changeset 0:fe71b97cc1a5 draft

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/goseq_1_22_0 commit 85e0f34aec3045f48ca9b1a00db02de199a99c95-dirty
author mvdbeek
date Wed, 24 Feb 2016 15:54:37 -0500
parents
children 3ab168143b69
files goseq.r goseq.xml tool-data/gene_ids.loc.sample tool-data/genomes.loc.sample tool_dependencies.xml
diffstat 5 files changed, 357 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/goseq.r	Wed Feb 24 15:54:37 2016 -0500
@@ -0,0 +1,71 @@
+sink(stdout(), type = "message")
+library(goseq)
+library(optparse)
+
+option_list <- list(
+    make_option(c("-d", "--dge_file"), type="character", help="Path to file with differential gene expression result"),
+    make_option(c("-w","--wallenius_tab"), type="character", help="Path to output file with P-values estimated using wallenius distribution."),
+    make_option(c("-s","--sampling_tab"), type="character", default=FALSE, help="Path to output file with P-values estimated using wallenius distribution."),
+    make_option(c("-n","--nobias_tab"), type="character", default=FALSE, help="Path to output file with P-values estimated using wallenius distribution and no correction for gene length bias."),
+    make_option(c("-l","--length_bias_plot"), type="character", default=FALSE, help="Path to length-bias plot."),
+    make_option(c("-sw","--sample_vs_wallenius_plot"), type="character", default=FALSE, help="Path to plot comparing sampling with wallenius p-values."),
+    make_option(c("-padj", "--p_adj_column"), type="integer",help="Column that contains p. adjust values"),
+    make_option(c("-c", "--cutoff"), type="double",dest="p_adj_cutoff",
+                help="Genes with p.adjust below cutoff are considered not differentially expressed and serve as control genes"),
+    make_option(c("-r", "--repcnt"), type="integer", default=100, help="Number of repeats for sampling"),
+    make_option(c("-g", "--genome"), type="character", help = "Genome [used for looking up correct gene length]"),
+    make_option(c("-i", "--gene_id"), type="character", help="Gene ID of gene column in DGE file")
+  )
+parser <- OptionParser(usage = "%prog [options] file", option_list=option_list)
+args = parse_args(parser)
+
+# Vars:
+dge_file = args$dge_file
+p_adj_column = args$p_adj_colum
+p_adj_cutoff = args$p_adj_cutoff
+genome = args$genome
+gene_id = args$gene_id
+wallenius_tab = args$wallenius_tab
+sampling_tab = args$sampling_tab
+nobias_tab = args$nobias_tab
+length_bias_plot = args$length_bias_plot
+sample_vs_wallenius_plot = args$sample_vs_wallenius_plot
+repcnt = args$repcnt
+
+
+# format DE genes into vector suitable for use with goseq
+dge_table = read.delim(dge_file, header = TRUE, sep="\t", check.names = FALSE)
+genes = as.integer(dge_table[,p_adj_column]<p_adj_cutoff)
+names(genes) = dge_table[,1] # Assuming first row contains gene names
+
+# Estimate PWF
+
+pdf(length_bias_plot)
+pwf=nullp(genes, genome , gene_id)
+dev.off()
+# Null dstribution wallenius
+GO.wall=goseq(pwf, genome, gene_id)
+
+GO.nobias=goseq(pwf, genome, gene_id, method="Hypergeometric")
+
+# Sampling dsitribution
+GO.samp=goseq(pwf,genome, gene_id, method="Sampling",repcnt=repcnt)
+
+# Compare sampling with wallenius
+pdf(sample_vs_wallenius_plot)
+plot(log10(GO.wall[,2]), log10(GO.samp[match(GO.samp[,1],GO.wall[,1]),2]),
+     xlab="log10(Wallenius p-values)",ylab="log10(Sampling p-values)",
+     xlim=c(-3,0))
+abline(0,1,col=3,lty=2)
+dev.off()
+
+
+write.table(GO.wall, wallenius_tab, sep="\t", row.names = FALSE, quote = FALSE)
