Mercurial > repos > artbio > mircounts

changeset 5:9ea96a02c416 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit 04980585c257ab5f8eb5d10de007316c47c5d1ce
author artbio
date Tue, 05 Sep 2017 06:33:16 -0400
parents da1aa7de2b19
children 543472c9e272
files mature_mir_gff_translation.py mircounts.xml test-data/translated_dme.gff3
diffstat 3 files changed, 33 insertions(+), 70 deletions(-) [+]
line wrap: on
line diff
--- a/mature_mir_gff_translation.py	Mon Sep 04 17:55:01 2017 -0400
+++ b/mature_mir_gff_translation.py	Tue Sep 05 06:33:16 2017 -0400
@@ -1,6 +1,6 @@
-#!/usr/bin/env python
+import argparse
 
-import argparse
+from datetime import datetime
 
 
 def Parser():
@@ -14,19 +14,14 @@
     return args
 
 
-GFF3_header = '''##gff-version 3
-##generated by mature_mir_gff_translation.py
-#
-# Chromosomal coordinates of microRNAs ** relative to the hairpin precursors **
-# microRNAs:               miRBase current_version
-# genome-build-id:         check http://mirbase.org/
-#
-# Hairpin precursor sequences have type "miRNA_primary_transcript".
-# Note, these sequences do not represent the full primary transcript,
-# rather a predicted stem-loop portion that includes the precursor
-# miRNA. Mature sequences have type "miRNA".
-#
-'''
+def get_gff_header(gff_input_file):
+    string_list = []
+    for line in open(gff_input_file, "r"):
+        if line[0] == '#':
+            string_list.append(line)
+    string_list.append('# generated by mature_mir_gff_translation.py %s\n#\n' %
+                       str(datetime.now()))
+    return ''.join(string_list)
 
 
 def load_gff_in_dict(gff_input_file):
@@ -51,9 +46,9 @@
         gff_dict[ID]["strand"] = gff_fields[6]
         gff_dict[ID]["phase"] = gff_fields[7]
         gff_dict[ID]["attributes"] = gff_fields[8]
-        if "Derives_from" in gff_dict[ID]["attributes"]:
+        if "erives_from" in gff_dict[ID]["attributes"]:
             parent_primary_transcript = gff_dict[ID]["attributes"].split(
-                "Derives_from=")[1]
+                "erives_from=")[1]
             parent_primary_transcript = gff_dict[parent_primary_transcript][
                                             "attributes"].split("Name=")[1]
             gff_dict[ID]["attributes"] = "%s;Parent_mir_Name=%s" % (
@@ -61,7 +56,7 @@
     return gff_dict
 
 
-def genome_to_mir_gff(gff_dict, output):
+def genome_to_mir_gff(gff_dict, output, header):
     '''
     Converts seqid field from chromosome to item Name
     Then converts coordinates relative to "miRNA_primary_transcript"
@@ -70,9 +65,9 @@
     for key in gff_dict:
         name = gff_dict[key]["attributes"].split("Name=")[1].split(";")[0]
         gff_dict[key]["seqid"] = name
-        if "Derives_from=" in gff_dict[key]["attributes"]:
+        if "erives_from=" in gff_dict[key]["attributes"]:
             parent_ID = gff_dict[key]["attributes"].split(
-                                        "Derives_from=")[1].split(";")[0]
+                                        "erives_from=")[1].split(";")[0]
             gff_dict[key]["start"] = str(int(gff_dict[key]["start"])-int(
                                        gff_dict[parent_ID]["start"])+1)
             gff_dict[key]["end"] = str(int(gff_dict[key]["end"])-int(
@@ -95,7 +90,7 @@
                                                         "Name=")[1].split(
                                                          ";")[0]
     with open(output, "w") as output:
-        output.write(GFF3_header)
+        output.write(header)
         for ID in sorted(hairpins, key=hairpins.get):
             output.write("\t".join([gff_dict[ID]["seqid"],
                          gff_dict[ID]["source"], gff_dict[ID]["type"],
@@ -117,7 +112,7 @@
 
 def main(infile, outfile):
     gff_dict = load_gff_in_dict(infile)
-    genome_to_mir_gff(gff_dict, outfile)
+    genome_to_mir_gff(gff_dict, outfile, get_gff_header(infile))
 
