Mercurial > repos > devteam > basecoverage

changeset 0:1e6a9e97fa41

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author devteam
date Tue, 01 Apr 2014 10:53:19 -0400
parents
children 642849141ae9
files basecoverage.xml gops_basecoverage.py operation_filter.py test-data/1.bed test-data/gops_basecoverage_out.txt test-data/gops_basecoverage_out2.txt test-data/gops_bigint.interval tool_dependencies.xml
diffstat 8 files changed, 281 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/basecoverage.xml	Tue Apr 01 10:53:19 2014 -0400
@@ -0,0 +1,49 @@
+<tool id="gops_basecoverage_1" name="Base Coverage" version="0.0.1">
+  <description>of all intervals</description>
+  <command interpreter="python">gops_basecoverage.py $input1 $output -1 ${input1.metadata.chromCol},${input1.metadata.startCol},${input1.metadata.endCol},${input1.metadata.strandCol}</command>
+  <requirements>
+    <requirement type="package" version="0.7.1">bx-python</requirement>
+    <requirement type="package" version="1.0.0">galaxy-ops</requirement>
+  </requirements>
+  <inputs>
+    <param format="interval" name="input1" type="data">
+      <label>Compute coverage for</label>
+    </param>
+   </inputs>
+  <outputs>
+    <data format="txt" name="output" />
+  </outputs>
+  <code file="operation_filter.py"/>
+  <tests>
+    <test>
+      <param name="input1" value="1.bed" />
+      <output name="output" file="gops_basecoverage_out.txt" />     
+    </test>
+    <test>
+      <param name="input1" value="gops_bigint.interval" />
+      <output name="output" file="gops_basecoverage_out2.txt" />     
+    </test>
+  </tests>
+  <help>
+
+.. class:: infomark
+
+**TIP:** If your dataset does not appear in the pulldown menu, it means that it is not in interval format. Use "edit attributes" to set chromosome, start, end, and strand columns.
+
+This operation counts the total bases covered by a set of intervals.  Bases that are covered by more than one interval are **not** counted more than once towards the total.
+
+-----
+
+**Screencasts!**
+
+See Galaxy Interval Operation Screencasts_ (right click to open this link in another window).
+
+.. _Screencasts: http://wiki.g2.bx.psu.edu/Learn/Interval%20Operations
+
+**Example**
+
+.. image:: ${static_path}/operation_icons/gops_baseCoverage.gif
+
+
+</help>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/gops_basecoverage.py	Tue Apr 01 10:53:19 2014 -0400
@@ -0,0 +1,48 @@
+#!/usr/bin/env python
+"""
+Count total base coverage.
+
+usage: %prog in_file out_file
+    -1, --cols1=N,N,N,N: Columns for start, end, strand in first file
+"""
+
+import sys, traceback, fileinput
+from warnings import warn
+from bx.intervals import *
+from bx.intervals.io import *
+from bx.intervals.operations.base_coverage import *
+from bx.cookbook import doc_optparse
+from galaxy.tools.util.galaxyops import *
+
+assert sys.version_info[:2] >= ( 2, 4 )
+
+def main():
+    upstream_pad = 0
+    downstream_pad = 0
+
+    options, args = doc_optparse.parse( __doc__ )
+    try:
+        chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
+        in_fname, out_fname = args
+    except:
+        doc_optparse.exception()
+        
+    g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
+                            chrom_col=chr_col_1,
+                            start_col=start_col_1,
+                            end_col=end_col_1,
+                            strand_col = strand_col_1,
+                            fix_strand=True )
+    
+    try:
+        bases = base_coverage(g1)
+    except ParseError, exc:
+        fail( "Invalid file format: %s" % str( exc ) )
+    out_file = open( out_fname, "w" )
+    out_file.write( "%s\n" % str( bases ) )
+    out_file.close()
+    if g1.skipped > 0:
+        print skipped( g1, filedesc="" )
+
+if __name__ == "__main__":
+    main()
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/operation_filter.py	Tue Apr 01 10:53:19 2014 -0400
@@ -0,0 +1,99 @@
+# runs after the job (and after the default post-filter)
+import os
+from galaxy import eggs
+from galaxy import jobs
+from galaxy.tools.parameters import DataToolParameter
+
+from galaxy.jobs.handler import JOB_ERROR
+
+# Older py compatibility
+try:
+    set()
+except:
+    from sets import Set as set
+
+#def exec_before_process(app, inp_data, out_data, param_dict, tool=None):
+#    """Sets the name of the data"""
+#    dbkeys = sets.Set( [data.dbkey for data in inp_data.values() ] ) 
+#    if len(dbkeys) != 1:
+#        raise Exception, '<p><font color="yellow">Both Queries must be from the same genome build</font></p>'
+
+def validate_input( trans, error_map, param_values, page_param_map ):
+    dbkeys = set()
+    data_param_names = set()
+    data_params = 0
+    for name, param in page_param_map.iteritems():
+        if isinstance( param, DataToolParameter ):
+            # for each dataset parameter
+            if param_values.get(name, None) != None:
+                dbkeys.add( param_values[name].dbkey )
+                data_params += 1
+                # check meta data
+                try:
+                    param = param_values[name]
+                    if isinstance( param.datatype, trans.app.datatypes_registry.get_datatype_by_extension( 'gff' ).__class__ ):
+                        # TODO: currently cannot validate GFF inputs b/c they are not derived from interval.
