Add PsiCLASS

tools/psiclass/.shed.yml

@@ -0,0 +1,14 @@
+categories:
+- Transcriptomics
+description:  PsiCLASS is a reference-based transcriptome assembler for single or multiple RNA-seq samples. 
+homepage_url: https://github.com/splicebox/PsiCLASS
+long_description: |
+    PsiCLASS is a reference-based transcriptome assembler for single or multiple
+    RNA-seq samples. Unlik e conventional methods that analyze each sample separately
+    and then merge the outcomes to create a unified set of meta-annotations, PsiCLASS
+    takes a multi-sample approach, simultaneously analyzing all RNA-seq data sets in
+    an experiment.
+name: psiclass
+owner: iuc
+remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/master/tools/psiclass
+type: unrestricted

tools/psiclass/macros.xml

@@ -0,0 +1,17 @@
+<macros>
+    <token name="@TOOL_VERSION@">1.0.3</token>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">psiclass</requirement>
+        </requirements>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1038/s41467-019-12990-0</citation>
+        </citations>
+    </xml>
+    <xml name="version_command">
+        <version_command>psiclass --version</version_command>
+    </xml>
+</macros>

tools/psiclass/psiclass.xml

@@ -0,0 +1,151 @@
+<tool id="psiclass" name="PsiCLASS" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
+    <description>reference-based transcriptome assembler</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <xrefs>
+        <xref type="bio.tools">psiclass</xref>
+    </xrefs>
+    <expand macro="requirements" />
+    <command detect_errors='exit_code'><![CDATA[
+            mkdir -p "annotation_files" &&
+            #set $bam_filenames = []
+            #for $i,$file in enumerate($bam_files)
+                #set $name = 'bam_' + str($i) + '.bam'
+                ln -s '${file}' $name &&
+                $bam_filenames.append($name)
+            #end for
+            #set $allFiles = ','.join( [ str( $file ) for $file in $bam_filenames ] )
+            psiclass
+                -b  $allFiles 
+                -p \${GALAXY_SLOTS:-8}
+                #if $splice_conditional.selector == 'true'
+                    -s '${splice_conditional.splice_file}'
+                #end if
+                -c $subexonClassifier
+                --sa $intronCoverage
+                --vd $transcriptCoverage
+                #if $stranded
+                    --stranded $stranded
+                #end if
+                --maxDpConstraintSize $maxDpConstraintSize
+                $primaryParalog
+                --tssTesQuantile $tssTesQuantile
+            && mv *sample* "./annotation_files"
+            #if $splice_conditional.selector == 'false'
+                && cat ./splice/psiclass_bam.trusted_splice > '${splice_sites}'
+            #end if
+    ]]></command>
+    <inputs>
+        <param argument="-b" name="bam_files" type="data" format="bam" multiple="true" label="BAM file(s)"
+             help="PsiCLASS has been tuned to run on alignments generated with the tools HISAT and STAR" />
+        <conditional name="splice_conditional">
+            <param name="selector" type="select" label="Provide trusted splice sites coordinates" help="It is possible to supply 
+                an set of trusted introns, for instance generated by RNASTAR or extracted from the GENCODE gene annotations">
+                <option value="true">Enabled</option>
+                <option value="false" selected="true">Disabled</option>
+            </param>
+            <when value="true">
+                <param argument="-s" name="splice_file" type="data" format="interval" optional="true" label="Splice junction sites file" help="High confidence collapsed splice junction file" />
+            </when>
+            <when value="false"/>
+        </conditional>
+        <param argument="-c" type="float" name="subexonClassifier" min="0" max="1" value="0.05" label="Subexon classifier score threshold" 
+            help="Only use the subexons with classifier score minor or equal than the given number" />
+        <param argument="--sa" name="intronCoverage" type="float" min="0" value="0.5" label="Minimum retained intron converage" 
+            help="Minimum average number of supported read for retained introns" />
+        <param argument="--vd" name="transcriptCoverage" type="float" min="0" value="1" label="Minimum transcript coverage" 
+            help="Minimum average coverage depth of a transcript to be reported" />
+        <param argument="--stranded" type="select" optional="true" label="Library strand information" help="Stranded data shows advantages over 
+            non-stranded RNA-Seq data such as higher assembly and differential expression accuracy">
+            <option value="un">unstranded</option>
+            <option value="rf">fr-firststrand (rf): first read from the opposite strand.</option>
+            <option value="fr">fr-secondstrand (fr): first read from the transcript strand</option>
+        </param>
+        <param argument="--maxDpConstraintSize" type="integer" min="-1" value="7" label="Constrain cover iN  median exon depth (DP)" help="-1 for infinite"/>
+        <param argument="--primaryParalog" type="boolean" truevalue="--primaryParalog" falsevalue="" checked="false" optional="true"
+            label="Use primary alignment to retain paralog genes" help="Default: use unique alignments" />
