Skip to content

Commit

Permalink
Updated to Human MSigDB v2022.1.Hs and Mouse MSigDB 2022.1.Mm
Browse files Browse the repository at this point in the history
  • Loading branch information
davideby committed Oct 3, 2022
1 parent cf45f49 commit 82c2db3
Show file tree
Hide file tree
Showing 11 changed files with 392 additions and 17 deletions.
11 changes: 8 additions & 3 deletions docs/v20/index.html
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
<!DOCTYPE html>
<!-- saved from url=(0083)http://software.broadinstitute.org/cancer/software/genepattern/modules/docs/GSEA/18 -->
<html class=""><head><meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<title>GSEA (v20.3.x)</title>
<title>GSEA (v20.4.x)</title>
<link href="./application.css" media="all" rel="stylesheet">
<script src="./application.js"></script><style>.cke{visibility:hidden;}</style><style type="text/css"></style>
<meta http-equiv="X-UA-Compatible" content="IE=edge">
Expand All @@ -15,7 +15,7 @@

<div class="gp-content-header fluid">
<div class="container">
<h1>GSEA (v20.3.x) <a style="float: right" href="https://www.genepattern.org"><img alt="GP Logo" src="gplogo.png" /></a></h1>
<h1>GSEA (v20.4.x) <a style="float: right" href="https://www.genepattern.org"><img alt="GP Logo" src="gplogo.png" /></a></h1>
</div>
</div>
<div class="container">
Expand All @@ -33,7 +33,7 @@ <h1>GSEA (v20.3.x) <a style="float: right" href="https://www.genepattern.org"><i
<p></p>
</div>
<div class="col-sm-4">
<p><strong>GSEA Version: </strong> 4.2.1</p>
<p><strong>GSEA Version: </strong> 4.3.<em>x</em></p>
</div>
</div>

Expand Down Expand Up @@ -409,6 +409,11 @@ <h2>Version Comments</h2>
</tr>
</thead>
<tbody>
<tr>
<td>20.4.0</td>
<td>2022-10-2</td>
<td>Updated to Human MSigDB v2022.1.Hs and Mouse MSigDB 2022.1.Mm.</td>
</tr>
<tr>
<td>20.3.6</td>
<td>2022-9-15</td>
Expand Down
11 changes: 8 additions & 3 deletions docs/v20/test.md
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# GSEA (v20.3.x)
# GSEA (v20.4.x)

Gene Set Enrichment Analysis

Expand All @@ -14,7 +14,7 @@ for GSEA questions.
team](http://software.broadinstitute.org/cancer/software/genepattern/contact)
for GenePattern issues.

**GSEA Version:** 4.2.1
**GSEA Version:** 4.3._x_

## Description

Expand Down Expand Up @@ -476,6 +476,11 @@ Java
</thead>
<tbody>
<tr class="even">
<td align="left">20.4.0</td>
<td align="left">2022-10-2</td>
<td align="left">Updated to Human MSigDB v2022.1.Hs and Mouse MSigDB 2022.1.Mm.</td>
</tr>
<tr class="even">
<td align="left">20.3.6</td>
<td align="left">2022-9-15</td>
<td align="left">Updated to Human MSigDB v2022.1.Hs. Direct support for Mouse MSigDB 2022.1.Mm is not yet available</td>
Expand Down Expand Up @@ -607,7 +612,7 @@ Java
</tbody>
</table>

Copyright © 2003-2021 Broad Institute, Inc., Massachusetts Institute of
Copyright © 2003-2022 Broad Institute, Inc., Massachusetts Institute of
Technology, and Regents of the University of California. All rights
reserved.

