Mercurial > repos > iuc > chira_merge

changeset 8:c836a05bd6a3 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/chira commit d8a9a5bb648d24f3917951cd7862f449e4dd0688"
author iuc
date Fri, 29 May 2020 06:58:21 -0400
parents 35f433d0bd7f
children 948f4bc1f030
files chira_merge.xml macros.xml test-data/chimeras test-data/interactions test-data/loci.counts test-data/singletons
diffstat 6 files changed, 29 insertions(+), 20 deletions(-) [+]
line wrap: on
line diff
--- a/chira_merge.xml	Thu May 07 03:35:27 2020 -0400
+++ b/chira_merge.xml	Fri May 29 06:58:21 2020 -0400
@@ -11,6 +11,7 @@
             -g '$annotation.gtf'
         #end if
         -so '$segment_overlap'
+        -lt '$length_threshold'
         #if str($merge.mode) == "blockbuster":
             -bb
             -d '$merge.distance'
@@ -19,6 +20,7 @@
             -sc '$merge.scale'
         #else:
             -ao '$merge.alignment_overlap'
+            -ls '$merge.min_locus_size'
         #end if
         #if str($reference.ref_type) == "split":
             -f1 '$reference.ref_fasta1'
@@ -44,6 +46,8 @@
         </conditional>
         <param name="segment_overlap" type="float" value="0.7" label="Overlap fraction for merging mapped read positions to segments" min="0" max="1"
             help="Matching read positions with greater than this fraction overlap are merged into a segment"/>
+        <param name="length_threshold" type="float" value="0.9" label="Minimum length of the alignments as a fraction of longest" min="0" max="1"
+            help="Consider the alignments of a that read have at least longer than this value times the longest alignment for that read"/>
         <conditional name="merge">
             <param name="mode" type="select" label="Select the mode of merging">
                 <option value="overlap">Overlap based</option>
@@ -52,15 +56,17 @@
             <when value="overlap">
                 <param name="alignment_overlap" type="float" value="0.7" label="Overlap fraction for merging alignments" min="0" max="1"
                     help="Minimum fraction of BED entries that must overlap inorder to merge"/>
+                <param name="min_locus_size" type="integer" value="1" label="Minimum locus size"
+                            help="Minimum number of alignments to be present to output the merged a locus"/>
             </when>
             <when value="blockbuster">
                 <param name="distance" type="integer" value="30" label="Blockbuster parameter distance"
                     help="Minimum distance between two clusters"/>
-                <param name="min_cluster_height" type="float" value="10" label="Blockbuster parameter minClusterHeight"
+                <param name="min_cluster_height" type="integer" value="10" label="Blockbuster parameter minClusterHeight"
                     help="minimum height (readno) of a cluster"/>
-                <param name="min_block_height" type="float" value="1" label="Blockbuster parameter minBlockHeight"
+                <param name="min_block_height" type="integer" value="10" label="Blockbuster parameter minBlockHeight"
                     help="minimum height (readno) of a block"/>
-                <param name="scale" type="float" value="0.4" label="Blockbuster parameter scale" min="0" max="1"
+                <param name="scale" type="float" value="0.1" label="Blockbuster parameter scale" min="0" max="1"
                     help="scale stddev for a single read"/>