+        <param argument="--tssTesQuantile" type="float" min="0" max="1" value="0.5" label="Quantile for transcription start/end sites in subexon graph"/>
+    </inputs>
+    <outputs>
+        <data name="meta_anotation" format="gtf"  from_work_dir="psiclass_vote.gtf" label="${tool.name} on ${on_string}: meta-annotation" />
+        <collection name="annotation_collection" type="list" label="${tool.name} on ${on_string}: per-sample annotations">
+            <discover_datasets pattern="__designation_and_ext__" format="gtf" directory="annotation_files"/>
+        </collection>
+        <data name="splice_sites" format="interval" label="${tool.name} on ${on_string}: splice sites">
+            <filter>splice_conditional["selector"] == "false"</filter>
+        </data>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="2">
+            <param name="bam_files" value="reads1.bam,reads2.bam"/>
+            <param name="subexonClassifier" value="0.05"/>
+            <param name="intronCoverage" value="0.5"/>
+            <param name="transcriptCoverage" value="1"/>
+            <param name="stranded" value="un"/>
+            <param name="maxDpConstraintSize" value="7"/>
+            <param name="primaryParalog" value="false"/>
+            <param name="tssTesQuantile" value="0.5"/>
+            <conditional name="splice_conditional">
+                <param name="selector" value="true"/>
+                <param name="splice_file" value="splice_sites.interval"/>
+            </conditional>
+            <output name="meta_anotation" ftype="gtf" file="test01_meta_annotation.gtf" lines_diff="2"/>
+            <output_collection name="annotation_collection" type="list" count="2">
+                <element name="psiclass_sample_0" ftype="gtf" file="test01_annotation_sample0.gtf" lines_diff="2"/>
+                <element name="psiclass_sample_1" ftype="gtf" file="test01_annotation_sample1.gtf" lines_diff="2"/>
+            </output_collection>
+        </test>
+        <test expect_num_outputs="3">
+            <param name="bam_files" value="reads1.bam,reads2.bam"/>
+            <param name="subexonClassifier" value="0.05"/>
+            <param name="intronCoverage" value="0.3"/>
+            <param name="transcriptCoverage" value="0.5"/>
+            <param name="stranded" value="rf"/>
+            <param name="maxDpConstraintSize" value="6"/>
+            <param name="primaryParalog" value="true"/>
+            <param name="tssTesQuantile" value="0.4"/>
+            <conditional name="splice_conditional">
+                <param name="selector" value="false"/>
+            </conditional>
+            <output name="meta_anotation" ftype="gtf" file="test02_meta_annotation.gtf"/>
+            <output_collection name="annotation_collection" type="list" count="2">
+                <element name="psiclass_sample_0" ftype="gtf" file="test02_annotation_sample0.gtf" lines_diff="2"/>
+                <element name="psiclass_sample_1" ftype="gtf" file="test02_annotation_sample1.gtf" lines_diff="2"/>
+            </output_collection>
+            <output name="splice_sites" ftype="interval" file="test02_splice_sites.txt"/>
+        </test>
+        <test expect_num_outputs="3">
+            <param name="bam_files" value="reads1.bam"/>
+            <output name="meta_anotation" ftype="gtf" file="test03_meta_annotation.gtf"/>
+            <output_collection name="annotation_collection" type="list" count="1">
+                <element name="psiclass_sample_0" ftype="gtf" file="test03_annotation_sample0.gtf" lines_diff="2"/>
+            </output_collection>
+            <output name="splice_sites" file="test03_splice_sites.txt" ftype="interval"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+
+.. class:: infomark
+
+**What is PsiCLASS?**
+
+PsiCLASS is a reference-based transcriptome assembler for single or multiple RNA-seq samples. 
+
+Unlike conventional methods that analyze each sample separately and then merge the outcomes to create a unified set of meta-annotations, 
+PsiCLASS takes a multi-sample approach, simultaneously analyzing all RNA-seq data sets in an experiment. 
+
+PsiCLASS is both a transcript assembler and a meta-assembler, producing separate transcript sets for the individual samples and a unified 
+set of meta-annotations. The algorithmic underpinnings of PsiCLASS include using a global subexon splice graph, statistical cross-sample 
+feature (intron, subexon) selection methods, and an efficient dynamic programming algorithm to select a subset of transcripts from among 
+those encoded in the graph, based on the read support in each sample.
+
+Lastly, the set of meta-annotations is selected from among the transcripts generated for individual samples by voting. While PsiCLASS is 
+highly accurate and efficient for medium-to-large collections of RNA-seq data, its accuracy is equally high for small RNA-seq data sets 
+(2-10 samples) and is competitive to reference methods for single samples. Additionally, its performance is robust with the aggregation 
+method used, including the built-in voting and assembly-based approaches such as StringTie-merge and TACO. Therefore, it can be effectively 
+used as a multi-sample and as a single-sample assembler, as well as in conventional assemble-and-merge protocols.
+
+    ]]></help>
+    <expand macro="citations" />
+</tool>