+write.table(GO.samp, sampling_tab, sep="\t", row.names = FALSE, quote = FALSE)
+write.table(GO.nobias, nobias_tab, sep="\t", row.names = FALSE, quote = FALSE)
+
+# Use the following to get a list of supported genomes / gene ids
+
+# write.table(supportedGenomes(), "available_genomes.tab", row.names = FALSE, quote=FALSE)
+# write.table(supportedGeneIDs(), "supported_gene_ids.tab", row.name = FALSE, quote = FALSE)
+# write.table(table.summary, "input_gene_count_matrix.tab", row.names = FALSE, quote = FALSE)
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/goseq.xml	Wed Feb 24 15:54:37 2016 -0500
@@ -0,0 +1,65 @@
+<tool id="goseq" name="goseq gene ontology analyser" version="0.1.1">
+    <description />
+    <requirements>
+        <requirement type="package" version="3.2.1">R</requirement>
+        <requirement type="package" version="1.22.0">goseq</requirement>
+    </requirements>
+    <command interpreter="Rscript">
+        goseq.r --dge_file "$dge_file"
+        --p_adj_column "$p_adj_column"
+        --cutoff "$p_adj_cutoff"
+        --genome "$genome"
+        --gene_id "$gene_id"
+        --wallenius_tab "$wallenius_tab"
+        --sampling_tab "$sampling_tab"
+        --nobias_tab "$nobias_tab"
+        --length_bias_plot "$length_bias_plot"
+        --sample_vs_wallenius_plot "$sample_vs_wallenius_plot"
+        --repcnt "$repcnt"
+    </command>
+    <inputs>
+        <param help="deseq2/edger/limma differential gene expression list" label="DGE list" name="dge_file" type="data" format="tabular" />
+        <param help="Select the column that contains the multiple-testing corrected p-value" label="p adjust column" name="p_adj_column" type="data_column" data_ref="dge_file"/>
+        <param help="Typically 0.05 after multiple testing correction" max="1" label="Minimum p adjust value to consider gene differentially expressed" name="p_adj_cutoff" type="float" value="0.05" />
+        <param help="Needed to retrive gene length for length correction" label="Select the genome source" name="genome" size="3" type="select">
+            <options from_file="genomes.loc">
+                <column name="value" index="0"/>
+                <column name="name" index="1"/>
+            </options>
+        </param>
+        <param help="Needed for GO analysis" label="Select gene identifier" name="gene_id" type="select">
+            <options from_file="gene_ids.loc">
+                <column name="value" index="0"/>
+                <column name="name" index="1"/>
+            </options>
+        </param>
+        <param help="Do this many random samplings. Larger values take a long time" label="Number of random sampling" name="repcnt" size="3" type="integer" min="100" max="10000" value="1000" />
+    </inputs>
+    <outputs>
+        <data format="tabular" label="Ranked category list - wallenius" name="wallenius_tab" />
+        <data format="tabular" label="Ranked category list - sampling" name="sampling_tab" />
+        <data format="tabular" label="Ranked category list - no length bias correction" name="nobias_tab" />
+        <data format="pdf" label="length bias plot" name="length_bias_plot" />
+        <data format="pdf" label="Plot P-value from sampling against wallenius distribution" name="sample_vs_wallenius_plot" />
+    </outputs>
+    <tests>
+        <test>
+
+        </test>
+    </tests>
+    <help>
+
+        **What it does**
+
+        Detects Gene Ontology and/or other user defined categories which are over/under represented in RNA-seq data.
