# HG changeset patch
# User artbio
# Date 1720477390 0
# Node ID 48e97429a7495ccc38c28f0e8fdd734875536f1f
# Parent  6ae3a402b9af74add39ad33f9ed5dfe588c829fc
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/lumpy_sv commit 37c0f0938a5cad74c954a89827a6a08bbbb81cb0

diff -r 6ae3a402b9af -r 48e97429a749 extractSplitReads_BwaMem.py
--- a/extractSplitReads_BwaMem.py	Sun May 24 18:48:46 2020 -0400
+++ b/extractSplitReads_BwaMem.py	Mon Jul 08 22:23:10 2024 +0000
@@ -21,7 +21,7 @@
             continue
         for el in sam.tags:
             if "SA:" in el:
-                if(len(el.split(";"))) <= numSplits:
+                if (len(el.split(";"))) <= numSplits:
                     split = 1
                     mate = el.split(",")
                     mateCigar = mate[3]
@@ -103,7 +103,6 @@
         cigarOps = []
         for opString in cigarOpStrings:
             cigarOpList = atomicCigarSearch.findall(opString)
-#            print cigarOpList
             # "struct" for the op and it's length
             cigar = cigarOp(cigarOpList[0][0], cigarOpList[0][1])
             # add to the list of cigarOps
@@ -120,8 +119,7 @@
             cigar = cigarOp(cigarOpList[0][0], cigarOpList[0][1])
             # add to the list of cigarOps
             cigarOps.append(cigar)
-#            cigarOps = cigarOps
-    return(cigarOps)
+    return cigarOps
 
 
 def calcQueryPosFromCigar(cigarOps):
@@ -202,7 +200,8 @@
                       help='''Include alignments marked as duplicates.
                       Default=False''')
     parser.add_option("-m", "--minNonOverlap", dest="minNonOverlap",
-                      default=20, type="int", help='''minimum non-overlap between
+                      default=20, type="int",
+                      help='''minimum non-overlap between
                       split alignments on the query (default=20)''',
                       metavar="INT")
     (opts, args) = parser.parse_args()
diff -r 6ae3a402b9af -r 48e97429a749 lumpy.xml
--- a/lumpy.xml	Sun May 24 18:48:46 2020 -0400
+++ b/lumpy.xml	Mon Jul 08 22:23:10 2024 +0000
@@ -1,9 +1,9 @@
-<tool id="lumpy" name="lumpy-sv" version="1.2.2">
+<tool id="lumpy" name="lumpy-sv" version="1.3">
     <description>find structural variants</description>
     <requirements>
-        <requirement type="package" version="0.2.13">lumpy-sv</requirement>
-        <requirement type="package" version="1.3.1">samtools</requirement>
-        <requirement type="package" version="1.11.2=py27_0">numpy</requirement>
+        <requirement type="package" version="0.3.1">lumpy-sv</requirement>
+        <requirement type="package" version="1.18">samtools</requirement>
+        <requirement type="package" version="1.16.5">numpy</requirement>
     </requirements>
     <stdio>
         <exit_code range="1:" level="fatal" description="Tool exception" />
@@ -33,7 +33,7 @@
                     |python $__tool_directory__/pairend_distro.py -r $analysis_type.readLength -X 4 -N $seq_method.additional_params.samplingValue -o input.lib.histo > meandev.txt &&
                 mean=\$(cat meandev.txt | sed s/mean:// | sed -r s/stdev:.+//) &&
                 stdev=\$(cat meandev.txt | sed -r s/mean:.+stdev://) &&
-                lumpy $seq_method.additional_params.evidence $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
+                lumpy $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
                     #if $output_format == "BEDPE":
                         -b
                     #end if
@@ -41,7 +41,7 @@
                     -sr id:'$one_sample_bam',bam_file:input.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > '$vcf_call'
             #elif $seq_method.seq_method_list == "single-read":
                 samtools view -@ \${GALAXY_SLOTS:-4} -h '$one_sample_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o input.splitters.bam &&
-                lumpy $seq_method.additional_params.evidence $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
+                lumpy $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
                     #if $output_format == "BEDPE":
                         -b
                     #end if
@@ -61,7 +61,7 @@
                 meanB=\$(cat meandevB.txt | sed s/mean:// | sed -r s/stdev:.+//) &&
                 stdevA=\$(cat meandevA.txt | sed -r s/mean:.+stdev://) &&
