Repository 'cuffmerge'
hg clone https://toolshed.g2.bx.psu.edu/repos/devteam/cuffmerge

Changeset 0:dbbd37e013aa (2013-10-01)
Next changeset 1:fdc55fd74f78 (2013-10-01)
Commit message:
Uploaded tool tarball.
added:
cuffmerge_wrapper.py
cuffmerge_wrapper.xml
test-data/cuffcompare_in1.gtf
test-data/cuffcompare_in2.gtf
test-data/cuffcompare_in3.gtf
test-data/cuffmerge_out1.gtf
tool_dependencies.xml
b
diff -r 000000000000 -r dbbd37e013aa cuffmerge_wrapper.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/cuffmerge_wrapper.py Tue Oct 01 12:57:24 2013 -0400
[
@@ -0,0 +1,138 @@
+#!/usr/bin/env python
+
+# Supports Cuffmerge versions 1.3 and newer.
+
+import optparse, os, shutil, subprocess, sys, tempfile
+
+def stop_err( msg ):
+    sys.stderr.write( '%s\n' % msg )
+    sys.exit()
+
+# Copied from sam_to_bam.py:
+def check_seq_file( dbkey, cached_seqs_pointer_file ):
+    seq_path = ''
+    for line in open( cached_seqs_pointer_file ):
+        line = line.rstrip( '\r\n' )
+        if line and not line.startswith( '#' ) and line.startswith( 'index' ):
+            fields = line.split( '\t' )
+            if len( fields ) < 3:
+                continue
+            if fields[1] == dbkey:
+                seq_path = fields[2].strip()
+                break
+    return seq_path
+
+def __main__():
+    #Parse Command Line
+    parser = optparse.OptionParser()
+    parser.add_option( '-g', dest='ref_annotation', help='An optional "reference" annotation GTF. Each sample is matched against this file, and sample isoforms are tagged as overlapping, matching, or novel where appropriate. See the refmap and tmap output file descriptions below.' )
+    parser.add_option( '-s', dest='use_seq_data', action="store_true", help='Causes cuffmerge to look into for fasta files with the underlying genomic sequences (one file per contig) against which your reads were aligned for some optional classification functions. For example, Cufflinks transcripts consisting mostly of lower-case bases are classified as repeats. Note that <seq_dir> must contain one fasta file per reference chromosome, and each file must be named after the chromosome, and have a .fa or .fasta extension.')
+    parser.add_option( '-p', '--num-threads', dest='num_threads', help='Use this many threads to align reads. The default is 1.' )
+    
+    
+    # Wrapper / Galaxy options.
+    parser.add_option( '', '--dbkey', dest='dbkey', help='The build of the reference dataset' )
+    parser.add_option( '', '--index_dir', dest='index_dir', help='GALAXY_DATA_INDEX_DIR' )
+    parser.add_option( '', '--ref_file', dest='ref_file', help='The reference dataset from the history' )
+    
+    # Outputs.
+    parser.add_option( '', '--merged-transcripts', dest='merged_transcripts' )
+    
+    (options, args) = parser.parse_args()
+    
+    # output version # of tool
+    try:
+        tmp = tempfile.NamedTemporaryFile().name
+        tmp_stdout = open( tmp, 'wb' )
+        proc = subprocess.Popen( args='cuffmerge -v 2>&1', shell=True, stdout=tmp_stdout )
+        tmp_stdout.close()
+        returncode = proc.wait()
+        stdout = None
+        for line in open( tmp_stdout.name, 'rb' ):
+            if line.lower().find( 'merge_cuff_asms v' ) >= 0:
+                stdout = line.strip()
+                break
+        if stdout:
+            sys.stdout.write( '%s\n' % stdout )
+        else:
+            raise Exception
+    except:
+        sys.stdout.write( 'Could not determine Cuffmerge version\n' )
+        
+    # Set/link to sequence file.
+    if options.use_seq_data:
+        if options.ref_file != 'None':
+            # Sequence data from history.
+            # Create symbolic link to ref_file so that index will be created in working directory.
+            seq_path = "ref.fa"
+            os.symlink( options.ref_file, seq_path  )
+        else:
+            # Sequence data from loc file.
+            cached_seqs_pointer_file = os.path.join( options.index_dir, 'sam_fa_indices.loc' )
+            if not os.path.exists( cached_seqs_pointer_file ):
+                stop_err( 'The required file (%s) does not exist.' % cached_seqs_pointer_file )
+            # If found for the dbkey, seq_path will look something like /galaxy/data/equCab2/sam_index/equCab2.fa,
+            # and the equCab2.fa file will contain fasta sequences.
+            seq_path = check_seq_file( options.dbkey, cached_seqs_pointer_file )
+            if seq_path == '':
+                stop_err( 'No sequence data found for dbkey %s, so sequence data cannot be used.' % options.dbkey  )
+    
+    # Build command.
+    
+    # Base.
+    cmd = "cuffmerge -o cm_output "
+    
+    # Add options.
+    if options.num_threads:
+        cmd += ( " -p %i " % int ( options.num_threads ) )
+    if options.ref_annotation:
+        cmd += " -g %s " % options.ref_annotation
+    if options.use_seq_data:
+        cmd += " -s %s " % seq_path
+        
+    # Add input files to a file.
+    inputs_file_name = tempfile.NamedTemporaryFile( dir="." ).name
+    inputs_file = open( inputs_file_name, 'w' )
+    for arg in args:
+        inputs_file.write( arg + "\n" )
+    inputs_file.close()
+    cmd += inputs_file_name
+
+    # Debugging.
+    print cmd
+    
+    # Run command.
+    try:        
+        tmp_name = tempfile.NamedTemporaryFile( dir="." ).name
+        tmp_stderr = open( tmp_name, 'wb' )
+        proc = subprocess.Popen( args=cmd, shell=True, stderr=tmp_stderr.fileno() )
+        returncode = proc.wait()
+        tmp_stderr.close()
+        
+        # Get stderr, allowing for case where it's very large.
+        tmp_stderr = open( tmp_name, 'rb' )
+        stderr = ''
+        buffsize = 1048576
+        try:
+            while True:
+                stderr += tmp_stderr.read( buffsize )
+                if not stderr or len( stderr ) % buffsize != 0:
+                    break
+        except OverflowError:
+            pass
+        tmp_stderr.close()
+        
+        # Error checking.
+        if returncode != 0:
+            raise Exception, stderr
+            
+        if len( open( "cm_output/merged.gtf", 'rb' ).read().strip() ) == 0:
+            raise Exception, 'The output file is empty, there may be an error with your input file or settings.'
+            
+        # Copy outputs.
+        shutil.copyfile( "cm_output/merged.gtf" , options.merged_transcripts )    
+            
+    except Exception, e:
+        stop_err( 'Error running cuffmerge. ' + str( e ) )
+        
+if __name__=="__main__": __main__()
b
diff -r 000000000000 -r dbbd37e013aa cuffmerge_wrapper.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/cuffmerge_wrapper.xml Tue Oct 01 12:57:24 2013 -0400
b
@@ -0,0 +1,129 @@
+<tool id="cuffmerge" name="Cuffmerge" version="0.0.5">
+    <!-- Wrapper supports Cuffmerge versions 1.3 and newer -->
+    <description>merge together several Cufflinks assemblies</description>
+    <requirements>
+        <requirement type="package" version="2.1.1">cufflinks</requirement>
+    </requirements>
+    <command interpreter="python">
+        cuffmerge_wrapper.py
+        
+            --num-threads="4"
+            
+            ## Use annotation reference?