+
+        Options map closely to the excellent manual_
+
+        .. _manual: https://bioconductor.org/packages/release/bioc/vignettes/goseq/inst/doc/goseq.pdf
+
+
+        </help>
+    <citations>
+            <citation type="doi">10.1186/gb-2010-11-2-r14</citation>
+    </citations>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/gene_ids.loc.sample	Wed Feb 24 15:54:37 2016 -0500
@@ -0,0 +1,42 @@
+knownGene	knownGene, UCSC Genes, NA, Entrez Gene ID
+knownGeneOld3	knownGeneOld3, Old UCSC Genes, NA, 
+ccdsGene	ccdsGene, CCDS, NA, 
+refGene	refGene, RefSeq Genes, NA, Entrez Gene ID
+xenoRefGene	xenoRefGene, Other RefSeq, NA, 
+vegaGene	vegaGene, Vega Genes, Vega Protein Genes, HAVANA Pseudogene ID
+vegaPseudoGene	vegaPseudoGene, Vega Genes, Vega Pseudogenes, HAVANA Pseudogene ID
+ensGene	ensGene, Ensembl Genes, NA, Ensembl gene ID
+acembly	acembly, AceView Genes, NA, 
+sibGene	sibGene, SIB Genes, NA, 
+nscanPasaGene	nscanPasaGene, N-SCAN, N-SCAN PASA-EST, 
+nscanGene	nscanGene, N-SCAN, N-SCAN, 
+sgpGene	sgpGene, SGP Genes, NA, 
+geneid	geneid, Geneid Genes, NA, 
+genscan	genscan, Genscan Genes, NA, 
+exoniphy	exoniphy, Exoniphy, NA, 
+augustusHints	augustusHints, Augustus, Augustus Hints, 
+augustusXRA	augustusXRA, Augustus, Augustus De Novo, 
+augustusAbinitio	augustusAbinitio, Augustus, Augustus Ab Initio, 
+acescan	acescan, ACEScan, NA, 
+lincRNAsTranscripts	lincRNAsTranscripts, lincRNAsTranscripts, NA, Name of gene
+wgEncodeGencodeManualV3	wgEncodeGencodeManualV3, Gencode Genes, Gencode Manual, Ensembl gene ID
+wgEncodeGencodeAutoV3	wgEncodeGencodeAutoV3, Gencode Genes, Gencode Auto, Ensembl gene ID
+wgEncodeGencodePolyaV3	wgEncodeGencodePolyaV3, Gencode Genes, Gencode PolyA, Ensembl gene ID
+wgEncodeGencodeBasicV17	wgEncodeGencodeBasicV17, GENCODE Genes V17, NA, Ensembl gene ID
+wgEncodeGencodeCompV17	wgEncodeGencodeCompV17, GENCODE Genes V17, NA, Ensembl gene ID
+wgEncodeGencodePseudoGeneV17	wgEncodeGencodePseudoGeneV17, GENCODE Genes V17, NA, Ensembl gene ID
+wgEncodeGencode2wayConsPseudoV17	wgEncodeGencode2wayConsPseudoV17, GENCODE Genes V17, NA, Ensembl gene ID
+wgEncodeGencodePolyaV17	wgEncodeGencodePolyaV17, GENCODE Genes V17, NA, Ensembl gene ID
+wgEncodeGencodeBasicV14	wgEncodeGencodeBasicV14, GENCODE Genes V14, NA, Ensembl gene ID
+wgEncodeGencodeCompV14	wgEncodeGencodeCompV14, GENCODE Genes V14, NA, Ensembl gene ID
+wgEncodeGencodePseudoGeneV14	wgEncodeGencodePseudoGeneV14, GENCODE Genes V14, NA, Ensembl gene ID
+wgEncodeGencode2wayConsPseudoV14	wgEncodeGencode2wayConsPseudoV14, GENCODE Genes V14, NA, Ensembl gene ID
+wgEncodeGencodePolyaV14	wgEncodeGencodePolyaV14, GENCODE Genes V14, NA, Ensembl gene ID
+wgEncodeGencodeBasicV7	wgEncodeGencodeBasicV7, GENCODE Genes V7, NA, Ensembl gene ID
+wgEncodeGencodeCompV7	wgEncodeGencodeCompV7, GENCODE Genes V7, NA, Ensembl gene ID
+wgEncodeGencodePseudoGeneV7	wgEncodeGencodePseudoGeneV7, GENCODE Genes V7, NA, Ensembl gene ID
+wgEncodeGencode2wayConsPseudoV7	wgEncodeGencode2wayConsPseudoV7, GENCODE Genes V7, NA, Ensembl gene ID
+wgEncodeGencodePolyaV7	wgEncodeGencodePolyaV7, GENCODE Genes V7, NA, Ensembl gene ID
+flyBaseGene	flyBaseGene, FlyBase Genes, NA, Name of canonical transcript in cluster
