Repository 'proteore_clusterprofiler'
hg clone https://toolshed.g2.bx.psu.edu/repos/proteore/proteore_clusterprofiler

Changeset 7:4609346d8108 (2018-12-18)
Previous changeset 6:5e16cec55146 (2018-03-29) Next changeset 8:b29255864039 (2018-12-21)
Commit message:
planemo upload commit 9af2cf12c26c94e7206751ccf101a3368f92d0ba
modified:
GO-enrich.R
README.rst
cluster_profiler.xml
added:
test-data/EGO_BP_bar-plot
test-data/EGO_BP_dot-plot
test-data/EGO_CC_bar-plot
test-data/EGO_CC_dot-plot
test-data/GGO.CC.png
test-data/GGO_BP_bar-plot
test-data/GGO_CC_bar-plot
test-data/GGO_MF_bar-plot
test-data/background_ids.txt
test-data/cluster_profiler_EGO_BP.csv
test-data/cluster_profiler_EGO_CC.csv
test-data/cluster_profiler_EGO_MF.csv
test-data/cluster_profiler_GGO_BP.csv
test-data/cluster_profiler_GGO_CC.csv
test-data/cluster_profiler_GGO_MF.csv
test-data/input_id_list.csv
test-data/input_test.txt
test-data/log.txt
test-data/mouse_geneID.txt
test-data/universe.csv
removed:
test-data/clusterProfiler_diagram_outputs__GGO.CC.png
test-data/clusterProfiler_text_output.tabular
b
diff -r 5e16cec55146 -r 4609346d8108 GO-enrich.R
--- a/GO-enrich.R Thu Mar 29 11:43:28 2018 -0400
+++ b/GO-enrich.R Tue Dec 18 09:21:32 2018 -0500
[
b'@@ -1,27 +1,47 @@\n-library(clusterProfiler)\n-\n-#library(org.Sc.sgd.db)\n-library(org.Hs.eg.db)\n-library(org.Mm.eg.db)\n+options(warn=-1)  #TURN OFF WARNINGS !!!!!!\n+suppressMessages(library(clusterProfiler,quietly = TRUE))\n \n # Read file and return file content as data.frame\n-readfile = function(filename, header) {\n-  if (header == "true") {\n-    # Read only first line of the file as header:\n-    headers <- read.table(filename, nrows = 1, header = FALSE, sep = "\\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE, quote = "")\n-    #Read the data of the files (skipping the first row)\n-    file <- read.table(filename, skip = 1, header = FALSE, sep = "\\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE, quote = "")\n-    # Remove empty rows\n+read_file <- function(path,header){\n+  file <- try(read.csv(path,header=header, sep="\\t",stringsAsFactors = FALSE, quote="",check.names = F),silent=TRUE)\n+  if (inherits(file,"try-error")){\n+    stop("File not found !")\n+  }else{\n     file <- file[!apply(is.na(file) | file == "", 1, all), , drop=FALSE]\n-    #And assign the header to the data\n-    names(file) <- headers\n+    return(file)\n   }\n-  else {\n-    file <- read.table(filename, header = FALSE, sep = "\\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE, quote = "")\n-    # Remove empty rows\n-    file <- file[!apply(is.na(file) | file == "", 1, all), , drop=FALSE]\n+}\n+\n+#return the number of character from the longest description found (from the 10 first)\n+max_str_length_10_first <- function(vector){\n+  vector <- as.vector(vector)\n+  nb_description = length(vector)\n+  if (nb_description >= 10){nb_description=10}\n+  return(max(nchar(vector[1:nb_description])))\n+}\n+\n+str2bool <- function(x){\n+  if (any(is.element(c("t","true"),tolower(x)))){\n+    return (TRUE)\n+  }else if (any(is.element(c("f","false"),tolower(x)))){\n+    return (FALSE)\n+  }else{\n+    return(NULL)\n   }\n-  return(file)\n+}\n+\n+#used before the limit was set to 50 characters\n+width_by_max_char <- function (nb_max_char) {\n+  if (nb_max_char < 50 ){\n+    width=600\n+  } else if (nb_max_char < 75) {\n+    width=800\n+  } else if (nb_max_char < 100) {\n+    width=900\n+  } else {\n+    width=1000\n+  }\n+  return (width)\n }\n \n repartition.GO <- function(geneid, orgdb, ontology, level=3, readable=TRUE) {\n@@ -30,37 +50,71 @@\n                ont=ontology, \n                level=level, \n                readable=TRUE)\n-  name <- paste("GGO.", ontology, ".png", sep = "")\n-  png(name)\n-  p <- barplot(ggo, showCategory=10)\n-  print(p)\n-  dev.off()\n-  return(ggo)\n+\n+  if (length(ggo@result$ID) > 0 ) {\n+    ggo@result$Description <- sapply(as.vector(ggo@result$Description), function(x) {ifelse(nchar(x)>50, substr(x,1,50),x)},USE.NAMES = FALSE)\n+    #nb_max_char = max_str_length_10_first(ggo$Description)\n+    #width = width_by_max_char(nb_max_char)\n+    name <- paste("GGO_", ontology, "_bar-plot", sep = "")\n+    png(name,height = 720, width = 600)\n+    p <- barplot(ggo, showCategory=10)\n+    print(p)\n+    dev.off()\n+    ggo <- as.data.frame(ggo)\n+    return(ggo)\n+  }\n }\n \n # GO over-representation test\n-enrich.GO <- function(geneid, universe, orgdb, ontology, pval_cutoff, qval_cutoff) {\n+enrich.GO <- function(geneid, universe, orgdb, ontology, pval_cutoff, qval_cutoff,plot) {\n   ego<-enrichGO(gene=geneid,\n                 universe=universe,\n                 OrgDb=orgdb,\n-                keytype="ENTREZID",\n                 ont=ontology,\n                 pAdjustMethod="BH",\n                 pvalueCutoff=pval_cutoff,\n                 qvalueCutoff=qval_cutoff,\n                 readable=TRUE)\n+  \n   # Plot bar & dot plots\n-  bar_name <- paste("EGO.", ontology, ".bar.png", sep = "")\n-  png(bar_name)\n-  p <- barplot(ego)\n-  print(p)\n-  dev.off()\n-  dot_name <- paste("EGO.", ontology, ".dot.png", sep = "")\n-  png(dot_name)\n-  p <- dotplot(ego, showCategory=10)\n-  print(p)\n-  dev.off()\n-  retu'..b' == "true") {\n-    go_represent <- args$go_represent\n-    level <- as.numeric(args$level)\n-  }\n-  if (args$go_enrich == "true") {\n-    go_enrich <- args$go_enrich\n+  if (go_represent) {level <- as.numeric(args$level)}\n+  if (go_enrich) {\n     pval_cutoff <- as.numeric(args$pval_cutoff)\n     qval_cutoff <- as.numeric(args$qval_cutoff)\n     # Extract universe background genes (same as input file)\n@@ -164,52 +219,59 @@\n       universe_type = args$universe_type\n       if (universe_type == "text") {\n         universe = strsplit(args$universe, "[ \\t\\n]+")[[1]]\n-      }\n-      else if (universe_type == "file") {\n+      } else if (universe_type == "file") {\n         universe_filename = args$universe\n         universe_ncol = args$uncol\n         # Check ncol\n         if (! as.numeric(gsub("c", "", universe_ncol)) %% 1 == 0) {\n           stop("Please enter the right format for column number: c[number]")\n-        }\n-        else {\n+        } else {\n           universe_ncol = as.numeric(gsub("c", "", universe_ncol))\n         }\n-        universe_header = args$uheader\n+        universe_header = str2bool(args$uheader)\n         # Get file content\n-        universe_file = readfile(universe_filename, universe_header)\n+        universe_file = read_file(universe_filename, universe_header)\n         # Extract Protein IDs list\n-        universe = c()\n-        for (row in as.character(universe_file[,universe_ncol])) {\n-          universe = c(universe, strsplit(row, ";")[[1]][1])\n-        }\n+        universe <- sapply(universe_file[,universe_ncol], function(x) rapply(strsplit(x,";"),c),USE.NAMES = FALSE)\n       }\n       universe_id_type = args$universe_id_type\n       ##to initialize\n-      if (universe_id_type=="Uniprot") {\n+      if (universe_id_type=="Uniprot" & any(check_ids(universe,"uniprot"))) {\n         idFrom<-"UNIPROT"\n         idTo<-"ENTREZID"\n-        universe_gene<-bitr(universe, fromType=idFrom, toType=idTo, OrgDb=orgdb)\n+        suppressMessages(universe_gene<-bitr(universe, fromType=idFrom, toType=idTo, OrgDb=orgdb))\n         universe_gene<-unique(universe_gene$ENTREZID)\n-      }\n-      else if (universe_id_type=="Entrez") {\n-        universe_gene<-unique(universe)\n-      }\n-    }\n-    else {\n+      } else if (universe_id_type=="Entrez" & any(check_ids(universe,"entrez"))) {\n+        universe_gene<-unique(unlist(universe))\n+      } else {\n+        if (universe_type=="text"){\n+          print(paste(universe_id_type,"not found in your background IDs list",sep=" "))\n+        } else {\n+          print(paste(universe_id_type,"not found in the column",universe_ncol,"of your background IDs file",sep=" "))\n+        }\n+        universe_gene = NULL\n+      } \n+    } else {\n       universe_gene = NULL\n     }\n+  } else {\n+    universe_gene = NULL\n   }\n \n   ##enrichGO : GO over-representation test\n   for (onto in ontology) {\n-    if (args$go_represent == "true") {\n+    if (go_represent) {\n       ggo<-repartition.GO(gene, orgdb, onto, level, readable=TRUE)\n-      write.table(ggo, args$text_output, append = TRUE, sep="\\t", row.names = FALSE, quote=FALSE)\n+      if (is.list(ggo)){ggo <- as.data.frame(apply(ggo, c(1,2), function(x) gsub("^$|^ $", NA, x)))}  #convert "" and " " to NA\n+      output_path = paste("cluster_profiler_GGO_",onto,".tsv",sep="")\n+      write.table(ggo, output_path, sep="\\t", row.names = FALSE, quote = FALSE )\n     }\n-    if (args$go_enrich == "true") {\n-      ego<-enrich.GO(gene, universe_gene, orgdb, onto, pval_cutoff, qval_cutoff)\n-      write.table(ego, args$text_output, append = TRUE, sep="\\t", row.names = FALSE, quote=FALSE)\n+\n+    if (go_enrich) {\n+      ego<-enrich.GO(gene, universe_gene, orgdb, onto, pval_cutoff, qval_cutoff,plot)\n+      if (is.list(ego)){ego <- as.data.frame(apply(ego, c(1,2), function(x) gsub("^$|^ $", NA, x)))}  #convert "" and " " to NA\n+      output_path = paste("cluster_profiler_EGO_",onto,".tsv",sep="")\n+      write.table(ego, output_path, sep="\\t", row.names = FALSE, quote = FALSE )\n     }\n   }\n }\n'
b
diff -r 5e16cec55146 -r 4609346d8108 README.rst
--- a/README.rst Thu Mar 29 11:43:28 2018 -0400
+++ b/README.rst Tue Dec 18 09:21:32 2018 -0500
[
@@ -31,7 +31,7 @@
 compared to a background (whole organism or user-defined list). 
 
 **Input required**
-
+    
 This component works with Gene ids (e.g : 4151, 7412) or Uniprot accession number (e.g. P31946). 
 You can copy/paste these identifiers or supply a tabular file (.csv, .tsv, .txt, .tab) where there are contained.
 
@@ -42,11 +42,4 @@
 
 **User manual / Documentation** of the clusterProfiler R package (functions and parameters):
 https://bioconductor.org/packages/3.7/bioc/vignettes/clusterProfiler/inst/doc/clusterProfiler.html
-(Very well explained)
-
-**Reference**

-clusterProfiler R package reference : 
-G Yu, LG Wang, Y Han, QY He. clusterProfiler: an R package for comparing biological themes among gene clusters. 
-OMICS: A Journal of Integrative Biology 2012, 16(5):284-287. 