+            #if $annotation.use_ref_annotation == "Yes":
+                -g $annotation.reference_annotation
+            #end if
+            
+            ## Use sequence data?
+            #if $seq_data.use_seq_data == "Yes":
+         -s
+                #if $seq_data.seq_source.index_source == "history":
+                    --ref_file=$seq_data.seq_source.ref_file
+                #else:
+                    --ref_file="None"
+                #end if
+                --dbkey=${first_input.metadata.dbkey} 
+                --index_dir=${GALAXY_DATA_INDEX_DIR}
+            #end if
+            
+            ## Outputs.
+            --merged-transcripts=${merged_transcripts}
+                        
+            ## Inputs.
+            ${first_input}
+            #for $input_file in $input_files:
+              ${input_file.additional_input}
+            #end for
+            
+    </command>
+    <inputs>
+        <param format="gtf" name="first_input" type="data" label="GTF file produced by Cufflinks" help=""/>
+        <repeat name="input_files" title="Additional GTF Input Files">
+            <param format="gtf" name="additional_input" type="data" label="GTF file produced by Cufflinks" help=""/>
+        </repeat>
+        <conditional name="annotation">
+            <param name="use_ref_annotation" type="select" label="Use Reference Annotation">
+                <option value="No">No</option>
+                <option value="Yes">Yes</option>
+            </param>
+            <when value="Yes">
+                <param format="gff3,gtf" name="reference_annotation" type="data" label="Reference Annotation" help="Requires an annotation file in GFF3 or GTF format."/>    
+            </when>
+            <when value="No">
+            </when>
+        </conditional>
+        <conditional name="seq_data">
+            <param name="use_seq_data" type="select" label="Use Sequence Data" help="Use sequence data for some optional classification functions, including the addition of the p_id attribute required by Cuffdiff.">
+                <option value="No">No</option>
+                <option value="Yes">Yes</option>
+            </param>
+            <when value="No"></when>
+            <when value="Yes">
+                <conditional name="seq_source">
+                  <param name="index_source" type="select" label="Choose the source for the reference list">
+                    <option value="cached">Locally cached</option>
+                    <option value="history">History</option>
+                  </param>
+                  <when value="cached"></when>
+                  <when value="history">
+                      <param name="ref_file" type="data" format="fasta" label="Using reference file" />
+                  </when>
+                </conditional>
+            </when>
+        </conditional>
+    </inputs>
+
+    <outputs>
+        <data format="gtf" name="merged_transcripts" label="${tool.name} on ${on_string}: merged transcripts"/>
+    </outputs>
+
+    <tests>
+        <!-- 
+            cuffmerge -g cuffcompare_in3.gtf cuffcompare_in1.gtf cuffcompare_in2.gtf
+        -->
+        <test>
+            <param name="first_input" value="cuffcompare_in1.gtf" ftype="gtf"/>
+            <param name="additional_input" value="cuffcompare_in2.gtf" ftype="gtf"/>
+            <param name="use_ref_annotation" value="Yes"/>
+            <param name="reference_annotation" value="cuffcompare_in3.gtf" ftype="gtf"/>
+            <param name="use_seq_data" value="No"/>
+ <!-- oId assignment differ/are non-deterministic -->
+            <output name="merged_transcripts" file="cuffmerge_out1.gtf" lines_diff="50"/>
+        </test>
+    </tests>
+
+    <help>
+**Cuffmerge Overview**
+
+Cuffmerge is part of Cufflinks_. Please cite: Trapnell C, Williams BA, Pertea G, Mortazavi AM, Kwan G, van Baren MJ, Salzberg SL, Wold B, Pachter L. Transcript assembly and abundance estimation from RNA-Seq reveals thousands of new transcripts and switching among isoforms. Nature Biotechnology doi:10.1038/nbt.1621
+
+.. _Cufflinks: http://cufflinks.cbcb.umd.edu/
+        
+------
+
+**Know what you are doing**
+
+.. class:: warningmark
+
+There is no such thing (yet) as an automated gearshift in expression analysis. It is all like stick-shift driving in San Francisco. In other words, running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy.
+
+.. __: http://cufflinks.cbcb.umd.edu/manual.html#cuffmerge
+
+------
+
+**Input format**
+
+Cuffmerge takes Cufflinks' GTF output as input, and optionally can take a "reference" annotation (such as from Ensembl_)
+
+.. _Ensembl: http://www.ensembl.org 
+
+------
+
+**Outputs**
+
+Cuffmerge produces the following output files:
+
+Merged transcripts file:
+
+Cuffmerge produces a GTF file that contains an assembly that merges together the input assemblies.    </help>
+</tool>
b
diff -r 000000000000 -r dbbd37e013aa test-data/cuffcompare_in1.gtf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cuffcompare_in1.gtf Tue Oct 01 12:57:24 2013 -0400
b
