Update for version 0.3

iwc-workflows · Feb 4, 2022 · d49f767 · d49f767
1 parent e830d7c
commit d49f767
Show file tree

Hide file tree

Showing 4 changed files with 62 additions and 29 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,38 @@
 # Changelog
 
+## [0.3] 2022-02-02
+
+### Fixed
+- Apply AF thresholds on unbiased AF values recalculated from DP4 and DP fields
+  instead of on AF values provided by the variant caller to ensure proper
+  variant gating (into consensus and ambiguous variants) for lofreq-called
+  data.
+
+  https://github.com/CSB5/lofreq/issues/80 means that lofreq-calculated AF
+  values are lower bounds of true AFs when bases are excluded from calling
+  based on base quality. The extent of AF underestimation depends on the
+  fraction of bases with sub-threshold (30 for this workflow) base qualities.
+
+  By recalculating AFs as (DP4[2] + DP4[3]) / DP we avoid this issue for
+  variant calls generated by lofreq. For variants called with Galaxy's medaka
+  consensus/variant wrappers, original AFs are computed with the exact same
+  formula so the recalculation by the workflow does not affect variant gating
+  in that case.
+
+### Changed
+- Increase the default for consensus variant allele frequency threshold to 0.75.
+  Correct calculation of unbiased AF values increases the typical AF of
+  consensus variants more than enough to justify the change.
+- The following tools are updated to their latest wrapper versions or revisions:
+
+  - bcftools_consensus
+  - collapse_collections
+  - the gops subtract and merge tools
+  - snpsift
+
+  None of these updates are expected to impact the generated consensus
+  sequences.
+
 ## [0.2.2] 2021-12-13
 
 ### Added
@@ -12,6 +45,7 @@
 Added RO-Crate metadata file. No functional changes.
 
 ## [0.2] - 2021-04-30
+
 ### Changed
 - Lower the default for consensus variant allele frequency threshold to 0.7
   (from 0.8).

diff --git a/README.md b/README.md
@@ -5,16 +5,16 @@ This workflow aims at generating reliable consensus sequences from variant
 calls according to transparent criteria that capture at least some of the
 complexity of variant calling.
 
-It takes a collection of VCFs and a collection of the corresponding
-aligned reads (for the purpose of calculating genome-wide coverage) such as
-produced by any of the four variant calling workflows in
+It takes a collection of VCFs (with DP and DP4 INFO fields) and a collection of
+the corresponding aligned reads (for the purpose of calculating genome-wide
+coverage) such as produced by any of the variant calling workflows in
 https://github.com/galaxyproject/iwc/tree/main/workflows/sars-cov-2-variant-calling
 and generates a collection of viral consensus sequences and a multisample FASTA
 of all these sequences.
 
-Each consensus sequence is guaranteed to capture all called, filter-passing
-variants as defined in the VCF of its sample that reach a user-defined
-consensus allele frequency threshold.
+Each consensus sequence is guaranteed to capture all called, filter-passing (as
+per the FILTER column of the VCF input) variants found in the VCF of its sample
+that reach a user-defined consensus allele frequency threshold.
 
 Filter-failing variants and variants below a second user-defined minimal
 allele frequency threshold will be ignored.