-doi:[10.1089/omi.2011.0118](http://dx.doi.org/10.1089/omi.2011.0118)
+(Very well explained)
\ No newline at end of file
b
diff -r 5e16cec55146 -r 4609346d8108 cluster_profiler.xml
--- a/cluster_profiler.xml Thu Mar 29 11:43:28 2018 -0400
+++ b/cluster_profiler.xml Tue Dec 18 09:21:32 2018 -0500
[
b'@@ -1,11 +1,10 @@\n-<tool id="cluter_profiler" name="clusterProfiler" version="0.1.0">\n-    <description>\n-    GO terms classification and enrichment analysis\n-    </description>\n+<tool id="cluter_profiler" name="GO terms classification and enrichment analysis" version="2018.12.18">\n+    <description>(Human, Mouse, Rat)[clusterProfiler]</description>\n     <requirements>\n         <requirement type="package" version="3.4.1">R</requirement>\n         <requirement type="package" version="3.5.0">bioconductor-org.hs.eg.db</requirement>\n         <requirement type="package" version="3.5.0">bioconductor-org.mm.eg.db</requirement>\n+        <requirement type="package" version="3.5.0">bioconductor-org.Rn.eg.db</requirement>\n         <requirement type="package" version="3.2.0">bioconductor-dose</requirement>\n         <requirement type="package" version="3.4.4">bioconductor-clusterprofiler</requirement>\n     </requirements>\n@@ -37,30 +36,29 @@\n             --pval_cutoff="$ego.pval"\n             --qval_cutoff="$ego.qval"\n             #if $ego.universe.universe_option == "true"\n-            #if $ego.universe.universe_input.universe_ids == "text"\n-                --universe_type="text"\n-                --universe="$ego.universe.universe_input.txt"\n-            #else\n-                --universe_type="file"\n-                --universe="$ego.universe.universe_input.file"\n-                --uncol="$ego.universe.universe_input.ncol"\n-                --uheader="$ego.universe.universe_input.header"\n+                #if $ego.universe.universe_input.universe_ids == "text"\n+                    --universe_type="text"\n+                    --universe="$ego.universe.universe_input.txt"\n+                #else\n+                    --universe_type="file"\n+                    --universe="$ego.universe.universe_input.file"\n+                    --uncol="$ego.universe.universe_input.ncol"\n+                    --uheader="$ego.universe.universe_input.header"\n+                #end if\n+                --universe_id_type="$ego.universe.universe_idti.universe_idtypein"\n             #end if\n-            --universe_id_type="$ego.universe.universe_idti.universe_idtypein"\n-        #end if\n         #else\n             --go_enrich="false"\n         #end if\n         \n-        --onto_opt="$ontology"\n-\n-        --text_output="$text_output"\n+        --plot="$ego.plot"        \n+        --onto_opt="$ontology" > $log\n     ]]></command>\n     <inputs>\n         <conditional name="input" >\n-            <param name="ids" type="select" label="Provide your identifiers" help="Copy/paste or ID list from a file (e.g. table)" >\n-                <option value="text">Copy/paste your identifiers</option>\n-                <option value="file" selected="true">Input file containing your identifiers</option>\n+            <param name="ids" type="select" label="Enter your IDs (UniProt Accession numer or Gene ID)" help="Copy/paste or from a file (e.g. table)" >\n+                <option value="text">Copy/paste your IDs</option>\n+                <option value="file" selected="true">Input file containing your IDs</option>\n             </param>\n             <when value="text" >\n                 <param name="txt" type="text" label="Copy/paste your identifiers" help=\'IDs must be separated by spaces into the form field, for example: P31946 P62258\' >\n@@ -76,50 +74,54 @@\n             </when>\n             <when value="file" >\n                 <param name="file" type="data" format="txt,tabular" label="Choose a file that contains your list of IDs" help="" />\n-                <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does your input file contain header?" />\n-                <param name="ncol" type="text" value="c1" label="The column number of IDs to map" help=\'For example, fill in "c1" if it is the first column, "c2" if it is the second column and so on\' />                \n+                <param name="header" type="boolean" checked="true" truevalue="true" falsevalue='..b'enes based on their projection at a specific level of the GO corpus (see parameter below), and provides functions (set to "Yes")\n+\n+"Ontology level (the higher this number, the deeper the GO level)": correspond to the level of GO hierarchy (from 1 to 3) (set to level "2" by default). In general the higher the level, the more semantically specific the term is.\n+\n+"Perform GO categories enrichment analysis?": calculate enrichment test for GO terms based on hypergeometric distribution (set to "Yes")\n \n-Two modes are allowed: either by supplying a tabular file (.csv, .tsv, .txt, .tab) including your IDs (identifiers) \n-or by copy/pasting your IDs (separated by a space).\n+"P-value cut off": P-value threshold value for the declaration of significance (default is < 0.01)\n+\n+"Q-value cut off": to prevent high false discovery rate (FDR) in multiple testing, Q-values (adjusted P-values) are estimated for FDR control. (default is < 0.05)\n+\n+"Define your own background IDs?": by default the whole genome/proteome is used as a reference background to compute the enrichment. As this reference set should normally only include genes/proteins that were monitored during your analysis, this option allows to provide your own background; this could be for instance, the total number of genes/proteins expressed in the tissue/sample under study. \n \n- \n+If you want to use your own background, click on the "Yes" button. Your gene/protein set must be a list of Entrez gene ID or Uniprot accession number (otherwise, use the ID-Converter tool of ProteoRE). Select the file containing your list of ID (as background), then specify the column number which contains IDs and the type of IDs (gene Entrez or Uniprot Accession number) as requested. \n+\n+Of note: for Human species, you can build your own background by using the "Build tissue-specific expression dataset" tool of ProteoRE.\n+\n+----- \n+\n **Output**\n \n-Text (tables) and graphics representing the repartition and/or enrichment of GO categories. \n+Diagram output: graphical output in the form of bar-plot or dot-plot (png, jpeg or pdf format), one figure for each GO category. \n+Text tables: with the following information GO category description (e.g.BP.Description), GO term identifier (e.g. BP.GOID) and GO term frequency (e.g. BP.Frequency)d graphics representing the repartition and/or enrichment of GO categories. One table and one graphic will be produced for each GO catagory. \n \n-**User manual / Documentation** of the clusterProfiler R package (functions and parameters):\n-https://bioconductor.org/packages/3.7/bioc/vignettes/clusterProfiler/inst/doc/clusterProfiler.html\n-(Very well explained)\n+-----\n \n-**Reference**\n- \n-clusterProfiler R package reference : \n+**Authors**\n G Yu, LG Wang, Y Han, QY He. clusterProfiler: an R package for comparing biological themes among gene clusters. \n-OMICS: A Journal of Integrative Biology 2012, 16(5):284-287. \n-doi:[10.1089/omi.2011.0118](http://dx.doi.org/10.1089/omi.2011.0118)\n+OMICS: A Journal of Integrative Biology 2012, 16(5):284-287. doi:[10.1089/omi.2011.0118](http://dx.doi.org/10.1089/omi.2011.0118)\n+\n+User manual / Documentation of the clusterProfiler R package (functions and parameters):\n+https://bioconductor.org/packages/3.7/bioc/vignettes/clusterProfiler/inst/doc/clusterProfiler.html\n \n -----\n \n@@ -231,9 +280,9 @@\n \n **Galaxy integration**\n \n-T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR\n+T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck - CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR\n \n-Sandra D\xc3\xa9rozier, Olivier Ru\xc3\xa9, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform\n+Sandra D\xc3\xa9rozier, Olivier Ru\xc3\xa9, Christophe Caron, Valentin Loux - INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform, FR\n \n This work has been partially funded through the French National Agency for Research (ANR) IFB project.\n \n'
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/EGO_BP_bar-plot
b
Binary file test-data/EGO_BP_bar-plot has changed
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/EGO_BP_dot-plot
b
Binary file test-data/EGO_BP_dot-plot has changed
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/EGO_CC_bar-plot
b
Binary file test-data/EGO_CC_bar-plot has changed
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/EGO_CC_dot-plot
b
Binary file test-data/EGO_CC_dot-plot has changed
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/GGO.CC.png
b
Binary file test-data/GGO.CC.png has changed
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/GGO_BP_bar-plot
b
Binary file test-data/GGO_BP_bar-plot has changed
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/GGO_CC_bar-plot
b
Binary file test-data/GGO_CC_bar-plot has changed
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/GGO_MF_bar-plot
b
Binary file test-data/GGO_MF_bar-plot has changed
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/background_ids.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/background_ids.txt Tue Dec 18 09:21:32 2018 -0500
b
