Mercurial > repos > iuc > stringtie

changeset 5:8836aad67a33 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author iuc
date Tue, 28 Apr 2015 22:56:45 -0400
parents c5fe1886445a
children ee1d80e5c45f
files stringtie.xml test-data/._stringtie_in1.bam test-data/._stringtie_out2.gtf test-data/ballgown/e2t.ctab test-data/ballgown/e_data.ctab test-data/ballgown/i2t.ctab test-data/ballgown/i_data.ctab test-data/ballgown/t_data.ctab test-data/stringtie_in.gtf test-data/stringtie_in1.bam test-data/stringtie_out1.gtf test-data/stringtie_out2.gtf test-data/stringtie_out3.gtf test-data/stringtie_out4.gtf test-data/stringtie_out5.gtf test-data/stringtie_out_coverage.gtf tool_dependencies.xml
diffstat 17 files changed, 218 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/stringtie.xml	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,168 @@
+<tool id="stringtie" name="StringTie" version="1.0.1">
+    <description>RNA-Seq assembler</description>
+    <requirements>
+        <requirement type="package" version="1.0.1">stringtie</requirement>
+    </requirements>
+    <command><![CDATA[
+stringtie "$input_bam"
+-o "$output_gtf"
+-p "\${GALAXY_SLOTS:-1}"
+#if str($guide.use_guide) == 'yes':
+    -C "$coverage" -G "$guide.guide_gff" $guide.input_estimation
+    #if str($guide.output_ballgown) == '-b':
+        $guide.output_ballgown `pwd`
+    #end if
+#end if
+#if str($option_set.options) == 'advanced':
+    -l "$option_set.name_prefix"
+    -f "$option_set.fraction"
+    -m "$option_set.min_tlen"
+    -a "$option_set.min_anchor_len"
+    -j "$option_set.min_anchor_cov"
+    -c "$option_set.min_bundle_cov"
+    -s "$option_set.maxcov"
+    -g "$option_set.bdist"    
+    -M "$option_set.bundle_fraction" $option_set.sensitive $option_set.disable_trimming
+#end if
+]]>
+</command>
+    <inputs>
+        <param format="bam" label="BAM file to assemble" name="input_bam" type="data" />
+        <conditional name="guide">
+            <param label="Use GFF file to guide assembly" name="use_guide" type="select">
+                <option value="yes">Use GFF</option>
+                <option selected="True" value="no">Do not use GFF</option>
+            </param>
+            <when value="no" />
+            <when value="yes">
+                <param format="gtf,gff3" help="(-G)" label="Reference annotation to use for guiding the assembly process" name="guide_gff" type="data" />
+                <param falsevalue="" help="(-e)" label="Perform abundance estimation only of input transcripts" name="input_estimation" truevalue="-e" type="boolean" />
+                <param falsevalue="" help="(-b)" label="Output additional files for use in Ballgown" name="output_ballgown" truevalue="-b" type="boolean" />
+            </when>
+        </conditional>
+        <conditional name="option_set">
+            <param label="Options" name="options" type="select">
+                <option selected="True" value="default">Use defaults</option>
+                <option value="advanced">Specify advanced options</option>
+            </param>
+            <when value="default" />
+            <when value="advanced">
+                <param falsevalue="" help="(-t)" label="Disable trimming of predicted transcripts based on coverage" name="disable_trimming" truevalue="-t" type="boolean" />
+                <param falsevalue="" help="(-S)" label="Increase sensitivity" name="sensitive" truevalue="-S" type="boolean" />
+                <param help="(-l)" label="Name prefix for output transcripts" name="name_prefix" type="text" value="STRG" />
+                <param help="(-f)" label="Minimum isoform fraction" max="1.0" min="0.0" name="fraction" type="float" value="0.15" />
+                <param help="(-m)" label="Minimum assembled transcript length" name="min_tlen" type="integer" value="200" />
+                <param help="(-a)" label="Minimum anchor length for junctions" name="min_anchor_len" type="integer" value="10" />
+                <param help="(-j)" label="Minimum junction coverage" name="min_anchor_cov" type="integer" value="1" />
+                <param help="(-c)" label="Minimum bundle reads per bp coverage to consider for assembly" name="min_bundle_cov" type="integer" value="2" />
+                <param help="(-s)" label="Coverage saturation threshold" name="maxcov" type="integer" value="1000000" />
+                <param help="(-g)" label="Gap between read mappings triggering a new bundle" name="bdist" type="integer" value="50" />