+                        pass
+                    else: # Validate interval datatype.
+                        startCol = int( param.metadata.startCol )
+                        endCol = int( param.metadata.endCol )
+                        chromCol = int( param.metadata.chromCol )
+                        if param.metadata.strandCol is not None:
+                            strandCol = int ( param.metadata.strandCol )
+                        else:
+                            strandCol = 0
+                except:
+                    error_msg = "The attributes of this dataset are not properly set. " + \
+                    "Click the pencil icon in the history item to set the chrom, start, end and strand columns."
+                    error_map[name] = error_msg
+            data_param_names.add( name )
+    if len( dbkeys ) > 1:
+        for name in data_param_names:
+            error_map[name] = "All datasets must belong to same genomic build, " \
+                "this dataset is linked to build '%s'" % param_values[name].dbkey
+    if data_params != len(data_param_names):
+        for name in data_param_names:
+            error_map[name] = "A dataset of the appropriate type is required"
+
+# Commented out by INS, 5/30/2007.  What is the PURPOSE of this?
+def exec_after_process(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None):
+    """Verify the output data after each run"""
+    items = out_data.items()
+
+    for name, data in items:
+        try:
+            if stderr and len( stderr ) > 0:
+                raise Exception( stderr )
+
+        except Exception, exc:
+            data.blurb = JOB_ERROR
+            data.state = JOB_ERROR
+
+## def exec_after_process(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None):
+##     pass
+
+
+def exec_after_merge(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None):
+    exec_after_process(
+        app, inp_data, out_data, param_dict, tool=tool, stdout=stdout, stderr=stderr)
+
+    # strip strand column if clusters were merged
+    items = out_data.items()
+    for name, data in items:
+        if param_dict['returntype'] == True:
+            data.metadata.chromCol = 1
+            data.metadata.startCol = 2
+            data.metadata.endCol = 3
+        # merge always clobbers strand
+        data.metadata.strandCol = None
+            
+
+def exec_after_cluster(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None):
+    exec_after_process(
+        app, inp_data, out_data, param_dict, tool=tool, stdout=stdout, stderr=stderr)
+
+    # strip strand column if clusters were merged
+    if param_dict["returntype"] == '1':
+        items = out_data.items()
+        for name, data in items:
+            data.metadata.strandCol = None
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/1.bed	Tue Apr 01 10:53:19 2014 -0400
@@ -0,0 +1,65 @@