+sgdGene	sgdGene, SGD Genes, NA, Name of canonical transcript in cluster
+geneSymbol	geneSymbol, refGene, refFlat, Gene Symbol
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/genomes.loc.sample	Wed Feb 24 15:54:37 2016 -0500
@@ -0,0 +1,170 @@
+hg38	hg38, Human, Dec. 2013, Genome Reference Consortium GRCh38
+hg19	hg19, Human, Feb. 2009, Genome Reference Consortium GRCh37
+hg18	hg18, Human, Mar. 2006, NCBI Build 36.1
+hg17	hg17, Human, May 2004, NCBI Build 35
+hg16	hg16, Human, Jul. 2003, NCBI Build 34
+vicPac2	vicPac2, Alpaca, Mar. 2013, Broad Institute Vicugna_pacos-2.0.1
+vicPac1	vicPac1, Alpaca, Jul. 2008, Broad Institute VicPac1.0
+dasNov3	dasNov3, Armadillo, Dec. 2011, Broad Institute DasNov3
+otoGar3	otoGar3, Bushbaby, Mar. 2011, Broad Institute OtoGar3
+papHam1	papHam1, Baboon, Nov. 2008, Baylor College of Medicine HGSC Pham_1.0
+papAnu2	papAnu2, Baboon, Mar. 2012, Baylor College of Medicine Panu_2.0
+felCat8	felCat8, Cat, Nov. 2014, ICGSC Felis_catus_8.0
+felCat5	felCat5, Cat, Sep. 2011, ICGSC Felis_catus-6.2
+felCat4	felCat4, Cat, Dec. 2008, NHGRI catChrV17e
+felCat3	felCat3, Cat, Mar. 2006, Broad Institute Release 3
+panTro4	panTro4, Chimp, Feb. 2011, CGSC Build 2.1.4
+panTro3	panTro3, Chimp, Oct. 2010, CGSC Build 2.1.3
+panTro2	panTro2, Chimp, Mar. 2006, CGSC Build 2.1
+panTro1	panTro1, Chimp, Nov. 2003, CGSC Build 1.1
+criGri1	criGri1, Chinese hamster, Jul. 2013, Beijing Genomics Institution-Shenzhen C_griseus_v1.0
+bosTau8	bosTau8, Cow, Jun. 2014, University of Maryland v3.1.1
+bosTau7	bosTau7, Cow, Oct. 2011, Baylor College of Medicine HGSC Btau_4.6.1
+bosTau6	bosTau6, Cow, Nov. 2009, University of Maryland v3.1
+bosTau4	bosTau4, Cow, Oct. 2007, Baylor College of Medicine HGSC Btau_4.0
+bosTau3	bosTau3, Cow, Aug. 2006, Baylor College of Medicine HGSC Btau_3.1
+bosTau2	bosTau2, Cow, Mar. 2005, Baylor College of Medicine HGSC Btau_2.0
+canFam3	canFam3, Dog, Sep. 2011, Broad Institute v3.1
+canFam2	canFam2, Dog, May 2005, Broad Institute v2.0
+canFam1	canFam1, Dog, Jul. 2004, Broad Institute v1.0
+turTru2	turTru2, Dolphin, Oct. 2011, Baylor College of Medicine Ttru_1.4
+loxAfr3	loxAfr3, Elephant, Jul. 2009, Broad Institute LoxAfr3
+musFur1	musFur1, Ferret, Apr. 2011, Ferret Genome Sequencing Consortium MusPutFur1.0
+nomLeu3	nomLeu3, Gibbon, Oct. 2012, Gibbon Genome Sequencing Consortium Nleu3.0
+nomLeu2	nomLeu2, Gibbon, Jun. 2011, Gibbon Genome Sequencing Consortium Nleu1.1
+nomLeu1	nomLeu1, Gibbon, Jan. 2010, Gibbon Genome Sequencing Consortium Nleu1.0
+gorGor3	gorGor3, Gorilla, May 2011, Wellcome Trust Sanger Institute gorGor3.1
+cavPor3	cavPor3, Guinea pig, Feb. 2008, Broad Institute cavPor3
+eriEur2	eriEur2, Hedgehog, May 2012, Broad Institute EriEur2.0
+eriEur1	eriEur1, Hedgehog, Jun. 2006, Broad Institute Draft_v1
+equCab2	equCab2, Horse, Sep. 2007, Broad Institute EquCab2
+equCab1	equCab1, Horse, Jan. 2007, Broad Institute EquCab1
+dipOrd1	dipOrd1, Kangaroo rat, Jul. 2008, Baylor/Broad Institute DipOrd1.0
+triMan1	triMan1, Manatee, Oct. 2011, Broad Institute TriManLat1.0
+calJac3	calJac3, Marmoset, Mar. 2009, WUSTL Callithrix_jacchus-v3.2
+calJac1	calJac1, Marmoset, Jun. 2007, WUSTL Callithrix_jacchus-v2.0.2
