manifest

# Copyright (c) 2003-2017 Broad Institute, Inc., Massachusetts Institute of Technology, and Regents of the University of California.  All rights reserved.
#GSEA
JVMLevel=1.8
LSID=urn\:lsid\:broad.mit.edu\:cancer.software.genepattern.module.analysis\:00072\:999999999
author=Aravind Subramanian, Pablo Tamayo, Broad Institute
commandLine=<run-with-env> -u "java/1.8" java <java_flags> -Djava.util.prefs.PreferencesFactory\=com.allaboutbalance.articles.disableprefs.DisabledPreferencesFactory -Djava.awt.headless\=true -cp <libdir>commons-lang3-3.4.jar<path.separator><libdir>commons-io-2.4.jar<path.separator><libdir>commons-cli-1.2.jar<path.separator><libdir>gp-gsea.jar<path.separator><libdir>disable-prefs.jar<path.separator><libdir>gsea-3.0.jar org.genepattern.modules.gsea.GseaWrapper -res <expression.dataset> -cls <phenotype.labels> -collapse <collapse.dataset> -mode <collapsing.mode.for.probe.sets.with.more.than.one.match> -norm <normalization.mode> -nperm <number.of.permutations> -permute <permutation.type> -rnd_type <randomization.mode> -scoring_scheme <scoring.scheme> -metric <metric.for.ranking.genes> -sort <gene.list.sorting.mode> -order <gene.list.ordering.mode> -include_only_symbols <omit.features.with.no.symbol.match> -make_sets <make.detailed.gene.set.report> -median <median.for.class.metrics> -num <number.of.markers> -plot_top_x <plot.graphs.for.the.top.sets.of.each.phenotype> -rnd_seed <random.seed> -save_rnd_lists <save.random.ranked.lists> -set_max <max.gene.set.size> -set_min <min.gene.set.size> <chip.platform.file> -gmx <gene.sets.database> -create_svgs <create.svgs> -create_gcts <create.gcts> -target_profile <target.profile>  <selected.gene.sets> <output.file.name> <alt.delim> -dev_mode <dev.mode> -create_zip <create.zip>
cpuType=any
taskDoc=doc.html
description=Gene Set Enrichment Analysis
fileFormat=zip
language=Java
name=GSEA
os=any

p1_MODE=IN
p1_TYPE=FILE
p1_default_value=
p1_description=Dataset file - .res, .gct
p1_fileFormat=gct;res
p1_flag=
p1_name=expression.dataset
p1_optional=
p1_prefix=
p1_prefix_when_specified=
p1_type=java.io.File
p1_value=

p2_MODE=IN
p2_TYPE=FILE
p2_default_value=
p2_description=Gene sets database from GSEA website. Upload a gene set if your gene set is not listed as a choice from MSigDB.
p2_fileFormat=gmt;gmx;grp
p2_numValues=1+
p2_flag=
p2_name=gene.sets.database
p2_optional=
p2_prefix=
p2_prefix_when_specified=
p2_type=java.io.File
p2_value=ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c1.all.v6.0.symbols.gmt\=c1.all.v6.0.symbols.gmt [Positional];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c2.all.v6.0.symbols.gmt\=c2.all.v6.0.symbols.gmt [Curated];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c2.cgp.v6.0.symbols.gmt\=c2.cgp.v6.0.symbols.gmt [Curated];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c2.cp.v6.0.symbols.gmt\=c2.cp.v6.0.symbols.gmt [Curated];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c2.cp.biocarta.v6.0.symbols.gmt\=c2.cp.biocarta.v6.0.symbols.gmt [Curated];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c2.cp.kegg.v6.0.symbols.gmt\=c2.cp.kegg.v6.0.symbols.gmt [Curated];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c2.cp.reactome.v6.0.symbols.gmt\=c2.cp.reactome.v6.0.symbols.gmt [Curated];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c3.all.v6.0.symbols.gmt\=c3.all.v6.0.symbols.gmt [Motif];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c3.mir.v6.0.symbols.gmt\=c3.mir.v6.0.symbols.gmt [Motif];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c3.tft.v6.0.symbols.gmt\=c3.tft.v6.0.symbols.gmt [Motif];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c4.all.v6.0.symbols.gmt\=c4.all.v6.0.symbols.gmt [Computational];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c4.cgn.v6.0.symbols.gmt\=c4.cgn.v6.0.symbols.gmt [Computational];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c4.cm.v6.0.symbols.gmt\=c4.cm.v6.0.symbols.gmt [Computational];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c5.all.v6.0.symbols.gmt\=c5.all.v6.0.symbols.gmt [Gene Ontology];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c5.bp.v6.0.symbols.gmt\=c5.bp.v6.0.symbols.gmt [Gene Ontology];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c5.cc.v6.0.symbols.gmt\=c5.cc.v6.0.symbols.gmt [Gene Ontology];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c5.mf.v6.0.symbols.gmt\=c5.mf.v6.0.symbols.gmt [Gene Ontology];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c6.all.v6.0.symbols.gmt\=c6.all.v6.0.symbols.gmt [Oncogenic Signatures];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/c7.all.v6.0.symbols.gmt\=c7.all.v6.0.symbols.gmt [Immunologic signatures];ftp\://gpftp.broadinstitute.org/module_support_files/msigdb/gmt/h.all.v6.0.symbols.gmt\=h.all.v6.0.symbols.gmt [Hallmarks]