+                <param help="(-M)" label="Fraction of bundle allowed to be covered by multi-hit reads" name="bundle_fraction" type="float" value="0.95" />
+            </when>
+        </conditional>
+    </inputs>
+    <outputs>
+        <data format="gtf" label="${tool.name} on ${on_string}: Assembled transcripts" name="output_gtf" />
+        <data format="gff3" label="${tool.name} on ${on_string}: Coverage" name="coverage">
+            <filter>guide['use_guide'] == "yes"</filter>
+        </data>
+        <data format="tabular" from_work_dir="e_data.ctab" label="${tool.name} on ${on_string}: exon-level expression measurements" name="exon_expression">
+            <filter>guide['output_ballgown']</filter>
+        </data>
+        <data format="tabular" from_work_dir="i_data.ctab" label="${tool.name} on ${on_string}: intron-level expression measurements" name="intron_expression">
+            <filter>guide['output_ballgown']</filter>
+        </data>
+        <data format="tabular" from_work_dir="t_data.ctab" label="${tool.name} on ${on_string}: transcript-level expression measurements" name="transcript_expression">
+            <filter>guide['output_ballgown']</filter>
+        </data>
+        <data format="tabular" from_work_dir="e2t.ctab" label="${tool.name} on ${on_string}: exon to transcript mapping" name="exon_transcript_mapping">
+            <filter>guide['output_ballgown']</filter>
+        </data>
+        <data format="tabular" from_work_dir="i2t.ctab" label="${tool.name} on ${on_string}: intron to transcript mapping" name="intron_transcript_mapping">
+            <filter>guide['output_ballgown']</filter>
+        </data>
+    </outputs>
+    <tests>
+        <test>
+            <param ftype="bam" name="input_bam" value="stringtie_in1.bam" />
+            <param name="use_guide" value="no" />
+            <param name="options" value="default" />
+            <output file="stringtie_out1.gtf" ftype="gtf" name="output_gtf" />
+        </test>
+        <test>
+            <param ftype="bam" name="input_bam" value="stringtie_in1.bam" />
+            <param name="use_guide" value="no" />
+            <param name="options" value="advanced" />
+            <param name="fraction" value="0.17" />
+            <output file="stringtie_out2.gtf" ftype="gtf" name="output_gtf" />
+        </test>
+        <test>
+            <param ftype="bam" name="input_bam" value="stringtie_in1.bam" />
+            <param name="use_guide" value="yes" />
+            <param name="guide_gff" value="stringtie_in.gtf" />
+            <param name="options" value="default" />
+            <output file="stringtie_out3.gtf" ftype="gtf" name="output_gtf" />
+        </test>
+        <test>
+            <param ftype="bam" name="input_bam" value="stringtie_in1.bam" />
+            <param name="use_guide" value="yes" />
+            <param name="guide_gff" value="stringtie_in.gtf" />
+            <param name="options" value="advanced" />
+            <param name="fraction" value="0.17" />
+            <output file="stringtie_out4.gtf" ftype="gtf" name="output_gtf" />
+        </test>
+        <test>
+            <param ftype="bam" name="input_bam" value="stringtie_in1.bam" />
+            <param name="use_guide" value="yes" />
+            <param name="output_ballgown" value="yes" />
+            <param name="guide_gff" value="stringtie_in.gtf" />
+            <param name="options" value="default" />
+            <output file="ballgown/e_data.ctab" ftype="tabular" name="exon_expression" />
+            <output file="ballgown/i_data.ctab" ftype="tabular" name="intron_expression" />
+            <output file="ballgown/t_data.ctab" ftype="tabular" name="transcript_expression" />
+            <output file="ballgown/e2t.ctab" ftype="tabular" name="exon_transcript_mapping" />
+            <output file="ballgown/i2t.ctab" ftype="tabular" name="intron_transcript_mapping" />
+            <output file="stringtie_out5.gtf" ftype="gtf" name="output_gtf" />
+            <output file="stringtie_out_coverage.gtf" ftype="gff3" name="coverage" />
+        </test>
+    </tests>
+    <help>
+<![CDATA[
+StringTie v1.0.1 usage:
+ stringtie <input.bam> [-G <guide_gff>] [-l <label>] [-o <out_gtf>] [-p <cpus>]
+  [-v] [-a <min_anchor_len>] [-m <min_tlen>] [-j <min_anchor_cov>] [-n sens]
+  [-C <coverage_file_name>] [-s <maxcov>] [-c <min_bundle_cov>] [-g <bdist>]
+  {-B | -b <dir_path>} [-e]
+
+Assemble RNA-Seq alignments into potential transcripts.