+pteVam1	pteVam1, Megabat, Jul. 2008, Broad Institute Ptevap1.0
+myoLuc2	myoLuc2, Microbat, Jul. 2010, Broad Institute MyoLuc2.0
+balAcu1	balAcu1, Minke whale, Oct. 2013, KORDI BalAcu1.0
+mm10	mm10, Mouse, Dec. 2011, Genome Reference Consortium GRCm38
+mm9	mm9, Mouse, Jul. 2007, NCBI Build 37
+mm8	mm8, Mouse, Feb. 2006, NCBI Build 36
+mm7	mm7, Mouse, Aug. 2005, NCBI Build 35
+micMur2	micMur2, Mouse lemur, May 2015, Baylor/Broad Institute Mmur_2.0
+micMur1	micMur1, Mouse lemur, Jul. 2007, Broad Institute MicMur1.0
+hetGla2	hetGla2, Naked mole-rat, Jan. 2012, Broad Institute HetGla_female_1.0
+hetGla1	hetGla1, Naked mole-rat, Jul. 2011, Beijing Genomics Institute HetGla_1.0
+monDom5	monDom5, Opossum, Oct. 2006, Broad Institute release MonDom5
+monDom4	monDom4, Opossum, Jan. 2006, Broad Institute release MonDom4
+monDom1	monDom1, Opossum, Oct. 2004, Broad Institute release MonDom1
+ponAbe2	ponAbe2, Orangutan, Jul. 2007, WUSTL Pongo_albelii-2.0.2
+ailMel1	ailMel1, Panda, Dec. 2009, BGI-Shenzhen AilMel 1.0
+susScr3	susScr3, Pig, Aug. 2011, Swine Genome Sequencing Consortium Sscrofa10.2
+susScr2	susScr2, Pig, Nov. 2009, Swine Genome Sequencing Consortium Sscrofa9.2
+ochPri3	ochPri3, Pika, May 2012, Broad Institute OchPri3.0
+ochPri2	ochPri2, Pika, Jul. 2008, Broad Institute OchPri2
+ornAna2	ornAna2, Platypus, Feb. 2007, WUSTL v5.0.1
+ornAna1	ornAna1, Platypus, Mar. 2007, WUSTL v5.0.1
+oryCun2	oryCun2, Rabbit, Apr. 2009, Broad Institute release OryCun2
+rn6	rn6, Rat, Jul. 2014, RGSC Rnor_6.0
+rn5	rn5, Rat, Mar. 2012, RGSC Rnor_5.0
+rn4	rn4, Rat, Nov. 2004, Baylor College of Medicine HGSC v3.4
+rn3	rn3, Rat, Jun. 2003, Baylor College of Medicine HGSC v3.1
+rheMac3	rheMac3, Rhesus, Oct. 2010, Beijing Genomics Institute CR_1.0
+rheMac2	rheMac2, Rhesus, Jan. 2006, Baylor College of Medicine HGSC v1.0 Mmul_051212
+proCap1	proCap1, Rock hyrax, Jul. 2008, Baylor College of Medicine HGSC Procap1.0
+oviAri3	oviAri3, Sheep, Aug. 2012, ISGC Oar_v3.1
+oviAri1	oviAri1, Sheep, Feb. 2010, ISGC Ovis aries 1.0
+sorAra2	sorAra2, Shrew, Aug. 2008, Broad Institute SorAra2.0
+sorAra1	sorAra1, Shrew, Jun. 2006, Broad Institute SorAra1.0
+choHof1	choHof1, Sloth, Jul. 2008, Broad Institute ChoHof1.0
+speTri2	speTri2, Squirrel, Nov. 2011, Broad Institute SpeTri2.0
+saiBol1	saiBol1, Squirrel monkey, Oct. 2011, Broad Institute SaiBol1.0
+tarSyr2	tarSyr2, Tarsier, Sep. 2013, WashU Tarsius_syrichta-2.0.1
+tarSyr1	tarSyr1, Tarsier, Aug. 2008, WUSTL/Broad Institute Tarsyr1.0
+sarHar1	sarHar1, Tasmanian devil, Feb. 2011, Wellcome Trust Sanger Institute Devil_refv7.0
+echTel2	echTel2, Tenrec, Nov. 2012, Broad Institute EchTel2.0
+echTel1	echTel1, Tenrec, Jul. 2005, Broad Institute echTel1
+tupBel1	tupBel1, Tree shrew, Dec. 2006, Broad Institute Tupbel1.0
+macEug2	macEug2, Wallaby, Sep. 2009, Tammar Wallaby Genome Sequencing Consortium Meug_1.1
+cerSim1	cerSim1, White rhinoceros, May 2012, Broad Institute CerSimSim1.0
+allMis1	allMis1, American alligator, Aug. 2012, Int. Crocodilian Genomes Working Group allMis0.2
+gadMor1	gadMor1, Atlantic cod, May 2010, Genofisk GadMor_May2010
+melUnd1	melUnd1, Budgerigar, Sep. 2011, WUSTL v6.3
+galGal4	galGal4, Chicken, Nov.