diff --git a/consensus-from-variation.ga b/consensus-from-variation.ga
@@ -11,7 +11,7 @@
     "format-version": "0.1",
     "license": "MIT",
     "name": "COVID-19: consensus construction",
-    "release": "0.2.2",
+    "release": "0.3",
     "steps": {
         "0": {
             "annotation": "Collection of VCFs produced by upstream workflows for variation analysis",
@@ -71,7 +71,7 @@
                 "y": 687.5
             },
             "tool_id": null,
-            "tool_state": "{\"default\": 0.7, \"parameter_type\": \"float\", \"optional\": true}",
+            "tool_state": "{\"default\": 0.75, \"parameter_type\": \"float\", \"optional\": true}",
             "tool_version": null,
             "type": "parameter_input",
             "uuid": "52664bd7-b500-40a1-935b-8ac6df7003e5",
@@ -267,7 +267,7 @@
                 "owner": "iuc",
                 "tool_shed": "toolshed.g2.bx.psu.edu"
             },
-            "tool_state": "{\"components\": [{\"__index__\": 0, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \"((FILTER = 'PASS') | ( na FILTER )) & (AF >= \"}}, {\"__index__\": 1, \"param_type\": {\"select_param_type\": \"float\", \"__current_case__\": 2, \"component_value\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 2, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \")\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+            "tool_state": "{\"components\": [{\"__index__\": 0, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \"( ( FILTER = 'PASS' ) | ( na FILTER ) ) & ( ( DP4[2] + DP4[3] ) >= ( \"}}, {\"__index__\": 1, \"param_type\": {\"select_param_type\": \"float\", \"__current_case__\": 2, \"component_value\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 2, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \" * DP ) )\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}",
             "tool_version": "0.1.1",
             "type": "tool",
             "uuid": "8ec54933-36d6-404c-b0a6-5a14b04eb30e",
@@ -321,7 +321,7 @@
                 "owner": "iuc",
                 "tool_shed": "toolshed.g2.bx.psu.edu"
             },
-            "tool_state": "{\"components\": [{\"__index__\": 0, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \"(AF > \"}}, {\"__index__\": 1, \"param_type\": {\"select_param_type\": \"float\", \"__current_case__\": 2, \"component_value\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 2, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \") & (AF < \"}}, {\"__index__\": 3, \"param_type\": {\"select_param_type\": \"float\", \"__current_case__\": 2, \"component_value\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 4, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \") & ((FILTER = 'PASS') | ( na FILTER ))\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+            "tool_state": "{\"components\": [{\"__index__\": 0, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \"( ( DP4[2] + DP4[3] ) > ( \"}}, {\"__index__\": 1, \"param_type\": {\"select_param_type\": \"float\", \"__current_case__\": 2, \"component_value\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 2, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \" * DP ) ) & ( ( DP4[2] + DP4[3] ) < ( \"}}, {\"__index__\": 3, \"param_type\": {\"select_param_type\": \"float\", \"__current_case__\": 2, \"component_value\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 4, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \" * DP ) ) & ( ( FILTER = 'PASS' ) | ( na FILTER ) )\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}",
             "tool_version": "0.1.1",
             "type": "tool",
             "uuid": "51ac3588-c801-4551-8345-b04cc3571fea",
@@ -480,7 +480,7 @@
             },
             "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/snpsift/snpSift_filter/4.3+t.galaxy1",
             "tool_shed_repository": {
-                "changeset_revision": "2e497a770bca",
+                "changeset_revision": "5fab4f81391d",
                 "name": "snpsift",
                 "owner": "iuc",
                 "tool_shed": "toolshed.g2.bx.psu.edu"
@@ -542,7 +542,7 @@
             },
             "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/snpsift/snpSift_filter/4.3+t.galaxy1",
             "tool_shed_repository": {
-                "changeset_revision": "2e497a770bca",
+                "changeset_revision": "5fab4f81391d",
                 "name": "snpsift",
                 "owner": "iuc",
                 "tool_shed": "toolshed.g2.bx.psu.edu"
@@ -656,7 +656,7 @@
             },
             "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/snpsift/snpSift_extractFields/4.3+t.galaxy0",
             "tool_shed_repository": {
-                "changeset_revision": "09d6806c609e",
+                "changeset_revision": "5fab4f81391d",
                 "name": "snpsift",
                 "owner": "iuc",
                 "tool_shed": "toolshed.g2.bx.psu.edu"
@@ -714,7 +714,7 @@
             },
             "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/snpsift/snpSift_extractFields/4.3+t.galaxy0",
             "tool_shed_repository": {
-                "changeset_revision": "09d6806c609e",
+                "changeset_revision": "5fab4f81391d",
                 "name": "snpsift",
                 "owner": "iuc",