b'@@ -0,0 +1,100 @@\n+chr1\tCufflinks\ttranscript\t3111450\t3111490\t1000\t.\t.\tgene_id "CUFF.1"; transcript_id "CUFF.1.1"; FPKM "20.6079364877"; frac "1.000000"; conf_lo "0.000000"; conf_hi "49.751960"; cov "1.317073";\n+chr1\tCufflinks\texon\t3111450\t3111490\t1000\t.\t.\tgene_id "CUFF.1"; transcript_id "CUFF.1.1"; exon_number "1"; FPKM "20.6079364877"; frac "1.000000"; conf_lo "0.000000"; conf_hi "49.751960"; cov "1.317073";\n+chr1\tCufflinks\ttranscript\t3111546\t3111576\t1000\t.\t.\tgene_id "CUFF.3"; transcript_id "CUFF.3.1"; FPKM "27.2556579354"; frac "1.000000"; conf_lo "0.000000"; conf_hi "65.800979"; cov "1.741935";\n+chr1\tCufflinks\texon\t3111546\t3111576\t1000\t.\t.\tgene_id "CUFF.3"; transcript_id "CUFF.3.1"; exon_number "1"; FPKM "27.2556579354"; frac "1.000000"; conf_lo "0.000000"; conf_hi "65.800979"; cov "1.741935";\n+chr1\tCufflinks\ttranscript\t3200326\t3200352\t1000\t.\t.\tgene_id "CUFF.5"; transcript_id "CUFF.5.1"; FPKM "31.2935331850"; frac "1.000000"; conf_lo "0.000000"; conf_hi "75.549272"; cov "2.000000";\n+chr1\tCufflinks\texon\t3200326\t3200352\t1000\t.\t.\tgene_id "CUFF.5"; transcript_id "CUFF.5.1"; exon_number "1"; FPKM "31.2935331850"; frac "1.000000"; conf_lo "0.000000"; conf_hi "75.549272"; cov "2.000000";\n+chr1\tCufflinks\ttranscript\t3200023\t3200191\t1000\t.\t.\tgene_id "CUFF.7"; transcript_id "CUFF.7.1"; FPKM "9.9991171124"; frac "1.000000"; conf_lo "0.000000"; conf_hi "19.998234"; cov "0.639053";\n+chr1\tCufflinks\texon\t3200023\t3200191\t1000\t.\t.\tgene_id "CUFF.7"; transcript_id "CUFF.7.1"; exon_number "1"; FPKM "9.9991171124"; frac "1.000000"; conf_lo "0.000000"; conf_hi "19.998234"; cov "0.639053";\n+chr1\tCufflinks\ttranscript\t3201078\t3201481\t1000\t.\t.\tgene_id "CUFF.9"; transcript_id "CUFF.9.1"; FPKM "17.7768957078"; frac "1.000000"; conf_lo "9.153835"; conf_hi "26.399957"; cov "1.136139";\n+chr1\tCufflinks\texon\t3201078\t3201481\t1000\t.\t.\tgene_id "CUFF.9"; transcript_id "CUFF.9.1"; exon_number "1"; FPKM "17.7768957078"; frac "1.000000"; conf_lo "9.153835"; conf_hi "26.399957"; cov "1.136139";\n+chr1\tCufflinks\ttranscript\t3201673\t3201699\t1000\t.\t.\tgene_id "CUFF.11"; transcript_id "CUFF.11.1"; FPKM "31.2935331850"; frac "1.000000"; conf_lo "0.000000"; conf_hi "75.549272"; cov "2.000000";\n+chr1\tCufflinks\texon\t3201673\t3201699\t1000\t.\t.\tgene_id "CUFF.11"; transcript_id "CUFF.11.1"; exon_number "1"; FPKM "31.2935331850"; frac "1.000000"; conf_lo "0.000000"; conf_hi "75.549272"; cov "2.000000";\n+chr1\tCufflinks\ttranscript\t3204755\t3204833\t1000\t.\t.\tgene_id "CUFF.13"; transcript_id "CUFF.13.1"; FPKM "10.6952581772"; frac "1.000000"; conf_lo "0.000000"; conf_hi "25.820637"; cov "0.683544";\n+chr1\tCufflinks\texon\t3204755\t3204833\t1000\t.\t.\tgene_id "CUFF.13"; transcript_id "CUFF.13.1"; exon_number "1"; FPKM "10.6952581772"; frac "1.000000"; conf_lo "0.000000"; conf_hi "25.820637"; cov "0.683544";\n+chr1\tCufflinks\ttranscript\t3212214\t3212292\t1000\t.\t.\tgene_id "CUFF.15"; transcript_id "CUFF.15.1"; FPKM "10.6952581772"; frac "1.000000"; conf_lo "0.000000"; conf_hi "25.820637"; cov "0.683544";\n+chr1\tCufflinks\texon\t3212214\t3212292\t1000\t.\t.\tgene_id "CUFF.15"; transcript_id "CUFF.15.1"; exon_number "1"; FPKM "10.6952581772"; frac "1.000000"; conf_lo "0.000000"; conf_hi "25.820637"; cov "0.683544";\n+chr1\tCufflinks\ttranscript\t3213096\t3213192\t1000\t.\t.\tgene_id "CUFF.17"; transcript_id "CUFF.17.1"; FPKM "8.7105710927"; frac "1.000000"; conf_lo "0.000000"; conf_hi "21.029179"; cov "0.556701";\n+chr1\tCufflinks\texon\t3213096\t3213192\t1000\t.\t.\tgene_id "CUFF.17"; transcript_id "CUFF.17.1"; exon_number "1"; FPKM "8.7105710927"; frac "1.000000"; conf_lo "0.000000"; conf_hi "21.029179"; cov "0.556701";\n+chr1\tCufflinks\ttranscript\t3212368\t3212439\t1000\t.\t.\tgene_id "CUFF.19"; transcript_id "CUFF.19.1"; FPKM "29.3376873610"; frac "1.000000"; conf_lo "3.097262"; conf_hi "55.578113"; cov "1.875000";\n+chr1\tCufflinks\texon\t3212368\t3212439\t1000\t.\t.\tgene_id "CUFF.19"; transcript_id "CUFF.19.1"; exon_number "1"; FPKM "29.3376873610"; frac "1.000000"; conf_lo "3.097262"; conf_hi "55.578113"; cov "1.875000";\n+chr1\tCufflinks'..b'0000";\n+chr1\tCufflinks\ttranscript\t3363215\t3363278\t1000\t.\t.\tgene_id "CUFF.81"; transcript_id "CUFF.81.1"; FPKM "13.2019593124"; frac "1.000000"; conf_lo "0.000000"; conf_hi "31.872349"; cov "0.843750";\n+chr1\tCufflinks\texon\t3363215\t3363278\t1000\t.\t.\tgene_id "CUFF.81"; transcript_id "CUFF.81.1"; exon_number "1"; FPKM "13.2019593124"; frac "1.000000"; conf_lo "0.000000"; conf_hi "31.872349"; cov "0.843750";\n+chr1\tCufflinks\ttranscript\t3363754\t3363849\t1000\t.\t.\tgene_id "CUFF.83"; transcript_id "CUFF.83.1"; FPKM "13.2019593124"; frac "1.000000"; conf_lo "0.000000"; conf_hi "28.446269"; cov "0.843750";\n+chr1\tCufflinks\texon\t3363754\t3363849\t1000\t.\t.\tgene_id "CUFF.83"; transcript_id "CUFF.83.1"; exon_number "1"; FPKM "13.2019593124"; frac "1.000000"; conf_lo "0.000000"; conf_hi "28.446269"; cov "0.843750";\n+chr1\tCufflinks\ttranscript\t3367136\t3367162\t1000\t.\t.\tgene_id "CUFF.85"; transcript_id "CUFF.85.1"; FPKM "31.2935331850"; frac "1.000000"; conf_lo "0.000000"; conf_hi "75.549272"; cov "2.000000";\n+chr1\tCufflinks\texon\t3367136\t3367162\t1000\t.\t.\tgene_id "CUFF.85"; transcript_id "CUFF.85.1"; exon_number "1"; FPKM "31.2935331850"; frac "1.000000"; conf_lo "0.000000"; conf_hi "75.549272"; cov "2.000000";\n+chr1\tCufflinks\ttranscript\t3367334\t3367382\t1000\t.\t.\tgene_id "CUFF.87"; transcript_id "CUFF.87.1"; FPKM "17.2433754285"; frac "1.000000"; conf_lo "0.000000"; conf_hi "41.629191"; cov "1.102041";\n+chr1\tCufflinks\texon\t3367334\t3367382\t1000\t.\t.\tgene_id "CUFF.87"; transcript_id "CUFF.87.1"; exon_number "1"; FPKM "17.2433754285"; frac "1.000000"; conf_lo "0.000000"; conf_hi "41.629191"; cov "1.102041";\n+chr1\tCufflinks\ttranscript\t3377212\t3377262\t1000\t.