Nextclade: QC tuning for SH dataset

nextclade/defaults/config.yaml

@@ -13,6 +13,8 @@ metadata_url: "https://data.nextstrain.org/files/workflows/mumps/metadata.tsv.zs
 
 strain_id_field: "accession"
 
+# Merge in clade_membership column from {metadata} file
+# If not defined, use {fallback} column
 clade_membership:
   metadata: "{build}/reference_strains.tsv"
   fallback: "MuV_genotype"
@@ -21,7 +23,7 @@ filter:
   exclude: "{build}/exclude.txt"
   include: "{build}/include.txt"
   sh: '--exclude-all'
-  genome: --subsample-max-sequences 300 --min-date 1950 --group-by MuV_genotype --min-length 12000 --exclude-where clade_membership=''
+  genome: --subsample-max-sequences 300 --min-date 1950 --group-by clade_membership --min-length 12000 --exclude-where clade_membership=''
 
 align:
   sh: '--fill-gaps --remove-reference'
@@ -40,8 +42,8 @@ ancestral:
 
 traits:
   sampling_bias_correction: 3
-  sh: clade_membership MuV_genotype
-  genome: clade_membership MuV_genotype
+  sh: clade_membership
+  genome: clade_membership
 
 colors:
   # Note: Reusing files from the phylogenetic workflow

nextclade/defaults/genome/auspice_config.json

@@ -1,5 +1,5 @@
 {
-  "title": "Real-time tracking of mumps virus evolution",
+  "title": "Mumps MuV Genotypes (Full genome)",
   "maintainers": [
     {"name": "the Nextstrain team", "url": "https://nextstrain.org/team"}
   ],
@@ -27,7 +27,7 @@
       "type": "categorical"
     },
     {
-      "key": "MuV_genotype",
+      "key": "clade_membership",
       "title": "MuV genotype",
       "type": "categorical"
     },
@@ -58,7 +58,6 @@
   },
   "filters": [
     "clade_membership",
-    "MuV_genotype",
     "country",
     "region",
     "author"
@@ -67,44 +66,5 @@
     "strain",
     "isolate",
     "host"
-  ],
-  "extensions": {
-    "nextclade": {
-      "clade_node_attrs": [
-        {
-          "name": "MuV_genotype",
-          "displayName": "MuV Genotype",
-          "description": "Mumps genotype"
-        }
-      ],
-      "pathogen": {
-        "schemaVersion":"3.0.0",
-        "attributes": {
-          "name": "Mumps genotype tree",
-          "reference name": "Jeryl-Lynn (genotype A)",
-          "reference accession": "D90232"
-        },
-        "alignmentParams": {
-          "minLength": 80,
-          "penaltyGapExtend": 1,
-          "penaltyGapOpen": 4,
-          "penaltyGapOpenInFrame": 4,
-          "penaltyGapOpenOutOfFrame": 6,
-          "penaltyMismatch": 1,
-          "scoreMatch": 4,
-          "noTranslatePastStop": false,
-          "excessBandwidth": 9,
-          "terminalBandwidth": 80,
-          "allowedMismatches": 12,
-          "minMatchLength": 30,
-          "maxAlignmentAttempts": 5,
-          "includeReference": true,
-          "includeNearestNodeInfo": true,
-          "retryReverseComplement": true,
-          "minSeedCover": 0.01
-        },
-        "defaultCds": "SH"
-      }
-    }
-  }
+  ]
 }

nextclade/defaults/sh/README.md

@@ -27,6 +27,8 @@ This dataset supports:
 
 - Assignment of genotype
 - Phylogenetic placement
+- Translation of annotated reading frames
+- Quality metrics based on unexpected frameshifts, stop codons, and coverage.
 
 ## What are Nextclade datasets
 

nextclade/defaults/sh/auspice_config.json

@@ -1,5 +1,5 @@
 {
-  "title": "Real-time tracking of mumps virus evolution",
+  "title": "Mumps MuV Genotypes (SH gene 315nt region)",
   "maintainers": [
     {"name": "the Nextstrain team", "url": "https://nextstrain.org/team"}
   ],
@@ -27,7 +27,7 @@
       "type": "categorical"
     },
     {
-      "key": "MuV_genotype",
+      "key": "clade_membership",
       "title": "MuV genotype",
       "type": "categorical"
     },
@@ -58,7 +58,6 @@
   },
   "filters": [
     "clade_membership",
-    "MuV_genotype",
     "country",
     "region",
     "author"
@@ -67,44 +66,5 @@
     "strain",
     "isolate",
     "host"
-  ],
-  "extensions": {
-    "nextclade": {
-      "clade_node_attrs": [
-        {
-          "name": "MuV_genotype",
-          "displayName": "MuV Genotype",
-          "description": "Mumps genotype"
-        }
-      ],
-      "pathogen": {
-        "schemaVersion":"3.0.0",
-        "attributes": {
-          "name": "Mumps genotype tree",
-          "reference name": "Jeryl-Lynn (genotype A)",
-          "reference accession": "D90232"
-        },
-        "alignmentParams": {
-          "minLength": 80,
-          "penaltyGapExtend": 1,
-          "penaltyGapOpen": 4,
-          "penaltyGapOpenInFrame": 4,
-          "penaltyGapOpenOutOfFrame": 6,
-          "penaltyMismatch": 1,
-          "scoreMatch": 4,
-          "noTranslatePastStop": false,
-          "excessBandwidth": 9,
-          "terminalBandwidth": 80,
-          "allowedMismatches": 12,
-          "minMatchLength": 30,
-          "maxAlignmentAttempts": 5,
-          "includeReference": true,
-          "includeNearestNodeInfo": true,
-          "retryReverseComplement": true,
-          "minSeedCover": 0.01
-        },
-        "defaultCds": "SH"
-      }
-    }
-  }
+  ]
 }

nextclade/defaults/sh/pathogen.json

@@ -47,5 +47,26 @@
   "version": {
     "tag": "unreleased"
   },
-  "defaultCds": "SH"
+  "defaultCds": "SH",
+    "qc": {
+    "missingData": {
+      "enabled": true,
+      "missingDataThreshold": 300,
+      "scoreBias": 500,
+      "scoreWeight": 50
+    },
+    "mixedSites": {
+      "enabled": true,
+      "mixedSitesThreshold": 15,
+      "scoreWeight": 50
+    },
+    "frameShifts": {
+      "enabled": true,
+      "scoreWeight": 20
+    },
+    "stopCodons": {
+      "enabled": true,
+      "scoreWeight": 50
+    }
+  }
 }