 
 if __name__ == "__main__":
--- a/mircounts.xml	Mon Sep 04 17:55:01 2017 -0400
+++ b/mircounts.xml	Tue Sep 05 06:33:16 2017 -0400
@@ -1,4 +1,4 @@
-<tool id="mircounts" name="miRcounts" version="0.9.4">
+<tool id="mircounts" name="miRcounts" version="1.0.0">
     <description> Counts miRNA alignments from small RNA sequence data</description>
     <requirements>
         <requirement type="package" version="1.18">gnu-wget</requirement>
@@ -9,9 +9,9 @@
         <requirement type="package" version="0.20_34=r3.3.2_0">r-lattice</requirement>
     </requirements>
     <command detect_errors="exit_code"><![CDATA[
-        wget ftp://mirbase.org/pub/mirbase/CURRENT/genomes/${genomeKey}.gff3 && ## download gff3 specified by the variable genomeKey
+        wget ftp://mirbase.org/pub/mirbase/${mirbase_version}/genomes/${genomeKey}.gff3 && ## download the gff3 file specified by the variable genomeKey
         python '$__tool_directory__'/mature_mir_gff_translation.py --input ${genomeKey}.gff3 --output $gff3 && ## transcode the mature miR genome coordinates into coordinates relative to the corresponding "miRNA_primary_transcript".
-        wget ftp://mirbase.org/pub/mirbase/CURRENT/hairpin.fa.gz &&
+        wget ftp://mirbase.org/pub/mirbase/${mirbase_version}/hairpin.fa.gz &&
         sh '$__tool_directory__'/format_fasta_hairpins.sh $genomeKey &&
         #if $cutadapt.cutoption == "yes":
             python '$__tool_directory__'/yac.py --input $cutadapt.input
@@ -74,48 +74,11 @@
                 <column name="value" index="0"/>
             </options>
         </param>
-        <!-- work on proper selection of the url (that varies between gff, gff2 and gff3)
         <param name="mirbase_version" type="select" label="Choose miRbase version">
             <option selected="true" value="CURRENT">Current</option>
-            <option value="1.0">1.0</option>
-            <option value="1.1">1.1</option>
-            <option value="1.2">1.2</option>
-            <option value="1.3">1.3</option>
-            <option value="1.4">1.4</option>
-            <option value="1.5">1.5</option>
-            <option value="2.0">2.0</option>
-            <option value="2.1">2.0</option>
-            <option value="2.2">2.2</option>
-            <option value="3.0">3.0</option>
-            <option value="3.1">3.1</option>
-            <option value="4.0">4.0</option>
-            <option value="5.0">5.0</option>
-            <option value="5.1">5.1</option>
-            <option value="6.0">6.0</option>
-            <option value="7.0">7.0</option>
-            <option value="7.1">7.1</option>
-            <option value="8.0">8.0</option>
-            <option value="8.1">8.1</option>
-            <option value="8.2">8.2</option>
-            <option value="9.0">9.0</option>
-            <option value="9.1">9.1</option>
-            <option value="9.2">9.2</option>
-            <option value="10.0">10.0</option>
-            <option value="10.1">10.1</option>
-            <option value="11.0">11.0</option>
-            <option value="12.0">12.0</option>
-            <option value="13.0">13.0</option>
-            <option value="14">14</option>
-            <option value="15">15</option>
-            <option value="16">16</option>
-            <option value="17">17</option>
-            <option value="18">18</option>
+            <option value="20">20</option>
             <option value="19">19</option>
-            <option value="20">20</option>
-            <option value="21">21</option>
-            </options>
         </param>
-        -->
         <param help="command [ bowtie -v 0,1,2,3 -M 1 --best --strata --norc ] will be used. Specify a value for -v (number of mismatches allowed)" label="Number of mismatches allowed" name="v" type="select">
             <option value="0">0</option>
             <option selected="true" value="1">1</option>
@@ -166,10 +129,11 @@