             </when>
         </conditional>
@@ -96,7 +102,7 @@
             <param name="ref_fasta2" value="ref2.fasta"/>
             <output name="segments_bed" >
                 <assert_contents>
-                    <has_text_matching expression="ENSMUST00000146006\t6703\t6718\t10\|2\|3,ENSMUST00000146006,6703,6718,\+,24S15M16S\t1\t\+" />
+                    <has_text_matching expression="ENSMUST00000037472\t672\t687\t2\|1\|4,ENSMUST00000037472,672,687,\+,14S15M25S\t1\t\+" />
                 </assert_contents>
             </output>
             <output name="merged_bed" >
@@ -133,6 +139,7 @@
             <param name="choice" value="yes" />
             <param name="gtf" value="annotation.gtf" />
             <param name="mode" value="blockbuster" />
+            <param name="min_block_height" value="1" />
             <param name="min_cluster_height" value="5" />
             <param name="ref_type" value="split"/>
             <param name="ref_fasta1" value="ref1.fasta"/>
--- a/macros.xml	Thu May 07 03:35:27 2020 -0400
+++ b/macros.xml	Fri May 29 06:58:21 2020 -0400
@@ -1,6 +1,6 @@
 <macros>
     <token name="@WRAPPER_VERSION@">@TOOL_VERSION@+galaxy</token>
-    <token name="@TOOL_VERSION@">1.2.0</token>
+    <token name="@TOOL_VERSION@">1.3.1</token>
     <xml name="requirements">
         <requirements>
             <requirement type="package" version="@TOOL_VERSION@">chira</requirement>
--- a/test-data/chimeras	Thu May 07 03:35:27 2020 -0400
+++ b/test-data/chimeras	Fri May 29 06:58:21 2020 -0400
@@ -1,3 +1,3 @@
 tagid	txid1	txid2	geneid1	geneid2	symbol1	symbol2	region1	region2	tx_pos_start1	tx_pos_end1	tx_pos_strand1	length1	tx_pos_start2	tx_pos_end2	tx_pos_strand2	length2	read_info	genomic_pos1	genomic_pos2	locus1	locus2	groupid1	groupid2	tpm1	tpm2	score1	score2	score	sequences	hybrid	hybrid_pos	mfe
-4|1	mmu-miR-6979-3p	ENSMUST00000136025	NA	NA	NA	NA	NA	NA	2	12	+	21	32	46	+	188	30,39,2,15,54	mmu-miR-6979-3p:2:12:+	ENSMUST00000136025:32:46:+	mmu-miR-6979-3p:2:12:+	ENSMUST00000136025:32:46:+	7	1	165100.0	121100.0	1.0	1.0	2.0	GUGUCUGUCU&CAGGACUCUUGGCU	NA	NA	NA
-3|2	mmu-miR-20a-5p	ENSMUST00000136025	NA	NA	NA	NA	NA	NA	0	23	+	23	132	142	+	188	6,28,35,44,55	mmu-miR-20a-5p:0:23:+	ENSMUST00000136025:132:142:+	mmu-miR-20a-5p:0:23:+	ENSMUST00000136025:132:142:+	5	2	75660.0	165100.0	1.0	1.0	2.0	UAAAGUGCUUAUAGUGCAGGUAG&CUGCCUGCCU	((.((((((((&))))))))))	13&1	-10.88
+3|2	mmu-miR-20a-5p	ENSMUST00000136025	NA	NA	NA	NA	NA	NA	0	23	+	23	132	142	+	188	6,28,35,44,55	mmu-miR-20a-5p:0:23:+	ENSMUST00000136025:132:142:+	mmu-miR-20a-5p:0:23:+	ENSMUST00000136025:132:142:+	5	2	75660.00	165100.00	1.0	1.0	2.0	UAAAGUGCUUAUAGUGCAGGUAG&CUGCCUGCCU	((((((((((&)).))))))))	1&13	-13.7
+4|1	mmu-miR-6979-3p	ENSMUST00000136025	NA	NA	NA	NA	NA	NA	2	12	+	21	32	46	+	188	30,39,2,15,54	mmu-miR-6979-3p:2:12:+	ENSMUST00000136025:32:46:+	mmu-miR-6979-3p:2:12:+	ENSMUST00000136025:32:46:+	7	1	165100.00	121100.00	1.0	1.0	2.0	GUGUCUGUCU&CAGGACUCUUGGCU	((((.....((&))....))))	3&1	-4
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/interactions	Fri May 29 06:58:21 2020 -0400
@@ -0,0 +1,2 @@
+mmu-miR-20a-5p:0:23:+	ENSMUST00000136025:132:142:+	1	UAAAGUGCUUAUAGUGCAGGUAG	CUGCCUGCCU	((((((((((&)).))))))))	1&13	-13.7	75660.00	165100.00	240760.0	1.0	1.0	2.0	NA	NA	mmu-miR-20a-5p	ENSMUST00000136025
+mmu-miR-6979-3p:2:12:+	ENSMUST00000136025:32:46:+	1	GUGUCUGUCU	CAGGACUCUUGGCU	((((.....((&))....))))	3&1	-4	165100.00	121100.00	286200.0	1.0	1.0	2.0	NA	NA	mmu-miR-6979-3p	ENSMUST00000136025