p3_MODE=
p3_TYPE=Integer
p3_default_value=1000
p3_description=Number of permutations to perform
p3_fileFormat=
p3_flag=
p3_name=number.of.permutations
p3_optional=
p3_prefix=
p3_prefix_when_specified=
p3_type=java.lang.Integer
p3_value=

p4_MODE=IN
p4_TYPE=FILE
p4_default_value=
p4_description=Cls file - .cls, must be binary
p4_fileFormat=cls
p4_flag=
p4_name=phenotype.labels
p4_optional=
p4_prefix=
p4_prefix_when_specified=
p4_type=java.io.File
p4_value=

p5_MODE=
p5_TYPE=TEXT
p5_default_value=
p5_description=Name of the target phenotype profile.  Only applicable if class file defines continuous labels (one or more phenotype profiles).  Leave blank if class file defines a discrete phenotype.
p5_fileFormat=
p5_flag=
p5_name=target.profile
p5_optional=on
p5_prefix=
p5_prefix_when_specified=
p5_type=java.lang.String
p5_value=

p6_MODE=
p6_TYPE=TEXT
p6_default_value=true
p6_description=Select true to have GSEA collapse each probe set in the expression dataset into a single vector for the gene, which gets identified by its gene symbol.
p6_fileFormat=
p6_flag=
p6_name=collapse.dataset
p6_optional=
p6_prefix=
p6_prefix_when_specified=
p6_type=java.lang.String
p6_value=false;true

p7_MODE=
p7_TYPE=TEXT
p7_default_value=phenotype
p7_description=Type of permutations to perform
p7_fileFormat=
p7_flag=
p7_name=permutation.type
p7_optional=
p7_prefix=
p7_prefix_when_specified=
p7_type=java.lang.String
p7_value=phenotype;gene_set

p8_MODE=IN
p8_TYPE=FILE
p8_choiceDir=ftp\://ftp.broadinstitute.org/pub/gsea/annotations/
p8_choiceDirFilter=*.chip
p8_default_value=
p8_description=DNA Chip (array) annotation file from GSEA website.  Upload your own chip file if the one corresponding to your DNA Microarray platform is not listed in the drop-down menu.  A chip file is only required if collapse dataset is set to true.
p8_fileFormat=chip
p8_flag=
p8_name=chip.platform.file
p8_optional=on
p8_prefix=-chip 
p8_prefix_when_specified=-chip 
p8_type=java.io.File
p8_value=

p9_MODE=
p9_TYPE=TEXT
p9_default_value=weighted
p9_description=The statistic used to score hits (gene set members) and misses (non-members)
p9_fileFormat=
p9_flag=
p9_name=scoring.scheme
p9_optional=
p9_prefix=
p9_prefix_when_specified=
p9_type=java.lang.String
p9_value=classic;weighted;weighted_p2;weighted_p1.5

