JQ-319 (cgates): Adjusted desc of JQ_SUMMARY_DP_AVERAGE; removed obso…

…lete badge from README; updated supported VC version

CHANGELOG.rst

@@ -4,6 +4,8 @@ Changelog
 1.1.0 (6/18/2018)
 -----------------
 - Adjusted *translate* to correctly parse newer versions of Mutect
+- Updated supported versions for Mutect, Strelka, Varscan
+- Fixed error in JQ_SUMMARY_DP_AVERAGE tag description 
 
 1.0.0 (6/5/2018)
 -----------------

README.rst

@@ -1,7 +1,7 @@
 ========
 Jacquard
 ========
-Suite of command-line tools to expedite analysis of exome variant data from 
+Suite of command-line tools to expedite analysis of exome variant data from
 multiple patients and multiple variant callers.
 
 .. image:: https://travis-ci.org/umich-brcf-bioinf/Jacquard.svg?branch=develop
@@ -20,9 +20,6 @@ multiple patients and multiple variant callers.
    :target: https://pypi.python.org/pypi/jacquard/
    :alt: Latest PyPI version
 
-.. image:: https://img.shields.io/pypi/dm/Jacquard.svg
-   :target: https://pypi.python.org/pypi/jacquard/
-    :alt: Downloads Counter
 
 The official repository is at:
 
@@ -61,4 +58,3 @@ See `ReadTheDocs <http://jacquard.readthedocs.org/>`_ for full documentation.
 Email bfx-jacquard@umich.edu for support and questions.
 
 UM BRCF Bioinformatics Core
-

jacquard/utils/summarize_rollup_transform.py

@@ -297,7 +297,7 @@ def __init__(self):
                              SUMMARY_ALLELE_FREQ_AVG,
                              ('Average allele frequency across recognized '
                               'variant callers that reported frequency for '
-                              'this position [average(JQ_*_AF)].'))
+                              'this sample-locus [average(JQ_*_AF)].'))
 
     def add_tag_values(self, record):
         new_sample_tag_values = {}
@@ -364,9 +364,9 @@ def __init__(self):
         super(self.__class__,
               self).__init__(SUMMARY_TAG,
                              SUMMARY_DEPTH_AVG,
-                             ('Average allele frequency across recognized '
-                              'variant callers that reported frequency for '
-                              'this position; rounded to integer '
+                             ('Average depth across recognized '
+                              'variant callers that reported depth for '
+                              'this sample-locus; rounded to integer '
                               '[round(average(JQ_*_DP))].'))
 
     def add_tag_values(self, record):
@@ -402,7 +402,7 @@ def __init__(self):
                              SUMMARY_SOMATIC_COUNT,
                              ('Count of recognized variant callers that '
                               'reported confident somatic call for this '
-                              'sample-position.'))
+                              'sample-locus.'))
 
     def add_tag_values(self, record):
         new_sample_tag_values = {}

jacquard/variant_caller_transforms/mutect.py

@@ -14,7 +14,7 @@
 
 JQ_MUTECT_TAG = "JQ_MT_"
 MUTECT_ABBREVIATION = "MT"
-VERSION = "v1.1.4"
+VERSION = "v1.1-4.0"
 
 class _GenotypeTag(common_tags.AbstractJacquardTag):
     #pylint: disable=too-few-public-methods

jacquard/variant_caller_transforms/strelka.py

@@ -23,7 +23,7 @@
 
 JQ_STRELKA_TAG = "JQ_SK_"
 STRELKA_ABBREVIATION = "SK"
-VERSION = "v1.0.14"
+VERSION = "v1.0-2.9"
 
 class _GenotypeTag(common_tags.AbstractJacquardTag):
     #pylint: disable=too-few-public-methods
@@ -379,4 +379,3 @@ def _add_tags(self, vcf_record):
         for tag in self.tags:
             tag.add_tag_values(vcf_record)
         return vcf_record
-

jacquard/variant_caller_transforms/varscan.py

@@ -33,7 +33,7 @@
                            "NORMAL|TUMOR").replace("|", "\t")
 JQ_VARSCAN_TAG = "JQ_VS_"
 VARSCAN_ABBREVIATION = "VS"
-VERSION = "v2.3"
+VERSION = "v2.3-2.4"
 
 def _varscan_hc_fileheader(line):
     return line.startswith("chrom\tposition")