                 stdevB=\$(cat meandevB.txt | sed -r s/mean:.+stdev://) &&
-                lumpy $seq_method.additional_params.evidence $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
+                lumpy $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
                     #if $output_format == "BEDPE":
                         -b
                     #end if
@@ -72,7 +72,7 @@
             #elif $seq_method.seq_method_list == "single-read":
                 samtools view -@ \${GALAXY_SLOTS:-4} -h '$sample_a_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o input.splitters.bam &&
                 samtools view -@ \${GALAXY_SLOTS:-4} -h '$sample_b_bam' | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o input.B.splitters.bam &&
-                lumpy $seq_method.additional_params.evidence $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
+                lumpy $seq_method.additional_params.probability_curve -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
                     #if $output_format == "BEDPE":
                         -b
                     #end if
@@ -116,7 +116,6 @@
                     <param name="weight" value="1"  type="integer" label="weight" help="e.g. 1" />
                     <param name="min_mapping_threshold" value="20"  type="integer" label="min_mapping_threshold" help="e.g. 20" />
                     <param name="probability_curve" argument="-P" type="boolean" truevalue="-P" falsevalue="" checked="true" label="output probability curve for each variant"/>
-                    <param name="evidence" argument="-e" type="boolean" truevalue="-e" falsevalue="" checked="true" label="show evidence for each call"/>
                 </section>
             </when>
             <when value="single-read">
@@ -127,7 +126,6 @@
                     <param name="weight" value="1"  type="integer" label="weight" help="e.g. 1" />
                     <param name="min_mapping_threshold" value="20"  type="integer" label="min_mapping_threshold" help="e.g. 20" />
                     <param name="probability_curve" argument="-P" type="boolean" truevalue="-P" falsevalue="" checked="false" label="output probability curve for each variant"/>
-                    <param name="evidence" argument="-e" type="boolean" truevalue="-e" falsevalue="" checked="false" label="show evidence for each call"/>
                 </section>
             </when>
 
@@ -139,21 +137,21 @@
     </inputs>
 
     <outputs>
-        <data format="tabular" name="histogram" label="Lumpy on ${on_string}: Fragment size distribution" from_work_dir="input.lib.histo">
+        <data format="tabular" name="histogram" label="Lumpy-sv: Fragment size distribution" from_work_dir="input.lib.histo">
             <filter>seq_method['seq_method_list'] == "paired-end"</filter>
         </data>
-        <data format="tabular" name="histogramB" label="Lumpy on ${on_string}: Fragment size distribution" from_work_dir="input.B.lib.histo">
+        <data format="tabular" name="histogramB" label="Lumpy-sv: FragmentB size distribution" from_work_dir="input.B.lib.histo">
             <filter>seq_method['seq_method_list'] == "paired-end"</filter>
             <filter>analysis_type['analysis_type_list'] == "two_sample"</filter>
         </data>
         <data format="bam" name="splits" label="Lumpy on ${on_string}: Split Reads (Bam format)" from_work_dir="input.splitters.bam"/>
-        <data format="bam" name="splitsB" label="Lumpy on ${on_string}: Split Reads (Bam format)" from_work_dir="input.B.splitters.bam">
+        <data format="bam" name="splitsB" label="Lumpy on ${on_string}: SplitB Reads (Bam format)" from_work_dir="input.B.splitters.bam">
             <filter>analysis_type['analysis_type_list'] == "two_sample"</filter>
         </data>
         <data format="bam" name="discordants" label="Lumpy on ${on_string}: Discordant Pairs (Bam format)" from_work_dir="input.discordants.bam">
             <filter>seq_method['seq_method_list'] == "paired-end"</filter>
         </data>
-        <data format="bam" name="discordantsB" label="Lumpy on ${on_string}: Discordant Pairs (Bam format)" from_work_dir="input.B.discordants.bam">
+        <data format="bam" name="discordantsB" label="Lumpy on ${on_string}: DiscordantB Pairs (Bam format)" from_work_dir="input.B.discordants.bam">