                 "tool_shed": "toolshed.g2.bx.psu.edu"
@@ -1191,7 +1191,7 @@
             },
             "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/merge/gops_merge_1/1.0.0",
             "tool_shed_repository": {
-                "changeset_revision": "0926c81f382c",
+                "changeset_revision": "381cd27bf67a",
                 "name": "merge",
                 "owner": "devteam",
                 "tool_shed": "toolshed.g2.bx.psu.edu"
@@ -1253,7 +1253,7 @@
             },
             "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/subtract/gops_subtract_1/1.0.0",
             "tool_shed_repository": {
-                "changeset_revision": "7a2a604ae9c8",
+                "changeset_revision": "0145969324c4",
                 "name": "subtract",
                 "owner": "devteam",
                 "tool_shed": "toolshed.g2.bx.psu.edu"
@@ -1389,7 +1389,7 @@
         },
         "26": {
             "annotation": "",
-            "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/bcftools_consensus/bcftools_consensus/1.10",
+            "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/bcftools_consensus/bcftools_consensus/1.10+galaxy1",
             "errors": null,
             "id": 26,
             "input_connections": {
@@ -1434,15 +1434,15 @@
                     "output_name": "output_file"
                 }
             },
-            "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/bcftools_consensus/bcftools_consensus/1.10",
+            "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/bcftools_consensus/bcftools_consensus/1.10+galaxy1",
             "tool_shed_repository": {
-                "changeset_revision": "e522022137f6",
+                "changeset_revision": "92182c270ce4",
                 "name": "bcftools_consensus",
                 "owner": "iuc",
                 "tool_shed": "toolshed.g2.bx.psu.edu"
             },
-            "tool_state": "{\"chain\": \"false\", \"input_file\": {\"__class__\": \"ConnectedValue\"}, \"reference_source\": {\"reference_source_selector\": \"history\", \"__current_case__\": 1, \"fasta_ref\": {\"__class__\": \"ConnectedValue\"}}, \"rename\": \"true\", \"sec_default\": {\"mask\": {\"__class__\": \"ConnectedValue\"}, \"iupac_codes\": \"false\", \"sample\": \"\", \"select_haplotype\": null}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
-            "tool_version": "1.10",
+            "tool_state": "{\"chain\": \"false\", \"input_file\": {\"__class__\": \"ConnectedValue\"}, \"reference_source\": {\"reference_source_selector\": \"history\", \"__current_case__\": 1, \"fasta_ref\": {\"__class__\": \"ConnectedValue\"}}, \"rename\": \"true\", \"sec_default\": {\"mask\": {\"__class__\": \"ConnectedValue\"}, \"iupac_codes\": \"false\", \"sample\": \"\", \"select_haplotype\": null}, \"sec_restrict\": {\"include\": \"\", \"exclude\": \"\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+            "tool_version": "1.10+galaxy1",
             "type": "tool",
             "uuid": "698a9a8c-f6fe-430b-a7e0-cf9e1d058d02",
             "workflow_outputs": [
@@ -1455,7 +1455,7 @@
         },
         "27": {
             "annotation": "",
-            "content_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/4.2",
+            "content_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0",
             "errors": null,
             "id": 27,
             "input_connections": {
@@ -1492,15 +1492,15 @@
                     "output_name": "output"
                 }
             },
-            "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/4.2",
+            "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0",
             "tool_shed_repository": {
-                "changeset_revision": "830961c48e42",
+                "changeset_revision": "90981f86000f",
                 "name": "collapse_collections",
                 "owner": "nml",
                 "tool_shed": "toolshed.g2.bx.psu.edu"
             },
             "tool_state": "{\"filename\": {\"add_name\": \"false\", \"__current_case__\": 1}, \"input_list\": {\"__class__\": \"ConnectedValue\"}, \"one_header\": \"false\", \"__page__\": null, \"__rerun_remap_job_id__\": null}",
-            "tool_version": "4.2",
+            "tool_version": "5.1.0",
             "type": "tool",
             "uuid": "acae0f3e-448b-483e-a44a-3e09ce9b3e77",
             "workflow_outputs": [
@@ -1516,6 +1516,5 @@
         "COVID-19",
         "covid19.galaxyproject.org"
     ],
-    "uuid": "06dc40a7-99f2-4b3c-ae21-b3dcb239306f",
-    "version": 0
+    "uuid": "06dc40a7-99f2-4b3c-ae21-b3dcb239306f"
 }
diff --git a/ro-crate-metadata.json b/ro-crate-metadata.json
@@ -21,7 +21,7 @@
         {
             "@id": "./",
             "@type": "Dataset",
-            "datePublished": "2021-12-20T17:04:47.625180",
+            "datePublished": "2022-02-04T11:28:57.510371",
             "hasPart": [
                 {
                     "@id": "consensus-from-variation.ga"
@@ -72,7 +72,7 @@
                 "@id": "#galaxy"
             },
             "url": "https://github.com/iwc-workflows/sars-cov-2-consensus-from-variation",
-            "version": "0.2.2"
+            "version": "0.3"
         },
         {
             "@id": "#galaxy",