b'@@ -0,0 +1,7380 @@\n+Gene\tGene.name\tTissue\tCell.type\tLevel\tReliability\tUniProt.AC\tGeneID\n+ENSG00000000938\tFGR\tlung\tmacrophages\tMedium\tEnhanced\tP09769\t2268\n+ENSG00000001167\tNFYA\tbronchus\trespiratory epithelial cells\tMedium\tEnhanced\tP23511\t4800\n+ENSG00000001167\tNFYA\tlung\tmacrophages\tLow\tEnhanced\tP23511\t4800\n+ENSG00000001167\tNFYA\tlung\tpneumocytes\tMedium\tEnhanced\tP23511\t4800\n+ENSG00000001497\tLAS1L\tbronchus\trespiratory epithelial cells\tHigh\tSupported\tQ9Y4W2\t81887\n+ENSG00000001497\tLAS1L\tlung\tpneumocytes\tMedium\tSupported\tQ9Y4W2\t81887\n+ENSG00000002549\tLAP3\tbronchus\trespiratory epithelial cells\tMedium\tEnhanced\tP28838\t51056\n+ENSG00000002549\tLAP3\tlung\tmacrophages\tMedium\tEnhanced\tP28838\t51056\n+ENSG00000002549\tLAP3\tlung\tpneumocytes\tLow\tEnhanced\tP28838\t51056\n+ENSG00000002586\tCD99\tbronchus\trespiratory epithelial cells\tMedium\tSupported\tP14209\t4267\n+ENSG00000002586\tCD99\tlung\tmacrophages\tLow\tSupported\tP14209\t4267\n+ENSG00000002822\tMAD1L1\tbronchus\trespiratory epithelial cells\tMedium\tSupported\tQ9Y6D9\t8379\n+ENSG00000002822\tMAD1L1\tlung\tmacrophages\tMedium\tSupported\tQ9Y6D9\t8379\n+ENSG00000002822\tMAD1L1\tlung\tpneumocytes\tLow\tSupported\tQ9Y6D9\t8379\n+ENSG00000002834\tLASP1\tbronchus\trespiratory epithelial cells\tLow\tEnhanced\tQ14847\t3927\n+ENSG00000002834\tLASP1\tlung\tmacrophages\tMedium\tEnhanced\tQ14847\t3927\n+ENSG00000002834\tLASP1\tlung\tpneumocytes\tLow\tEnhanced\tQ14847\t3927\n+ENSG00000003436\tTFPI\tbronchus\trespiratory epithelial cells\tMedium\tSupported\tP10646\t7035\n+ENSG00000003436\tTFPI\tlung\tmacrophages\tHigh\tSupported\tP10646\t7035\n+ENSG00000003436\tTFPI\tlung\tpneumocytes\tMedium\tSupported\tP10646\t7035\n+ENSG00000004478\tFKBP4\tbronchus\trespiratory epithelial cells\tLow\tEnhanced\tQ02790\t2288\n+ENSG00000004478\tFKBP4\tlung\tmacrophages\tLow\tEnhanced\tQ02790\t2288\n+ENSG00000004487\tKDM1A\tbronchus\trespiratory epithelial cells\tHigh\tSupported\tO60341\t23028\n+ENSG00000004487\tKDM1A\tlung\tmacrophages\tMedium\tSupported\tO60341\t23028\n+ENSG00000004487\tKDM1A\tlung\tpneumocytes\tHigh\tSupported\tO60341\t23028\n+ENSG00000004534\tRBM6\tbronchus\trespiratory epithelial cells\tHigh\tEnhanced\tP78332\t10180\n+ENSG00000004534\tRBM6\tlung\tmacrophages\tHigh\tEnhanced\tP78332\t10180\n+ENSG00000004534\tRBM6\tlung\tpneumocytes\tHigh\tEnhanced\tP78332\t10180\n+ENSG00000004700\tRECQL\tbronchus\trespiratory epithelial cells\tMedium\tEnhanced\tP46063\t5965\n+ENSG00000004700\tRECQL\tlung\tmacrophages\tLow\tEnhanced\tP46063\t5965\n+ENSG00000004700\tRECQL\tlung\tpneumocytes\tLow\tEnhanced\tP46063\t5965\n+ENSG00000004777\tARHGAP33\tbronchus\trespiratory epithelial cells\tLow\tSupported\tO14559\t115703\n+ENSG00000004777\tARHGAP33\tlung\tmacrophages\tLow\tSupported\tO14559\t115703\n+ENSG00000004777\tARHGAP33\tlung\tpneumocytes\tMedium\tSupported\tO14559\t115703\n+ENSG00000004897\tCDC27\tbronchus\trespiratory epithelial cells\tHigh\tSupported\tP30260\t996\n+ENSG00000004897\tCDC27\tlung\tmacrophages\tLow\tSupported\tP30260\t996\n+ENSG00000004897\tCDC27\tlung\tpneumocytes\tMedium\tSupported\tP30260\t996\n+ENSG00000005020\tSKAP2\tlung\tmacrophages\tMedium\tEnhanced\tO75563\t8935\n+ENSG00000005059\tMCUB\tbronchus\trespiratory epithelial cells\tLow\tEnhanced\tQ9NWR8\t55013\n+ENSG00000005108\tTHSD7A\tlung\tmacrophages\tLow\tSupported\tQ9UPZ6\t221981\n+ENSG00000005156\tLIG3\tbronchus\trespiratory epithelial cells\tHigh\tSupported\tP49916\t3980\n+ENSG00000005156\tLIG3\tlung\tmacrophages\tMedium\tSupported\tP49916\t3980\n+ENSG00000005156\tLIG3\tlung\tpneumocytes\tMedium\tSupported\tP49916\t3980\n+ENSG00000005175\tRPAP3\tbronchus\trespiratory epithelial cells\tHigh\tEnhanced\tQ9H6T3\t79657\n+ENSG00000005175\tRPAP3\tlung\tmacrophages\tMedium\tEnhanced\tQ9H6T3\t79657\n+ENSG00000005175\tRPAP3\tlung\tpneumocytes\tMedium\tEnhanced\tQ9H6T3\t79657\n+ENSG00000005189\tAC004381.6\tbronchus\trespiratory epithelial cells\tMedium\tEnhanced\tQ96IC2\t81691\n+ENSG00000005189\tAC004381.6\tlung\tmacrophages\tMedium\tEnhanced\tQ96IC2\t81691\n+ENSG00000005194\tCIAPIN1\tbronchus\trespiratory epithelial cells\tLow\tEnhanced\tQ6FI81\t57019\n+ENSG00000005249\tPRKAR2B\tbronchus\trespiratory epithelial cells\tLow\tEnhanced\tNA\tNA\n+ENSG00000005249\tPRKAR2B\tlung\tmacrophages\tLow\tEnhanced\tNA\tNA\n+ENSG00000005339\tCREBBP\tbronchus\trespiratory epithelial cells\tMedium\tEnhanc'..b'78\t8331\n+ENSG00000276410\tHIST1H2BB\tbronchus\trespiratory epithelial cells\tHigh\tSupported\tP33778\t3018\n+ENSG00000276410\tHIST1H2BB\tlung\tmacrophages\tHigh\tSupported\tP33778\t3018\n+ENSG00000276410\tHIST1H2BB\tlung\tpneumocytes\tHigh\tSupported\tP33778\t3018\n+ENSG00000276903\tHIST1H2AL\tbronchus\trespiratory epithelial cells\tMedium\tSupported\tNA\tNA\n+ENSG00000276903\tHIST1H2AL\tlung\tmacrophages\tHigh\tSupported\tNA\tNA\n+ENSG00000276903\tHIST1H2AL\tlung\tpneumocytes\tHigh\tSupported\tNA\tNA\n+ENSG00000276966\tHIST1H4E\tbronchus\trespiratory epithelial cells\tMedium\tSupported\tNA\tNA\n+ENSG00000276966\tHIST1H4E\tlung\tpneumocytes\tLow\tSupported\tNA\tNA\n+ENSG00000277075\tHIST1H2AE\tbronchus\trespiratory epithelial cells\tMedium\tSupported\tNA\tNA\n+ENSG00000277075\tHIST1H2AE\tlung\tmacrophages\tMedium\tSupported\tNA\tNA\n+ENSG00000277075\tHIST1H2AE\tlung\tpneumocytes\tHigh\tSupported\tNA\tNA\n+ENSG00000277157\tHIST1H4D\tbronchus\trespiratory epithelial cells\tMedium\tSupported\tNA\tNA\n+ENSG00000277157\tHIST1H4D\tlung\tpneumocytes\tLow\tSupported\tNA\tNA\n+ENSG00000277224\tHIST1H2BF\tbronchus\trespiratory epithelial cells\tHigh\tSupported\tNA\tNA\n+ENSG00000277224\tHIST1H2BF\tlung\tmacrophages\tHigh\tSupported\tNA\tNA\n+ENSG00000277224\tHIST1H2BF\tlung\tpneumocytes\tHigh\tSupported\tNA\tNA\n+ENSG00000277363\tSRCIN1\tbronchus\trespiratory epithelial cells\tLow\tEnhanced\tNA\tNA\n+ENSG00000277363\tSRCIN1\tlung\tmacrophages\tLow\tEnhanced\tNA\tNA\n+ENSG00000277443\tMARCKS\tbronchus\trespiratory epithelial cells\tHigh\tEnhanced\tP29966\t4082\n+ENSG00000277443\tMARCKS\tlung\tpneumocytes\tMedium\tEnhanced\tP29966\t4082\n+ENSG00000277775\tHIST1H3F\tbronchus\trespiratory epithelial cells\tHigh\tSupported\tNA\tNA\n+ENSG00000277775\tHIST1H3F\tlung\tmacrophages\tMedium\tSupported\tNA\tNA\n+ENSG00000277775\tHIST1H3F\tlung\tpneumocytes\tHigh\tSupported\tNA\tNA\n+ENSG00000278272\tHIST1H3C\tbronchus\trespiratory epithelial cells\tHigh\tSupported\tNA\tNA\n+ENSG00000278272\tHIST1H3C\tlung\tmacrophages\tMedium\tSupported\tNA\tNA\n+ENSG00000278272\tHIST1H3C\tlung\tpneumocytes\tHigh\tSupported\tNA\tNA\n+ENSG00000278463\tHIST1H2AB\tbronchus\trespiratory epithelial cells\tMedium\tSupported\tNA\tNA\n+ENSG00000278463\tHIST1H2AB\tlung\tmacrophages\tHigh\tSupported\tNA\tNA\n+ENSG00000278463\tHIST1H2AB\tlung\tpneumocytes\tHigh\tSupported\tNA\tNA\n+ENSG00000278535\tDHRS11\tbronchus\trespiratory epithelial cells\tLow\tEnhanced\tNA\tNA\n+ENSG00000278588\tHIST1H2BI\tbronchus\trespiratory epithelial cells\tHigh\tSupported\tNA\tNA\n+ENSG00000278588\tHIST1H2BI\tlung\tmacrophages\tHigh\tSupported\tNA\tNA\n+ENSG00000278588\tHIST1H2BI\tlung\tpneumocytes\tHigh\tSupported\tNA\tNA\n+ENSG00000278619\tMRM1\tbronchus\trespiratory epithelial cells\tMedium\tSupported\tNA\tNA\n+ENSG00000278619\tMRM1\tlung\tmacrophages\tMedium\tSupported\tNA\tNA\n+ENSG00000278637\tHIST1H4A\tbronchus\trespiratory epithelial cells\tHigh\tSupported\tNA\tNA\n+ENSG00000278637\tHIST1H4A\tlung\tmacrophages\tHigh\tSupported\tNA\tNA\n+ENSG00000278637\tHIST1H4A\tlung\tpneumocytes\tHigh\tSupported\tNA\tNA\n+ENSG00000278677\tHIST1H2AM\tbronchus\trespiratory epithelial cells\tMedium\tSupported\tNA\tNA\n+ENSG00000278677\tHIST1H2AM\tlung\tmacrophages\tHigh\tSupported\tNA\tNA\n+ENSG00000278677\tHIST1H2AM\tlung\tpneumocytes\tHigh\tSupported\tNA\tNA\n+ENSG00000278705\tHIST1H4B\tbronchus\trespiratory epithelial cells\tMedium\tSupported\tNA\tNA\n+ENSG00000278705\tHIST1H4B\tlung\tpneumocytes\tLow\tSupported\tNA\tNA\n+ENSG00000278828\tHIST1H3H\tbronchus\trespiratory epithelial cells\tHigh\tSupported\tNA\tNA\n+ENSG00000278828\tHIST1H3H\tlung\tmacrophages\tMedium\tSupported\tNA\tNA\n+ENSG00000278828\tHIST1H3H\tlung\tpneumocytes\tHigh\tSupported\tNA\tNA\n+ENSG00000278845\tMRPL45\tbronchus\trespiratory epithelial cells\tHigh\tEnhanced\tA0A087X2D5\t84311\n+ENSG00000278845\tMRPL45\tlung\tmacrophages\tMedium\tEnhanced\tA0A087X2D5\t84311\n+ENSG00000278845\tMRPL45\tlung\tpneumocytes\tLow\tEnhanced\tA0A087X2D5\t84311\n+ENSG00000280987\tMATR3\tbronchus\trespiratory epithelial cells\tHigh\tSupported\tA8MXP9\tNA\n+ENSG00000280987\tMATR3\tlung\tmacrophages\tMedium\tSupported\tA8MXP9\tNA\n+ENSG00000280987\tMATR3\tlung\tpneumocytes\tHigh\tSupported\tA8MXP9\tNA\n+ENSG00000283496\tZNF511-PRAP1\tbronchus\trespiratory epithelial cells\tLow\tSupported\tH7BY64\tNA\n+ENSG00000283496\tZNF511-PRAP1\tlung\tmacrophages\tLow\tSupported\tH7BY64\tNA\n'
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/clusterProfiler_diagram_outputs__GGO.CC.png
b
Binary file test-data/clusterProfiler_diagram_outputs__GGO.CC.png has changed
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/clusterProfiler_text_output.tabular
--- a/test-data/clusterProfiler_text_output.tabular Thu Mar 29 11:43:28 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
b'@@ -1,378 +0,0 @@\n-ID\tDescription\tCount\tGeneRatio\tgeneID\n-GO:0005886\tplasma membrane\t56\t56/153\tDSP/DSG1/ANXA2/JUP/MUC5B/ACTG1/FABP5/PIGR/ENO1/AZGP1/PLEC/TGM3/HRNR/ANXA1/HSPA5/TF/CAT/SERPINB12/CSTA/GAPDH/EEF2/MYH9/HSP90AA1/UBA52/FLNB/SOD1/HSPB1/HSPA8/EPPK1/GSTP1/DSC3/C1orf68/CTSV/CAPN1/VCL/YWHAE/IL1RN/SPRR1B/CST6/GSN/IDE/LYPD3/FLG/PERP/RPSA/LAMP1/LAMP2/RPS3/ATP5A1/PIP/MUC7/KRT1/KRT2/KRT10/SERPINA12/SPRR2E\n-GO:0005628\tprospore membrane\t0\t0/153\t\n-GO:0005789\tendoplasmic reticulum membrane\t1\t1/153\tHSPA5\n-GO:0019867\touter membrane\t2\t2/153\tARG1/UBA52\n-GO:0031090\torganelle membrane\t24\t24/153\tDSP/DSG1/ANXA2/FABP5/PIGR/LMNA/ANXA1/TF/CAT/SFN/SERPINB12/ARG1/GAPDH/SERPINA1/UBA52/DMBT1/HSPA8/YWHAZ/YWHAE/MDH2/LAMP1/LAMP2/RPS3/ATP5A1\n-GO:0034357\tphotosynthetic membrane\t0\t0/153\t\n-GO:0036362\tascus membrane\t0\t0/153\t\n-GO:0042175\tnuclear outer membrane-endoplasmic reticulum membrane network\t1\t1/153\tHSPA5\n-GO:0044425\tmembrane part\t28\t28/153\tDSP/DSG1/ANXA2/JUP/PIGR/TGM3/ANXA1/HSPA5/TF/EEF2/MYH9/TUBA1B/HSP90AA1/CTSD/DMBT1/FLNB/HSPA8/EPPK1/DSC3/CTSV/PGK1/LYPD3/PERP/LAMP1/LAMP2/RPS3/ATP5A1/PIP\n-GO:0048475\tcoated membrane\t0\t0/153\t\n-GO:0055036\tvirion membrane\t0\t0/153\t\n-GO:0098552\tside of membrane\t8\t8/153\tDSG1/JUP/TGM3/ANXA1/TF/HSPA8/CTSV/LAMP1\n-GO:0098589\tmembrane region\t7\t7/153\tANXA2/TF/EEF2/TUBA1B/CTSD/PGK1/LAMP2\n-GO:0098590\tplasma membrane region\t10\t10/153\tDSP/DSG1/ANXA2/JUP/ANXA1/TF/HSP90AA1/EPPK1/RPS3/PIP\n-GO:0098796\tmembrane protein complex\t3\t3/153\tJUP/MYH9/ATP5A1\n-GO:0098805\twhole