+chr1	147962192	147962580	CCDS989.1_cds_0_0_chr1_147962193_r	0	-
+chr1	147984545	147984630	CCDS990.1_cds_0_0_chr1_147984546_f	0	+
+chr1	148078400	148078582	CCDS993.1_cds_0_0_chr1_148078401_r	0	-
+chr1	148185136	148185276	CCDS996.1_cds_0_0_chr1_148185137_f	0	+
+chr10	55251623	55253124	CCDS7248.1_cds_0_0_chr10_55251624_r	0	-
+chr11	116124407	116124501	CCDS8374.1_cds_0_0_chr11_116124408_r	0	-
+chr11	116206508	116206563	CCDS8377.1_cds_0_0_chr11_116206509_f	0	+
+chr11	116211733	116212337	CCDS8378.1_cds_0_0_chr11_116211734_r	0	-
+chr11	1812377	1812407	CCDS7726.1_cds_0_0_chr11_1812378_f	0	+
+chr12	38440094	38440321	CCDS8736.1_cds_0_0_chr12_38440095_r	0	-
+chr13	112381694	112381953	CCDS9526.1_cds_0_0_chr13_112381695_f	0	+
+chr14	98710240	98712285	CCDS9949.1_cds_0_0_chr14_98710241_r	0	-
+chr15	41486872	41487060	CCDS10096.1_cds_0_0_chr15_41486873_r	0	-
+chr15	41673708	41673857	CCDS10097.1_cds_0_0_chr15_41673709_f	0	+
+chr15	41679161	41679250	CCDS10098.1_cds_0_0_chr15_41679162_r	0	-
+chr15	41826029	41826196	CCDS10101.1_cds_0_0_chr15_41826030_f	0	+
+chr16	142908	143003	CCDS10397.1_cds_0_0_chr16_142909_f	0	+
+chr16	179963	180135	CCDS10401.1_cds_0_0_chr16_179964_r	0	-
+chr16	244413	244681	CCDS10402.1_cds_0_0_chr16_244414_f	0	+
+chr16	259268	259383	CCDS10403.1_cds_0_0_chr16_259269_r	0	-
+chr18	23786114	23786321	CCDS11891.1_cds_0_0_chr18_23786115_r	0	-
+chr18	59406881	59407046	CCDS11985.1_cds_0_0_chr18_59406882_f	0	+
+chr18	59455932	59456337	CCDS11986.1_cds_0_0_chr18_59455933_r	0	-
+chr18	59600586	59600754	CCDS11988.1_cds_0_0_chr18_59600587_f	0	+
+chr19	59068595	59069564	CCDS12866.1_cds_0_0_chr19_59068596_f	0	+
+chr19	59236026	59236146	CCDS12872.1_cds_0_0_chr19_59236027_r	0	-
+chr19	59297998	59298008	CCDS12877.1_cds_0_0_chr19_59297999_f	0	+
+chr19	59302168	59302288	CCDS12878.1_cds_0_0_chr19_59302169_r	0	-
+chr2	118288583	118288668	CCDS2120.1_cds_0_0_chr2_118288584_f	0	+
+chr2	118394148	118394202	CCDS2121.1_cds_0_0_chr2_118394149_r	0	-
+chr2	220190202	220190242	CCDS2441.1_cds_0_0_chr2_220190203_f	0	+
+chr2	220229609	220230869	CCDS2443.1_cds_0_0_chr2_220229610_r	0	-
+chr20	33330413	33330423	CCDS13249.1_cds_0_0_chr20_33330414_r	0	-
+chr20	33513606	33513792	CCDS13255.1_cds_0_0_chr20_33513607_f	0	+
+chr20	33579500	33579527	CCDS13256.1_cds_0_0_chr20_33579501_r	0	-
+chr20	33593260	33593348	CCDS13257.1_cds_0_0_chr20_33593261_f	0	+
+chr21	32707032	32707192	CCDS13614.1_cds_0_0_chr21_32707033_f	0	+
+chr21	32869641	32870022	CCDS13615.1_cds_0_0_chr21_32869642_r	0	-
+chr21	33321040	33322012	CCDS13620.1_cds_0_0_chr21_33321041_f	0	+
+chr21	33744994	33745040	CCDS13625.1_cds_0_0_chr21_33744995_r	0	-
+chr22	30120223	30120265	CCDS13897.1_cds_0_0_chr22_30120224_f	0	+
+chr22	30160419	30160661	CCDS13898.1_cds_0_0_chr22_30160420_r	0	-
+chr22	30665273	30665360	CCDS13901.1_cds_0_0_chr22_30665274_f	0	+
+chr22	30939054	30939266	CCDS13903.1_cds_0_0_chr22_30939055_r	0	-