45 changes: 45 additions & 0 deletions gpunit_functionality/version_check/invalid_mix_species1_test.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,45 @@
# Copyright (c) 2003-2022 Broad Institute, Inc., Massachusetts Institute of Technology, and Regents of the University of California. All rights reserved.
#module: urn:lsid:broad.mit.edu:cancer.software.genepattern.module.analysis:00072:20
module: GSEA
name: GSEA invalid_mix_species1_test
description: Test the GSEA version check with files of mixed species no collapsing; expect an error. Note that we need to use remote files to trigger the check.
params:
expression.dataset: "<%gpunit.testData%>gpunit/GSEA/v20/input/Diabetes_collapsed_symbols.gct"
gene.sets.database: [ "https://data.broadinstitute.org/gsea-msigdb/msigdb/release/2022.1.Hs/h.all.v2022.1.Hs.symbols.gmt",
"https://data.broadinstitute.org/gsea-msigdb/msigdb/release/2022.1.Mm/m1.all.v2022.1.Mm.symbols.gmt" ]
number.of.permutations: "10"
phenotype.labels: "<%gpunit.testData%>gpunit/GSEA/v20/input/Diabetes.cls"
target.profile: ""
permutation.type: "phenotype"
collapse.dataset: "No_Collapse"
#chip.platform.file:
output.file.name: "<expression.dataset_basename>.zip"
scoring.scheme: "weighted"
metric.for.ranking.genes: "Signal2Noise"
gene.list.sorting.mode: "real"
gene.list.ordering.mode: "descending"
max.gene.set.size: "500"
min.gene.set.size: "15"
collapsing.mode.for.probe.sets.with.more.than.one.match: "Max_probe"
normalization.mode: "meandiv"
randomization.mode: "no_balance"
omit.features.with.no.symbol.match: "true"
median.for.class.metrics: "false"
number.of.markers: "100"
# Note that we use a fixed random seed rather than the 'timestamp' default so that we'll have reproducible test results
random.seed: "149"
create.svgs: "false"
create.gcts: "false"
save.random.ranked.lists: "false"
plot.graphs.for.the.top.sets.of.each.phenotype: "20"
make.detailed.gene.set.report: "false"
selected.gene.sets: ""
dev.mode: "true"
alt.delim: ""
create.zip: "false"
assertions:
jobStatus: fail
files:
"stderr.txt":
diffCmd: ../grepMessages.sh
diff: "<%gpunit.resultData%>gpunit/GSEA/v20/output/version_check/invalid_mix_species1_test/stderrMatches.txt"
47 changes: 47 additions & 0 deletions gpunit_functionality/version_check/invalid_mix_species2_test.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
# Copyright (c) 2003-2022 Broad Institute, Inc., Massachusetts Institute of Technology, and Regents of the University of California. All rights reserved.
#module: urn:lsid:broad.mit.edu:cancer.software.genepattern.module.analysis:00072:20
module: GSEA
name: GSEA invalid_mix_species2_test
description: Test the GSEA version check with files of mixed species no collapsing; expect an error. Note that we need to use remote files to trigger the check.
params:
expression.dataset: "<%gpunit.testData%>gpunit/GSEA/v20/input/Diabetes_hgu133a.gct"
gene.sets.database: [ "https://data.broadinstitute.org/gsea-msigdb/msigdb/release/2022.1.Hs/h.all.v2022.1.Hs.symbols.gmt" ]
number.of.permutations: "10"
phenotype.labels: "<%gpunit.testData%>gpunit/GSEA/v20/input/Diabetes.cls"
target.profile: ""
permutation.type: "phenotype"
collapse.dataset: "Collapse"
chip.platform.file: "https://data.broadinstitute.org/gsea-msigdb/msigdb/annotations/mouse/Human_AFFY_HG_U133_Mouse_Orthologs_MSigDB.v2022.1.Mm.chip"
# Modifying the ZIP name here so that the diffCmd can find the RNK inside. We could modify the diffCmd
# to be able to find it, but that makes the code somewhat complicated.
output.file.name: "Diabetes_hgu133a_collapsed_to_symbols.zip"
scoring.scheme: "weighted"
metric.for.ranking.genes: "Signal2Noise"
gene.list.sorting.mode: "real"
gene.list.ordering.mode: "descending"
max.gene.set.size: "500"
min.gene.set.size: "15"
collapsing.mode.for.probe.sets.with.more.than.one.match: "Mean_of_probes"
normalization.mode: "meandiv"
randomization.mode: "no_balance"
omit.features.with.no.symbol.match: "true"
median.for.class.metrics: "false"
number.of.markers: "100"
# Note that we use a fixed random seed rather than the 'timestamp' default so that we'll have reproducible test results
random.seed: "149"
create.svgs: "false"
create.gcts: "false"
save.random.ranked.lists: "false"
plot.graphs.for.the.top.sets.of.each.phenotype: "20"
make.detailed.gene.set.report: "false"
selected.gene.sets: ""
dev.mode: "true"
alt.delim: ""
create.zip: "true"
assertions:
jobStatus: fail
files:
"stderr.txt":
diffCmd: ../grepMessages.sh
diff: "<%gpunit.resultData%>gpunit/GSEA/v20/output/version_check/invalid_mix_species2_test/stderrMatches.txt"

Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
# Copyright (c) 2003-2022 Broad Institute, Inc., Massachusetts Institute of Technology, and Regents of the University of California. All rights reserved.
#module: urn:lsid:broad.mit.edu:cancer.software.genepattern.module.analysis:00072:20
module: GSEA
name: GSEA valid_same_vers_with_chip_test
description: Test the GSEA version check with files of matching version with collapsing. Note that we need to use remote files to trigger the check.
params:
expression.dataset: "<%gpunit.testData%>gpunit/GSEA/v20/input/Diabetes_hgu133a.gct"
gene.sets.database: [ "https://data.broadinstitute.org/gsea-msigdb/msigdb/release/2022.1.Hs/h.all.v2022.1.Hs.symbols.gmt" ]
number.of.permutations: "10"
phenotype.labels: "<%gpunit.testData%>gpunit/GSEA/v20/input/Diabetes.cls"
target.profile: ""
permutation.type: "phenotype"
collapse.dataset: "Collapse"
chip.platform.file: "https://data.broadinstitute.org/gsea-msigdb/msigdb/annotations/human/Human_AFFY_HG_U133_MSigDB.v2022.1.Hs.chip"
# Modifying the ZIP name here so that the diffCmd can find the RNK inside. We could modify the diffCmd
# to be able to find it, but that makes the code somewhat complicated.
output.file.name: "Diabetes_hgu133a_collapsed_to_symbols.zip"
scoring.scheme: "weighted"
metric.for.ranking.genes: "Signal2Noise"
gene.list.sorting.mode: "real"
gene.list.ordering.mode: "descending"
max.gene.set.size: "500"
min.gene.set.size: "15"
collapsing.mode.for.probe.sets.with.more.than.one.match: "Mean_of_probes"
normalization.mode: "meandiv"
randomization.mode: "no_balance"
omit.features.with.no.symbol.match: "true"
median.for.class.metrics: "false"
number.of.markers: "100"
# Note that we use a fixed random seed rather than the 'timestamp' default so that we'll have reproducible test results
random.seed: "149"
create.svgs: "false"
create.gcts: "false"
save.random.ranked.lists: "false"
plot.graphs.for.the.top.sets.of.each.phenotype: "20"
make.detailed.gene.set.report: "false"
selected.gene.sets: ""
dev.mode: "true"
alt.delim: ""
create.zip: "true"
assertions:
jobStatus: success
files:
"results.edb":
diffCmd: diff -q --strip-trailing-cr
diff: "<%gpunit.resultData%>gpunit/GSEA/v20/output/version_check/valid_same_vers_with_chip_test/results.edb"
"gene_sets.gmt":
diffCmd: diff -q --strip-trailing-cr
diff: "<%gpunit.resultData%>gpunit/GSEA/v20/output/version_check/valid_same_vers_with_chip_test/gene_sets.gmt"
"Diabetes_hgu133a_collapsed_to_symbols.rnk":
diffCmd: diff -q --strip-trailing-cr
diff: "<%gpunit.resultData%>gpunit/GSEA/v20/output/version_check/valid_same_vers_with_chip_test/Diabetes_hgu133a_collapsed_to_symbols.rnk"
51 changes: 51 additions & 0 deletions gpunit_functionality/version_check/valid_same_version_test.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
# Copyright (c) 2003-2022 Broad Institute, Inc., Massachusetts Institute of Technology, and Regents of the University of California. All rights reserved.
#module: urn:lsid:broad.mit.edu:cancer.software.genepattern.module.analysis:00072:20
module: GSEA
name: GSEA valid_same_version_test
description: Test the GSEA version check with files of matching version and no collapsing. Note that we need to use remote files to trigger the check.
params:
expression.dataset: "<%gpunit.testData%>gpunit/GSEA/v20/input/Diabetes_collapsed_symbols.gct"
gene.sets.database: [ "https://data.broadinstitute.org/gsea-msigdb/msigdb/release/2022.1.Hs/h.all.v2022.1.Hs.symbols.gmt",
"https://data.broadinstitute.org/gsea-msigdb/msigdb/release/2022.1.Hs/c1.all.v2022.1.Hs.symbols.gmt" ]
number.of.permutations: "10"
phenotype.labels: "<%gpunit.testData%>gpunit/GSEA/v20/input/Diabetes.cls"
target.profile: ""
permutation.type: "phenotype"
collapse.dataset: "No_Collapse"
#chip.platform.file:
output.file.name: "<expression.dataset_basename>.zip"
scoring.scheme: "weighted"
metric.for.ranking.genes: "Signal2Noise"
gene.list.sorting.mode: "real"
gene.list.ordering.mode: "descending"
max.gene.set.size: "500"
min.gene.set.size: "15"
collapsing.mode.for.probe.sets.with.more.than.one.match: "Max_probe"
normalization.mode: "meandiv"