test/functional_tests/03_summarize/benchmark/summarized.vcf

@@ -12,18 +12,18 @@
 ##FORMAT=<ID=JQ_SK_AF,Number=A,Type=Float,Description="Jacquard allele frequency for Strelka: Decimal allele frequency rounded to 4 digits (based on alt_depth/total_depth. Uses TAR if available, otherwise uses uses DP2 if available, otherwise uses ACGT tier2 depth)">
 ##FORMAT=<ID=JQ_SK_DP,Number=1,Type=Integer,Description="Jacquard depth for Strelka (uses DP2 if available, otherwise uses ACGT tier2 depth)">
 ##FORMAT=<ID=JQ_SK_HC_SOM,Number=1,Type=Integer,Description="Jacquard somatic status for Strelka: 0=non-somatic,1=somatic (based on PASS in FILTER column)">
-##FORMAT=<ID=JQ_SUMMARY_AF_AVERAGE,Number=1,Type=Float,Description="Average allele frequency across recognized variant callers that reported frequency for this position [average(JQ_*_AF)].">
+##FORMAT=<ID=JQ_SUMMARY_AF_AVERAGE,Number=1,Type=Float,Description="Average allele frequency across recognized variant callers that reported frequency for this sample-locus [average(JQ_*_AF)].">
 ##FORMAT=<ID=JQ_SUMMARY_AF_RANGE,Number=1,Type=Float,Description="Max(allele frequency) - min (allele frequency) across recognized callers.">
 ##FORMAT=<ID=JQ_SUMMARY_AF_ZSCORE,Number=1,Type=Float,Description="Concordance of reported allele frequencies across callers: [(this AF range - mean AF range)/standard dev(all AF ranges)]. Values with null or missing AF range will be assigned zscore of '.'; for multi-valued ranges, zscore is of largest range.">
 ##FORMAT=<ID=JQ_SUMMARY_CALLERS_PASSED_COUNT,Number=1,Type=Integer,Description="Count of variant callers where FILTER = PASS for this variant in the Jacquard tagged VCF">
 ##FORMAT=<ID=JQ_SUMMARY_CALLERS_PASSED_LIST,Number=.,Type=String,Description="Comma-separated list of variant caller short-names where FILTER = PASS for this variant in the Jacquard tagged VCF">
 ##FORMAT=<ID=JQ_SUMMARY_CALLERS_REPORTED_COUNT,Number=1,Type=Integer,Description="Count of variant callers which listed this variant in the Jacquard tagged VCF">
 ##FORMAT=<ID=JQ_SUMMARY_CALLERS_REPORTED_LIST,Number=.,Type=String,Description="Comma-separated list variant callers which listed this variant in the Jacquard tagged VCF">
-##FORMAT=<ID=JQ_SUMMARY_DP_AVERAGE,Number=1,Type=Float,Description="Average allele frequency across recognized variant callers that reported frequency for this position; rounded to integer [round(average(JQ_*_DP))].">
+##FORMAT=<ID=JQ_SUMMARY_DP_AVERAGE,Number=1,Type=Float,Description="Average depth across recognized variant callers that reported depth for this sample-locus; rounded to integer [round(average(JQ_*_DP))].">
 ##FORMAT=<ID=JQ_SUMMARY_DP_RANGE,Number=1,Type=Float,Description="Max(depth) - min (depth) across recognized callers.">
 ##FORMAT=<ID=JQ_SUMMARY_DP_ZSCORE,Number=1,Type=Float,Description="Concordance of reported depth across callers: [(this DP range - mean DP range)/standard dev(all DP ranges)]. Values with null or missing DP range will be assigned zscore of '.'.">
 ##FORMAT=<ID=JQ_SUMMARY_HC_GT,Number=1,Type=String,Description="High confidence consensus genotype (inferred from JQ_*_GT and JQ_*_CALLER_PASSED). Majority rules; ties go to the least unusual variant (0/1>0/2>1/1). Variants which failed their filter are ignored.">
-##FORMAT=<ID=JQ_SUMMARY_SOM_COUNT,Number=1,Type=Integer,Description="Count of recognized variant callers that reported confident somatic call for this sample-position.">
+##FORMAT=<ID=JQ_SUMMARY_SOM_COUNT,Number=1,Type=Integer,Description="Count of recognized variant callers that reported confident somatic call for this sample-locus.">
 #CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	tiny_strelka|NORMAL	tiny_strelka|TUMOR
 chr1	1147545	.	A	G	.	.	JQ_SUMMARY_SAMPLES_REPORTED_COUNT=2;JQ_SUMMARY_SAMPLES_PASSED_COUNT=0	JQ_SK_AF:JQ_SK_DP:JQ_SK_HC_SOM:JQ_SK_CALLER_REPORTED:JQ_SK_CALLER_PASSED:JQ_SUMMARY_CALLERS_REPORTED_COUNT:JQ_SUMMARY_CALLERS_PASSED_COUNT:JQ_SUMMARY_CALLERS_REPORTED_LIST:JQ_SUMMARY_CALLERS_PASSED_LIST:JQ_SUMMARY_AF_AVERAGE:JQ_SUMMARY_AF_RANGE:JQ_SUMMARY_DP_AVERAGE:JQ_SUMMARY_DP_RANGE:JQ_SUMMARY_SOM_COUNT:JQ_SUMMARY_HC_GT	0.0:27:1:1:0:1:0:SK:.:0.0:.:27:.:1:.	0.31:35:1:1:0:1:0:SK:.:0.31:.:35:.:1:.
 chr1	1169795	.	C	T		.	JQ_SUMMARY_SAMPLES_REPORTED_COUNT=2;JQ_SUMMARY_SAMPLES_PASSED_COUNT=2	JQ_SK_AF:JQ_SK_DP:JQ_SK_HC_SOM:JQ_SK_CALLER_REPORTED:JQ_SK_CALLER_PASSED:JQ_SUMMARY_CALLERS_REPORTED_COUNT:JQ_SUMMARY_CALLERS_PASSED_COUNT:JQ_SUMMARY_CALLERS_REPORTED_LIST:JQ_SUMMARY_CALLERS_PASSED_LIST:JQ_SUMMARY_AF_AVERAGE:JQ_SUMMARY_AF_RANGE:JQ_SUMMARY_DP_AVERAGE:JQ_SUMMARY_DP_RANGE:JQ_SUMMARY_SOM_COUNT:JQ_SUMMARY_HC_GT	0.0:37:0:1:1:1:1:SK:SK:0.0:.:37:.:0:.	0.22:46:1:1:1:1:1:SK:SK:0.22:.:46:.:1:.