+chr5	131424298	131424460	CCDS4149.1_cds_0_0_chr5_131424299_f	0	+
+chr5	131556601	131556672	CCDS4151.1_cds_0_0_chr5_131556602_r	0	-
+chr5	131621326	131621419	CCDS4152.1_cds_0_0_chr5_131621327_f	0	+
+chr5	131847541	131847666	CCDS4155.1_cds_0_0_chr5_131847542_r	0	-
+chr6	108299600	108299744	CCDS5061.1_cds_0_0_chr6_108299601_r	0	-
+chr6	108594662	108594687	CCDS5063.1_cds_0_0_chr6_108594663_f	0	+
+chr6	108640045	108640151	CCDS5064.1_cds_0_0_chr6_108640046_r	0	-
+chr6	108722976	108723115	CCDS5067.1_cds_0_0_chr6_108722977_f	0	+
+chr7	113660517	113660685	CCDS5760.1_cds_0_0_chr7_113660518_f	0	+
+chr7	116512159	116512389	CCDS5771.1_cds_0_0_chr7_116512160_r	0	-
+chr7	116714099	116714152	CCDS5773.1_cds_0_0_chr7_116714100_f	0	+
+chr7	116945541	116945787	CCDS5774.1_cds_0_0_chr7_116945542_r	0	-
+chr8	118881131	118881317	CCDS6324.1_cds_0_0_chr8_118881132_r	0	-
+chr9	128764156	128764189	CCDS6914.1_cds_0_0_chr9_128764157_f	0	+
+chr9	128787519	128789136	CCDS6915.1_cds_0_0_chr9_128787520_r	0	-
+chr9	128882427	128882523	CCDS6917.1_cds_0_0_chr9_128882428_f	0	+
+chr9	128937229	128937445	CCDS6919.1_cds_0_0_chr9_128937230_r	0	-
+chrX	122745047	122745924	CCDS14606.1_cds_0_0_chrX_122745048_f	0	+
+chrX	152648964	152649196	CCDS14733.1_cds_0_0_chrX_152648965_r	0	-
+chrX	152691446	152691471	CCDS14735.1_cds_0_0_chrX_152691447_f	0	+
+chrX	152694029	152694263	CCDS14736.1_cds_0_0_chrX_152694030_r	0	-
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gops_basecoverage_out.txt	Tue Apr 01 10:53:19 2014 -0400
@@ -0,0 +1,1 @@
+17987
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gops_basecoverage_out2.txt	Tue Apr 01 10:53:19 2014 -0400
@@ -0,0 +1,1 @@
+12117
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gops_bigint.interval	Tue Apr 01 10:53:19 2014 -0400
@@ -0,0 +1,9 @@
+chrM	69	852	uc009vev.1_exon_0_0_chrM_70_f	0	+
+chrM	1148	3703	uc009vew.1_exon_0_0_chrM_1149_f	0	+
+chrM	3848	4933	uc009vex.1_exon_0_0_chrM_3849_f	0	+
+chrM	5326	6938	uc009vey.1_exon_0_0_chrM_5327_f	0	+
+chrM	7009	7699	uc009vez.1_exon_0_0_chrM_7010_f	0	+
+chrM	7765	8607	uc009vfa.1_exon_0_0_chrM_7766_f	0	+
+chrM	9875	11542	uc009vfb.1_exon_0_0_chrM_9876_f	0	+
+chrM	12405	15288	uc009vfc.1_exon_0_0_chrM_12406_f	0	+
+chrM	4294967295	4294967322	EAS38_1_45_638_677	2	+
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Tue Apr 01 10:53:19 2014 -0400
@@ -0,0 +1,9 @@
+<?xml version="1.0"?>
+<tool_dependency>
+  <package name="bx-python" version="0.7.1">
+      <repository changeset_revision="41eb9d9f667d" name="package_bx_python_0_7" owner="devteam" prior_installation_required="False" toolshed="http://toolshed.g2.bx.psu.edu" />
+    </package>
+    <package name="galaxy-ops" version="1.0.0">
+      <repository changeset_revision="4e39032e4ec6" name="package_galaxy_ops_1_0_0" owner="devteam" prior_installation_required="False" toolshed="http://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>