+ 
+ Options:
+ -G reference annotation to use for guiding the assembly process (GTF/GFF3)
+ -l name prefix for output transcripts (default: STRG)
+ -f minimum isoform fraction (default: 0.1)
+ -m minimum assembled transcript length to report (default 200bp)
+ -o output path/file name for the assembled transcripts GTF (default: stdout)
+ -a minimum anchor length for junctions (default: 10)
+ -j minimum junction coverage (default: 1)
+ -t disable trimming of predicted transcripts based on coverage
+    (default: coverage trimming is enabled)
+ -c minimum reads per bp coverage to consider for transcript assembly (default: 2.5)
+ -s coverage saturation threshold; further read alignments will be
+    ignored in a region where a local coverage depth of <maxcov> 
+    is reached (default: 1,000,000);
+ -v verbose (log bundle processing details)
+ -g gap between read mappings triggering a new bundle (default: 50)
+ -C output file with reference transcripts that are covered by reads
+ -M fraction of bundle allowed to be covered by multi-hit reads (default:0.95)
+ -p number of threads (CPUs) to use (default: 1)
+ -B enable output of Ballgown table files which will be created in the
+    same directory as the output GTF (requires -G, -o recommended)
+ -b enable output of Ballgown table files but these files will be 
+    created under the directory path given as <dir_path>
+ -e only estimates the abundance of given reference transcripts (requires -G)
+ ]]>
+    </help>
+    <citations>
+        <citation type="doi">doi:10.1038/nbt.3122</citation>
+    </citations>
+</tool>
Binary file test-data/._stringtie_in1.bam has changed
Binary file test-data/._stringtie_out2.gtf has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/ballgown/e2t.ctab	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,4 @@
+e_id	t_id
+1	1
+2	1
+3	1
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/ballgown/e_data.ctab	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,4 @@
+e_id	chr	strand	start	end	rcount	ucount	mrcount	cov	cov_sd	mcov	mcov_sd
+1	test_chromosome	+	53	250	154	154	154.00	49.7778	22.0747	49.7778	22.0747
+2	test_chromosome	+	351	400	73	73	73.00	54.1600	6.1753	54.1600	6.1753
+3	test_chromosome	+	501	550	38	38	38.00	21.6400	12.4350	21.6400	12.4350
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/ballgown/i2t.ctab	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,3 @@
+i_id	t_id
+1	1
+2	1
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/ballgown/i_data.ctab	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,3 @@
+i_id	chr	strand	start	end	rcount	ucount	mrcount
+1	test_chromosome	+	251	350	49	49	49.00
+2	test_chromosome	+	401	500	38	38	38.00
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/ballgown/t_data.ctab	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,2 @@
+t_id	chr	strand	start	end	t_name	num_exons	length	gene_id	gene_name	cov	FPKM
+1	test_chromosome	+	53	550	CUFF.1.1	3	298	CUFF.1	.	44.724823	3276543.750000
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/stringtie_in.gtf	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,4 @@
+test_chromosome	Cufflinks	transcript	53	550	1000	+	.	gene_id "CUFF.1"; transcript_id "CUFF.1.1"; FPKM "10679134.4063403048"; frac "1.000000"; conf_lo "8542701.791788"; conf_hi "12815567.020892"; cov "145.770185";
+test_chromosome	Cufflinks	exon	53	250	1000	+	.	gene_id "CUFF.1"; transcript_id "CUFF.1.1"; exon_number "1"; FPKM "10679134.4063403048"; frac "1.000000"; conf_lo "8542701.791788"; conf_hi "12815567.020892"; cov "145.770185";
+test_chromosome	Cufflinks	exon	351	400	1000	+	.	gene_id "CUFF.1"; transcript_id "CUFF.1.1"; exon_number "2"; FPKM "10679134.4063403048"; frac "1.000000"; conf_lo "8542701.791788"; conf_hi "12815567.020892"; cov "145.770185";
+test_chromosome	Cufflinks	exon	501	550	1000	+	.	gene_id "CUFF.1"; transcript_id "CUFF.1.1"; exon_number "3"; FPKM "10679134.4063403048"; frac "1.000000"; conf_lo "8542701.791788"; conf_hi "12815567.020892"; cov "145.770185";