membrane\t19\t19/153\tDSP/DSG1/ANXA2/FABP5/PIGR/ANXA1/TF/CAT/SERPINB12/ARG1/EEF2/TUBA1B/CTSD/UBA52/DMBT1/HSPA8/PGK1/LAMP1/LAMP2\n-GO:1990195\tmacrolide transmembrane transporter complex\t0\t0/153\t\n-GO:1990196\tMacAB-TolC complex\t0\t0/153\t\n-GO:1990578\tperinuclear endoplasmic reticulum membrane\t0\t0/153\t\n-GO:1990850\tH-gal-GP complex\t0\t0/153\t\n-GO:0010367\textracellular isoamylase complex\t0\t0/153\t\n-GO:0031012\textracellular matrix\t28\t28/153\tDSP/DSG1/ANXA2/JUP/ACTG1/CASP14/PLEC/LMNA/HSPA5/PKM/PRDX1/CSTA/GAPDH/EEF2/MYH9/TUBB4B/SERPINA1/CTSD/FLNB/SOD1/HSPB1/HSPA8/EIF4A1/SBSN/RPS3/ATP5A1/KRT1/DCD\n-GO:0043083\tsynaptic cleft\t0\t0/153\t\n-GO:0043230\textracellular organelle\t130\t130/153\tDSP/KRT6A/ALB/KRT16/DSG1/ANXA2/JUP/LTF/MUC5B/SERPINB3/ACTG1/KRT78/KRT17/FABP5/CASP14/PIGR/ENO1/AZGP1/PLEC/TGM3/KRT13/HRNR/KRT6B/ANXA1/HSPA5/TF/CAT/S100A7/SFN/SERPINB12/PKM/TPI1/PRDX1/CSTA/ARG1/GAPDH/HSPA1A/HSPA1B/EEF2/MYH9/TUBB4B/LYZ/TUBA1B/SERPINA1/HSP90AA1/ACTN4/GGCT/LDHA/CTSD/UBA52/TXN/DMBT1/LGALS7B/BLMH/FLNB/SOD1/HSPB1/HSPA8/EIF4A1/PPIA/YWHAZ/GGH/GSTP1/LCN1/SERPINB4/C1orf68/SBSN/CTSV/PGK1/ALDOA/CAPN1/VCL/YWHAE/HBB/A2ML1/HP/SERPINA3/ORM1/IL1RN/SPRR1B/SERPINB1/LCN2/CST6/S100A14/GSN/AGA/PSMA3/EEF1G/SERPINB5/MDH2/FCGBP/PNP/CSTB/ALDOC/KRT15/SERPINB13/APOD/KLK1/CTSB/RPSA/LAMP1/LAMP2/PPIB/RPS3/ATP5A1/CALML3/S100A11/CAPG/CAPZB/GSS/PSMB3/GDI2/ARPC4/ACTR2/NPC2/AMY1A/AMY1B/AMY1C/CALML5/PIP/ZG16B/CST4/MUC7/KRT1/KRT2/KRT10/FLG2/KPRP/DCD/DEFA3\n-GO:0044421\textracellular region part\t141\t141/153\tDSP/KRT6A/ALB/KRT16/DSG1/ANXA2/JUP/LTF/MUC5B/SERPINB3/ACTG1/KRT78/KRT17/FABP5/CASP14/PIGR/ENO1/AZGP1/PLEC/TGM3/KRT13/HRNR/KRT6B/LMNA/ANXA1/HSPA5/TF/CAT/S100A7/SFN/SERPINB12/PKM/TPI1/PRDX1/CSTA/ARG1/GAPDH/HSPA1A/HSPA1B/EEF2/MYH9/TUBB4B/SERPINB7/LYZ/TUBA1B/SERPINA1/HSP90AA1/IL36G/ACTN4/GGCT/LDHA/CTSD/UBA52/TXN/DMBT1/CPA4/LGALS7B/BLMH/PLBD1/FLNB/SOD1/HSPB1/HSPA8/EIF4A1/PPIA/YWHAZ/GGH/GSTP1/LCN1/SERPINB4/C1orf68/SBSN/CTSV/PGK1/ALDOA/CAPN1/VCL/YWHAE/HBB/A2ML1/HP/SERPINA3/ORM1/IL1RN/SPRR1B/SERPINB1/LCN2/CST6/S100A14/GSN/IDE/AGA/PSMA3/EEF1G/SERPINB5/MDH2/FCGBP/LYPD3/PNP/CSTB/ALDOC/KRT15/SERPINB13/APOD/KLK1/CTSB/RPSA/LAMP1/LAMP2/PPIB/RPS3/ATP5A1/CALML3/S100A11/CAPG/CAPZB/GSS/PSMB3/GDI2/ARPC4/ACTR2/NPC2/AMY1A/AMY1B/AMY1C/CALML5/PIP/ZG16B/CST4/MUC7/CST1/CST2/KRT1/KRT2/KRT10/FLG2/KPRP/SERPINA12/DCD/DEFA3/KRT85\n-GO:0048046\tapoplast\t0\t0/153\t\n-GO:0070062\textracellular exosome\t130\t130/153\tDSP/KRT6A/ALB/KRT16/DSG1/ANXA2/JUP/LTF/MUC5B/SERPINB3/ACTG1/KRT78/KRT17/FABP5/CASP14/PIGR/ENO1/AZGP1/PLEC/TGM3/KRT13/HRNR/KRT6B/ANXA1/HSPA5/TF/CAT/S100A7/SFN/SERPINB'..b'A2\n-GO:0043684\ttype IV secretion system complex\t0\t0/153\t\n-GO:0044099\tpolar tube\t0\t0/153\t\n-GO:0044297\tcell body\t6\t6/153\tARG1/FLNB/SOD1/CTSV/APOD/LAMP1\n-GO:0044424\tintracellular part\t133\t133/153\tDSP/KRT6A/ALB/KRT16/DSG1/ANXA2/JUP/LTF/MUC5B/SERPINB3/ACTG1/KRT78/KRT17/FABP5/CASP14/PIGR/ENO1/AZGP1/PLEC/KRT80/TGM3/KRT13/HRNR/KRT6B/LMNA/ANXA1/HSPA5/TF/CAT/S100A7/SFN/SERPINB12/PKM/TPI1/PRDX1/CSTA/ARG1/GAPDH/HSPA1A/HSPA1B/EEF2/MYH9/TUBB4B/SERPINB7/LYZ/TUBA1B/SERPINA1/HSP90AA1/ACTN4/GGCT/LDHA/CTSD/UBA52/TXN/DMBT1/LGALS7B/BLMH/PLBD1/FLNB/SOD1/HSPB1/HSPA8/EPPK1/EIF4A1/PPIA/YWHAZ/GGH/ALOX12B/GSTP1/SERPINB4/DSC3/C1orf68/CTSV/PGK1/ALDOA/CAPN1/VCL/YWHAE/HBB/KRT23/HP/SERPINA3/ORM1/IL1RN/SPRR1B/SERPINB1/LCN2/S100A14/GSN/IDE/AGA/PSMA3/EEF1G/SERPINB5/MDH2/PNP/CSTB/ALDOC/KRT15/FLG/PERP/SERPINB13/APOD/KLK1/CTSB/RPSA/LAMP1/LAMP2/TYMP/PPIB/RPS3/ATP5A1/S100A11/CAPG/HAL/CAPZB/GSS/PSMB3/GDI2/ARPC4/ACTR2/NPC2/CALML5/PIP/MUC7/KRT1/KRT2/KRT10/FLG2/KPRP/SPRR2E/DEFA3/KRT85\n-GO:0044457\tcell septum part\t0\t0/153\t\n-GO:0044462\texternal encapsulating structure part\t0\t0/153\t\n-GO:0044463\tcell projection part\t5\t5/153\tHSP90AA1/SOD1/HSPB1/YWHAE/RPS3\n-GO:0044697\tHICS complex\t0\t0/153\t\n-GO:0045177\tapical part of cell\t5\t5/153\tDSG1/ANXA1/TF/CTSV/PIP\n-GO:0045178\tbasal part of cell\t1\t1/153\tTF\n-GO:0051286\tcell tip\t0\t0/153\t\n-GO:0060187\tcell pole\t0\t0/153\t\n-GO:0061835\tventral surface of cell\t0\t0/153\t\n-GO:0070056\tprospore membrane leading edge\t0\t0/153\t\n-GO:0070258\tinner membrane complex\t0\t0/153\t\n-GO:0070331\tCD20-Lck-Fyn complex\t0\t0/153\t\n-GO:0070332\tCD20-Lck-Lyn-Fyn complex\t0\t0/153\t\n-GO:0070938\tcontractile ring\t1\t1/153\tMYH9\n-GO:0071944\tcell periphery\t59\t59/153\tDSP/DSG1/ANXA2/JUP/MUC5B/ACTG1/KRT17/FABP5/PIGR/ENO1/AZGP1/PLEC/TGM3/HRNR/ANXA1/HSPA5/TF/CAT/SERPINB12/CSTA/GAPDH/EEF2/MYH9/HSP90AA1/ACTN4/UBA52/FLNB/SOD1/HSPB1/HSPA8/EPPK1/GSTP1/DSC3/C1orf68/CTSV/CAPN1/VCL/YWHAE/IL1RN/SPRR1B/CST6/GSN/IDE/LYPD3/FLG/PERP/RPSA/LAMP1/LAMP2/RPS3/ATP5A1/ACTR2/PIP/MUC7/KRT1/KRT2/KRT10/SERPINA12/SPRR2E\n-GO:0072324\tascus epiplasm\t0\t0/153\t\n-GO:0090543\tFlemming body\t1\t1/153\tCAPG\n-GO:0090635\textracellular core region of desmosome\t0\t0/153\t\n-GO:0090636\touter dense plaque of desmosome\t0\t0/153\t\n-GO:0090637\tinner dense plaque of desmosome\t0\t0/153\t\n-GO:0097223\tsperm part\t0\t0/153\t\n-GO:0097268\tcytoophidium\t0\t0/153\t\n-GO:0097458\tneuron part\t10\t10/153\tARG1/ACTN4/FLNB/SOD1/HSPB1/HSPA8/CTSV/YWHAE/APOD/LAMP1\n-GO:0097569\tlateral shield\t0\t0/153\t\n-GO:0097574\tlateral part of cell\t0\t0/153\t\n-GO:0097610\tcell surface furrow\t1\t1/153\tMYH9\n-GO:0097613\tdinoflagellate epicone\t0\t0/153\t\n-GO:0097614\tdinoflagellate hypocone\t0\t0/153\t\n-GO:0097653\tunencapsulated part of cell\t0\t0/153\t\n-GO:0097683\tdinoflagellate apex\t0\t0/153\t\n-GO:0097684\tdinoflagellate antapex\t0\t0/153\t\n-GO:0098046\ttype V protein secretion system complex\t0\t0/153\t\n-GO:0098862\tcluster of actin-based cell projections\t4\t4/153\tPLEC/MYH9/ACTN4/FLNB\n-GO:1990015\tensheathing process\t0\t0/153\t\n-GO:1990016\tneck portion of tanycyte\t0\t0/153\t\n-GO:1990018\ttail portion of tanycyte\t0\t0/153\t\n-GO:1990225\trhoptry neck\t0\t0/153\t\n-GO:1990794\tbasolateral part of cell\t0\t0/153\t\n-GO:0031594\tneuromuscular junction\t1\t1/153\tMYH9\n-GO:0044456\tsynapse part\t3\t3/153\tHSPA8/LAMP1/ACTR2\n-GO:0060076\texcitatory synapse\t0\t0/153\t\n-GO:0060077\tinhibitory synapse\t0\t0/153\t\n-GO:0097470\tribbon synapse\t0\t0/153\t\n-GO:0098685\tSchaffer collateral - CA1 synapse\t0\t0/153\t\n-GO:0098686\thippocampal mossy fiber to CA3 synapse\t0\t0/153\t\n-GO:0098978\tglutamatergic synapse\t0\t0/153\t\n-GO:0098979\tpolyadic synapse\t0\t0/153\t\n-GO:0098981\tcholinergic synapse\t0\t0/153\t\n-GO:0098982\tGABA-ergic synapse\t0\t0/153\t\n-GO:0098984\tneuron to neuron synapse\t1\t1/153\tACTR2\n-GO:0009506\tplasmodesma\t0\t0/153\t\n-GO:0005818\taster\t0\t0/153\t\n-GO:0097740\tparaflagellar rod\t0\t0/153\t\n-GO:0097741\tmastigoneme\t0\t0/153\t\n-GO:0098644\tcomplex of collagen trimers\t0\t0/153\t\n-GO:0099081\tsupramolecular polymer\t30\t30/153\tDSP/KRT6A/KRT16/JUP/ACTG1/KRT78/KRT17/CASP14/ENO1/PLEC/KRT80/KRT13/KRT6B/LMNA/TUBB4B/TUBA1B/ACTN4/FLNB/HSPB1/EPPK1/ALDOA/VCL/KRT23/KRT15/FLG/CAPZB/KRT1/KRT2/KRT10/KRT85\n'
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/cluster_profiler_EGO_BP.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cluster_profiler_EGO_BP.csv Tue Dec 18 09:21:32 2018 -0500
b
@@ -0,0 +1,20 @@
+ID Description GeneRatio BgRatio pvalue p.adjust qvalue geneID Count
+GO:0002283 neutrophil activation involved in immune response 27/149 168/2853 5.99262610186788e-08 5.02726307819038e-05 5.02726307819038e-05 DSP/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 27
+GO:0043312 neutrophil degranulation 27/149 168/2853 5.99262610186788e-08 5.02726307819038e-05 5.02726307819038e-05 DSP/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 27
+GO:0002446 neutrophil mediated immunity 27/149 169/2853 6.82352392138906e-08 5.02726307819038e-05 5.02726307819038e-05 DSP/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 27
+GO:0042119 neutrophil activation 27/149 172/2853 1.00061112604686e-07 5.02726307819038e-05 5.02726307819038e-05 DSP/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 27
+GO:0036230 granulocyte activation 27/149 173/2853 1.13431026132454e-07 5.02726307819038e-05 5.02726307819038e-05 DSP/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 27
+GO:0043299 leukocyte degranulation 27/149 180/2853 2.65006585212016e-07 8.25330901595836e-05 8.25330901595836e-05 DSP/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 27
+GO:0031424 keratinization 10/149 26/2853 2.89179325599142e-07 8.25330901595836e-05 8.25330901595836e-05 DSP/KRT6A/DSG1/JUP/KRT17/KRT6B/SFN/CSTA/CAPN1/KRT15 10
+GO:0002444 myeloid leukocyte mediated immunity 27/149 181/2853 2.97953394077919e-07 8.25330901595836e-05 8.25330901595836e-05 DSP/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 27
+GO:0002275 myeloid cell activation involved in immune response 27/149 183/2853 3.75549726596481e-07 9.24686882375336e-05 9.24686882375336e-05 DSP/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 27
+GO:0070268 cornification 9/149 23/2853 9.92125868947906e-07 0.000219855092558856 0.000219855092558856 DSP/KRT6A/DSG1/JUP/KRT17/KRT6B/CSTA/CAPN1/KRT15 9
+GO:0045055 regulated exocytosis 29/149 223/2853 2.0213368484075e-06 0.000407207496006457 0.000407207496006457 DSP/ALB/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/SOD1/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 29
+GO:0002274 myeloid leukocyte activation 27/149 203/2853 3.12478790836653e-06 0.000577044167078353 0.000577044167078353 DSP/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 27
+GO:0006887 exocytosis 30/149 244/2853 4.33119966176751e-06 0.000738302957728985 0.000738302957728985 DSP/ALB/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/ANXA1/CAT/EEF2/TUBB4B/LYZ/CTSD/SOD1/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 30
+GO:0002366 leukocyte activation involved in immune response 28/149 221/2853 5.31851626919331e-06 0.000806185471823388 0.000806185471823388 DSP/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/ANXA1/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 28
+GO:0030216 keratinocyte differentiation 12/149 50/2853 5.7487351124723e-06 0.000806185471823388 0.000806185471823388 DSP/KRT6A/DSG1/JUP/KRT17/KRT6B/ANXA1/SFN/CSTA/FLNB/CAPN1/KRT15 12