randomization.mode: "no_balance"
omit.features.with.no.symbol.match: "true"
median.for.class.metrics: "false"
number.of.markers: "100"
# Note that we use a fixed random seed rather than the 'timestamp' default so that we'll have reproducible test results
random.seed: "149"
create.svgs: "false"
create.gcts: "false"
save.random.ranked.lists: "false"
plot.graphs.for.the.top.sets.of.each.phenotype: "20"
make.detailed.gene.set.report: "false"
selected.gene.sets: ""
dev.mode: "true"
alt.delim: ""
create.zip: "false"
assertions:
jobStatus: success
files:
"results.edb":
diffCmd: diff -q --strip-trailing-cr
diff: "<%gpunit.resultData%>gpunit/GSEA/v20/output/version_check/valid_same_version_test/results.edb"
"gene_sets.gmt":
diffCmd: diff -q --strip-trailing-cr
diff: "<%gpunit.resultData%>gpunit/GSEA/v20/output/version_check/valid_same_version_test/gene_sets.gmt"
"Diabetes_collapsed_symbols.rnk":
diffCmd: diff -q --strip-trailing-cr
diff: "<%gpunit.resultData%>gpunit/GSEA/v20/output/version_check/valid_same_version_test/Diabetes_collapsed_symbols.rnk"
Original file line number Diff line number Diff line change
@@ -0,0 +1,57 @@
# Copyright (c) 2003-2022 Broad Institute, Inc., Massachusetts Institute of Technology, and Regents of the University of California. All rights reserved.
#module: urn:lsid:broad.mit.edu:cancer.software.genepattern.module.analysis:00072:20
module: GSEA
name: GSEA valid_warn_mix_vers_with_chip1_test
description: Test the GSEA version check with files of mixed versions with collapsing; should warn but complete. Note that we need to use remote files to trigger the check.
params:
expression.dataset: "<%gpunit.testData%>gpunit/GSEA/v20/input/Diabetes_hgu133a.gct"
gene.sets.database: [ "https://data.broadinstitute.org/gsea-msigdb/msigdb/release/7.5.1/h.all.v7.5.1.symbols.gmt",
"https://data.broadinstitute.org/gsea-msigdb/msigdb/release/2022.1.Hs/c1.all.v2022.1.Hs.symbols.gmt" ]
number.of.permutations: "10"
phenotype.labels: "<%gpunit.testData%>gpunit/GSEA/v20/input/Diabetes.cls"
target.profile: ""
permutation.type: "phenotype"
collapse.dataset: "Collapse"
chip.platform.file: [ "https://data.broadinstitute.org/gsea-msigdb/msigdb/annotations/human/Human_AFFY_HG_U133_MSigDB.v2022.1.Hs.chip" ]
# Modifying the ZIP name here so that the diffCmd can find the RNK inside. We could modify the diffCmd
# to be able to find it, but that makes the code somewhat complicated.
output.file.name: "Diabetes_hgu133a_collapsed_to_symbols.zip"
scoring.scheme: "weighted"
metric.for.ranking.genes: "Signal2Noise"
gene.list.sorting.mode: "real"
gene.list.ordering.mode: "descending"
max.gene.set.size: "500"
min.gene.set.size: "15"
collapsing.mode.for.probe.sets.with.more.than.one.match: "Mean_of_probes"
normalization.mode: "meandiv"
randomization.mode: "no_balance"
omit.features.with.no.symbol.match: "true"
median.for.class.metrics: "false"
number.of.markers: "100"
# Note that we use a fixed random seed rather than the 'timestamp' default so that we'll have reproducible test results
random.seed: "149"
create.svgs: "false"
create.gcts: "false"
save.random.ranked.lists: "false"
plot.graphs.for.the.top.sets.of.each.phenotype: "20"
make.detailed.gene.set.report: "false"
selected.gene.sets: ""
dev.mode: "true"
alt.delim: ""
create.zip: "true"
assertions:
jobStatus: success
files:
"results.edb":
diffCmd: diff -q --strip-trailing-cr
diff: "<%gpunit.resultData%>gpunit/GSEA/v20/output/version_check/valid_warn_mix_vers_with_chip1_test/results.edb"
"gene_sets.gmt":
diffCmd: diff -q --strip-trailing-cr
diff: "<%gpunit.resultData%>gpunit/GSEA/v20/output/version_check/valid_warn_mix_vers_with_chip1_test/gene_sets.gmt"
"Diabetes_hgu133a_collapsed_to_symbols.rnk":
diffCmd: diff -q --strip-trailing-cr
diff: "<%gpunit.resultData%>gpunit/GSEA/v20/output/version_check/valid_warn_mix_vers_with_chip1_test/Diabetes_hgu133a_collapsed_to_symbols.rnk"
"stdout.txt":
diffCmd: ../grepMessages.sh
diff: "<%gpunit.resultData%>gpunit/GSEA/v20/output/version_check/ valid_warn_mix_vers_with_chip1_test/stdoutMatches.txt"

Loading

0 comments on commit 82c2db3

Please sign in to comment.