Binary file test-data/stringtie_in1.bam has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/stringtie_out1.gtf	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,4 @@
+test_chromosome	StringTie	transcript	53	550	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; cov "44.724823";FPKM "3276543.750000";
+test_chromosome	StringTie	exon	53	250	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "1"; cov "49.011967";
+test_chromosome	StringTie	exon	351	400	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "2"; cov "51.382565";
+test_chromosome	StringTie	exon	501	550	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "3"; cov "21.090000";
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/stringtie_out2.gtf	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,4 @@
+test_chromosome	StringTie	transcript	53	550	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; cov "44.724823";FPKM "3276543.750000";
+test_chromosome	StringTie	exon	53	250	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "1"; cov "49.011967";
+test_chromosome	StringTie	exon	351	400	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "2"; cov "51.382565";
+test_chromosome	StringTie	exon	501	550	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "3"; cov "21.090000";
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/stringtie_out3.gtf	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,4 @@
+test_chromosome	StringTie	transcript	53	550	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; reference_id "CUFF.1.1"; cov "44.724823";FPKM "3276543.750000";
+test_chromosome	StringTie	exon	53	250	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "1"; reference_id "CUFF.1.1"; cov "49.011967";
+test_chromosome	StringTie	exon	351	400	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "2"; reference_id "CUFF.1.1"; cov "51.382565";
+test_chromosome	StringTie	exon	501	550	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "3"; reference_id "CUFF.1.1"; cov "21.090000";
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/stringtie_out4.gtf	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,4 @@
+test_chromosome	StringTie	transcript	53	550	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; reference_id "CUFF.1.1"; cov "44.724823";FPKM "3276543.750000";
+test_chromosome	StringTie	exon	53	250	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "1"; reference_id "CUFF.1.1"; cov "49.011967";
+test_chromosome	StringTie	exon	351	400	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "2"; reference_id "CUFF.1.1"; cov "51.382565";
+test_chromosome	StringTie	exon	501	550	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "3"; reference_id "CUFF.1.1"; cov "21.090000";
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/stringtie_out5.gtf	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,4 @@
+test_chromosome	StringTie	transcript	53	550	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; reference_id "CUFF.1.1"; cov "44.724823";FPKM "3276543.750000";
+test_chromosome	StringTie	exon	53	250	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "1"; reference_id "CUFF.1.1"; cov "49.011967";
+test_chromosome	StringTie	exon	351	400	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "2"; reference_id "CUFF.1.1"; cov "51.382565";
+test_chromosome	StringTie	exon	501	550	1000	+	.	gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "3"; reference_id "CUFF.1.1"; cov "21.090000";
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/stringtie_out_coverage.gtf	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,4 @@
+test_chromosome	Cufflinks	transcript	53	550	1000.00	+	.	ID=CUFF.1.1;geneID=CUFF.1
+test_chromosome	Cufflinks	exon	53	250	1000.00	+	.	Parent=CUFF.1.1
+test_chromosome	Cufflinks	exon	351	400	1000.00	+	.	Parent=CUFF.1.1
+test_chromosome	Cufflinks	exon	501	550	1000.00	+	.	Parent=CUFF.1.1
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Tue Apr 28 22:56:45 2015 -0400
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+  <package name="stringtie" version="1.0.1">
+      <repository changeset_revision="2238c6c6d46a" name="package_stringtie_1_0_1" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>