+GO:0002263 cell activation involved in immune response 28/149 222/2853 5.82083373157681e-06 0.000806185471823388 0.000806185471823388 DSP/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/ANXA1/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 28
+GO:0009913 epidermal cell differentiation 13/149 60/2853 7.8304899549941e-06 0.00102072739648629 0.00102072739648629 DSP/KRT6A/DSG1/JUP/KRT17/KRT6B/ANXA1/SFN/CSTA/FLNB/SOD1/CAPN1/KRT15 13
+GO:0002443 leukocyte mediated immunity 28/149 241/2853 2.87263795698714e-05 0.00353653650704639 0.00353653650704639 DSP/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/SERPINB4/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 28
+GO:0008544 epidermis development 14/149 83/2853 7.05318311161389e-05 0.00822623882912441 0.00822623882912441 DSP/KRT6A/DSG1/JUP/KRT17/FABP5/KRT6B/ANXA1/SFN/CSTA/FLNB/SOD1/CAPN1/KRT15 14
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/cluster_profiler_EGO_CC.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cluster_profiler_EGO_CC.csv Tue Dec 18 09:21:32 2018 -0500
b
@@ -0,0 +1,18 @@
+ID Description GeneRatio BgRatio pvalue p.adjust qvalue geneID Count
+GO:0034774 secretory granule lumen 22/152 111/2939 2.07482731603193e-08 3.16370874431657e-06 2.781282412586e-06 ALB/ANXA2/JUP/LTF/SERPINB3/FABP5/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/VCL/SERPINA3/LCN2/GSN/AGA/PNP/S100A11/GDI2/NPC2 22
+GO:0031983 vesicle lumen 22/152 114/2939 3.4766030157325e-08 3.16370874431657e-06 2.781282412586e-06 ALB/ANXA2/JUP/LTF/SERPINB3/FABP5/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/VCL/SERPINA3/LCN2/GSN/AGA/PNP/S100A11/GDI2/NPC2 22
+GO:0060205 cytoplasmic vesicle lumen 22/152 114/2939 3.4766030157325e-08 3.16370874431657e-06 2.781282412586e-06 ALB/ANXA2/JUP/LTF/SERPINB3/FABP5/CAT/EEF2/TUBB4B/LYZ/CTSD/GSTP1/ALDOA/VCL/SERPINA3/LCN2/GSN/AGA/PNP/S100A11/GDI2/NPC2 22
+GO:0030141 secretory granule 30/152 232/2939 1.22925605779538e-06 8.38967259445349e-05 7.3755363467723e-05 DSP/ALB/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/DMBT1/SOD1/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 30
+GO:0099503 secretory vesicle 30/152 251/2939 6.60174269183974e-06 0.00036045515097445 0.000316883649208308 DSP/ALB/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/CAT/EEF2/TUBB4B/LYZ/CTSD/DMBT1/SOD1/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 30
+GO:0101002 ficolin-1-rich granule 14/152 72/2939 1.18733421290438e-05 0.000540237066871494 0.000474933685161753 DSP/DSG1/JUP/CAT/EEF2/CTSD/GSTP1/ALDOA/CAPN1/VCL/GSN/PNP/LAMP1/LAMP2 14
+GO:0005766 primary lysosome 12/152 61/2939 4.56978270565284e-05 0.00143685132139962 0.00126316599683483 ANXA2/SERPINB3/FABP5/PIGR/TUBB4B/LYZ/SERPINA3/AGA/LAMP1/LAMP2/GDI2/NPC2 12
+GO:0042582 azurophil granule 12/152 61/2939 4.56978270565284e-05 0.00143685132139962 0.00126316599683483 ANXA2/SERPINB3/FABP5/PIGR/TUBB4B/LYZ/SERPINA3/AGA/LAMP1/LAMP2/GDI2/NPC2 12
+GO:0031012 extracellular matrix 17/152 113/2939 4.73687248813062e-05 0.00143685132139962 0.00126316599683483 DSP/DSG1/ANXA2/JUP/PLEC/LMNA/HSPA5/CSTA/GAPDH/EEF2/MYH9/TUBB4B/CTSD/FLNB/SOD1/HSPB1/ATP5A1 17
+GO:0005882 intermediate filament 7/152 21/2939 5.43339859285434e-05 0.00148331781584923 0.00130401566228504 DSP/KRT6A/JUP/KRT17/KRT6B/LMNA/KRT15 7
+GO:0035578 azurophil granule lumen 9/152 39/2939 0.000116381481601412 0.00288837677065322 0.00253923232584899 ANXA2/SERPINB3/FABP5/TUBB4B/LYZ/SERPINA3/AGA/GDI2/NPC2 9
+GO:0045111 intermediate filament cytoskeleton 8/152 32/2939 0.000154925405587284 0.00352455297711071 0.00309850811174568 DSP/KRT6A/JUP/KRT17/PLEC/KRT6B/LMNA/KRT15 8
+GO:1904813 ficolin-1-rich granule lumen 10/152 53/2939 0.000289825905131926 0.00573615147717977 0.00504277052938881 JUP/CAT/EEF2/CTSD/GSTP1/ALDOA/CAPN1/VCL/GSN/PNP 10
+GO:0005775 vacuolar lumen 11/152 63/2939 0.000294161614214347 0.00573615147717977 0.00504277052938881 ANXA2/SERPINB3/FABP5/TUBB4B/LYZ/CTSD/SERPINA3/AGA/LAMP2/GDI2/NPC2 11
+GO:0001533 cornified envelope 5/152 13/2939 0.000318245371505049 0.00579206576139188 0.00509192594408078 DSP/DSG1/JUP/ANXA1/CSTA 5
+GO:0044433 cytoplasmic vesicle part 32/152 338/2939 0.000357212587465447 0.00590003159894176 0.00518684096610265 DSP/ALB/DSG1/ANXA2/JUP/LTF/SERPINB3/FABP5/PIGR/ANXA1/CAT/SFN/EEF2/TUBB4B/LYZ/CTSD/UBA52/DMBT1/GSTP1/ALDOA/CAPN1/VCL/SERPINA3/LCN2/GSN/AGA/PNP/LAMP1/LAMP2/S100A11/GDI2/NPC2 32
+GO:0035580 specific granule lumen 6/152 20/2939 0.000367401235098937 0.00590003159894176 0.00518684096610265 JUP/LTF/LYZ/CTSD/VCL/LCN2 6
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/cluster_profiler_EGO_MF.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cluster_profiler_EGO_MF.csv Tue Dec 18 09:21:32 2018 -0500
b
@@ -0,0 +1,2 @@
+x
+No Go terms enriched (EGO) found for  MF ontology
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/cluster_profiler_GGO_BP.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cluster_profiler_GGO_BP.csv Tue Dec 18 09:21:32 2018 -0500
b
b'@@ -0,0 +1,586 @@\n+ID\tDescription\tCount\tGeneRatio\tgeneID\n+GO:0019953\tsexual reproduction\t3\t3/153\tSOD1/CTSV/ALDOA\n+GO:0019954\tasexual reproduction\t0\t0/153\t\n+GO:0022414\treproductive process\t10\t10/153\tDSG1/ANXA1/ARG1/MYH9/SOD1/CTSV/ALDOA/SERPINB5/CTSB/ACTR2\n+GO:0032504\tmulticellular organism reproduction\t6\t6/153\tDSG1/ANXA1/ARG1/SOD1/CTSV/CTSB\n+GO:0032505\treproduction of a single-celled organism\t0\t0/153\t\n+GO:0061887\treproduction of symbiont in host\t0\t0/153\t\n+GO:0055114\toxidation-reduction process\t16\t16/153\tENO1/CAT/PKM/TPI1/PRDX1/GAPDH/LDHA/UBA52/TXN/SOD1/ALOX12B/PGK1/ALDOA/MDH2/ALDOC/APOD\n+GO:0006807\tnitrogen compound metabolic process\t105\t105/153\tDSP/ALB/ANXA2/JUP/LTF/MUC5B/SERPINB3/KRT17/FABP5/CASP14/ENO1/AZGP1/TGM3/ANXA1/HSPA5/TF/CAT/S100A7/SFN/SERPINB12/PKM/TPI1/PRDX1/CSTA/ARG1/GAPDH/HSPA1A/HSPA1B/EEF2/MYH9/SERPINB7/LYZ/SERPINA1/HSP90AA1/ACTN4/GGCT/LDHA/CTSD/UBA52/TXN/DMBT1/CPA4/BLMH/PLBD1/SOD1/HSPB1/HSPA8/EIF4A1/PPIA/YWHAZ/GGH/ALOX12B/GSTP1/LCN1/SERPINB4/C1orf68/CTSV/PGK1/ALDOA/CAPN1/YWHAE/HBB/A2ML1/SERPINA3/SPRR1B/SERPINB1/CST6/GSN/IDE/AGA/PSMA3/EEF1G/SERPINB5/MDH2/LYPD3/PNP/CSTB/ALDOC/FLG/PERP/SERPINB13/APOD/KLK1/CTSB/RPSA/LAMP2/TYMP/PPIB/RPS3/ATP5A1/S100A11/HAL/GSS/PSMB3/PIP/CST4/MUC7/CST1/CST2/KRT1/KRT2/KRT10/SERPINA12/DCD/SPRR2E\n+GO:0009056\tcatabolic process\t41\t41/153\tANXA2/FABP5/ENO1/HSPA5/CAT/SERPINB12/PKM/TPI1/PRDX1/ARG1/GAPDH/HSPA1A/HSPA1B/LYZ/HSP90AA1/LDHA/CTSD/UBA52/BLMH/PLBD1/HSPB1/HSPA8/EIF4A1/YWHAZ/CTSV/PGK1/ALDOA/CAPN1/HBB/HP/IDE/PSMA3/PNP/ALDOC/CTSB/RPSA/LAMP2/TYMP/RPS3/HAL/PSMB3\n+GO:0009058\tbiosynthetic process\t47\t47/153\tJUP/LTF/MUC5B/KRT17/FABP5/ENO1/ANXA1/HSPA5/CAT/PKM/TPI1/ARG1/GAPDH/HSPA1A/HSPA1B/EEF2/SERPINB7/HSP90AA1/ACTN4/GGCT/UBA52/TXN/SOD1/HSPB1/HSPA8/EIF4A1/PPIA/ALOX12B/GSTP1/PGK1/ALDOA/HBB/PSMA3/EEF1G/MDH2/LYPD3/PNP/ALDOC/RPSA/TYMP/RPS3/ATP5A1/S100A11/GSS/PSMB3/MUC7/SERPINA12\n+GO:0009892\tnegative regulation of metabolic process\t42\t42/153\tANXA2/LTF/SERPINB3/ENO1/SFN/SERPINB12/CSTA/GAPDH/HSPA1A/HSPA1B/SERPINB7/SERPINA1/UBA52/TXN/SOD1/HSPB1/HSPA8/EIF4A1/YWHAZ/GSTP1/LCN1/SERPINB4/YWHAE/A2ML1/HP/SERPINA3/SERPINB1/CST6/IDE/PSMA3/SERPINB5/CSTB/SERPINB13/APOD/RPSA/RPS3/S100A11/PSMB3/CST4/CST1/CST2/SERPINA12\n+GO:0009893\tpositive regulation of metabolic process\t31\t31/153\tANXA2/LTF/SERPINB3/KRT17/ENO1/LMNA/ANXA1/HSPA5/S100A7/HSPA1A/HSPA1B/EEF2/MYH9/SERPINB7/HSP90AA1/UBA52/TXN/SOD1/HSPB1/HSPA8/ALOX12B/GSTP1/HBB/LCN2/GSN/IDE/PSMA3/PERP/RPS3/PSMB3/PIP\n+GO:0018933\tnicotine metabolic process\t0\t0/153\t\n+GO:0019222\tregulation of metabolic process\t62\t62/153\tANXA2/JUP/LTF/SERPINB3/KRT17/ENO1/LMNA/ANXA1/HSPA5/CAT/S100A7/SFN/SERPINB12/PRDX1/CSTA/GAPDH/HSPA1A/HSPA1B/EEF2/MYH9/SERPINB7/SERPINA1/HSP90AA1/ACTN4/UBA52/TXN/SOD1/HSPB1/HSPA8/EIF4A1/YWHAZ/ALOX12B/GSTP1/LCN1/SERPINB4/CAPN1/YWHAE/HBB/A2ML1/HP/SERPINA3/SERPINB1/LCN2/CST6/GSN/IDE/PSMA3/SERPINB5/CSTB/PERP/SERPINB13/APOD/RPSA/RPS3/S100A11/PSMB3/NPC2/PIP/CST4/CST1/CST2/SERPINA12\n+GO:0019694\talkanesulfonate metabolic process\t0\t0/153\t\n+GO:0019748\tsecondary metabolic process\t0\t0/153\t\n+GO:0032259\tmethylation\t2\t2/153\tEEF2/HSPA8\n+GO:0042440\tpigment metabolic process\t0\t0/153\t\n+GO:0042445\thormone metabolic process\t1\t1/153\tIDE\n+GO:0044033\tmulti-organism metabolic process\t1\t1/153\tANXA2\n+GO:0044236\tmulticellular organism metabolic process\t4\t4/153\tARG1/SERPINB7/CTSD/CTSB\n+GO:0044237\tcellular metabolic process\t103\t103/153\tDSP/ALB/ANXA2/JUP/LTF/MUC5B/SERPINB3/KRT17/FABP5/ENO1/AZGP1/TGM3/ANXA1/HSPA5/TF/CAT/S100A7/SFN/SERPINB12/PKM/TPI1/PRDX1/CSTA/ARG1/GAPDH/HSPA1A/HSPA1B/EEF2/MYH9/SERPINB7/LYZ/SERPINA1/HSP90AA1/ACTN4/GGCT/LDHA/CTSD/UBA52/TXN/DMBT1/CPA4/BLMH/PLBD1/SOD1/HSPB1/HSPA8/EIF4A1/PPIA/YWHAZ/GGH/ALOX12B/GSTP1/LCN1/SERPINB4/C1orf68/CTSV/PGK1/ALDOA/CAPN1/YWHAE/HBB/A2ML1/HP/SERPINA3/SPRR1B/SERPINB1/CST6/GSN/IDE/AGA/PSMA3/EEF1G/SERPINB5/MDH2/LYPD3/PNP/CSTB/ALDOC/FLG/PERP/SERPINB13/APOD/CTSB/RPSA/LAMP2/TYMP/PPIB/RPS3/ATP5A1/S100A11/HAL/GSS/PSMB3/NPC2/CST4/MUC7/CST1/CST2/KRT1/KRT2/KRT10/SERPINA12/SPRR2E\n+GO:0044238\tprimary metabolic process\t108\t108/153\tDSP/ALB/ANXA2/JUP/LTF/MUC5B/SE'..b'POD/RPSA/LAMP1/LAMP2/RPS3/ATP5A1/CAPZB/ACTR2/NPC2\n+GO:0051674\tlocalization of cell\t19\t19/153\tKRT16/JUP/SERPINB3/LMNA/ANXA1/HSPA5/S100A7/MYH9/ACTN4/HSPB1/EPPK1/PPIA/GSTP1/VCL/YWHAE/S100A14/APOD/ATP5A1/KRT2\n+GO:0061842\tmicrotubule organizing center localization\t0\t0/153\t\n+GO:1902579\tmulti-organism localization\t1\t1/153\tUBA52\n+GO:0051707\tresponse to other organism\t17\t17/153\tLTF/ENO1/S100A7/ARG1/GAPDH/LYZ/DMBT1/HSPB1/GSTP1/HP/LCN2/S100A14/EEF1G/NPC2/MUC7/DCD/DEFA3\n+GO:0044366\tfeeding on or from other organism\t0\t0/153\t\n+GO:0044419\tinterspecies interaction between organisms\t27\t27/153\tALB/ANXA2/LTF/SERPINB3/ARG1/GAPDH/HSPA1A/HSPA1B/LYZ/UBA52/DMBT1/HSPA8/EIF4A1/PPIA/YWHAE/GSN/IDE/PSMA3/CTSB/RPSA/LAMP1/PPIB/RPS3/PSMB3/MUC7/DCD/DEFA3\n+GO:0051703\tintraspecies interaction between organisms\t0\t0/153\t\n+GO:0051816\tacquisition of nutrients from other organism during symbiotic interaction\t0\t0/153\t\n+GO:0098630\taggregation of unicellular organisms\t0\t0/153\t\n+GO:0098740\tmulti organism cell adhesion\t0\t0/153\t\n+GO:0050789\tregulation of biological