             <param name="clip_sequence" value="TCGTATGCCGTCTTCTGCTTG"/>
             <param name="v" value="0"/>
             <param name="genomeKey" value="dme"/>
+            <param name="mirbase_version" value="CURRENT"/>
             <param name="input" value="input.unclipped.fastqsanger" ftype="fastqsanger"/>
             <param name="plottingOption" value="no"/>
             <output name="output" file="unclipped.out.bam" ftype="bam"/>
-            <output name="gff3" file="translated_dme.gff3" ftype="gff3"/>
+            <output name="gff3" file="translated_dme.gff3" ftype="gff3" lines_diff="22"/>
             <output name="pre_mir_count_file" file="pre_mirs_unclipped_count.tab"/>
             <output name="mir_count_file" file="mirs_unclipped_count.tab"/>
         </test>
@@ -181,11 +145,12 @@
             <param name="clip_sequence" value="TCGTATGCCGTCTTCTGCTTG"/>
             <param name="v" value="0"/>
             <param name="genomeKey" value="dme"/>
+            <param name="mirbase_version" value="CURRENT"/>
             <param name="input" value="input.unclipped.fastqsanger" ftype="fastqsanger"/>
             <param name="plottingOption" value="yes"/>
             <param name="display" value="relative"/>
             <output name="output" file="unclipped.out.bam" ftype="bam"/>
-            <output name="gff3" file="translated_dme.gff3" ftype="gff3"/>
+            <output name="gff3" file="translated_dme.gff3" ftype="gff3"  lines_diff="22"/>
             <output name="pre_mir_count_file" file="pre_mirs_unclipped_count.tab"/>
             <output name="mir_count_file" file="mirs_unclipped_count.tab"/>
             <output name="latticePDF" file="mir_unclipped_coverage.pdf" ftype="pdf"/>
@@ -195,11 +160,12 @@
             <param name="cutoption" value="no" />
             <param name="v" value="1"/>
             <param name="genomeKey" value="dme"/>
+            <param name="mirbase_version" value="CURRENT"/>
             <param name="clipped_input" value="input.clipped.fastqsanger" ftype="fastqsanger"/>
             <param name="plottingOption" value="yes"/>
             <param name="display" value="absolute"/>
             <output name="output" file="clipped.out.bam" ftype="bam"/>
-            <output name="gff3" file="translated_dme.gff3" ftype="gff3"/>
+            <output name="gff3" file="translated_dme.gff3" ftype="gff3"  lines_diff="22"/>
             <output name="pre_mir_count_file" file="pre_mirs_clipped_count.tab"/>
             <output name="mir_count_file" file="mirs_clipped_count.tab"/>
             <output name="latticePDF" file="mir_clipped_coverage.pdf" ftype="pdf"/>
--- a/test-data/translated_dme.gff3	Mon Sep 04 17:55:01 2017 -0400
+++ b/test-data/translated_dme.gff3	Tue Sep 05 06:33:16 2017 -0400
@@ -1,15 +1,17 @@
 ##gff-version 3
-##generated by mature_mir_gff_translation.py
+##date 2014-6-22
 #
-# Chromosomal coordinates of microRNAs ** relative to the hairpin precursors **
-# microRNAs:               miRBase current_version
-# genome-build-id:         check http://mirbase.org/
+# Chromosomal coordinates of Drosophila melanogaster microRNAs
+# microRNAs: miRBase v21
+# genome-build-id: BDGP5.0
 #
 # Hairpin precursor sequences have type "miRNA_primary_transcript".
 # Note, these sequences do not represent the full primary transcript,
 # rather a predicted stem-loop portion that includes the precursor
 # miRNA. Mature sequences have type "miRNA".
 #
+# generated by mature_mir_gff_translation.py 2017-09-05 11:53:29.042787
+#
 dme-bantam	.	miRNA_primary_transcript	1	81	.	+	.	ID=MI0000387;Alias=MI0000387;Name=dme-bantam
 dme-bantam-5p	.	miRNA	15	37	.	+	.	ID=MIMAT0020823;Alias=MIMAT0020823;Name=dme-bantam-5p;Derives_from=MI0000387;Parent_mir_Name=dme-bantam
 dme-bantam-3p	.	miRNA	52	74	.	+	.	ID=MIMAT0000365;Alias=MIMAT0000365;Name=dme-bantam-3p;Derives_from=MI0000387;Parent_mir_Name=dme-bantam