+2011, ICGC Gallus-gallus-4.0
+galGal3	galGal3, Chicken, May 2006, WUSTL Gallus-gallus-2.1
+galGal2	galGal2, Chicken, Feb. 2004, WUSTL Gallus-gallus-1.0
+latCha1	latCha1, Coelacanth, Aug. 2011, Broad Institute LatCha1
+calMil1	calMil1, Elephant shark, Dec. 2013, IMCB Callorhinchus_milli_6.1.3
+fr3	fr3, Fugu, Oct. 2011, JGI v5.0
+fr2	fr2, Fugu, Oct. 2004, JGI v4.0
+fr1	fr1, Fugu, Aug. 2002, JGI v3.0
+petMar2	petMar2, Lamprey, Sep. 2010, WUGSC 7.0
+petMar1	petMar1, Lamprey, Mar. 2007, WUSTL v3.0
+anoCar2	anoCar2, Lizard, May 2010, Broad Institute AnoCar2
+anoCar1	anoCar1, Lizard, Feb. 2007, Broad Institute AnoCar1
+oryLat2	oryLat2, Medaka, Oct. 2005, NIG v1.0
+geoFor1	geoFor1, Medium ground finch, Apr. 2012, BGI GeoFor_1.0 / NCBI 13302
+oreNil2	oreNil2, Nile tilapia, Jan. 2011, Broad Institute Release OreNil1.1
+chrPic1	chrPic1, Painted turtle, Dec. 2011, IPTGSC Chrysemys_picta_bellii-3.0.1
+gasAcu1	gasAcu1, Stickleback, Feb. 2006, Broad Institute Release 1.0
+tetNig2	tetNig2, Tetraodon, Mar. 2007, Genoscope v7
+tetNig1	tetNig1, Tetraodon, Feb. 2004, Genoscope v7
+melGal1	melGal1, Turkey, Dec. 2009, Turkey Genome Consortium v2.01
+xenTro7	xenTro7, X. tropicalis, Sep. 2012, JGI v.7.0
+xenTro3	xenTro3, X. tropicalis, Nov. 2009, JGI v.4.2
+xenTro2	xenTro2, X. tropicalis, Aug. 2005, JGI v.4.1
+xenTro1	xenTro1, X. tropicalis, Oct. 2004, JGI v.3.0
+taeGut2	taeGut2, Zebra finch, Feb. 2013, WashU taeGut324
+taeGut1	taeGut1, Zebra finch, Jul. 2008, WUSTL v3.2.4
+danRer10	danRer10, Zebrafish, Sep. 2014, Genome Reference Consortium GRCz10 
+danRer7	danRer7, Zebrafish, Jul. 2010, Sanger Institute Zv9 
+danRer6	danRer6, Zebrafish, Dec. 2008, Sanger Institute Zv8 
+danRer5	danRer5, Zebrafish, Jul. 2007, Sanger Institute Zv7 
+danRer4	danRer4, Zebrafish, Mar. 2006, Sanger Institute Zv6 
+danRer3	danRer3, Zebrafish, May 2005, Sanger Institute Zv5 
+ci2	ci2, C. intestinalis, Mar. 2005, JGI v2.0
+ci1	ci1, C. intestinalis, Dec. 2002, JGI v1.0
+braFlo1	braFlo1, Lancelet, Mar. 2006, JGI v1.0
+strPur2	strPur2, S. purpuratus, Sep. 2006, Baylor College of Medicine HGSC v. Spur 2.1
+strPur1	strPur1, S. purpuratus, Apr. 2005, Baylor College of Medicine HGSC v. Spur_0.5
+apiMel2	apiMel2, A. mellifera, Jan. 2005, Baylor College of Medicine HGSC v.Amel_2.0 
+apiMel1	apiMel1, A. mellifera, Jul. 2004, Baylor College of Medicine HGSC v.Amel_1.2 
+anoGam1	anoGam1, A. gambiae, Feb. 2003, IAGP v.MOZ2
+droAna2	droAna2, D. ananassae, Aug. 2005, Agencourt Arachne release
+droAna1	droAna1, D. ananassae, Jul. 2004, TIGR Celera release