test/functional_tests/jacquard_test/03_summarize/benchmark/summarized.vcf

@@ -23,18 +23,18 @@
 ##FORMAT=<ID=JQ_SK_DP,Number=1,Type=Integer,Description="Jacquard depth for Strelka (uses DP2 if available, otherwise uses ACGT tier2 depth)">
 ##FORMAT=<ID=JQ_SK_GT,Number=1,Type=String,Description="Jacquard genotype (based on SGT). Example for snv: REF=A, ALT=C, INFO:SGT=AA->AC is translated as normal=0/0, tumor=0/1. Example for indel: INFO:SGT=ref->het is translated as normal=0/0, tumor=0/1.">
 ##FORMAT=<ID=JQ_SK_HC_SOM,Number=1,Type=Integer,Description="Jacquard somatic status for Strelka: 0=non-somatic,1=somatic (based on PASS in FILTER column)">
-##FORMAT=<ID=JQ_SUMMARY_AF_AVERAGE,Number=1,Type=Float,Description="Average allele frequency across recognized variant callers that reported frequency for this position [average(JQ_*_AF)].">
+##FORMAT=<ID=JQ_SUMMARY_AF_AVERAGE,Number=1,Type=Float,Description="Average allele frequency across recognized variant callers that reported frequency for this sample-locus [average(JQ_*_AF)].">
 ##FORMAT=<ID=JQ_SUMMARY_AF_RANGE,Number=1,Type=Float,Description="Max(allele frequency) - min (allele frequency) across recognized callers.">
 ##FORMAT=<ID=JQ_SUMMARY_AF_ZSCORE,Number=1,Type=Float,Description="Concordance of reported allele frequencies across callers: [(this AF range - mean AF range)/standard dev(all AF ranges)]. Values with null or missing AF range will be assigned zscore of '.'; for multi-valued ranges, zscore is of largest range.">
 ##FORMAT=<ID=JQ_SUMMARY_CALLERS_PASSED_COUNT,Number=1,Type=Integer,Description="Count of variant callers where FILTER = PASS for this variant in the Jacquard tagged VCF">
 ##FORMAT=<ID=JQ_SUMMARY_CALLERS_PASSED_LIST,Number=.,Type=String,Description="Comma-separated list of variant caller short-names where FILTER = PASS for this variant in the Jacquard tagged VCF">
 ##FORMAT=<ID=JQ_SUMMARY_CALLERS_REPORTED_COUNT,Number=1,Type=Integer,Description="Count of variant callers which listed this variant in the Jacquard tagged VCF">
 ##FORMAT=<ID=JQ_SUMMARY_CALLERS_REPORTED_LIST,Number=.,Type=String,Description="Comma-separated list variant callers which listed this variant in the Jacquard tagged VCF">
-##FORMAT=<ID=JQ_SUMMARY_DP_AVERAGE,Number=1,Type=Float,Description="Average allele frequency across recognized variant callers that reported frequency for this position; rounded to integer [round(average(JQ_*_DP))].">
+##FORMAT=<ID=JQ_SUMMARY_DP_AVERAGE,Number=1,Type=Float,Description="Average depth across recognized variant callers that reported depth for this sample-locus; rounded to integer [round(average(JQ_*_DP))].">
 ##FORMAT=<ID=JQ_SUMMARY_DP_RANGE,Number=1,Type=Float,Description="Max(depth) - min (depth) across recognized callers.">
 ##FORMAT=<ID=JQ_SUMMARY_DP_ZSCORE,Number=1,Type=Float,Description="Concordance of reported depth across callers: [(this DP range - mean DP range)/standard dev(all DP ranges)]. Values with null or missing DP range will be assigned zscore of '.'.">
 ##FORMAT=<ID=JQ_SUMMARY_HC_GT,Number=1,Type=String,Description="High confidence consensus genotype (inferred from JQ_*_GT and JQ_*_CALLER_PASSED). Majority rules; ties go to the least unusual variant (0/1>0/2>1/1). Variants which failed their filter are ignored.">
-##FORMAT=<ID=JQ_SUMMARY_SOM_COUNT,Number=1,Type=Integer,Description="Count of recognized variant callers that reported confident somatic call for this sample-position.">
+##FORMAT=<ID=JQ_SUMMARY_SOM_COUNT,Number=1,Type=Integer,Description="Count of recognized variant callers that reported confident somatic call for this sample-locus.">
 ##FORMAT=<ID=JQ_VS_AF,Number=A,Type=Float,Description="Jacquard allele frequency for VarScan: Decimal allele frequency rounded to 4 digits (based on FREQ)">
 ##FORMAT=<ID=JQ_VS_CALLER_PASSED,Number=1,Type=Integer,Description="1 = variant FILTER is PASS in original VCF">
 ##FORMAT=<ID=JQ_VS_CALLER_REPORTED,Number=1,Type=Integer,Description="1 = variant present in original VCF">