             <filter>seq_method['seq_method_list'] == "paired-end"</filter>
             <filter>analysis_type['analysis_type_list'] == "two_sample"</filter>
         </data>
@@ -165,7 +163,7 @@
     </outputs>
 
     <tests>
-        <test>
+        <test expect_num_outputs="7">
             <param name="analysis_type_list" value="two_sample" />
             <param name="input_file" value="sample_Del.bam" ftype="bam"/>
             <param name="input_fileB" value="sample_cle.bam" ftype="bam"/>
@@ -177,7 +175,7 @@
             <param name="min_mapping_threshold" value="20" />
             <output name="vcf_call" file="output_two.paired_end.vcf" ftype="vcf"/>
         </test>
-        <test>
+        <test expect_num_outputs="2">
             <param name="analysis_type_list" value="one_sample" />
             <param name="input_file" value="sr.input.bam" ftype="bam"/>
             <param name="seq_method_list" value="single-read" />
@@ -188,7 +186,7 @@
             <param name="min_mapping_threshold" value="20" />
             <output name="vcf_call" file="output.vcf" ftype="vcf"/>
         </test>
-        <test>
+        <test expect_num_outputs="2">
             <param name="analysis_type_list" value="one_sample" />
             <param name="input_file" value="sr.input.bam" ftype="bam"/>
             <param name="seq_method_list" value="single-read" />
@@ -197,11 +195,10 @@
             <param name="back_distance" value="10"/>
             <param name="weight" value="1" />
             <param name="min_mapping_threshold" value="20" />
-            <param name="evidence" value="true" />
             <param name="probability_curve" value="true" />
             <output name="vcf_call" file="output_extended.vcf" ftype="vcf" compare="sim_size"/>
         </test>
-        <test>
+        <test expect_num_outputs="3">
             <param name="analysis_type_list" value="two_sample" />
             <param name="input_file" value="sr.input.bam" ftype="bam"/>
             <param name="input_fileB" value="sr.input.bam" ftype="bam"/>
diff -r 6ae3a402b9af -r 48e97429a749 test-data/output_extended.vcf
--- a/test-data/output_extended.vcf	Sun May 24 18:48:46 2020 -0400
+++ b/test-data/output_extended.vcf	Mon Jul 08 22:23:10 2024 +0000
@@ -31,45 +31,7 @@
 ##FORMAT=<ID=SR,Number=1,Type=Integer,Description="Number of split reads supporting the variant">
 ##FORMAT=<ID=BD,Number=1,Type=Integer,Description="Amount of BED evidence supporting the variant">
 #CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	sr_input_bam
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:22421:6659_2	hg38_gold_U07000.1	8	50	hg38_gold_U07000.1	1885	1932	0x17456f0	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:21503:6234_2	hg38_gold_U07000.1	13	52	hg38_gold_U07000.1	1885	1933	0x17451d0	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:14108:4338_2	hg38_gold_U07000.1	8	53	hg38_gold_U07000.1	1879	1932	0x1747410	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:22281:3587_2	hg38_gold_U07000.1	8	52	hg38_gold_U07000.1	1879	1944	0x174d920	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:9129:3504_2	hg38_gold_U07000.1	13	50	hg38_gold_U07000.1	1872	1932	0x1748e60	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:10154:5887_2	hg38_gold_U07000.1	10	41	hg38_gold_U07000.1	1872	1931	0x17499d0	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:9382:5932_2	hg38_gold_U07000.1	8	53	hg38_gold_U07000.1	1871	1921	0x174d580	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:22747:6442_2	hg38_gold_U07000.1	8	52	hg38_gold_U07000.1	1870	1933	0x1748cc0	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:6411:6050_2	hg38_gold_U07000.1	13	49	hg38_gold_U07000.1	1868	1932	0x17486a0	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:23865:5544_2	hg38_gold_U07000.1	13	56	hg38_gold_U07000.1	1868	1923	0x1748480	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:20349:5252_2	hg38_gold_U07000.1	13	51	hg38_gold_U07000.1	1868	1931	0x174ce80	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:22571:4203_2	hg38_gold_U07000.1	13	50	hg38_gold_U07000.1	1868	1926	0x1745050	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:16719:4051_2	hg38_gold_U07000.1	8	51	hg38_gold_U07000.1	1868	1932	0x1747b70	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:8961:3182_2	hg38_gold_U07000.1	15	51	hg38_gold_U07000.1	1868	1917	0x1744130	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:18427:2937_2	hg38_gold_U07000.1	8	41	hg38_gold_U07000.1	1868	1932	0x174b760	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:21139:5913_2	hg38_gold_U07000.1	12	50	hg38_gold_U07000.1	1868	1924	0x174d640	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:10523:5853_2	hg38_gold_U07000.1	8	50	hg38_gold_U07000.1	1868	1935	0x174de60	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:16433:5445_2	hg38_gold_U07000.1	13	51	hg38_gold_U07000.1	1868	1932	0x174d870	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:12490:4165_2	hg38_gold_U07000.1	13	58	hg38_gold_U07000.1	1868	1917	0x174d9f0	0	-	+	id:1	weight:1