p10_MODE=
p10_TYPE=TEXT
p10_default_value=Signal2Noise
p10_description=Class separation metric - gene markers are ranked using this metric to produce the gene list
p10_fileFormat=
p10_flag=
p10_name=metric.for.ranking.genes
p10_optional=
p10_prefix=
p10_prefix_when_specified=
p10_type=java.lang.String
p10_value=Signal2Noise;tTest;Ratio_of_Means\=Ratio_of_Classes;Diff_of_Means\=Diff_of_Classes;log2_ratio_of_means\=log2_Ratio_of_Classes;Pearson;Cosine;Manhatten\=Manhattan;Euclidean

p11_MODE=
p11_TYPE=TEXT
p11_default_value=real
p11_description=Mode in which scores from the gene list should be considered
p11_fileFormat=
p11_flag=
p11_name=gene.list.sorting.mode
p11_optional=
p11_prefix=
p11_prefix_when_specified=
p11_type=java.lang.String
p11_value=real;abs

p12_MODE=
p12_TYPE=TEXT
p12_default_value=descending
p12_description=Direction in which the gene list should be ordered
p12_fileFormat=
p12_flag=
p12_name=gene.list.ordering.mode
p12_optional=
p12_prefix=
p12_prefix_when_specified=
p12_type=java.lang.String
p12_value=ascending;descending

p13_MODE=
p13_TYPE=Integer
p13_default_value=500
p13_description=Gene sets larger than this are excluded from the analysis
p13_fileFormat=
p13_flag=
p13_name=max.gene.set.size
p13_optional=
p13_prefix=
p13_prefix_when_specified=
p13_type=java.lang.Integer
p13_value=

p14_MODE=
p14_TYPE=Integer
p14_default_value=15
p14_description=Gene sets smaller than this are excluded from the analysis
p14_fileFormat=
p14_flag=
p14_name=min.gene.set.size
p14_optional=
p14_prefix=
p14_prefix_when_specified=
p14_type=java.lang.Integer
p14_value=

p15_MODE=
p15_TYPE=TEXT
p15_default_value=Max_probe
p15_description=Collapsing mode
p15_fileFormat=
p15_flag=
p15_name=collapsing.mode.for.probe.sets.with.more.than.one.match
p15_optional=
p15_prefix=
p15_prefix_when_specified=
p15_type=java.lang.String
p15_value=Max_probe;Median_of_probes

p16_MODE=
p16_TYPE=TEXT
p16_default_value=meandiv
p16_description=Normalization mode
p16_fileFormat=
p16_flag=
p16_name=normalization.mode
p16_optional=
p16_prefix=
p16_prefix_when_specified=
p16_type=java.lang.String
p16_value=meandiv;None

p17_MODE=
p17_TYPE=TEXT
p17_default_value=no_balance
p17_description=Type of phenotype randomization (does not apply to gene set permutations)
p17_fileFormat=
p17_flag=
p17_name=randomization.mode
p17_optional=
p17_prefix=
p17_prefix_when_specified=
p17_type=java.lang.String
p17_value=equalize_and_balance;no_balance

p18_MODE=
p18_TYPE=TEXT
p18_default_value=true
p18_description=If there is no known gene symbol match for a probe set, omit it from the collapsed dataset
p18_fileFormat=
p18_flag=
p18_name=omit.features.with.no.symbol.match
p18_optional=
p18_prefix=
p18_prefix_when_specified=
p18_type=java.lang.String
p18_value=false;true

p19_MODE=
p19_TYPE=TEXT
p19_default_value=true
p19_description=Create detailed gene set report (heat map, mountain plot, etc.) for every enriched gene set
p19_fileFormat=
p19_flag=
p19_name=make.detailed.gene.set.report
p19_optional=
p19_prefix=
p19_prefix_when_specified=
p19_type=java.lang.String
p19_value=false;true

p20_MODE=
p20_TYPE=TEXT
p20_default_value=false
p20_description=Use the median of each class instead of the mean for the class separation metrics
p20_fileFormat=
p20_flag=
p20_name=median.for.class.metrics
p20_optional=
p20_prefix=
p20_prefix_when_specified=
p20_type=java.lang.String
p20_value=true;false

p21_MODE=
p21_TYPE=Integer
p21_default_value=100
p21_description=Number of markers
p21_fileFormat=
p21_flag=
p21_name=number.of.markers
p21_optional=
p21_prefix=
p21_prefix_when_specified=
p21_type=java.lang.Integer
p21_value=