tools/psiclass/test-data/splice_sites.interval

@@ -0,0 +1,2 @@
+test_chromosome	251	350	1	1	0	27	0	37
+test_chromosome	401	500	1	1	0	25	0	36

tools/psiclass/test-data/test01_annotation_sample0.gtf

@@ -0,0 +1,15 @@
+#PsiCLASS_v1.0.3
+#/home/laptop/miniconda3/envs/mulled-v1-4549fe7ad5b22a1b35ab5aa0ada6322e374f13375e517a18654c3ddd9bb8d124/bin/classes -p 1 -c 0.05 --stranded un --maxDpConstraintSize 7 -b bam_0.bam -b bam_1.bam -s ./subexon/psiclass_subexon_combined.out -o ./psiclass
+#bam_0.bam
+chr16	PsiCLASS	transcript	784996	786471	1000	.	.	gene_id "chr16.1"; transcript_id "chr16.1.0"; FPKM "90057.137790"; TPM "395522.152415"; cov "33.028455";
+chr16	PsiCLASS	exon	784996	786471	1000	.	.	gene_id "chr16.1"; transcript_id "chr16.1.0"; exon_number "1"; FPKM "90057.137790"; TPM "395522.152415"; cov "33.028455";
+chr16	PsiCLASS	transcript	787203	787744	1000	.	.	gene_id "chr16.7"; transcript_id "chr16.7.0"; FPKM "14337.566689"; TPM "62969.192406"; cov "5.258303";
+chr16	PsiCLASS	exon	787203	787744	1000	.	.	gene_id "chr16.7"; transcript_id "chr16.7.0"; exon_number "1"; FPKM "14337.566689"; TPM "62969.192406"; cov "5.258303";
+chr16	PsiCLASS	transcript	790525	792347	1000	.	.	gene_id "chr16.17"; transcript_id "chr16.17.0"; FPKM "19967.535928"; TPM "87695.467370"; cov "7.323094";
+chr16	PsiCLASS	exon	790525	792347	1000	.	.	gene_id "chr16.17"; transcript_id "chr16.17.0"; exon_number "1"; FPKM "19967.535928"; TPM "87695.467370"; cov "7.323094";
+chr16	PsiCLASS	transcript	794054	794361	1000	.	.	gene_id "chr16.25"; transcript_id "chr16.25.0"; FPKM "10623.323507"; TPM "46656.599158"; cov "3.896104";
+chr16	PsiCLASS	exon	794054	794361	1000	.	.	gene_id "chr16.25"; transcript_id "chr16.25.0"; exon_number "1"; FPKM "10623.323507"; TPM "46656.599158"; cov "3.896104";
+chr16	PsiCLASS	transcript	795132	795356	1000	.	.	gene_id "chr16.27"; transcript_id "chr16.27.0"; FPKM "30902.067712"; TPM "135718.862884"; cov "11.333333";
+chr16	PsiCLASS	exon	795132	795356	1000	.	.	gene_id "chr16.27"; transcript_id "chr16.27.0"; exon_number "1"; FPKM "30902.067712"; TPM "135718.862884"; cov "11.333333";
+chr16	PsiCLASS	transcript	797839	798063	1000	.	.	gene_id "chr16.39"; transcript_id "chr16.39.0"; FPKM "61804.135424"; TPM "271437.725768"; cov "22.666667";
+chr16	PsiCLASS	exon	797839	798063	1000	.	.	gene_id "chr16.39"; transcript_id "chr16.39.0"; exon_number "1"; FPKM "61804.135424"; TPM "271437.725768"; cov "22.666667";