 hg38_gold_U07000.1	14	1_1	N	[hg38_gold_U07000.1:1876[N	.	.	SVTYPE=BND;STRANDS=--:19;EVENT=1;MATEID=1_2;CIPOS=0,0;CIEND=0,2;CIPOS95=0,0;CIEND95=0,0;SU=19;SR=19;PRPOS=1;PREND=0.99996,3.98091e-05,1.58483e-09	GT:SU:SR	./.:19:19
 hg38_gold_U07000.1	1876	1_2	N	[hg38_gold_U07000.1:14[N	.	.	SVTYPE=BND;STRANDS=--:19;SECONDARY;EVENT=1;MATEID=1_1;CIPOS=0,2;CIEND=0,0;CIPOS95=0,0;CIEND95=0,0;SU=19;SR=19;PRPOS=0.99996,3.98091e-05,1.58483e-09;PREND=1	GT:SU:SR	./.:19:19
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:7043:5583_2	hg38_gold_U07000.1	13	56	hg38_gold_U07000.1	1899	1935	0x1742010	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:19472:2185_2	hg38_gold_U07000.1	0	56	hg38_gold_U07000.1	1898	1945	0x1744270	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:9324:6462_2	hg38_gold_U07000.1	0	51	hg38_gold_U07000.1	1898	1933	0x1748fd0	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:23764:6273_2	hg38_gold_U07000.1	13	48	hg38_gold_U07000.1	1898	1945	0x17490a0	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:7772:5906_2	hg38_gold_U07000.1	0	54	hg38_gold_U07000.1	1898	1942	0x1747240	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:6971:4906_2	hg38_gold_U07000.1	13	51	hg38_gold_U07000.1	1898	1935	0x1746170	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:10511:4776_2	hg38_gold_U07000.1	8	50	hg38_gold_U07000.1	1898	1934	0x174a840	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:19677:3538_2	hg38_gold_U07000.1	13	51	hg38_gold_U07000.1	1898	1940	0x174c190	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:22109:4922_2	hg38_gold_U07000.1	13	53	hg38_gold_U07000.1	1897	1933	0x1743ac0	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:14027:4470_2	hg38_gold_U07000.1	0	51	hg38_gold_U07000.1	1896	1933	0x174b500	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:22736:5607_2	hg38_gold_U07000.1	13	57	hg38_gold_U07000.1	1893	1945	0x174cf30	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:10768:5508_2	hg38_gold_U07000.1	13	56	hg38_gold_U07000.1	1893	1935	0x17480b0	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:14449:3437_2	hg38_gold_U07000.1	13	48	hg38_gold_U07000.1	1893	1933	0x174b150	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:18009:3360_2	hg38_gold_U07000.1	13	47	hg38_gold_U07000.1	1893	1925	0x1749390	0	+	-	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:16615:6513_2	hg38_gold_U07000.1	13	51	hg38_gold_U07000.1	1893	1931	0x174b860	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:19235:5076_2	hg38_gold_U07000.1	13	45	hg38_gold_U07000.1	1893	1932	0x174a790	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:14629:4828_2	hg38_gold_U07000.1	8	50	hg38_gold_U07000.1	1893	1932	0x174b360	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:22780:4994_2	hg38_gold_U07000.1	13	50	hg38_gold_U07000.1	1892	1924	0x174aaf0	0	-	+	id:1	weight:1
-	Evidence:	M00860:26:000000000-A6UGV:1:1101:12387:3929_2	hg38_gold_U07000.1	13	51	hg38_gold_U07000.1	1892	1931	0x174c000	0	-	+	id:1	weight:1
 hg38_gold_U07000.1	10	2_1	N	[hg38_gold_U07000.1:1897[N	.	.	SVTYPE=BND;STRANDS=--:19;EVENT=2;MATEID=2_2;CIPOS=-1,0;CIEND=-7,5;CIPOS95=0,1;CIEND95=-2,1;IMPRECISE;SU=19;SR=19;PRPOS=9.99999e-13,9.99999e-07;PREND=4.89496e-31,1.94872e-23,7.75799e-16,3.08851e-08,0.0308851,0.0775799,0.194872,0.489496,0.194872,0.0122956,1.94872e-09,4.89496e-17,1.22956e-24	GT:SU:SR	./.:19:19
 hg38_gold_U07000.1	1897	2_2	N	[hg38_gold_U07000.1:10[N	.	.	SVTYPE=BND;STRANDS=--:19;SECONDARY;EVENT=2;MATEID=2_1;CIPOS=-7,5;CIEND=-1,0;CIPOS95=-2,1;CIEND95=0,1;IMPRECISE;SU=19;SR=19;PRPOS=4.89496e-31,1.94872e-23,7.75799e-16,3.08851e-08,0.0308851,0.0775799,0.194872,0.489496,0.194872,0.0122956,1.94872e-09,4.89496e-17,1.22956e-24;PREND=9.99999e-13,9.99999e-07	GT:SU:SR	./.:19:19