--- a/test-data/loci.counts	Thu May 07 03:35:27 2020 -0400
+++ b/test-data/loci.counts	Fri May 29 06:58:21 2020 -0400
@@ -1,9 +1,9 @@
-6|1|1	ENSMUST00000182010	4	0	19	68	+	5S49M1S	ENSMUST00000182010:19:68:+	ENSMUST00000182010:19:74:+	1	1	6.485e+04
-7|9|1	ENSMUST00000182010	4	0	24	74	+	5S50M	ENSMUST00000182010:24:74:+	ENSMUST00000182010:19:74:+	1	1	6.485e+04
-4|1|2	ENSMUST00000136025	0	1	32	46	+	1S14M39S	ENSMUST00000136025:32:46:+	ENSMUST00000136025:32:46:+	1	1	1.211e+05
-3|2|2	ENSMUST00000136025	1	2	132	142	+	34S10M11S	ENSMUST00000136025:132:142:+	ENSMUST00000136025:132:142:+	1	1	1.651e+05
-2|2|2	ENSMUST00000137264	2	3	12	27	+	4S15M30S	ENSMUST00000137264:12:27:+	ENSMUST00000137264:12:27:+	1	1	1.135e+05
-6|1|4	ENSMUST00000160533	3	4	69	82	+	42S13M	ENSMUST00000160533:69:82:+	ENSMUST00000160533:69:82:+	1	1	1.297e+05
-3|2|1	mmu-miR-20a-5p	5	5	0	23	+	5S23M27S	mmu-miR-20a-5p:0:23:+	mmu-miR-20a-5p:0:23:+	1	1	7.566e+04
-2|2|1	mmu-miR-6898-5p	6	6	11	21	+	10M39S	mmu-miR-6898-5p:11:21:+	mmu-miR-6898-5p:11:21:+	1	1	1.651e+05
-4|1|1	mmu-miR-6979-3p	7	7	2	12	+	29S10M15S	mmu-miR-6979-3p:2:12:+	mmu-miR-6979-3p:2:12:+	1	1	1.651e+05
+2|2|1	mmu-miR-6898-5p	6	6	11	21	+	10M39S	mmu-miR-6898-5p:11:21:+	mmu-miR-6898-5p:11:21:+	1.00	1.00	1.651e+05
+2|2|2	ENSMUST00000137264	2	3	12	27	+	4S15M30S	ENSMUST00000137264:12:27:+	ENSMUST00000137264:12:27:+	1.00	1.00	1.135e+05
+3|2|1	mmu-miR-20a-5p	5	5	0	23	+	5S23M27S	mmu-miR-20a-5p:0:23:+	mmu-miR-20a-5p:0:23:+	1.00	1.00	7.566e+04
+3|2|2	ENSMUST00000136025	1	2	132	142	+	34S10M11S	ENSMUST00000136025:132:142:+	ENSMUST00000136025:132:142:+	1.00	1.00	1.651e+05
+4|1|1	mmu-miR-6979-3p	7	7	2	12	+	29S10M15S	mmu-miR-6979-3p:2:12:+	mmu-miR-6979-3p:2:12:+	1.00	1.00	1.651e+05
+4|1|2	ENSMUST00000136025	0	1	32	46	+	1S14M39S	ENSMUST00000136025:32:46:+	ENSMUST00000136025:32:46:+	1.00	1.00	1.211e+05
+6|1|1	ENSMUST00000182010	4	0	19	68	+	5S49M1S	ENSMUST00000182010:19:68:+	ENSMUST00000182010:19:74:+	1.00	1.00	6.485e+04
+6|1|4	ENSMUST00000160533	3	4	69	82	+	42S13M	ENSMUST00000160533:69:82:+	ENSMUST00000160533:69:82:+	1.00	1.00	1.297e+05
+7|9|1	ENSMUST00000182010	4	0	24	74	+	5S50M	ENSMUST00000182010:24:74:+	ENSMUST00000182010:19:74:+	1.00	1.00	6.485e+04
--- a/test-data/singletons	Thu May 07 03:35:27 2020 -0400
+++ b/test-data/singletons	Fri May 29 06:58:21 2020 -0400
@@ -1,4 +1,4 @@
-tagid	txid	geneid	symbol	region	tx_pos_start	tx_pos_end	tx_pos_strand	length	read_info	genomic_pos	locus	groupid	tpm	score	score	sequences
-6|1	ENSMUST00000182010	NA	NA	NA	19	68	+	NA	6,54,55	ENSMUST00000182010:19:68:+	ENSMUST00000182010:19:74:+	0	64850.0	1.0	1.0	UCAUUAAUCAAGAACGAAAGUCGGAGUUUCGAAGACGAUCAGAUACCGUUGUAGU
-7|9	ENSMUST00000182010	NA	NA	NA	24	74	+	NA	6,55,55	ENSMUST00000182010:24:74:+	ENSMUST00000182010:19:74:+	0	64850.0	1.0	1.0	UCAUUAAUCAAGAACGAAAGUCGGAGUUUCGAAGACGAUCAGAUACCGUUGUAGU
-2|2	ENSMUST00000137264	NA	NA	NA	12	27	+	NA	5,19,49	ENSMUST00000137264:12:27:+	ENSMUST00000137264:12:27:+	3	113500.0	1.0	1.0	AGGGAGGACGAUGCG
+tagid	txid	geneid	symbol	region	tx_pos_start	tx_pos_end	tx_pos_strand	length	read_info	genomic_pos	locus	groupid	tpm	score
+2|2	mmu-miR-6898-5p	NA	NA	NA	11	21	+	NA	1,10,49	mmu-miR-6898-5p:11:21:+	mmu-miR-6898-5p:11:21:+	6	165100.00	1.00
+6|1	ENSMUST00000160533	NA	NA	NA	69	82	+	NA	43,55,55	ENSMUST00000160533:69:82:+	ENSMUST00000160533:69:82:+	4	129700.00	1.00
+7|9	ENSMUST00000182010	NA	NA	NA	24	74	+	NA	6,55,55	ENSMUST00000182010:24:74:+	ENSMUST00000182010:19:74:+	0	64850.00	1.00