md file

nextclade/datasets/all/README.md

@@ -1,7 +1,26 @@
-# Nextclade dataset for "Dengue Virus"
+# De dataset
 
-## Dataset attributes
+| Key  | Value  |
+| :-- | :-- |
+| name  | Dengue (serotype-level) |
+| authors | [Nextstrain](https://nextstrain.org) |
+| reference | NC_002640.1 |
+| workflow  | https://github.com/nextstrain/dengue/tree/main/nextclade  |
+| path  | `nextstrain/dengue/all` |
 
-Nextclade dataset
 
-Read more about Nextclade datasets in Nextclade documentation: https://docs.nextstrain.org/projects/nextclade/en/stable/user/datasets.html
+## Scope of this dataset
+
+This dataset assigns serotype to dengue samples based on [criteria outlined by the WHO](https://pubmed.ncbi.nlm.nih.gov/26868382/) and tree placement nearest references [NC_001477.1 (DENV1)](https://www.ncbi.nlm.nih.gov/nuccore/NC_001477.1), [NC_001474.2 (DENV2)](https://www.ncbi.nlm.nih.gov/nuccore/NC_001474.2), [NC_001475.2 (DENV3)](https://www.ncbi.nlm.nih.gov/nuccore/NC_001475.2), and [NC_002640.1 (DENV4)](https://www.ncbi.nlm.nih.gov/nuccore/NC_002640.1).
+
+## Features
+
+This dataset supports:
+
+- Assignment of serotypes
+- Phylogenetic placement
+- Sequence quality control (QC)
+
+## What are Nextclade datasets
+
+Read more about Nextclade datasets in the Nextclade documentation: https://docs.nextstrain.org/projects/nextclade/en/stable/user/datasets.html

nextclade/datasets/all/genome_annotation.gff3

@@ -1,14 +1,14 @@
 ##gff-version 3
-##sequence-region NC_002640.1 1 10649
-NC_002640.1	feature	gene	102	440	.	+	.	codon_start=1;gene=C;gene_name=C;
-NC_002640.1	feature	gene	441	713	.	+	.	codon_start=1;gene=pr;gene_name=pr;
-NC_002640.1	feature	gene	441	938	.	+	.	codon_start=1;gene=M;gene_name=M;
-NC_002640.1	feature	gene	939	2423	.	+	.	codon_start=1;gene=E;gene_name=E;
-NC_002640.1	feature	gene	2424	3479	.	+	.	codon_start=1;gene=NS1;gene_name=NS1;
-NC_002640.1	feature	gene	3480	4133	.	+	.	codon_start=1;gene=NS2A;gene_name=NS2A;
-NC_002640.1	feature	gene	4134	4523	.	+	.	codon_start=1;gene=NS2B;gene_name=NS2B;
-NC_002640.1	feature	gene	4524	6377	.	+	.	codon_start=1;gene=NS3;gene_name=NS3;
-NC_002640.1	feature	gene	6378	6758	.	+	.	codon_start=1;gene=NS4A;gene_name=NS4A;
-NC_002640.1	feature	gene	6759	6827	.	+	.	codon_start=1;gene=2K;gene_name=2K;
-NC_002640.1	feature	gene	6828	7562	.	+	.	codon_start=1;gene=NS4B;gene_name=NS4B;
-NC_002640.1	feature	gene	7563	10262	.	+	.	codon_start=1;gene=NS5;gene_name=NS5;
+##sequence-region Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome 1 10649
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome	feature	gene	102	440	.	+	.	codon_start=1;gene=C;gene_name=C;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome	feature	gene	441	713	.	+	.	codon_start=1;gene=pr;gene_name=pr;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome	feature	gene	441	938	.	+	.	codon_start=1;gene=M;gene_name=M;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome	feature	gene	939	2423	.	+	.	codon_start=1;gene=E;gene_name=E;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome	feature	gene	2424	3479	.	+	.	codon_start=1;gene=NS1;gene_name=NS1;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome	feature	gene	3480	4133	.	+	.	codon_start=1;gene=NS2A;gene_name=NS2A;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome	feature	gene	4134	4523	.	+	.	codon_start=1;gene=NS2B;gene_name=NS2B;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome	feature	gene	4524	6377	.	+	.	codon_start=1;gene=NS3;gene_name=NS3;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome	feature	gene	6378	6758	.	+	.	codon_start=1;gene=NS4A;gene_name=NS4A;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome	feature	gene	6759	6827	.	+	.	codon_start=1;gene=2K;gene_name=2K;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome	feature	gene	6828	7562	.	+	.	codon_start=1;gene=NS4B;gene_name=NS4B;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/all/genome	feature	gene	7563	10262	.	+	.	codon_start=1;gene=NS5;gene_name=NS5;