\t.\tgene_id "CUFF.89"; transcript_id "CUFF.89.1"; FPKM "16.5671646274"; frac "1.000000"; conf_lo "0.000000"; conf_hi "39.996674"; cov "1.058824";\n+chr1\tCufflinks\texon\t3377212\t3377262\t1000\t.\t.\tgene_id "CUFF.89"; transcript_id "CUFF.89.1"; exon_number "1"; FPKM "16.5671646274"; frac "1.000000"; conf_lo "0.000000"; conf_hi "39.996674"; cov "1.058824";\n+chr1\tCufflinks\ttranscript\t3391326\t3391352\t1000\t.\t.\tgene_id "CUFF.91"; transcript_id "CUFF.91.1"; FPKM "31.2935331850"; frac "1.000000"; conf_lo "0.000000"; conf_hi "75.549272"; cov "2.000000";\n+chr1\tCufflinks\texon\t3391326\t3391352\t1000\t.\t.\tgene_id "CUFF.91"; transcript_id "CUFF.91.1"; exon_number "1"; FPKM "31.2935331850"; frac "1.000000"; conf_lo "0.000000"; conf_hi "75.549272"; cov "2.000000";\n+chr1\tCufflinks\ttranscript\t3435842\t3435880\t1000\t.\t.\tgene_id "CUFF.93"; transcript_id "CUFF.93.1"; FPKM "21.6647537435"; frac "1.000000"; conf_lo "0.000000"; conf_hi "52.303342"; cov "1.384615";\n+chr1\tCufflinks\texon\t3435842\t3435880\t1000\t.\t.\tgene_id "CUFF.93"; transcript_id "CUFF.93.1"; exon_number "1"; FPKM "21.6647537435"; frac "1.000000"; conf_lo "0.000000"; conf_hi "52.303342"; cov "1.384615";\n+chr1\tCufflinks\ttranscript\t3447762\t3447788\t1000\t.\t.\tgene_id "CUFF.95"; transcript_id "CUFF.95.1"; FPKM "46.9402997776"; frac "1.000000"; conf_lo "0.000000"; conf_hi "101.142289"; cov "3.000000";\n+chr1\tCufflinks\texon\t3447762\t3447788\t1000\t.\t.\tgene_id "CUFF.95"; transcript_id "CUFF.95.1"; exon_number "1"; FPKM "46.9402997776"; frac "1.000000"; conf_lo "0.000000"; conf_hi "101.142289"; cov "3.000000";\n+chr1\tCufflinks\ttranscript\t3450907\t3450965\t1000\t.\t.\tgene_id "CUFF.97"; transcript_id "CUFF.97.1"; FPKM "21.4811541355"; frac "1.000000"; conf_lo "0.000000"; conf_hi "46.285454"; cov "1.372881";\n+chr1\tCufflinks\texon\t3450907\t3450965\t1000\t.\t.\tgene_id "CUFF.97"; transcript_id "CUFF.97.1"; exon_number "1"; FPKM "21.4811541355"; frac "1.000000"; conf_lo "0.000000"; conf_hi "46.285454"; cov "1.372881";\n+chr1\tCufflinks\ttranscript\t3451052\t3451109\t1000\t.\t.\tgene_id "CUFF.99"; transcript_id "CUFF.99.1"; FPKM "14.5676792413"; frac "1.000000"; conf_lo "0.000000"; conf_hi "35.169489"; cov "0.931034";\n+chr1\tCufflinks\texon\t3451052\t3451109\t1000\t.\t.\tgene_id "CUFF.99"; transcript_id "CUFF.99.1"; exon_number "1"; FPKM "14.5676792413"; frac "1.000000"; conf_lo "0.000000"; conf_hi "35.169489"; cov "0.931034";\n'
b
diff -r 000000000000 -r dbbd37e013aa test-data/cuffcompare_in2.gtf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cuffcompare_in2.gtf Tue Oct 01 12:57:24 2013 -0400
b
b'@@ -0,0 +1,100 @@\n+chr1\tCufflinks\ttranscript\t3174766\t3174792\t1000\t.\t.\tgene_id "CUFF.1"; transcript_id "CUFF.1.1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\texon\t3174766\t3174792\t1000\t.\t.\tgene_id "CUFF.1"; transcript_id "CUFF.1.1"; exon_number "1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\ttranscript\t3187402\t3187428\t1000\t.\t.\tgene_id "CUFF.3"; transcript_id "CUFF.3.1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\texon\t3187402\t3187428\t1000\t.\t.\tgene_id "CUFF.3"; transcript_id "CUFF.3.1"; exon_number "1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\ttranscript\t3188522\t3188548\t1000\t.\t.\tgene_id "CUFF.5"; transcript_id "CUFF.5.1"; FPKM "21.2266273824"; frac "1.000000"; conf_lo "0.000000"; conf_hi "59.889707"; cov "1.205672";\n+chr1\tCufflinks\texon\t3188522\t3188548\t1000\t.\t.\tgene_id "CUFF.5"; transcript_id "CUFF.5.1"; exon_number "1"; FPKM "21.2266273824"; frac "1.000000"; conf_lo "0.000000"; conf_hi "59.889707"; cov "1.205672";\n+chr1\tCufflinks\ttranscript\t3190859\t3191434\t1000\t.\t.\tgene_id "CUFF.7"; transcript_id "CUFF.7.1"; FPKM "29.7095235531"; frac "1.000000"; conf_lo "19.806349"; conf_hi "39.612698"; cov "1.687500";\n+chr1\tCufflinks\texon\t3190859\t3191434\t1000\t.\t.\tgene_id "CUFF.7"; transcript_id "CUFF.7.1"; exon_number "1"; FPKM "29.7095235531"; frac "1.000000"; conf_lo "19.806349"; conf_hi "39.612698"; cov "1.687500";\n+chr1\tCufflinks\ttranscript\t3191513\t3192077\t1000\t.\t.\tgene_id "CUFF.9"; transcript_id "CUFF.9.1"; FPKM "34.0729325807"; frac "1.000000"; conf_lo "23.364686"; conf_hi "44.781179"; cov "1.935341";\n+chr1\tCufflinks\texon\t3191513\t3192077\t1000\t.\t.\tgene_id "CUFF.9"; transcript_id "CUFF.9.1"; exon_number "1"; FPKM "34.0729325807"; frac "1.000000"; conf_lo "23.364686"; conf_hi "44.781179"; cov "1.935341";\n+chr1\tCufflinks\ttranscript\t3189811\t3190789\t1000\t.\t.\tgene_id "CUFF.11"; transcript_id "CUFF.11.1"; FPKM "32.5317765567"; frac "1.000000"; conf_lo "24.582998"; conf_hi "40.480555"; cov "1.847804";\n+chr1\tCufflinks\texon\t3189811\t3190789\t1000\t.\t.\tgene_id "CUFF.11"; transcript_id "CUFF.11.1"; exon_number "1"; FPKM "32.5317765567"; frac "1.000000"; conf_lo "24.582998"; conf_hi "40.480555"; cov "1.847804";\n+chr1\tCufflinks\ttranscript\t3192251\t3192336\t1000\t.\t.\tgene_id "CUFF.13"; transcript_id "CUFF.13.1"; FPKM "16.5820596576"; frac "1.000000"; conf_lo "0.000000"; conf_hi "35.729373"; cov "0.941860";\n+chr1\tCufflinks\texon\t3192251\t3192336\t1000\t.\t.\tgene_id "CUFF.13"; transcript_id "CUFF.13.1"; exon_number "1"; FPKM "16.5820596576"; frac "1.000000"; conf_lo "0.000000"; conf_hi "35.729373"; cov "0.941860";\n+chr1\tCufflinks\ttranscript\t3192650\t3192676\t1000\t.\t.\tgene_id "CUFF.15"; transcript_id "CUFF.15.1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\texon\t3192650\t3192676\t1000\t.