+droEre1	droEre1, D. erecta, Aug. 2005, Agencourt Arachne release
+droGri1	droGri1, D. grimshawi, Aug. 2005, Agencourt Arachne release
+dm6	dm6, D. melanogaster, Aug. 2014, BDGP Release 6 + ISO1 MT
+dm3	dm3, D. melanogaster, Apr. 2006, BDGP Release 5
+dm2	dm2, D. melanogaster, Apr. 2004, BDGP Release 4
+dm1	dm1, D. melanogaster, Jan. 2003, BDGP Release 3
+droMoj2	droMoj2, D. mojavensis, Aug. 2005, Agencourt Arachne release
+droMoj1	droMoj1, D. mojavensis, Aug. 2004, Agencourt Arachne release
+droPer1	droPer1, D. persimilis, Oct. 2005, Broad Institute release
+dp3	dp3, D. pseudoobscura, Nov. 2004, Flybase Release 1.0
+dp2	dp2, D. pseudoobscura, Aug. 2003, Baylor College of Medicine HGSC Freeze 1
+droSec1	droSec1, D. sechellia, Oct. 2005, Broad Institute Release 1.0
+droSim1	droSim1, D. simulans, Apr. 2005, WUSTL Release 1.0
+droVir2	droVir2, D. virilis, Aug. 2005, Agencourt Arachne release
+droVir1	droVir1, D. virilis, Jul. 2004, Agencourt Arachne release
+droYak2	droYak2, D. yakuba, Nov. 2005, WUSTL Release 2.0
+droYak1	droYak1, D. yakuba, Apr. 2004, WUSTL Release 1.0
+caePb2	caePb2, C. brenneri, Feb. 2008, WUSTL 6.0.1
+caePb1	caePb1, C. brenneri, Jan. 2007, WUSTL 4.0
+cb3	cb3, C. briggsae, Jan. 2007, WUSTL Cb3
+cb1	cb1, C. briggsae, Jul. 2002, WormBase v. cb25.agp8
+ce10	ce10, C. elegans, Oct. 2010, WormBase v. WS220
+ce6	ce6, C. elegans, May 2008, WormBase v. WS190
+ce4	ce4, C. elegans, Jan. 2007, WormBase v. WS170
+ce2	ce2, C. elegans, Mar. 2004, WormBase v. WS120
+caeJap1	caeJap1, C. japonica, Mar. 2008, WUSTL 3.0.2
+caeRem3	caeRem3, C. remanei, May 2007, WUSTL 15.0.1
+caeRem2	caeRem2, C. remanei, Mar. 2006, WUSTL 1.0
+priPac1	priPac1, P. pacificus, Feb. 2007, WUSTL 5.0
+aplCal1	aplCal1, Sea Hare, Sep. 2008, Broad Release Aplcal2.0
+sacCer3	sacCer3, Yeast, April 2011, SGD April 2011 sequence
+sacCer2	sacCer2, Yeast, June 2008, SGD June 2008 sequence
+sacCer1	sacCer1, Yeast, Oct. 2003, SGD 1 Oct 2003 sequence
+eboVir3	eboVir3, Ebola Virus, June 2014, Sierra Leone 2014 (G3683/KM034562.1)
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Wed Feb 24 15:54:37 2016 -0500
@@ -0,0 +1,9 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="R" version="3.2.1">
+         <repository changeset_revision="d0bf97420fb5" name="package_r_3_2_1" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+    <package name="goseq" version="1.22.0">
+         <repository changeset_revision="0552aea78457" name="package_r_3_2_1_goseq_1_22_0" owner="mvdbeek" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>