nextclade/datasets/all/pathogen.json

@@ -1,5 +1,9 @@
 {
   "alignmentParams": {
+    "penaltyGapOpen": 8,
+    "penaltyGapOpenInFrame": 12,
+    "penaltyGapOpenOutOfFrame": 14,
+    "gapAlignmentSide": "left",
     "minSeedCover": 0.01,
     "minLength": 1000
   },
@@ -30,7 +34,7 @@
   },
   "qc": {
     "frameShifts": {
-      "enabled": false
+      "enabled": true
     },
     "missingData": {
       "enabled": false,
@@ -56,7 +60,7 @@
       "windowSize": 100
     },
     "stopCodons": {
-      "enabled": false
+      "enabled": true
     }
   },
   "schemaVersion": "3.0.0",

nextclade/datasets/denv1/genome_annotation.gff3

@@ -1,14 +1,14 @@
 ##gff-version 3
-##sequence-region NC_001477.1 1 10735
-NC_001477.1	feature	gene	95	436	.	+	.	codon_start=1;gene=C;gene_name=C;
-NC_001477.1	feature	gene	437	709	.	+	.	codon_start=1;gene=pr;gene_name=pr;
-NC_001477.1	feature	gene	437	934	.	+	.	codon_start=1;gene=M;gene_name=M;
-NC_001477.1	feature	gene	935	2419	.	+	.	codon_start=1;gene=E;gene_name=E;
-NC_001477.1	feature	gene	2420	3475	.	+	.	codon_start=1;gene=NS1;gene_name=NS1;
-NC_001477.1	feature	gene	3476	4129	.	+	.	codon_start=1;gene=NS2A;gene_name=NS2A;
-NC_001477.1	feature	gene	4130	4519	.	+	.	codon_start=1;gene=NS2B;gene_name=NS2B;
-NC_001477.1	feature	gene	4520	6376	.	+	.	codon_start=1;gene=NS3;gene_name=NS3;
-NC_001477.1	feature	gene	6377	6757	.	+	.	codon_start=1;gene=NS4A;gene_name=NS4A;
-NC_001477.1	feature	gene	6758	6826	.	+	.	codon_start=1;gene=2K;gene_name=2K;
-NC_001477.1	feature	gene	6827	7573	.	+	.	codon_start=1;gene=NS4B;gene_name=NS4B;
-NC_001477.1	feature	gene	7574	10270	.	+	.	codon_start=1;gene=NS5;gene_name=NS5;
+##sequence-region Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome 1 10735
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome	feature	gene	95	436	.	+	.	codon_start=1;gene=C;gene_name=C;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome	feature	gene	437	709	.	+	.	codon_start=1;gene=pr;gene_name=pr;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome	feature	gene	437	934	.	+	.	codon_start=1;gene=M;gene_name=M;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome	feature	gene	935	2419	.	+	.	codon_start=1;gene=E;gene_name=E;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome	feature	gene	2420	3475	.	+	.	codon_start=1;gene=NS1;gene_name=NS1;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome	feature	gene	3476	4129	.	+	.	codon_start=1;gene=NS2A;gene_name=NS2A;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome	feature	gene	4130	4519	.	+	.	codon_start=1;gene=NS2B;gene_name=NS2B;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome	feature	gene	4520	6376	.	+	.	codon_start=1;gene=NS3;gene_name=NS3;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome	feature	gene	6377	6757	.	+	.	codon_start=1;gene=NS4A;gene_name=NS4A;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome	feature	gene	6758	6826	.	+	.	codon_start=1;gene=2K;gene_name=2K;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome	feature	gene	6827	7573	.	+	.	codon_start=1;gene=NS4B;gene_name=NS4B;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv1/genome	feature	gene	7574	10270	.	+	.	codon_start=1;gene=NS5;gene_name=NS5;

nextclade/datasets/denv1/pathogen.json

@@ -1,5 +1,9 @@
 {
   "alignmentParams": {
+    "penaltyGapOpen": 8,
+    "penaltyGapOpenInFrame": 12,
+    "penaltyGapOpenOutOfFrame": 14,
+    "gapAlignmentSide": "left",
     "minSeedCover": 0.1,
     "minLength": 1000
   },
@@ -17,6 +21,7 @@
   "experimental": true,
   "files": {
     "changelog": "CHANGELOG.md",
+    "examples": "sequences.fasta",
     "genomeAnnotation": "genome_annotation.gff3",
     "pathogenJson": "pathogen.json",
     "readme": "README.md",
@@ -29,7 +34,7 @@
   },
   "qc": {
     "frameShifts": {
-      "enabled": false
+      "enabled": true
     },
     "missingData": {
       "enabled": false,
@@ -55,7 +60,7 @@
       "windowSize": 100
     },
     "stopCodons": {
-      "enabled": false
+      "enabled": true
     }
   },
   "schemaVersion": "3.0.0",