process\t101\t101/153\tDSP/ALB/KRT16/ANXA2/JUP/LTF/MUC5B/SERPINB3/ACTG1/KRT17/PIGR/ENO1/AZGP1/LMNA/ANXA1/HSPA5/TF/CAT/S100A7/SFN/SERPINB12/PRDX1/CSTA/ARG1/GAPDH/HSPA1A/HSPA1B/EEF2/MYH9/TUBB4B/SERPINB7/SERPINA1/HSP90AA1/IL36G/ACTN4/GGCT/LDHA/UBA52/TXN/DMBT1/FLNB/SOD1/HSPB1/HSPA8/EPPK1/EIF4A1/PPIA/YWHAZ/ALOX12B/GSTP1/LCN1/SERPINB4/CTSV/PGK1/ALDOA/CAPN1/VCL/YWHAE/HBB/A2ML1/HP/SERPINA3/ORM1/IL1RN/SERPINB1/LCN2/CST6/S100A14/GSN/IDE/PSMA3/SERPINB5/PNP/CSTB/PERP/SERPINB13/APOD/CTSB/RPSA/LAMP1/TYMP/PPIB/RPS3/ATP5A1/S100A11/CAPG/CAPZB/PSMB3/GDI2/ARPC4/ACTR2/NPC2/CALML5/PIP/CST4/MUC7/CST1/CST2/KRT1/SERPINA12/DEFA3\n+GO:0065008\tregulation of biological quality\t60\t60/153\tDSP/ALB/KRT16/DSG1/ANXA2/JUP/LTF/ACTG1/PIGR/AZGP1/HRNR/ANXA1/HSPA5/TF/S100A7/SFN/PRDX1/GAPDH/HSPA1A/HSPA1B/MYH9/LYZ/SERPINA1/HSP90AA1/UBA52/TXN/FLNB/SOD1/HSPB1/HSPA8/YWHAZ/ALOX12B/GSTP1/LCN1/ALDOA/VCL/YWHAE/HBB/SERPINA3/IL1RN/LCN2/S100A14/GSN/IDE/PSMA3/FLG/LAMP1/LAMP2/PPIB/CAPG/CAPZB/PSMB3/ARPC4/ACTR2/NPC2/PIP/ZG16B/CST4/KRT1/FLG2\n+GO:0065009\tregulation of molecular function\t48\t48/153\tANXA2/JUP/LTF/SERPINB3/ANXA1/HSPA5/CAT/SFN/SERPINB12/CSTA/GAPDH/HSPA1A/HSPA1B/SERPINB7/SERPINA1/HSP90AA1/IL36G/ACTN4/UBA52/TXN/SOD1/HSPB1/GSTP1/LCN1/SERPINB4/CAPN1/YWHAE/A2ML1/HP/SERPINA3/IL1RN/SERPINB1/CST6/GSN/PSMA3/SERPINB5/CSTB/PERP/SERPINB13/CTSB/TYMP/RPS3/PSMB3/GDI2/CST4/CST1/CST2/SERPINA12\n+GO:1902727\tnegative regulation of growth factor dependent skeletal muscle satellite cell proliferation\t0\t0/153\t\n+GO:1902728\tpositive regulation of growth factor dependent skeletal muscle satellite cell proliferation\t0\t0/153\t\n+GO:0044085\tcellular component biogenesis\t33\t33/153\tDSG1/ANXA2/JUP/ACTG1/PLEC/TGM3/CAT/PKM/ARG1/HSPA1A/HSPA1B/TUBB4B/POF1B/SERPINA1/HSP90AA1/ACTN4/UBA52/HSPA8/YWHAZ/ALDOA/VCL/YWHAE/HBB/LCN2/GSN/IDE/APOD/RPSA/RPS3/CAPG/CAPZB/ARPC4/ACTR2\n+GO:0001502\tcartilage condensation\t0\t0/153\t\n+GO:0009407\ttoxin catabolic process\t0\t0/153\t\n+GO:0010127\tmycothiol-dependent detoxification\t0\t0/153\t\n+GO:0010312\tdetoxification of zinc ion\t0\t0/153\t\n+GO:0051410\tdetoxification of nitrogen compound\t0\t0/153\t\n+GO:0061687\tdetoxification of inorganic compound\t0\t0/153\t\n+GO:0071722\tdetoxification of arsenic-containing substance\t0\t0/153\t\n+GO:1990748\tcellular detoxification\t8\t8/153\tALB/CAT/PRDX1/TXN/SOD1/GSTP1/HBB/HP\n+GO:0016080\tsynaptic vesicle targeting\t0\t0/153\t\n+GO:0007269\tneurotransmitter secretion\t1\t1/153\tHSPA8\n+GO:0016079\tsynaptic vesicle exocytosis\t0\t0/153\t\n+GO:0016081\tsynaptic vesicle docking\t0\t0/153\t\n+GO:0016082\tsynaptic vesicle priming\t0\t0/153\t\n+GO:0031629\tsynaptic vesicle fusion to presynaptic active zone membrane\t0\t0/153\t\n+GO:0051583\tdopamine uptake involved in synaptic transmission\t0\t0/153\t\n+GO:0099069\tsynaptic vesicle tethering involved in synaptic vesicle exocytosis\t0\t0/153\t\n+GO:0099502\tcalcium-dependent activation of synaptic vesicle fusion\t0\t0/153\t\n+GO:0099703\tinduction of synaptic vesicle exocytosis by positive regulation of presynaptic cytosolic calcium ion concentration\t0\t0/153\t\n'
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/cluster_profiler_GGO_CC.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cluster_profiler_GGO_CC.csv Tue Dec 18 09:21:32 2018 -0500
b
b'@@ -0,0 +1,381 @@\n+ID\tDescription\tCount\tGeneRatio\tgeneID\n+GO:0005886\tplasma membrane\t56\t56/153\tDSP/DSG1/ANXA2/JUP/MUC5B/ACTG1/FABP5/PIGR/ENO1/AZGP1/PLEC/TGM3/HRNR/ANXA1/HSPA5/TF/CAT/SERPINB12/CSTA/GAPDH/EEF2/MYH9/HSP90AA1/UBA52/FLNB/SOD1/HSPB1/HSPA8/EPPK1/GSTP1/DSC3/C1orf68/CTSV/CAPN1/VCL/YWHAE/IL1RN/SPRR1B/CST6/GSN/IDE/LYPD3/FLG/PERP/RPSA/LAMP1/LAMP2/RPS3/ATP5A1/PIP/MUC7/KRT1/KRT2/KRT10/SERPINA12/SPRR2E\n+GO:0005628\tprospore membrane\t0\t0/153\t\n+GO:0005789\tendoplasmic reticulum membrane\t2\t2/153\tHSPA5/UBA52\n+GO:0019867\touter membrane\t2\t2/153\tARG1/UBA52\n+GO:0031090\torganelle membrane\t24\t24/153\tDSP/DSG1/ANXA2/FABP5/PIGR/LMNA/ANXA1/TF/CAT/SFN/SERPINB12/ARG1/GAPDH/SERPINA1/UBA52/DMBT1/HSPA8/YWHAZ/YWHAE/MDH2/LAMP1/LAMP2/RPS3/ATP5A1\n+GO:0034357\tphotosynthetic membrane\t0\t0/153\t\n+GO:0036362\tascus membrane\t0\t0/153\t\n+GO:0042175\tnuclear outer membrane-endoplasmic reticulum membrane network\t2\t2/153\tHSPA5/UBA52\n+GO:0044425\tmembrane part\t29\t29/153\tDSP/DSG1/ANXA2/JUP/PIGR/TGM3/ANXA1/HSPA5/TF/EEF2/MYH9/TUBA1B/HSP90AA1/CTSD/UBA52/DMBT1/FLNB/HSPA8/EPPK1/DSC3/CTSV/PGK1/LYPD3/PERP/LAMP1/LAMP2/RPS3/ATP5A1/PIP\n+GO:0048475\tcoated membrane\t0\t0/153\t\n+GO:0055036\tvirion membrane\t0\t0/153\t\n+GO:0098589\tmembrane region\t7\t7/153\tANXA2/TF/EEF2/TUBA1B/CTSD/PGK1/LAMP2\n+GO:0098590\tplasma membrane region\t10\t10/153\tDSP/DSG1/ANXA2/JUP/ANXA1/TF/HSP90AA1/EPPK1/RPS3/PIP\n+GO:0098805\twhole membrane\t19\t19/153\tDSP/DSG1/ANXA2/FABP5/PIGR/ANXA1/TF/CAT/SERPINB12/ARG1/EEF2/TUBA1B/CTSD/UBA52/DMBT1/HSPA8/PGK1/LAMP1/LAMP2\n+GO:1990578\tperinuclear endoplasmic reticulum membrane\t0\t0/153\t\n+GO:0043083\tsynaptic cleft\t0\t0/153\t\n+GO:0044421\textracellular region part\t141\t141/153\tDSP/KRT6A/ALB/KRT16/DSG1/ANXA2/JUP/LTF/MUC5B/SERPINB3/ACTG1/KRT78/KRT17/FABP5/CASP14/PIGR/ENO1/AZGP1/PLEC/TGM3/KRT13/HRNR/KRT6B/LMNA/ANXA1/HSPA5/TF/CAT/S100A7/SFN/SERPINB12/PKM/TPI1/PRDX1/CSTA/ARG1/GAPDH/HSPA1A/HSPA1B/EEF2/MYH9/TUBB4B/SERPINB7/LYZ/TUBA1B/SERPINA1/HSP90AA1/IL36G/ACTN4/GGCT/LDHA/CTSD/UBA52/TXN/DMBT1/CPA4/LGALS7B/BLMH/PLBD1/FLNB/SOD1/HSPB1/HSPA8/EIF4A1/PPIA/YWHAZ/GGH/GSTP1/LCN1/SERPINB4/C1orf68/SBSN/CTSV/PGK1/ALDOA/CAPN1/VCL/YWHAE/HBB/A2ML1/HP/SERPINA3/ORM1/IL1RN/SPRR1B/SERPINB1/LCN2/CST6/S100A14/GSN/IDE/AGA/PSMA3/EEF1G/SERPINB5/MDH2/FCGBP/LYPD3/PNP/CSTB/ALDOC/KRT15/SERPINB13/APOD/KLK1/CTSB/RPSA/LAMP1/LAMP2/PPIB/RPS3/ATP5A1/CALML3/S100A11/CAPG/CAPZB/GSS/PSMB3/GDI2/ARPC4/ACTR2/NPC2/AMY1A/AMY1B/AMY1C/CALML5/PIP/ZG16B/CST4/MUC7/CST1/CST2/KRT1/KRT2/KRT10/FLG2/KPRP/SERPINA12/DCD/DEFA3/KRT85\n+GO:0048046\tapoplast\t0\t0/153\t\n+GO:0098595\tperivitelline space\t0\t0/153\t\n+GO:0099544\tperisynaptic space\t0\t0/153\t\n+GO:0044464\tcell part\t137\t137/153\tDSP/KRT6A/ALB/KRT16/DSG1/ANXA2/JUP/LTF/MUC5B/SERPINB3/ACTG1/KRT78/KRT17/FABP5/CASP14/PIGR/ENO1/AZGP1/PLEC/KRT80/TGM3/KRT13/HRNR/KRT6B/LMNA/ANXA1/HSPA5/TF/CAT/S100A7/SFN/SERPINB12/PKM/TPI1/PRDX1/CSTA/ARG1/GAPDH/HSPA1A/HSPA1B/EEF2/MYH9/TUBB4B/POF1B/SERPINB7/LYZ/TUBA1B/SERPINA1/HSP90AA1/ACTN4/GGCT/LDHA/CTSD/UBA52/TXN/DMBT1/LGALS7B/BLMH/PLBD1/FLNB/SOD1/HSPB1/HSPA8/EPPK1/EIF4A1/PPIA/YWHAZ/GGH/ALOX12B/GSTP1/SERPINB4/DSC3/C1orf68/CTSV/PGK1/ALDOA/CAPN1/VCL/YWHAE/HBB/KRT23/HP/SERPINA3/ORM1/IL1RN/SPRR1B/SERPINB1/LCN2/CST6/S100A14/GSN/IDE/AGA/PSMA3/EEF1G/SERPINB5/MDH2/LYPD3/PNP/CSTB/ALDOC/KRT15/FLG/PERP/SERPINB13/APOD/KLK1/CTSB/RPSA/LAMP1/LAMP2/TYMP/PPIB/RPS3/ATP5A1/S100A11/CAPG/HAL/CAPZB/GSS/PSMB3/GDI2/ARPC4/ACTR2/NPC2/CALML5/PIP/MUC7/KRT1/KRT2/KRT10/FLG2/KPRP/SERPINA12/SPRR2E/DEFA3/KRT85\n+GO:0039642\tvirion nucleoid\t0\t0/153\t\n+GO:0042645\tmitochondrial nucleoid\t0\t0/153\t\n+GO:0042646\tplastid nucleoid\t0\t0/153\t\n+GO:0043590\tbacterial nucleoid\t0\t0/153\t\n+GO:0044777\tsingle-stranded DNA-binding protein complex\t0\t0/153\t\n+GO:0044423\tvirion part\t0\t0/153\t\n+GO:0005911\tcell-cell junction\t13\t13/153\tDSP/DSG1/ANXA2/JUP/ANXA1/MYH9/POF1B/ACTN4/EPPK1/DSC3/VCL/PERP/S100A11\n+GO:0030055\tcell-substrate junction\t25\t25/153\tJUP/ACTG1/PLEC/ANXA1/HSPA5/CAT/S100A7/HSPA1A/HSPA1B/MYH9/ACTN4/FLNB/HSPB1/HSPA8/EPPK1/PPIA/YWHAZ/CAPN1/VCL/YWHAE/GSN/PPIB/RPS3/GDI2/ACTR2\n+GO:0061466\tplasma membrane part of cell junction\t0\t0/153\t\n+G'..b'A/ARG1/GAPDH/HSPA1A/HSPA1B/EEF2/MYH9/TUBB4B/POF1B/SERPINB7/LYZ/TUBA1B/SERPINA1/HSP90AA1/ACTN4/GGCT/LDHA/CTSD/UBA52/TXN/DMBT1/LGALS7B/BLMH/PLBD1/FLNB/SOD1/HSPB1/HSPA8/EPPK1/EIF4A1/PPIA/YWHAZ/GGH/ALOX12B/GSTP1/SERPINB4/C1orf68/CTSV/PGK1/ALDOA/CAPN1/VCL/YWHAE/HBB/KRT23/HP/SERPINA3/ORM1/IL1RN/SPRR1B/SERPINB1/LCN2/S100A14/GSN/IDE/AGA/PSMA3/EEF1G/SERPINB5/MDH2/PNP/CSTB/ALDOC/KRT15/FLG/PERP/SERPINB13/APOD/KLK1/CTSB/RPSA/LAMP1/LAMP2/TYMP/PPIB/RPS3/ATP5A1/S100A11/CAPG/HAL/CAPZB/GSS/PSMB3/GDI2/ARPC4/ACTR2/NPC2/CALML5/PIP/MUC7/KRT1/KRT2/KRT10/FLG2/KPRP/SPRR2E/DEFA3/KRT85\n+GO:0044457\tcell septum part\t0\t0/153\t\n+GO:0044462\texternal encapsulating structure part\t0\t0/153\t\n+GO:0044463\tcell projection part\t5\t5/153\tHSP90AA1/SOD1/HSPB1/YWHAE/RPS3\n+GO:0044697\tHICS complex\t0\t0/153\t\n+GO:0045177\tapical part of cell\t5\t5/153\tDSG1/ANXA1/TF/CTSV/PIP\n+GO:0045178\tbasal part of cell\t1\t1/153\tTF\n+GO:0051286\tcell tip\t0\t0/153\t\n+GO:0060187\tcell pole\t0\t0/153\t\n+GO:0061835\tventral surface of cell\t0\t0/153\t\n+GO:0070056\tprospore membrane leading edge\t0\t0/153\t\n+GO:0070258\tinner membrane complex\t0\t0/153\t\n+GO:0070331\tCD20-Lck-Fyn complex\t0\t0/153\t\n+GO:0070332\tCD20-Lck-Lyn-Fyn complex\t0\t0/153\t\n+GO:0070938\tcontractile ring\t1\t1/153\tMYH9\n+GO:0071944\tcell periphery\t59\t59/153\tDSP/DSG1/ANXA2/JUP/MUC5B/ACTG1/KRT17/FABP5/PIGR/ENO1/AZGP1/PLEC/TGM3/HRNR/ANXA1/HSPA5/TF/CAT/SERPINB12/CSTA/GAPDH/EEF2/MYH9/HSP90AA1/ACTN4/UBA52/FLNB/SOD1/HSPB1/HSPA8/EPPK1/GSTP1/DSC3/C1orf68/CTSV/CAPN1/VCL/YWHAE/IL1RN/SPRR1B/CST6/GSN/IDE/LYPD3/FLG/PERP/RPSA/LAMP1/LAMP2/RPS3/ATP5A1/ACTR2/PIP/MUC7/KRT1/KRT2/KRT10/SERPINA12/SPRR2E\n+GO:0072324\tascus epiplasm\t0\t0/153\t\n+GO:0090543\tFlemming body\t1\t1/153\tCAPG\n+GO:0090635\textracellular core region of desmosome\t0\t0/153\t\n+GO:0090636\touter dense plaque of desmosome\t0\t0/153\t\n+GO:0090637\tinner dense plaque of desmosome\t0\t0/153\t\n+GO:0097223\tsperm part\t1\t1/153\tALDOA\n+GO:0097268\tcytoophidium\t0\t0/153\t\n+GO:0097458\tneuron part\t11\t11/153\tARG1/ACTN4/FLNB/SOD1/HSPB1/HSPA8/CTSV/YWHAE/APOD/LAMP1/ACTR2\n+GO:0097569\tlateral shield\t0\t0/153\t\n+GO:0097574\tlateral part of cell\t0\t0/153\t\n+GO:0097610\tcell surface furrow\t1\t1/153\tMYH9\n+GO:0097613\tdinoflagellate epicone\t0\t0/153\t\n+GO:0097614\tdinoflagellate hypocone\t0\t0/153\t\n+GO:0097653\tunencapsulated part of cell\t0\t0/153\t\n+GO:0097683\tdinoflagellate apex\t0\t0/153\t\n+GO:0097684\tdinoflagellate antapex\t0\t0/153\t\n+GO:0098046\ttype V protein secretion system complex\t0\t0/153\t\n+GO:0098862\tcluster of actin-based cell projections\t4\t4/153\tPLEC/MYH9/ACTN4/FLNB\n+GO:0140022\tcnida\t0\t0/153\t\n+GO:1990015\tensheathing process\t0\t0/153\t\n+GO:1990016\tneck