\t.\tgene_id "CUFF.15"; transcript_id "CUFF.15.1"; exon_number "1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\ttranscript\t3194707\t3194733\t1000\t.\t.\tgene_id "CUFF.17"; transcript_id "CUFF.17.1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\texon\t3194707\t3194733\t1000\t.\t.\tgene_id "CUFF.17"; transcript_id "CUFF.17.1"; exon_number "1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\ttranscript\t3197426\t3197452\t1000\t.\t.\tgene_id "CUFF.19"; transcript_id "CUFF.19.1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\texon\t3197426\t3197452\t1000\t.\t.\tgene_id "CUFF.19"; transcript_id "CUFF.19.1"; exon_number "1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1'..b'760563";\n+chr1\tCufflinks\ttranscript\t3355908\t3356119\t1000\t.\t.\tgene_id "CUFF.81"; transcript_id "CUFF.81.1"; FPKM "11.2111409634"; frac "1.000000"; conf_lo "1.183592"; conf_hi "21.238690"; cov "0.636792";\n+chr1\tCufflinks\texon\t3355908\t3356119\t1000\t.\t.\tgene_id "CUFF.81"; transcript_id "CUFF.81.1"; exon_number "1"; FPKM "11.2111409634"; frac "1.000000"; conf_lo "1.183592"; conf_hi "21.238690"; cov "0.636792";\n+chr1\tCufflinks\ttranscript\t3356181\t3356225\t1000\t.\t.\tgene_id "CUFF.83"; transcript_id "CUFF.83.1"; FPKM "21.1267723045"; frac "1.000000"; conf_lo "0.000000"; conf_hi "51.004540"; cov "1.200000";\n+chr1\tCufflinks\texon\t3356181\t3356225\t1000\t.\t.\tgene_id "CUFF.83"; transcript_id "CUFF.83.1"; exon_number "1"; FPKM "21.1267723045"; frac "1.000000"; conf_lo "0.000000"; conf_hi "51.004540"; cov "1.200000";\n+chr1\tCufflinks\ttranscript\t3363077\t3363176\t1000\t.\t.\tgene_id "CUFF.85"; transcript_id "CUFF.85.1"; FPKM "19.0140950740"; frac "1.000000"; conf_lo "0.000000"; conf_hi "38.028190"; cov "1.080000";\n+chr1\tCufflinks\texon\t3363077\t3363176\t1000\t.\t.\tgene_id "CUFF.85"; transcript_id "CUFF.85.1"; exon_number "1"; FPKM "19.0140950740"; frac "1.000000"; conf_lo "0.000000"; conf_hi "38.028190"; cov "1.080000";\n+chr1\tCufflinks\ttranscript\t3363388\t3363446\t1000\t.\t.\tgene_id "CUFF.87"; transcript_id "CUFF.87.1"; FPKM "24.1704598398"; frac "1.000000"; conf_lo "0.000000"; conf_hi "52.080103"; cov "1.372881";\n+chr1\tCufflinks\texon\t3363388\t3363446\t1000\t.\t.\tgene_id "CUFF.87"; transcript_id "CUFF.87.1"; exon_number "1"; FPKM "24.1704598398"; frac "1.000000"; conf_lo "0.000000"; conf_hi "52.080103"; cov "1.372881";\n+chr1\tCufflinks\ttranscript\t3364872\t3364919\t1000\t.\t.\tgene_id "CUFF.89"; transcript_id "CUFF.89.1"; FPKM "29.7095235531"; frac "1.000000"; conf_lo "0.000000"; conf_hi "64.015126"; cov "1.687500";\n+chr1\tCufflinks\texon\t3364872\t3364919\t1000\t.\t.\tgene_id "CUFF.89"; transcript_id "CUFF.89.1"; exon_number "1"; FPKM "29.7095235531"; frac "1.000000"; conf_lo "0.000000"; conf_hi "64.015126"; cov "1.687500";\n+chr1\tCufflinks\ttranscript\t3367211\t3367237\t1000\t.\t.\tgene_id "CUFF.91"; transcript_id "CUFF.91.1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\texon\t3367211\t3367237\t1000\t.\t.\tgene_id "CUFF.91"; transcript_id "CUFF.91.1"; exon_number "1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\ttranscript\t3369581\t3369607\t1000\t.\t.\tgene_id "CUFF.93"; transcript_id "CUFF.93.1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\texon\t3369581\t3369607\t1000\t.\t.\tgene_id "CUFF.93"; transcript_id "CUFF.93.1"; exon_number "1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\ttranscript\t3375002\t3375028\t1000\t.\t.\tgene_id "CUFF.95"; transcript_id "CUFF.95.1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\texon\t3375002\t3375028\t1000\t.\t.\tgene_id "CUFF.95"; transcript_id "CUFF.95.1"; exon_number "1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\ttranscript\t3379889\t3379915\t1000\t.\t.\tgene_id "CUFF.97"; transcript_id "CUFF.97.1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\texon\t3379889\t3379915\t1000\t.\t.\tgene_id "CUFF.97"; transcript_id "CUFF.97.1"; exon_number "1"; FPKM "35.2112871741"; frac "1.000000"; conf_lo "0.000000"; conf_hi "85.007567"; cov "2.000000";\n+chr1\tCufflinks\ttranscript\t3386740\t3386836\t1000\t.\t.\tgene_id "CUFF.99"; transcript_id "CUFF.99.1"; FPKM "19.6021598701"; frac "1.000000"; conf_lo "0.000000"; conf_hi "39.204320"; cov "1.113402";\n+chr1\tCufflinks\texon\t3386740\t3386836\t1000\t.\t.\tgene_id "CUFF.99"; transcript_id "CUFF.99.1"; exon_number "1"; FPKM "19.6021598701"; frac "1.000000"; conf_lo "0.000000"; conf_hi "39.204320"; cov "1.113402";\n'
b
diff -r 000000000000 -r dbbd37e013aa test-data/cuffcompare_in3.gtf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cuffcompare_in3.gtf Tue Oct 01 12:57:24 2013 -0400
b