nextclade/datasets/denv2/genome_annotation.gff3

@@ -1,14 +1,14 @@
 ##gff-version 3
-##sequence-region NC_001474.2 1 10723
-NC_001474.2	feature	gene	97	438	.	+	.	codon_start=1;gene=C;gene_name=C;
-NC_001474.2	feature	gene	439	711	.	+	.	codon_start=1;gene=pr;gene_name=pr;
-NC_001474.2	feature	gene	439	936	.	+	.	codon_start=1;gene=M;gene_name=M;
-NC_001474.2	feature	gene	937	2421	.	+	.	codon_start=1;gene=E;gene_name=E;
-NC_001474.2	feature	gene	2422	3477	.	+	.	codon_start=1;gene=NS1;gene_name=NS1;
-NC_001474.2	feature	gene	3478	4131	.	+	.	codon_start=1;gene=NS2A;gene_name=NS2A;
-NC_001474.2	feature	gene	4132	4521	.	+	.	codon_start=1;gene=NS2B;gene_name=NS2B;
-NC_001474.2	feature	gene	4522	6375	.	+	.	codon_start=1;gene=NS3;gene_name=NS3;
-NC_001474.2	feature	gene	6376	6756	.	+	.	codon_start=1;gene=NS4A;gene_name=NS4A;
-NC_001474.2	feature	gene	6757	6825	.	+	.	codon_start=1;gene=2K;gene_name=2K;
-NC_001474.2	feature	gene	6826	7569	.	+	.	codon_start=1;gene=NS4B;gene_name=NS4B;
-NC_001474.2	feature	gene	7570	10269	.	+	.	codon_start=1;gene=NS5;gene_name=NS5;
+##sequence-region Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome 1 10723
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome	feature	gene	97	438	.	+	.	codon_start=1;gene=C;gene_name=C;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome	feature	gene	439	711	.	+	.	codon_start=1;gene=pr;gene_name=pr;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome	feature	gene	439	936	.	+	.	codon_start=1;gene=M;gene_name=M;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome	feature	gene	937	2421	.	+	.	codon_start=1;gene=E;gene_name=E;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome	feature	gene	2422	3477	.	+	.	codon_start=1;gene=NS1;gene_name=NS1;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome	feature	gene	3478	4131	.	+	.	codon_start=1;gene=NS2A;gene_name=NS2A;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome	feature	gene	4132	4521	.	+	.	codon_start=1;gene=NS2B;gene_name=NS2B;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome	feature	gene	4522	6375	.	+	.	codon_start=1;gene=NS3;gene_name=NS3;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome	feature	gene	6376	6756	.	+	.	codon_start=1;gene=NS4A;gene_name=NS4A;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome	feature	gene	6757	6825	.	+	.	codon_start=1;gene=2K;gene_name=2K;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome	feature	gene	6826	7569	.	+	.	codon_start=1;gene=NS4B;gene_name=NS4B;
+Reconstructed_root_sequence_of_https_nextstrain_org_dengue/denv2/genome	feature	gene	7570	10269	.	+	.	codon_start=1;gene=NS5;gene_name=NS5;

nextclade/datasets/denv2/pathogen.json

@@ -1,5 +1,9 @@
 {
   "alignmentParams": {
+    "penaltyGapOpen": 8,
+    "penaltyGapOpenInFrame": 12,
+    "penaltyGapOpenOutOfFrame": 14,
+    "gapAlignmentSide": "left",
     "minSeedCover": 0.1,
     "minLength": 1000
   },
@@ -17,6 +21,7 @@
   "experimental": true,
   "files": {
     "changelog": "CHANGELOG.md",
+    "examples": "sequences.fasta",
     "genomeAnnotation": "genome_annotation.gff3",
     "pathogenJson": "pathogen.json",
     "readme": "README.md",
@@ -29,7 +34,7 @@
   },
   "qc": {
     "frameShifts": {
-      "enabled": false
+      "enabled": true
     },
     "missingData": {
       "enabled": false,
@@ -55,7 +60,7 @@
       "windowSize": 100
     },
     "stopCodons": {
-      "enabled": false
+      "enabled": true
     }
   },
   "schemaVersion": "3.0.0",