tools/psiclass/test-data/test01_annotation_sample1.gtf

@@ -0,0 +1,3 @@
+#PsiCLASS_v1.0.3
+#/home/laptop/miniconda3/envs/mulled-v1-4549fe7ad5b22a1b35ab5aa0ada6322e374f13375e517a18654c3ddd9bb8d124/bin/classes -p 1 -c 0.05 --stranded un --maxDpConstraintSize 7 -b bam_0.bam -b bam_1.bam -s ./subexon/psiclass_subexon_combined.out -o ./psiclass
+#bam_1.bam

tools/psiclass/test-data/test01_meta_annotation.gtf

@@ -0,0 +1,12 @@
+chr16	PsiCLASS	transcript	784996	786471	1000	.	.	gene_id "chr16.1"; transcript_id "chr16.1.0"; FPKM "90057.137790"; TPM "395522.152415"; cov "33.028455"; sample_cnt "1";
+chr16	PsiCLASS	exon	784996	786471	1000	.	.	gene_id "chr16.1"; transcript_id "chr16.1.0"; exon_number "1"; FPKM "90057.137790"; TPM "395522.152415"; cov "33.028455"; sample_cnt "1";
+chr16	PsiCLASS	transcript	787203	787744	1000	.	.	gene_id "chr16.7"; transcript_id "chr16.7.0"; FPKM "14337.566689"; TPM "62969.192406"; cov "5.258303"; sample_cnt "1";
+chr16	PsiCLASS	exon	787203	787744	1000	.	.	gene_id "chr16.7"; transcript_id "chr16.7.0"; exon_number "1"; FPKM "14337.566689"; TPM "62969.192406"; cov "5.258303"; sample_cnt "1";
+chr16	PsiCLASS	transcript	790525	792347	1000	.	.	gene_id "chr16.17"; transcript_id "chr16.17.0"; FPKM "19967.535928"; TPM "87695.467370"; cov "7.323094"; sample_cnt "1";
+chr16	PsiCLASS	exon	790525	792347	1000	.	.	gene_id "chr16.17"; transcript_id "chr16.17.0"; exon_number "1"; FPKM "19967.535928"; TPM "87695.467370"; cov "7.323094"; sample_cnt "1";
+chr16	PsiCLASS	transcript	794054	794361	1000	.	.	gene_id "chr16.25"; transcript_id "chr16.25.0"; FPKM "10623.323507"; TPM "46656.599158"; cov "3.896104"; sample_cnt "1";
+chr16	PsiCLASS	exon	794054	794361	1000	.	.	gene_id "chr16.25"; transcript_id "chr16.25.0"; exon_number "1"; FPKM "10623.323507"; TPM "46656.599158"; cov "3.896104"; sample_cnt "1";
+chr16	PsiCLASS	transcript	795132	795356	1000	.	.	gene_id "chr16.27"; transcript_id "chr16.27.0"; FPKM "30902.067712"; TPM "135718.862884"; cov "11.333333"; sample_cnt "1";
+chr16	PsiCLASS	exon	795132	795356	1000	.	.	gene_id "chr16.27"; transcript_id "chr16.27.0"; exon_number "1"; FPKM "30902.067712"; TPM "135718.862884"; cov "11.333333"; sample_cnt "1";
+chr16	PsiCLASS	transcript	797839	798063	1000	.	.	gene_id "chr16.39"; transcript_id "chr16.39.0"; FPKM "61804.135424"; TPM "271437.725768"; cov "22.666667"; sample_cnt "1";
+chr16	PsiCLASS	exon	797839	798063	1000	.	.	gene_id "chr16.39"; transcript_id "chr16.39.0"; exon_number "1"; FPKM "61804.135424"; TPM "271437.725768"; cov "22.666667"; sample_cnt "1";