b'@@ -0,0 +1,100 @@\n+chr1\tmm9_refFlat\tstop_codon\t3206103\t3206105\t0.000000\t-\t.\tgene_id "Xkr4"; transcript_id "Xkr4"; \n+chr1\tmm9_refFlat\tCDS\t3206106\t3207049\t0.000000\t-\t2\tgene_id "Xkr4"; transcript_id "Xkr4"; \n+chr1\tmm9_refFlat\texon\t3204563\t3207049\t0.000000\t-\t.\tgene_id "Xkr4"; transcript_id "Xkr4"; \n+chr1\tmm9_refFlat\tCDS\t3411783\t3411982\t0.000000\t-\t1\tgene_id "Xkr4"; transcript_id "Xkr4"; \n+chr1\tmm9_refFlat\texon\t3411783\t3411982\t0.000000\t-\t.\tgene_id "Xkr4"; transcript_id "Xkr4"; \n+chr1\tmm9_refFlat\tCDS\t3660633\t3661429\t0.000000\t-\t0\tgene_id "Xkr4"; transcript_id "Xkr4"; \n+chr1\tmm9_refFlat\tstart_codon\t3661427\t3661429\t0.000000\t-\t.\tgene_id "Xkr4"; transcript_id "Xkr4"; \n+chr1\tmm9_refFlat\texon\t3660633\t3661579\t0.000000\t-\t.\tgene_id "Xkr4"; transcript_id "Xkr4"; \n+chr1\tmm9_refFlat\tstop_codon\t4334681\t4334683\t0.000000\t-\t.\tgene_id "Rp1"; transcript_id "Rp1"; \n+chr1\tmm9_refFlat\tCDS\t4334684\t4340172\t0.000000\t-\t2\tgene_id "Rp1"; transcript_id "Rp1"; \n+chr1\tmm9_refFlat\texon\t4334224\t4340172\t0.000000\t-\t.\tgene_id "Rp1"; transcript_id "Rp1"; \n+chr1\tmm9_refFlat\tCDS\t4341991\t4342162\t0.000000\t-\t0\tgene_id "Rp1"; transcript_id "Rp1"; \n+chr1\tmm9_refFlat\texon\t4341991\t4342162\t0.000000\t-\t.\tgene_id "Rp1"; transcript_id "Rp1"; \n+chr1\tmm9_refFlat\tCDS\t4342283\t4342906\t0.000000\t-\t0\tgene_id "Rp1"; transcript_id "Rp1"; \n+chr1\tmm9_refFlat\tstart_codon\t4342904\t4342906\t0.000000\t-\t.\tgene_id "Rp1"; transcript_id "Rp1"; \n+chr1\tmm9_refFlat\texon\t4342283\t4342918\t0.000000\t-\t.\tgene_id "Rp1"; transcript_id "Rp1"; \n+chr1\tmm9_refFlat\texon\t4350281\t4350473\t0.000000\t-\t.\tgene_id "Rp1"; transcript_id "Rp1"; \n+chr1\tmm9_refFlat\tstop_codon\t4481797\t4481799\t0.000000\t-\t.\tgene_id "Sox17"; transcript_id "Sox17"; \n+chr1\tmm9_refFlat\tCDS\t4481800\t4482749\t0.000000\t-\t2\tgene_id "Sox17"; transcript_id "Sox17"; \n+chr1\tmm9_refFlat\texon\t4481009\t4482749\t0.000000\t-\t.\tgene_id "Sox17"; transcript_id "Sox17"; \n+chr1\tmm9_refFlat\tCDS\t4483181\t4483487\t0.000000\t-\t0\tgene_id "Sox17"; transcript_id "Sox17"; \n+chr1\tmm9_refFlat\tstart_codon\t4483485\t4483487\t0.000000\t-\t.\tgene_id "Sox17"; transcript_id "Sox17"; \n+chr1\tmm9_refFlat\texon\t4483181\t4483547\t0.000000\t-\t.\tgene_id "Sox17"; transcript_id "Sox17"; \n+chr1\tmm9_refFlat\texon\t4483853\t4483944\t0.000000\t-\t.\tgene_id "Sox17"; transcript_id "Sox17"; \n+chr1\tmm9_refFlat\texon\t4485217\t4486023\t0.000000\t-\t.\tgene_id "Sox17"; transcript_id "Sox17"; \n+chr1\tmm9_refFlat\texon\t4486372\t4486494\t0.000000\t-\t.\tgene_id "Sox17"; transcript_id "Sox17"; \n+chr1\tmm9_refFlat\tstop_codon\t4766545\t4766547\t0.000000\t-\t.\tgene_id "Mrpl15"; transcript_id "Mrpl15"; \n+chr1\tmm9_refFlat\tCDS\t4766548\t4766882\t0.000000\t-\t2\tgene_id "Mrpl15"; transcript_id "Mrpl15"; \n+chr1\tmm9_refFlat\texon\t4763279\t4766882\t0.000000\t-\t.\tgene_id "Mrpl15"; transcript_id "Mrpl15"; \n+chr1\tmm9_refFlat\tCDS\t4767606\t4767729\t0.000000\t-\t0\tgene_id "Mrpl15"; transcript_id "Mrpl15"; \n+chr1\tmm9_refFlat\texon\t4767606\t4767729\t0.000000\t-\t.\tgene_id "Mrpl15"; transcript_id "Mrpl15"; \n+chr1\tmm9_refFlat\tCDS\t4772649\t4772814\t0.000000\t-\t1\tgene_id "Mrpl15"; transcript_id "Mrpl15"; \n+chr1\tmm9_refFlat\texon\t4772649\t4772814\t0.000000\t-\t.\tgene_id "Mrpl15"; transcript_id "Mrpl15"; \n+chr1\tmm9_refFlat\tCDS\t4774032\t4774186\t0.000000\t-\t0\tgene_id "Mrpl15"; transcript_id "Mrpl15"; \n+chr1\tmm9_refFlat\texon\t4774032\t4774186\t0.000000\t-\t.\tgene_id "Mrpl15"; transcript_id "Mrpl15"; \n+chr1\tmm9_refFlat\tCDS\t4775654\t4775758\t0.000000\t-\t0\tgene_id "Mrpl15"; transcript_id "Mrpl15"; \n+chr1\tmm9_refFlat\tstart_codon\t4775756\t4775758\t0.000000\t-\t.\tgene_id "Mrpl15"; transcript_id "Mrpl15"; \n+chr1\tmm9_refFlat\texon\t4775654\t4775807\t0.000000\t-\t.\tgene_id "Mrpl15"; transcript_id "Mrpl15"; \n+chr1\tmm9_refFlat\tstop_codon\t4764533\t4764535\t0.000000\t-\t.\tgene_id "Mrpl15"; transcript_id "Mrpl15_dup1"; \n+chr1\tmm9_refFlat\tCDS\t4764536\t4764597\t0.000000\t-\t2\tgene_id "Mrpl15"; transcript_id "Mrpl15_dup1"; \n+chr1\tmm9_refFlat\texon\t4763279\t4764597\t0.000000\t-\t.\tgene_id "Mrpl15"; transcript_id "Mrpl15_dup1"; \n+chr1\tmm9_refFlat\tCDS\t4767606\t4767729\t0.000000\t-\t0\tgene_id "Mrpl15"; transcript_id "Mrpl15_dup1"; \n+chr1\tmm9_refFlat\texon\t4767606\t4'..b'Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\texon\t4798536\t4798567\t0.000000\t+\t.\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\tCDS\t4818665\t4818730\t0.000000\t+\t1\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\texon\t4818665\t4818730\t0.000000\t+\t.\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\tCDS\t4820349\t4820396\t0.000000\t+\t1\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\texon\t4820349\t4820396\t0.000000\t+\t.\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\tCDS\t4822392\t4822462\t0.000000\t+\t1\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\texon\t4822392\t4822462\t0.000000\t+\t.\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\tCDS\t4827082\t4827155\t0.000000\t+\t2\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\texon\t4827082\t4827155\t0.000000\t+\t.\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\tCDS\t4829468\t4829569\t0.000000\t+\t0\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\texon\t4829468\t4829569\t0.000000\t+\t.\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\tCDS\t4831037\t4831213\t0.000000\t+\t0\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\texon\t4831037\t4831213\t0.000000\t+\t.\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\tCDS\t4835044\t4835094\t0.000000\t+\t0\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\tstop_codon\t4835095\t4835097\t0.000000\t+\t.\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\texon\t4835044\t4836816\t0.000000\t+\t.