test/summarize_test.py

@@ -12,7 +12,6 @@
 import test.utils.test_case as test_case
 from test.utils.vcf_test import MockFileWriter, MockVcfReader
 
-
 #TODO (cgates): The module summarize is not adequately unit-tested
 class MockSummarizeCaller(object):
     def __init__(self, metaheaders_list=None):
@@ -85,4 +84,3 @@ def test_summarize(self):
                                          "summarized.vcf")
 
             self.assertCommand(command, expected_file)
-

test/utils/summarize_rollup_transform_test.py

@@ -326,7 +326,7 @@ class AlleleFreqAverageTagTestCase(test_case.JacquardBaseTestCase):
 
     def test_metaheader(self):
         split_meta_header = summarize_caller._AlleleFreqAverageTag().metaheader.split("\n")
-        self.assertEqual('##FORMAT=<ID={0}AF_AVERAGE,Number=1,Type=Float,Description="Average allele frequency across recognized variant callers that reported frequency for this position [average(JQ_*_AF)].">'.format(summarize_caller.JQ_SUMMARY_TAG),
+        self.assertEqual('##FORMAT=<ID={0}AF_AVERAGE,Number=1,Type=Float,Description="Average allele frequency across recognized variant callers that reported frequency for this sample-locus [average(JQ_*_AF)].">'.format(summarize_caller.JQ_SUMMARY_TAG),
                          split_meta_header[0])
 
     def test_add_tag_values(self):
@@ -501,7 +501,7 @@ class DepthAverageTagTestCase(test_case.JacquardBaseTestCase):
 
     def test_metaheader(self):
         split_meta_header = summarize_caller._DepthAverageTag().metaheader.split("\n")
-        self.assertEquals('##FORMAT=<ID={}DP_AVERAGE,Number=1,Type=Float,Description="Average allele frequency across recognized variant callers that reported frequency for this position; rounded to integer [round(average(JQ_*_DP))].">'.format(summarize_caller.JQ_SUMMARY_TAG),
+        self.assertEquals('##FORMAT=<ID={}DP_AVERAGE,Number=1,Type=Float,Description="Average depth across recognized variant callers that reported depth for this sample-locus; rounded to integer [round(average(JQ_*_DP))].">'.format(summarize_caller.JQ_SUMMARY_TAG),
                           split_meta_header[0])
 
     def test_add_tag_values(self):
@@ -595,7 +595,7 @@ def test_metaheader(self):
         self.assertEqual('##FORMAT=<ID={0}SOM_COUNT,Number=1,Type=Integer,' \
                       'Description="Count of recognized variant callers ' \
                       'that reported confident somatic call for this '\
-                      'sample-position.">'\
+                      'sample-locus.">'\
                       .format(summarize_caller.JQ_SUMMARY_TAG), split_meta_header[0])
 
     def test_add_tag_values(self):
@@ -786,4 +786,3 @@ def test_get_new_metaheaders(self):
         self.assertEqual(expected, first_meta_header)
         self.assertEqual(12, len(actual))
         self.assertEqual(1, len(split_actual))
-