tools/psiclass/test-data/test01_splice_sites.txt

@@ -0,0 +1,68 @@
+chr16 786377 786827 10 - 10 0 0 0
+chr16 786928 787068 10 - 10 0 0 0
+chr16 786928 787077 10 - 10 0 0 0
+chr16 787179 787354 10 - 10 0 0 0
+chr16 787477 787556 10 - 10 0 0 0
+chr16 787744 788256 10 - 10 0 0 0
+chr16 789125 789210 10 + 10 0 0 0
+chr16 789360 789547 10 + 10 0 0 0
+chr16 789715 790177 10 + 10 0 0 0
+chr16 790269 790347 10 + 10 0 0 0
+chr16 790399 790525 10 + 10 0 0 0
+chr16 790666 791161 10 + 10 0 0 0
+chr16 791370 791851 10 + 10 0 0 0
+chr16 791948 792224 10 + 10 0 0 0
+chr16 792347 792439 10 + 10 0 0 0
+chr16 792590 792718 10 + 10 0 0 0
+chr16 792811 792966 10 + 10 0 0 0
+chr16 793064 793144 10 + 10 0 0 0
+chr16 793274 794054 10 + 10 0 0 0
+chr16 794201 795132 10 + 10 0 0 0
+chr16 795356 795685 10 + 10 0 0 0
+chr16 795834 795947 10 + 10 0 0 0
+chr16 796077 796717 10 + 10 0 0 0
+chr16 796861 796961 10 + 10 0 0 0
+chr16 797092 797694 10 + 10 0 0 0
+chr16 797751 797839 10 + 10 0 0 0
+chr16 854706 868944 10 - 10 0 0 0
+chr16 869056 869883 10 - 10 0 0 0
+chr16 870066 870729 10 - 10 0 0 0
+chr16 870882 871161 10 - 10 0 0 0
+chr16 871341 879570 10 - 10 0 0 0
+chr16 893072 910931 10 - 10 0 0 0
+chr16 954666 970788 10 - 10 0 0 0
+chr19 567648 571440 10 - 10 0 0 0
+chr19 571579 580379 10 - 10 0 0 0
+chr19 572701 577774 10 - 10 0 0 0
+chr19 578121 579500 10 - 10 0 0 0
+chr19 579656 580379 10 - 10 0 0 0
+chr19 580461 580646 10 - 10 0 0 0
+chr19 580782 581315 10 - 10 0 0 0
+chr19 581610 582514 10 - 10 0 0 0
+chr19 582582 582750 10 - 10 0 0 0
+chr19 590577 603544 10 - 10 0 0 0
+chr19 603967 605061 10 - 10 0 0 0
+chr19 605222 607964 10 - 10 0 0 0
+chr19 608182 610259 10 - 10 0 0 0
+chr19 610405 613248 10 - 10 0 0 0
+chr19 613488 613852 10 - 10 0 0 0
+chr19 614016 615795 10 - 10 0 0 0
+chr19 617323 617419 10 - 10 0 0 0
+chr19 617480 617570 10 - 10 0 0 0
+chr19 617655 617777 10 - 10 0 0 0
+chr19 617849 618488 10 - 10 0 0 0
+chr19 618586 618705 10 - 10 0 0 0
+chr19 618760 618997 10 - 10 0 0 0
+chr19 619110 619210 10 - 10 0 0 0
+chr19 619765 619958 10 - 10 0 0 0
+chr19 620080 620365 10 - 10 0 0 0
+chr19 620487 621058 10 - 10 0 0 0
+chr19 621846 622149 10 - 10 0 0 0
+chr19 622373 622582 10 - 10 0 0 0
+chr19 622752 622821 10 - 10 0 0 0
+chr19 622985 623454 10 - 10 0 0 0
+chr19 623603 624719 10 - 10 0 0 0
+chr19 624905 625124 10 - 10 0 0 0
+chr19 625254 629540 10 - 10 0 0 0
+chr19 630168 632834 10 - 10 0 0 0
+chr19 632938 633425 10 - 10 0 0 0