\tgene_id "Lypla1"; transcript_id "Lypla1"; \n+chr1\tmm9_refFlat\tstart_codon\t4847995\t4847997\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\tCDS\t4847995\t4848057\t0.000000\t+\t0\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\texon\t4847775\t4848057\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\tCDS\t4857551\t4857613\t0.000000\t+\t0\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\texon\t4857551\t4857613\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\tCDS\t4868108\t4868213\t0.000000\t+\t0\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\texon\t4868108\t4868213\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\tCDS\t4876825\t4876912\t0.000000\t+\t2\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\texon\t4876825\t4876912\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\tCDS\t4879538\t4879683\t0.000000\t+\t1\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\texon\t4879538\t4879683\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\tCDS\t4880821\t4880877\t0.000000\t+\t2\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\texon\t4880821\t4880877\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\tCDS\t4881996\t4882150\t0.000000\t+\t2\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\texon\t4881996\t4882150\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\tCDS\t4883498\t4883644\t0.000000\t+\t0\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\texon\t4883498\t4883644\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\tCDS\t4885015\t4885086\t0.000000\t+\t0\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\texon\t4885015\t4885086\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\tCDS\t4886437\t4886442\t0.000000\t+\t0\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\tstop_codon\t4886443\t4886445\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\texon\t4886437\t4887987\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1"; \n+chr1\tmm9_refFlat\tstart_codon\t4847995\t4847997\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1_dup1"; \n+chr1\tmm9_refFlat\tCDS\t4847995\t4848057\t0.000000\t+\t0\tgene_id "Tcea1"; transcript_id "Tcea1_dup1"; \n+chr1\tmm9_refFlat\texon\t4847775\t4848057\t0.000000\t+\t.\tgene_id "Tcea1"; transcript_id "Tcea1_dup1"; \n+chr1\tmm9_refFlat\tCDS\t4857551\t4857613\t0.000000\t+\t0\tgene_id "Tcea1"; transcript_id "Tcea1_dup1"; \n'
b
diff -r 000000000000 -r dbbd37e013aa test-data/cuffmerge_out1.gtf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cuffmerge_out1.gtf Tue Oct 01 12:57:24 2013 -0400
b
b'@@ -0,0 +1,74 @@\n+chr1\tCufflinks\texon\t4797974\t4798063\t.\t+\t.\tgene_id "XLOC_000001"; transcript_id "TCONS_00000001"; exon_number "1"; gene_name "Lypla1"; oId "Lypla1"; nearest_ref "Lypla1"; class_code "="; tss_id "TSS1";\n+chr1\tCufflinks\texon\t4798536\t4798567\t.\t+\t.\tgene_id "XLOC_000001"; transcript_id "TCONS_00000001"; exon_number "2"; gene_name "Lypla1"; oId "Lypla1"; nearest_ref "Lypla1"; class_code "="; tss_id "TSS1";\n+chr1\tCufflinks\texon\t4818665\t4818730\t.\t+\t.\tgene_id "XLOC_000001"; transcript_id "TCONS_00000001"; exon_number "3"; gene_name "Lypla1"; oId "Lypla1"; nearest_ref "Lypla1"; class_code "="; tss_id "TSS1";\n+chr1\tCufflinks\texon\t4820349\t4820396\t.\t+\t.\tgene_id "XLOC_000001"; transcript_id "TCONS_00000001"; exon_number "4"; gene_name "Lypla1"; oId "Lypla1"; nearest_ref "Lypla1"; class_code "="; tss_id "TSS1";\n+chr1\tCufflinks\texon\t4822392\t4822462\t.\t+\t.\tgene_id "XLOC_000001"; transcript_id "TCONS_00000001"; exon_number "5"; gene_name "Lypla1"; oId "Lypla1"; nearest_ref "Lypla1"; class_code "="; tss_id "TSS1";\n+chr1\tCufflinks\texon\t4827082\t4827155\t.\t+\t.\tgene_id "XLOC_000001"; transcript_id "TCONS_00000001"; exon_number "6"; gene_name "Lypla1"; oId "Lypla1"; nearest_ref "Lypla1"; class_code "="; tss_id "TSS1";\n+chr1\tCufflinks\texon\t4829468\t4829569\t.\t+\t.\tgene_id "XLOC_000001"; transcript_id "TCONS_00000001"; exon_number "7"; gene_name "Lypla1"; oId "Lypla1"; nearest_ref "Lypla1"; class_code "="; tss_id "TSS1";\n+chr1\tCufflinks\texon\t4831037\t4831213\t.\t+\t.\tgene_id "XLOC_000001"; transcript_id "TCONS_00000001"; exon_number "8"; gene_name "Lypla1"; oId "Lypla1"; nearest_ref "Lypla1"; class_code "="; tss_id "TSS1";\n+chr1\tCufflinks\texon\t4835044\t4836816\t.\t+\t.\tgene_id "XLOC_000001"; transcript_id "TCONS_00000001"; exon_number "9"; gene_name "Lypla1"; oId "Lypla1"; nearest_ref "Lypla1"; class_code "="; tss_id "TSS1";\n+chr1\tCufflinks\texon\t4847775\t4848057\t.\t+\t.\tgene_id "XLOC_000002"; transcript_id "TCONS_00000002"; exon_number "1"; gene_name "Tcea1"; oId "Tcea1_dup1"; contained_in "TCONS_00000003"; nearest_ref "Tcea1_dup1"; class_code "="; tss_id "TSS2";\n+chr1\tCufflinks\texon\t4857551\t4857613\t.\t+\t.\tgene_id "XLOC_000002"; transcript_id "TCONS_00000002"; exon_number "2"; gene_name "Tcea1"; oId "Tcea1_dup1"; contained_in "TCONS_00000003"; nearest_ref "Tcea1_dup1"; class_code "="; tss_id "TSS2";\n+chr1\tCufflinks\texon\t4847775\t4848057\t.\t+\t.\tgene_id "XLOC_000002"; transcript_id "TCONS_00000003"; exon_number "1"; gene_name "Tcea1"; oId "Tcea1"; nearest_ref "Tcea1"; class_code "="; tss_id "TSS2";\n+chr1\tCufflinks\texon\t4857551\t4857613\t.\t+\t.\tgene_id "XLOC_000002"; transcript_id "TCONS_00000003"; exon_number "2"; gene_name "Tcea1"; oId "Tcea1"; nearest_ref "Tcea1"; class_code "="; tss_id "TSS2";\n+chr1\tCufflinks\texon\t4868108\t4868213\t.\t+\t.\tgene_id "XLOC_000002"; transcript_id "TCONS_00000003"; exon_number "3"; gene_name "Tcea1"; oId "Tcea1"; nearest_ref "Tcea1"; class_code "="; tss_id "TSS2";\n+chr1\tCufflinks\texon\t4876825\t4876912\t.\t+\t.\tgene_id "XLOC_000002"; transcript_id "TCONS_00000003"; exon_number "4"; gene_name "Tcea1"; oId "Tcea1"; nearest_ref "Tcea1"; class_code "="; tss_id "TSS2";\n+chr1\tCufflinks\texon\t4879538\t4879683\t.\t+\t.