portion of tanycyte\t0\t0/153\t\n+GO:1990018\ttail portion of tanycyte\t0\t0/153\t\n+GO:1990065\tDxr protein complex\t0\t0/153\t\n+GO:1990204\toxidoreductase complex\t0\t0/153\t\n+GO:1990225\trhoptry neck\t0\t0/153\t\n+GO:1990455\tPTEN phosphatase complex\t0\t0/153\t\n+GO:1990722\tDAPK1-calmodulin complex\t0\t0/153\t\n+GO:1990794\tbasolateral part of cell\t0\t0/153\t\n+GO:0031594\tneuromuscular junction\t1\t1/153\tMYH9\n+GO:0044456\tsynapse part\t3\t3/153\tHSPA8/LAMP1/ACTR2\n+GO:0060076\texcitatory synapse\t0\t0/153\t\n+GO:0060077\tinhibitory synapse\t0\t0/153\t\n+GO:0097470\tribbon synapse\t0\t0/153\t\n+GO:0098685\tSchaffer collateral - CA1 synapse\t0\t0/153\t\n+GO:0098686\thippocampal mossy fiber to CA3 synapse\t0\t0/153\t\n+GO:0098690\tglycinergic synapse\t0\t0/153\t\n+GO:0098691\tdopaminergic synapse\t0\t0/153\t\n+GO:0098692\tnoradrenergic synapse\t0\t0/153\t\n+GO:0098978\tglutamatergic synapse\t0\t0/153\t\n+GO:0098979\tpolyadic synapse\t0\t0/153\t\n+GO:0098981\tcholinergic synapse\t0\t0/153\t\n+GO:0098982\tGABA-ergic synapse\t0\t0/153\t\n+GO:0098984\tneuron to neuron synapse\t1\t1/153\tACTR2\n+GO:0099154\tserotonergic synapse\t0\t0/153\t\n+GO:0009506\tplasmodesma\t0\t0/153\t\n+GO:0005818\taster\t0\t0/153\t\n+GO:0097740\tparaflagellar rod\t0\t0/153\t\n+GO:0097741\tmastigoneme\t0\t0/153\t\n+GO:0098644\tcomplex of collagen trimers\t0\t0/153\t\n+GO:0099081\tsupramolecular polymer\t31\t31/153\tDSP/KRT6A/KRT16/JUP/ACTG1/KRT78/KRT17/CASP14/ENO1/PLEC/KRT80/KRT13/KRT6B/LMNA/TUBB4B/POF1B/TUBA1B/ACTN4/FLNB/HSPB1/EPPK1/ALDOA/VCL/KRT23/KRT15/FLG/CAPZB/KRT1/KRT2/KRT10/KRT85\n'
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/cluster_profiler_GGO_MF.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cluster_profiler_GGO_MF.csv Tue Dec 18 09:21:32 2018 -0500
b
b'@@ -0,0 +1,155 @@\n+ID\tDescription\tCount\tGeneRatio\tgeneID\n+GO:0004133\tglycogen debranching enzyme activity\t0\t0/153\t\n+GO:0016491\toxidoreductase activity\t11\t11/153\tCAT/PRDX1/GAPDH/LDHA/TXN/SOD1/ALOX12B/GSTP1/PGK1/HBB/MDH2\n+GO:0008987\tquinolinate synthetase A activity\t0\t0/153\t\n+GO:0009975\tcyclase activity\t0\t0/153\t\n+GO:0010280\tUDP-L-rhamnose synthase activity\t0\t0/153\t\n+GO:0016740\ttransferase activity\t10\t10/153\tTGM3/PKM/GAPDH/HSP90AA1/GGCT/GSTP1/PGK1/EEF1G/PNP/TYMP\n+GO:0016787\thydrolase activity\t37\t37/153\tLTF/CASP14/AZGP1/ANXA1/HSPA5/CAT/ARG1/HSPA1A/HSPA1B/EEF2/MYH9/TUBB4B/LYZ/TUBA1B/HSP90AA1/CTSD/CPA4/BLMH/PLBD1/HSPA8/EIF4A1/GGH/CTSV/CAPN1/IDE/AGA/PSMA3/KLK1/CTSB/RPS3/ATP5A1/PSMB3/AMY1A/AMY1B/AMY1C/PIP/DCD\n+GO:0016829\tlyase activity\t5\t5/153\tENO1/ALDOA/ALDOC/RPS3/HAL\n+GO:0016853\tisomerase activity\t3\t3/153\tTPI1/PPIA/PPIB\n+GO:0016874\tligase activity\t1\t1/153\tGSS\n+GO:0032451\tdemethylase activity\t0\t0/153\t\n+GO:0046572\tversicolorin B synthase activity\t0\t0/153\t\n+GO:0046905\tphytoene synthase activity\t0\t0/153\t\n+GO:0061783\tpeptidoglycan muralytic activity\t1\t1/153\tLYZ\n+GO:0070283\tradical SAM enzyme activity\t0\t0/153\t\n+GO:0140096\tcatalytic activity, acting on a protein\t22\t22/153\tLTF/CASP14/TGM3/GAPDH/HSP90AA1/GGCT/CTSD/CPA4/BLMH/PPIA/GGH/CTSV/CAPN1/IDE/AGA/PSMA3/KLK1/CTSB/PPIB/PSMB3/PIP/DCD\n+GO:0140097\tcatalytic activity, acting on DNA\t2\t2/153\tANXA1/RPS3\n+GO:0140098\tcatalytic activity, acting on RNA\t2\t2/153\tAZGP1/EIF4A1\n+GO:1990055\tphenylacetaldehyde synthase activity\t0\t0/153\t\n+GO:0000156\tphosphorelay response regulator activity\t0\t0/153\t\n+GO:0004879\tnuclear receptor activity\t0\t0/153\t\n+GO:0004708\tMAP kinase kinase activity\t0\t0/153\t\n+GO:0005057\tsignal transducer activity, downstream of receptor\t0\t0/153\t\n+GO:0005068\ttransmembrane receptor protein tyrosine kinase adaptor activity\t0\t0/153\t\n+GO:0030297\ttransmembrane receptor protein tyrosine kinase activator activity\t0\t0/153\t\n+GO:0008086\tlight-activated voltage-gated calcium channel activity\t0\t0/153\t\n+GO:0008384\tIkappaB kinase activity\t0\t0/153\t\n+GO:0009927\thistidine phosphotransfer kinase activity\t0\t0/153\t\n+GO:0038023\tsignaling receptor activity\t3\t3/153\tKRT17/PIGR/DMBT1\n+GO:0038078\tMAP kinase phosphatase activity involved in regulation of innate immune response\t0\t0/153\t\n+GO:0097199\tcysteine-type endopeptidase activity involved in apoptotic signaling pathway\t0\t0/153\t\n+GO:0099107\tion channel regulator activity involved in G-protein coupled receptor signaling pathway\t0\t0/153\t\n+GO:1990890\tnetrin receptor binding\t0\t0/153\t\n+GO:0003735\tstructural constituent of ribosome\t3\t3/153\tUBA52/RPSA/RPS3\n+GO:0005199\tstructural constituent of cell wall\t1\t1/153\tJUP\n+GO:0005200\tstructural constituent of cytoskeleton\t11\t11/153\tDSP/KRT16/ACTG1/KRT17/KRT6B/TUBB4B/TUBA1B/KRT15/ARPC4/ACTR2/KRT2\n+GO:0005201\textracellular matrix structural constituent\t0\t0/153\t\n+GO:0005212\tstructural constituent of eye lens\t0\t0/153\t\n+GO:0005213\tstructural constituent of chorion\t0\t0/153\t\n+GO:0008147\tstructural constituent of bone\t0\t0/153\t\n+GO:0008307\tstructural constituent of muscle\t1\t1/153\tPLEC\n+GO:0016490\tstructural constituent of peritrophic membrane\t0\t0/153\t\n+GO:0017056\tstructural constituent of nuclear pore\t0\t0/153\t\n+GO:0019911\tstructural constituent of myelin sheath\t0\t0/153\t\n+GO:0030280\tstructural constituent of epidermis\t5\t5/153\tFLG/KRT1/KRT2/KRT10/SPRR2E\n+GO:0030527\tstructural constituent of chromatin\t0\t0/153\t\n+GO:0032947\tprotein complex scaffold activity\t0\t0/153\t\n+GO:0035804\tstructural constituent of egg coat\t0\t0/153\t\n+GO:0039660\tstructural constituent of virion\t0\t0/153\t\n+GO:0042302\tstructural constituent of cuticle\t0\t0/153\t\n+GO:0043886\tstructural constituent of carboxysome\t0\t0/153\t\n+GO:0097099\tstructural constituent of albumen\t0\t0/153\t\n+GO:0097493\tstructural molecule activity conferring elasticity\t0\t0/153\t\n+GO:0098918\tstructural constituent of synapse\t0\t0/153\t\n+GO:0005344\toxygen carrier activity\t1\t1/153\tHBB\n+GO:0022857\ttransmembrane transporter activity\t3\t3/153\tAZGP1/TF/ATP5A1\n+GO:0005326\tneurotransmitter transporter activity\t0\t0/153\t\n+G'..b"ding\t0\t0/153\t\n+GO:0050997\tquaternary ammonium group binding\t0\t0/153\t\n+GO:0051540\tmetal cluster binding\t1\t1/153\tRPS3\n+GO:0060090\tmolecular adaptor activity\t5\t5/153\tDSP/ANXA1/CSTA/SPRR1B/ARPC4\n+GO:0070026\tnitric oxide binding\t1\t1/153\tGSTP1\n+GO:0072328\talkene binding\t0\t0/153\t\n+GO:0072341\tmodified amino acid binding\t3\t3/153\tHSPA8/GSTP1/GSS\n+GO:0097159\torganic cyclic compound binding\t50\t50/153\tDSP/ALB/ANXA2/LTF/ACTG1/ENO1/PLEC/ANXA1/HSPA5/CAT/PKM/PRDX1/GAPDH/HSPA1A/HSPA1B/EEF2/MYH9/TUBB4B/TUBA1B/HSP90AA1/ACTN4/LDHA/TXN/FLNB/HSPB1/HSPA8/EPPK1/EIF4A1/PPIA/YWHAZ/PGK1/ALDOA/YWHAE/HBB/SERPINA3/IDE/EEF1G/MDH2/PNP/CSTB/APOD/RPSA/PPIB/RPS3/ATP5A1/GSS/GDI2/ACTR2/NPC2/DCD\n+GO:0097243\tflavonoid binding\t0\t0/153\t\n+GO:0097367\tcarbohydrate derivative binding\t21\t21/153\tLTF/ACTG1/HSPA5/PKM/HSPA1A/HSPA1B/EEF2/MYH9/TUBB4B/TUBA1B/HSP90AA1/ACTN4/HSPA8/EIF4A1/PGK1/IDE/PNP/CTSB/ATP5A1/GSS/ACTR2\n+GO:1901363\theterocyclic compound binding\t48\t48/153\tDSP/ALB/ANXA2/LTF/ACTG1/ENO1/PLEC/ANXA1/HSPA5/CAT/PKM/PRDX1/GAPDH/HSPA1A/HSPA1B/EEF2/MYH9/TUBB4B/TUBA1B/HSP90AA1/ACTN4/LDHA/TXN/FLNB/HSPB1/HSPA8/EPPK1/EIF4A1/PPIA/YWHAZ/PGK1/ALDOA/YWHAE/HBB/SERPINA3/IDE/EEF1G/MDH2/PNP/CSTB/RPSA/PPIB/RPS3/ATP5A1/GSS/GDI2/ACTR2/DCD\n+GO:1901567\tfatty acid derivative binding\t0\t0/153\t\n+GO:1901681\tsulfur compound binding\t3\t3/153\tLTF/GSTP1/GSS\n+GO:1902670\tcarbon dioxide binding\t0\t0/153\t\n+GO:1904012\tplatinum binding\t0\t0/153\t\n+GO:1904013\txenon atom binding\t0\t0/153\t\n+GO:1904483\tsynthetic cannabinoid binding\t0\t0/153\t\n+GO:1904493\ttetrahydrofolyl-poly(glutamate) polymer binding\t0\t0/153\t\n+GO:1904517\tMgATP(2-) binding\t0\t0/153\t\n+GO:0004362\tglutathione-disulfide reductase activity\t0\t0/153\t\n+GO:0004601\tperoxidase activity\t4\t4/153\tCAT/PRDX1/GSTP1/HBB\n+GO:0004784\tsuperoxide dismutase activity\t1\t1/153\tSOD1\n+GO:0004791\tthioredoxin-disulfide reductase activity\t1\t1/153\tTXN\n+GO:0032542\tsulfiredoxin activity\t0\t0/153\t\n+GO:0045174\tglutathione dehydrogenase (ascorbate) activity\t0\t0/153\t\n+GO:0050605\tsuperoxide reductase activity\t0\t0/153\t\n+GO:0051920\tperoxiredoxin activity\t1\t1/153\tPRDX1\n+GO:0004694\teukaryotic translation initiation factor 2alpha kinase activity\t0\t0/153\t\n+GO:0030371\ttranslation repressor activity\t0\t0/153\t\n+GO:0044748\t3'-5'-exoribonuclease activity involved in mature miRNA 3'-end processing\t0\t0/153\t\n+GO:0045183\ttranslation factor activity, non-nucleic acid binding\t0\t0/153\t\n+GO:0090079\ttranslation regulator activity, nucleic acid binding\t0\t0/153\t\n+GO:0090624\tendoribonuclease activity, cleaving miRNA-paired mRNA\t0\t0/153\t\n+GO:0004679\tAMP-activated protein kinase activity\t0\t0/153\t\n+GO:0004690\tcyclic nucleotide-dependent protein kinase activity\t0\t0/153\t\n+GO:0004872\treceptor activity\t5\t5/153\tKRT17/PIGR/DMBT1/RPSA/KRT1\n+GO:0017132\tcAMP-dependent guanyl-nucleotide exchange factor activity\t0\t0/153\t\n+GO:0031992\tenergy transducer activity\t0\t0/153\t\n+GO:0097472\tcyclin-dependent protein kinase activity\t0\t0/153\t\n+GO:0005085\tguanyl-nucleotide exchange factor activity\t1\t1/153\tYWHAE\n+GO:0016247\tchannel regulator activity\t1\t1/153\tYWHAE\n+GO:0030234\tenzyme regulator activity\t27\t27/153\tANXA2/LTF/SERPINB3/ANXA1/SFN/SERPINB12/CSTA/GAPDH/SERPINB7/SERPINA1/HSP90AA1/HSPB1/GSTP1/LCN1/SERPINB4/A2ML1/SERPINA3/SERPINB1/CST6/SERPINB5/CSTB/SERPINB13/GDI2/CST4/CST1/CST2/SERPINA12\n+GO:0030545\treceptor regulator activity\t3\t3/153\tIL36G/IL1RN/TYMP\n+GO:0001618\tvirus receptor activity\t6\t6/153\tSERPINB3/HSPA1A/HSPA1B/IDE/RPSA/LAMP1\n+GO:0000036\tacyl carrier activity\t0\t0/153\t\n+GO:0016530\tmetallochaperone activity\t0\t0/153\t\n+GO:0036370\tD-alanyl carrier activity\t0\t0/153\t\n+GO:1904091\tpeptidyl carrier protein activity involved in nonribosomal peptide biosynthesis\t0\t0/153\t\n+GO:0000988\ttranscription factor activity, protein binding\t3\t3/153\tJUP/HSPA1A/ACTN4\n+GO:0001070\tRNA binding transcription regulator activity\t0\t0/153\t\n+GO:0001072\ttranscription antitermination factor activity, RNA binding\t0\t0/153\t\n+GO:0001073\ttranscription antitermination factor activity, DNA binding\t0\t0/153\t\n+GO:0003700\tDNA binding transcription factor activity\t1\t1/153\tENO1\n"