p22_MODE=
p22_TYPE=Integer
p22_default_value=20
p22_description=Plot GSEA mountain and related plots for the top sets of each phenotype
p22_fileFormat=
p22_flag=
p22_name=plot.graphs.for.the.top.sets.of.each.phenotype
p22_optional=
p22_prefix=
p22_prefix_when_specified=
p22_type=java.lang.Integer
p22_value=

p23_MODE=
p23_TYPE=TEXT
p23_default_value=timestamp
p23_description=Seed to use for randomization
p23_fileFormat=
p23_flag=
p23_name=random.seed
p23_optional=
p23_prefix=
p23_prefix_when_specified=
p23_type=java.lang.String
p23_value=

p24_MODE=
p24_TYPE=TEXT
p24_default_value=false
p24_description=Whether to save random ranked lists
p24_fileFormat=
p24_flag=
p24_name=save.random.ranked.lists
p24_optional=
p24_prefix=
p24_prefix_when_specified=
p24_type=java.lang.String
p24_value=false;true

p25_MODE=
p25_TYPE=TEXT
p25_default_value=false
p25_description=Whether to create SVG images (compressed) along with PNGs
p25_fileFormat=
p25_flag=
p25_name=create.svgs
p25_optional=
p25_prefix=
p25_prefix_when_specified=
p25_type=java.lang.String
p25_value=false;true

p26_MODE=
p26_TYPE=TEXT
p26_default_value=
p26_description=Semicolon-separated list of gene sets from the provided gene sets database files (GMT/GMX/GRP).  If you are using multiple files then you *must* prefix each selected gene set with its file name followed by '#' (like "my_file1.gmt#selected_gene_set1,my_file2.gmt#selected_gene_set2").  With a single file only the names are necessary.  Leave this blank to select all gene sets.
p26_fileFormat=
p26_flag=
p26_name=selected.gene.sets
p26_optional=on
p26_prefix=
p26_prefix_when_specified=-selected_gene_sets 
p26_type=java.lang.String
p26_value=

p27_MODE=
p27_TYPE=TEXT
p27_default_value=<expression.dataset_basename>.zip
p27_description=Name of the output file.  Note that this only applies if create.zip=true.
p27_fileFormat=
p27_flag=
p27_name=output.file.name
p27_optional=on
p27_prefix=
p27_prefix_when_specified=-output_file_name 
p27_type=java.lang.String
p27_value=

p28_MODE=
p28_TYPE=TEXT
p28_default_value=
p28_description=Optional alternate delimiter character for gene set names instead of comma for use with selected.gene.sets.  If used, a semicolon is recommended.
p28_fileFormat=
p28_flag=
p28_name=alt.delim
p28_optional=on
p28_prefix=
p28_prefix_when_specified=--altDelim=
p28_type=java.lang.String
p28_value=

p29_MODE=
p29_TYPE=TEXT
p29_default_value=true
p29_description=Create a ZIP bundle of the output files.
p29_fileFormat=
p29_flag=
p29_name=create.zip
p29_optional=
p29_prefix=
p29_prefix_when_specified=
p29_type=java.lang.String
p29_value=false;true

p30_MODE=
p30_TYPE=TEXT
p30_default_value=false
p30_description=Whether to save the dataset subsets backing the GSEA report heatmaps as GCT files; these will be subsets of your original dataset corresponding only to the genes of the heatmap.
p30_fileFormat=
p30_flag=
p30_name=create.gcts
p30_optional=
p30_prefix=
p30_prefix_when_specified=
p30_type=java.lang.String
p30_value=false;true

p31_MODE=
p31_TYPE=TEXT
p31_default_value=false
p31_description=Enable developer mode.
p31_fileFormat=
p31_flag=
p31_name=dev.mode
p31_optional=
p31_prefix=
p31_prefix_when_specified=
p31_type=java.lang.String
p31_value=false;true

pipelineModel=
privacy=public
quality=development
requiredPatchLSIDs=
requiredPatchURLs=
serializedModel=
taskType=Gene List Selection
category=beta
userid=eby@broadinstitute.org
version=Beta series: Updating to use the GSEA v3.0 open-source code base.  Unified the Gene Set DB selector parameters and better downloading of MSigDB files.  Added selected.gene.sets, alt.delim, creat.gcts and create.svgs parameters.  Better temp file clean-up and other internal code improvements.  Open-source release.