\tgene_id "XLOC_000002"; transcript_id "TCONS_00000003"; exon_number "5"; gene_name "Tcea1"; oId "Tcea1"; nearest_ref "Tcea1"; class_code "="; tss_id "TSS2";\n+chr1\tCufflinks\texon\t4880821\t4880877\t.\t+\t.\tgene_id "XLOC_000002"; transcript_id "TCONS_00000003"; exon_number "6"; gene_name "Tcea1"; oId "Tcea1"; nearest_ref "Tcea1"; class_code "="; tss_id "TSS2";\n+chr1\tCufflinks\texon\t4881996\t4882150\t.\t+\t.\tgene_id "XLOC_000002"; transcript_id "TCONS_00000003"; exon_number "7"; gene_name "Tcea1"; oId "Tcea1"; nearest_ref "Tcea1"; class_code "="; tss_id "TSS2";\n+chr1\tCufflinks\texon\t4883498\t4883644\t.\t+\t.\tgene_id "XLOC_000002"; transcript_id "TCONS_00000003"; exon_number "8"; gene_name "Tcea1"; oId "Tcea1"; nearest_ref "Tcea1"; class_code "="; tss_id "TSS2";\n+chr1\tCufflinks\texon\t4885015\t4885086\t.\t+\t.\tgene_id "XLOC_000002"; transcript_id "TCONS_00000'..b'12"; exon_number "1"; oId "CUFF.3.1"; class_code "u"; tss_id "TSS9";\n+chr1\tCufflinks\texon\t3187402\t3187428\t.\t.\t.\tgene_id "XLOC_000010"; transcript_id "TCONS_00000013"; exon_number "1"; oId "CUFF.4.1"; class_code "u"; tss_id "TSS10";\n+chr1\tCufflinks\texon\t3188522\t3188548\t.\t.\t.\tgene_id "XLOC_000011"; transcript_id "TCONS_00000014"; exon_number "1"; oId "CUFF.5.1"; class_code "u"; tss_id "TSS11";\n+chr1\tCufflinks\texon\t3189811\t3190789\t.\t.\t.\tgene_id "XLOC_000012"; transcript_id "TCONS_00000015"; exon_number "1"; oId "CUFF.6.1"; class_code "u"; tss_id "TSS12";\n+chr1\tCufflinks\texon\t3190859\t3191434\t.\t.\t.\tgene_id "XLOC_000013"; transcript_id "TCONS_00000016"; exon_number "1"; oId "CUFF.7.1"; class_code "u"; tss_id "TSS13";\n+chr1\tCufflinks\texon\t3191513\t3192077\t.\t.\t.\tgene_id "XLOC_000014"; transcript_id "TCONS_00000017"; exon_number "1"; oId "CUFF.8.1"; class_code "u"; tss_id "TSS14";\n+chr1\tCufflinks\texon\t3192251\t3192336\t.\t.\t.\tgene_id "XLOC_000015"; transcript_id "TCONS_00000018"; exon_number "1"; oId "CUFF.9.1"; class_code "u"; tss_id "TSS15";\n+chr1\tCufflinks\texon\t3192442\t3192494\t.\t.\t.\tgene_id "XLOC_000016"; transcript_id "TCONS_00000019"; exon_number "1"; oId "CUFF.10.1"; class_code "u"; tss_id "TSS16";\n+chr1\tCufflinks\texon\t3192551\t3192676\t.\t.\t.\tgene_id "XLOC_000017"; transcript_id "TCONS_00000020"; exon_number "1"; oId "CUFF.11.1"; class_code "u"; tss_id "TSS17";\n+chr1\tCufflinks\texon\t3192732\t3192811\t.\t.\t.\tgene_id "XLOC_000018"; transcript_id "TCONS_00000021"; exon_number "1"; oId "CUFF.12.1"; class_code "u"; tss_id "TSS18";\n+chr1\tCufflinks\texon\t3192941\t3193042\t.\t.\t.\tgene_id "XLOC_000019"; transcript_id "TCONS_00000022"; exon_number "1"; oId "CUFF.13.1"; class_code "u"; tss_id "TSS19";\n+chr1\tCufflinks\texon\t3194186\t3194226\t.\t.\t.\tgene_id "XLOC_000020"; transcript_id "TCONS_00000023"; exon_number "1"; oId "CUFF.14.1"; class_code "u"; tss_id "TSS20";\n+chr1\tCufflinks\texon\t3194303\t3194329\t.\t.\t.\tgene_id "XLOC_000021"; transcript_id "TCONS_00000024"; exon_number "1"; oId "CUFF.15.1"; class_code "u"; tss_id "TSS21";\n+chr1\tCufflinks\texon\t3194707\t3194733\t.\t.\t.\tgene_id "XLOC_000022"; transcript_id "TCONS_00000025"; exon_number "1"; oId "CUFF.16.1"; class_code "u"; tss_id "TSS22";\n+chr1\tCufflinks\texon\t3195084\t3195110\t.\t.\t.\tgene_id "XLOC_000023"; transcript_id "TCONS_00000026"; exon_number "1"; oId "CUFF.17.1"; class_code "u"; tss_id "TSS23";\n+chr1\tCufflinks\texon\t3195451\t3195477\t.\t.\t.\tgene_id "XLOC_000024"; transcript_id "TCONS_00000027"; exon_number "1"; oId "CUFF.18.1"; class_code "u"; tss_id "TSS24";\n+chr1\tCufflinks\texon\t3197090\t3197116\t.\t.\t.\tgene_id "XLOC_000025"; transcript_id "TCONS_00000028"; exon_number "1"; oId "CUFF.19.1"; class_code "u"; tss_id "TSS25";\n+chr1\tCufflinks\texon\t3197247\t3197273\t.\t.\t.\tgene_id "XLOC_000026"; transcript_id "TCONS_00000029"; exon_number "1"; oId "CUFF.20.1"; class_code "u"; tss_id "TSS26";\n+chr1\tCufflinks\texon\t3197347\t3197373\t.\t.\t.\tgene_id "XLOC_000027"; transcript_id "TCONS_00000030"; exon_number "1"; oId "CUFF.21.1"; class_code "u"; tss_id "TSS27";\n+chr1\tCufflinks\texon\t3197426\t3197452\t.\t.\t.\tgene_id "XLOC_000028"; transcript_id "TCONS_00000031"; exon_number "1"; oId "CUFF.22.1"; class_code "u"; tss_id "TSS28";\n+chr1\tCufflinks\texon\t3200023\t3200191\t.\t.\t.\tgene_id "XLOC_000029"; transcript_id "TCONS_00000032"; exon_number "1"; oId "CUFF.23.1"; class_code "u"; tss_id "TSS29";\n+chr1\tCufflinks\texon\t3200326\t3200352\t.\t.\t.\tgene_id "XLOC_000030"; transcript_id "TCONS_00000033"; exon_number "1"; oId "CUFF.24.1"; class_code "u"; tss_id "TSS30";\n+chr1\tCufflinks\texon\t3200431\t3200457\t.\t.\t.\tgene_id "XLOC_000031"; transcript_id "TCONS_00000034"; exon_number "1"; oId "CUFF.25.1"; class_code "u"; tss_id "TSS31";\n+chr1\tCufflinks\texon\t3201008\t3201481\t.\t.\t.\tgene_id "XLOC_000032"; transcript_id "TCONS_00000035"; exon_number "1"; oId "CUFF.26.1"; class_code "u"; tss_id "TSS32";\n+chr1\tCufflinks\texon\t3201597\t3201809\t.\t.\t.\tgene_id "XLOC_000033"; transcript_id "TCONS_00000036"; exon_number "1"; oId "CUFF.27.1"; class_code "u"; tss_id "TSS33";\n'
b
diff -r 000000000000 -r dbbd37e013aa tool_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml Tue Oct 01 12:57:24 2013 -0400
b
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="cufflinks" version="2.1.1">
+        <repository changeset_revision="394b13717223" name="package_cufflinks_2_1_1" owner="devteam" toolshed="http://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>