Printing all markers and asking how many to create

manifest

@@ -1,9 +1,9 @@
 #Tue, 17 Dec 2019 14:15:10 -0800
 JVMLevel=
-LSID=urn\:lsid\:broad.mit.edu\:cancer.software.genepattern.module.analysis\:00408\:0.2
+LSID=urn\:lsid\:broad.mit.edu\:cancer.software.genepattern.module.analysis\:00408\:0.3
 author=Satija Lab New York Genome Canter, Wrapped as a module by Ted Liefeld, UCSD School of Medicine.
 categories=SingleCell;Clustering
-commandLine=/opt/R3.6/bin/Rscript --no-save --quiet --slave --no-restore /seurat/run_seurat_clustering.R --input.file\=<input.seurat.rds.file> --output.file\=<output.filename>.rds --max_dim\=<maximum_dimension> --resolution\=<resolution> --reduction\=<reduction>
+commandLine=/opt/R3.6/bin/Rscript --no-save --quiet --slave --no-restore /seurat/run_seurat_clustering.R --input.file\=<input.seurat.rds.file> --output.file\=<output.filename>.rds --max_dim\=<maximum_dimension> --resolution\=<resolution> --reduction\=<reduction> --nmarkers\=<nmarkers>
 
 cpuType=any
 description=Companion module for the <a href="">Seurat notebook</a>. Performs clustering and marker identification on single cell data.
@@ -85,11 +85,25 @@ p5_prefix_when_specified=
 p5_type=java.lang.String
 p5_value=umap;tsne
 
+p6_MODE=
+p6_TYPE=Integer
+p6_default_value=50
+p6_description=How many cluster markers to output (a CSV file with this number of top markers per cluster will be created in addition to a CSV file with all of the cluster markers found)
+p6_fileFormat=
+p6_flag=--nmarkers
+p6_name=nmarkers
+p6_numValues=0..1
+p6_optional=
+p6_prefix=
+p6_prefix_when_specified=
+p6_type=java.lang.Integer
+p6_value=
+
 privacy=public
 publicationDate=2020-01-14
 quality=${quality.level}
 requiredPatchLSIDs=
 requiredPatchURLs=
 taskDoc=doc.html
 taskType=SingleCell
-version=Updating module description.
+version=Adding number of cluster markers as option.

run_seurat_clustering.R

@@ -38,7 +38,8 @@ option_list <- list(
   make_option("--output.file", dest="output.file"),
   make_option("--max_dim", dest="max_dim", type="integer"),
   make_option("--resolution", dest="resolution", type="double"),
-  make_option("--reduction", dest="reduction")
+  make_option("--reduction", dest="reduction"),
+  make_option("--nmarkers", dest="nmarkers",type="integer")
 )
 
 # Parse the command line arguments with the option list, printing the result
@@ -76,9 +77,10 @@ DimPlot(pbmc, reduction = opts$reduction)
 # find markers for every cluster compared to all remaining cells, report only the positive ones
 print('Finding markers for all clusters.')
 pbmc.markers <- FindAllMarkers(pbmc, only.pos = TRUE, min.pct = 0.25, logfc.threshold = 0.25)
-print('Here are the top to markers for each cluster')
-pbmc.markers %>% group_by(cluster) %>% top_n(n = 2, wt = avg_logFC)
-write.csv(pbmc.markers %>% group_by(cluster) %>% top_n(n = 2, wt = avg_logFC),paste(opts$output.file, ".csv", sep=""), row.names = FALSE)
+print('Here are the top markers for each cluster')
+pbmc.markers %>% group_by(cluster) %>% top_n(n = opts$nmarkers, wt = avg_logFC)
+write.csv(pbmc.markers %>% group_by(cluster) %>% top_n(n = opts$nmarkers, wt = avg_logFC),paste(opts$output.file, ".csv", sep=""), row.names = FALSE)
+write.csv(pbmc.markers %>% group_by(cluster) %>% top_n(n = n(), wt = avg_logFC),paste(opts$output.file, "_all_markers.csv", sep=""), row.names = FALSE)
 
 # This is too specific to PBMC, so it won't be implemented
 # new.cluster.ids <- c("Naive CD4 T", "Memory CD4 T", "CD14+ Mono", "B", "CD8 T", "FCGR3A+ Mono",

testLocal.sh

@@ -1,3 +1,3 @@
 rm -rf Job_1/*
 
-docker run -v $PWD:$PWD -w $PWD/Job_1 -t genepattern/seurat-clustering:1.0 /opt/R3.6/bin/Rscript --no-save --quiet --slave --no-restore  $PWD/run_seurat_clustering.R  --input.file=$PWD/test/data/pbmc_preprocessed.rds --output.file=postmarker --max_dim=10 --resolution=0.5 --reduction=umap
+docker run -v $PWD:$PWD -w $PWD/Job_1 -t genepattern/seurat-clustering:1.0 /opt/R3.6/bin/Rscript --no-save --quiet --slave --no-restore  $PWD/run_seurat_clustering.R  --input.file=$PWD/test/data/pbmc_preprocessed.rds --output.file=postmarker --max_dim=10 --resolution=0.5 --reduction=umap --nmarkers=4