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/input_id_list.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input_id_list.csv Tue Dec 18 09:21:32 2018 -0500
b
b'@@ -0,0 +1,179 @@\n+V1\tneXtProt_ID\tEnsembl\tSeqLength\tMW\tIsoPoint\tTMDomains\tProteinExistence\tChr\tSubcellLocations\tDiseases\tGene\tGene description\tRNA tissue category\tReliability (IH)\tRNA TS TPM\n+A0AVF1\tNX_A0AVF1\tENSG00000105948\t554\t64178\t6.5\t0\tPE1\t7\tCytoplasm;Nucleus;Nucleus;Cytoskeleton;Cytoplasm;Cilium\tNA\tTTC26\tTetratricopeptide repeat domain 26\tTissue enhanced\tSupported\tfallopian tube: 22.4;testis: 22.0\n+A1A519\tNX_A1A519\tENSG00000164334\t330\t37158\t5\t0\tPE1\t5\tNucleus\tNA\tFAM170A\tFamily with sequence similarity 170, member A\tTissue enriched\tApproved\ttestis: 20.8\n+A4FU69\tNX_A4FU69\tENSG00000176927\t1503\t173404\t5.58\t0\tPE1\t17\tNA\tNA\tEFCAB5\tEF-hand calcium binding domain 5\tTissue enriched\tUncertain\ttestis: 15.3\n+A5D8V7\tNX_A5D8V7\tENSG00000198003\t595\t69140\t9.11\t0\tPE1\t19\tCilium;Cilium basal body;Centriole;Cilium axoneme\tCiliary dyskinesia, primary, 30\tCCDC151\tCoiled-coil domain containing 151\tTissue enhanced\tSupported\tfallopian tube: 13.6;parathyroid gland: 7.0;testis: 7.5\n+A5D8W1\tNX_A5D8W1\tENSG00000105792\t941\t105883\t6.81\t0\tPE1\t7\tNA\tNA\tCFAP69\tCilia and flagella associated protein 69\tTissue enhanced\tUncertain\tprostate: 24.6\n+A6NCJ1\tNX_A6NCJ1\tENSG00000183397\t209\t24176\t9.14\t0\tPE1\t19\tCell membrane;Cytoplasm\tNA\tC19orf71\tChromosome 19 open reading frame 71\tMixed\tUncertain\tNA\n+A6NIV6\tNX_A6NIV6\tENSG00000188306\t560\t63977\t8.43\t0\tPE1\t3\tNA\tNA\tLRRIQ4\tLeucine-rich repeats and IQ motif containing 4\tTissue enhanced\tUncertain\ttestis: 4.3\n+A6NJV1\tNX_A6NJV1\tENSG00000173557\t201\t23421\t10\t0\tPE1\t2\tCytoplasm;Cytoplasmic vesicle;Nucleus\tNA\tC2orf70\tChromosome 2 open reading frame 70\tGroup enriched\tApproved\tfallopian tube: 11.9;stomach: 4.9;testis: 17.5\n+A6NNW6\tNX_A6NNW6\tENSG00000188316\t628\t68821\t5.7\t0\tPE1\t10\tNucleus\tNA\tENO4\tEnolase family member 4\tTissue enhanced\tSupported\tfallopian tube: 14.6\n+B2RC85\tNX_B2RC85\tENSG00000169402\t870\t100547\t7.16\t0\tPE2\t7\tNA\tNA\tRSPH10B2\tRadial spoke head 10 homolog B2 (Chlamydomonas)\tGroup enriched\tUncertain\tfallopian tube: 16.2;testis: 35.7\n+O14734\tNX_O14734\tENSG00000101473\t319\t35914\t7.22\t0\tPE1\t20\tMitochondrion;Cytoplasmic vesicle;Cytoplasm;Peroxisome matrix\tNA\tACOT8\tAcyl-CoA thioesterase 8\tExpressed in all\tApproved\tNA\n+O14967\tNX_O14967\tENSG00000153132\t610\t70039\t4.58\t1\tPE1\t4\tEndoplasmic reticulum;Endoplasmic reticulum membrane\tNA\tCLGN\tCalmegin\tTissue enhanced\tSupported\ttestis: 185.4\n+O15371\tNX_O15371\tENSG00000100353\t548\t63973\t5.79\t0\tPE1\t22\tCytoplasm;Nucleus;Cytoplasm\tNA\tEIF3D\tEukaryotic translation initiation factor 3, subunit D\tExpressed in all\tApproved\tNA\n+O43236\tNX_O43236\tENSG00000108387\t478\t55098\t5.77\t0\tPE1\t17\tNucleoplasm;Cytoplasm;Cytoskeleton;Flagellum;Mitochondrion;Nucleus\tNA\tSEPT4\tSeptin 4\tGroup enriched\tSupported\tadrenal gland: 218.2;cerebral cortex: 288.7;spleen: 57.8\n+O60733\tNX_O60733\tENSG00000184381\t806\t89903\t6.86\t0\tPE1\t22\tCytoplasm;Membrane\tNeurodegeneration with brain iron accumulation 2A;Parkinson disease 14;Neurodegeneration with brain iron accumulation 2B\tPLA2G6\tPhospholipase A2, group VI (cytosolic, calcium-independent)\tExpressed in all\tApproved\tNA\n+O75367\tNX_O75367\tENSG00000113648\t372\t39617\t9.8\t0\tPE1\t5\tNucleus;Nucleus;Chromosome\tNA\tH2AFY\tH2A histone family, member Y\tExpressed in all\tSupported\tNA\n+O75425\tNX_O75425\tENSG00000106330\t235\t25519\t9.29\t2\tPE1\t7\tNucleoplasm;Cytoplasm;Membrane\tNA\tMOSPD3\tMotile sperm domain containing 3\tExpressed in all\tUncertain\tNA\n+O75487\tNX_O75487\tENSG00000076716\t556\t62412\t6.26\t0\tPE1\tX\tCytoplasmic vesicle;Cell membrane;Extracellular space\tNA\tGPC4\tGlypican 4\tMixed\tApproved\tNA\n+O75610\tNX_O75610\tENSG00000243709\t366\t40880\t8.6\t0\tPE1\t1\tSecreted\tNA\tLEFTY1\tLeft-right determination factor 1\tTissue enhanced\tApproved\tcolon: 59.7;rectum: 35.8\n+O75787\tNX_O75787\tENSG00000182220\t350\t39008\t5.76\t1\tPE1\tX\tMembrane\tParkinsonism with spasticity, X-linked;Mental retardation, X-linked, with epilepsy\tATP6AP2\tATPase, H+ transporting, lysosomal accessory protein 2\tExpressed in all\tApproved\tNA\n+O95995\tNX_O95995\tENSG00000141013\t478\t56356\t7.72\t0\tPE1\t16\tCytoplasm;Cytoskeleton;Flagellum;Cilium axoneme;Cilium basal body;Golgi'..b'NA\tNA\tRIBC2\tRIB43A domain with coiled-coils 2\tGroup enriched\tUncertain\tfallopian tube: 15.8;testis: 37.3\n+Q9HBG6\tNX_Q9HBG6\tENSG00000163913\t1241\t141825\t6.08\t0\tPE1\t3\tCytoplasm;Nucleoplasm;Cytoplasm;Cilium;Cilium basal body\tCranioectodermal dysplasia 1\tIFT122\tIntraflagellar transport 122\tExpressed in all\tApproved\tNA\n+Q9HCU5\tNX_Q9HCU5\tENSG00000138073\t417\t45468\t8.02\t1\tPE1\t2\tEndoplasmic reticulum;Endoplasmic reticulum membrane;Nucleus\tNA\tPREB\tProlactin regulatory element binding\tExpressed in all\tUncertain\tNA\n+Q9NR50\tNX_Q9NR50\tENSG00000070785\t452\t50240\t6.08\t0\tPE1\t1\tCytoplasm;Cytoplasmic vesicle;Cytoplasm\tLeukodystrophy with vanishing white matter\tEIF2B3\tEukaryotic translation initiation factor 2B, subunit 3 gamma, 58kDa\tExpressed in all\tSupported\tNA\n+Q9NU02\tNX_Q9NU02\tENSG00000132623\t776\t86664\t8.51\t0\tPE1\t20\tNA\tNA\tANKEF1\tAnkyrin repeat and EF-hand domain containing 1\tTissue enhanced\tApproved\ttestis: 33.7\n+Q9NVH1\tNX_Q9NVH1\tENSG00000007923\t559\t63278\t8.54\t0\tPE1\t1\tCytoplasm;Mitochondrion\tNA\tDNAJC11\tDnaJ (Hsp40) homolog, subfamily C, member 11\tExpressed in all\tUncertain\tNA\n+Q9NWB7\tNX_Q9NWB7\tENSG00000114446\t429\t49108\t4.93\t0\tPE1\t3\tCilium basal body\tNA\tIFT57\tIntraflagellar transport 57\tMixed\tSupported\tNA\n+Q9P0V9\tNX_Q9P0V9\tENSG00000186522\t454\t52593\t6.35\t0\tPE1\t2\tCytoplasm;Cell membrane;Cytoskeleton;Cytoskeleton;Cytoplasm;Cytoskeleton\tNA\tSEPT10\tSeptin 10\tMixed\tApproved\tNA\n+Q9P1Z9\tNX_Q9P1Z9\tENSG00000197816\t1646\t191100\t5.74\t1\tPE1\t9\tMembrane\tNA\tCCDC180\tCoiled-coil domain containing 180\tGroup enriched\tNA\tfallopian tube: 15.6;testis: 37.7\n+Q9P2H3\tNX_Q9P2H3\tENSG00000068885\t777\t88035\t7.59\t0\tPE1\t3\tCytoplasm;Cilium basal body;Cilium axoneme\tShort-rib thoracic dysplasia 2 with or without polydactyly\tIFT80\tIntraflagellar transport 80\tExpressed in all\tUncertain\tNA\n+Q9P2M1\tNX_Q9P2M1\tENSG00000109771\t347\t39780\t7.99\t0\tPE1\t4\tCytoplasm\tNA\tLRP2BP\tLRP2 binding protein\tTissue enhanced\tApproved\tfallopian tube: 12.5;testis: 20.2\n+Q9P2S6\tNX_Q9P2S6\tENSG00000144504\t941\t105516\t6.28\t0\tPE1\t2\tCytoplasm;Cytoplasm;Nucleus\tNA\tANKMY1\tAnkyrin repeat and MYND domain containing 1\tGroup enriched\tUncertain\tfallopian tube: 39.0;testis: 118.1\n+Q9UFE4\tNX_Q9UFE4\tENSG00000145075\t941\t109901\t6.1\t0\tPE1\t3\tMitochondrion;Cilium axoneme\tCiliary dyskinesia, primary, 14\tCCDC39\tCoiled-coil domain containing 39\tMixed\tSupported\tNA\n+Q9UHP6\tNX_Q9UHP6\tENSG00000100218\t348\t38592\t6.43\t0\tPE1\t22\tNA\tNA\tRSPH14\tRadial spoke head 14 homolog (Chlamydomonas)\tTissue enhanced\tUncertain\tfallopian tube: 18.8;testis: 30.8\n+Q9UI46\tNX_Q9UI46\tENSG00000122735\t699\t79283\t6.4\t0\tPE1\t9\tCilium axoneme\tCiliary dyskinesia, primary, 1;Kartagener syndrome\tDNAI1\tDynein, axonemal, intermediate chain 1\tGroup enriched\tApproved\tfallopian tube: 53.6;testis: 60.9\n+Q9UIF3\tNX_Q9UIF3\tENSG00000092850\t430\t49672\t5.39\t0\tPE1\t1\tFlagellum;Cilium axoneme;Flagellum axoneme\tNA\tTEKT2\tTektin 2 (testicular)\tGroup enriched\tApproved\tfallopian tube: 96.6;testis: 63.3\n+Q9Y238\tNX_Q9Y238\tENSG00000008226\t1755\t195684\t5.92\t0\tPE1\t3\tCytoplasm\tLung cancer;Esophageal cancer\tDLEC1\tDeleted in lung and esophageal cancer 1\tTissue enhanced\tSupported\tfallopian tube: 29.4;testis: 17.3\n+Q9Y366\tNX_Q9Y366\tENSG00000101052\t437\t49706\t5.14\t0\tPE1\t20\tCytoplasm;Cilium\tShort-rib thoracic dysplasia 16 with or without polydactyly\tIFT52\tIntraflagellar transport 52\tExpressed in all\tSupported\tNA\n+Q9Y4P3\tNX_Q9Y4P3\tENSG00000106638\t447\t49798\t9.52\t0\tPE1\t7\tCytoplasm\tNA\tTBL2\tTransducin (beta)-like 2\tTissue enriched\tNA\ttestis: 83.4\n+Q9Y512\tNX_Q9Y512\tENSG00000100347\t469\t51976\t6.44\t0\tPE1\t22\tMitochondrion;Mitochondrion outer membrane;Cytoplasm;Mitochondrion\tNA\tSAMM50\tSAMM50 sorting and assembly machinery component\tExpressed in all\tSupported\tNA\n+Q9Y678\tNX_Q9Y678\tENSG00000181789\t874\t97718\t5.32\t0\tPE1\t3\tGolgi apparatus;Cytoplasm;Golgi apparatus membrane;COPI-coated vesicle membrane\tNA\tCOPG1\tCoatomer protein complex, subunit gamma 1\tExpressed in all\tSupported\tNA\n+Q9Y6J8\tNX_Q9Y6J8\tENSG00000127952\t313\t35818\t5.73\t0\tPE1\t7\tNA\tNA\tSTYXL1\tSerine/threonine/tyrosine interacting-like 1\tExpressed in all\tUncertain\tNA\n'
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/input_test.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input_test.txt Tue Dec 18 09:21:32 2018 -0500
b
b'@@ -0,0 +1,142 @@\n+Protein accession number (UniProt)\tProtein name\tNumber of peptides (razor + unique)\tEnsembl\tGene\tGene description\tRNA tissue category\tRNA TS TPM\r\n+P15924\tDesmoplakin\t69\tENSG00000096696\tDSP\tDesmoplakin\tGroup enriched\tesophagus: 346.9;skin: 1019.0\r\n+P02538\tKeratin, type II cytoskeletal 6A\t53\tENSG00000205420\tKRT6A\tKeratin 6A, type II\tTissue enriched\tesophagus: 5726.3\r\n+P02768\tSerum albumin\t44\tENSG00000163631\tALB\tAlbumin\tTissue enriched\tliver: 105632.0\r\n+P08779\tKeratin, type I cytoskeletal 16\t29\tENSG00000186832\tKRT16\tKeratin 16, type I\tGroup enriched\tesophagus: 479.6;tonsil: 106.5\r\n+Q02413\tDesmoglein-1\t24\tENSG00000134760\tDSG1\tDesmoglein 1\tTissue enriched\tskin: 727.4\r\n+P07355\tAnnexin A2;Putative annexin A2-like protein\t22\tENSG00000182718\tANXA2\tAnnexin A2\tExpressed in all\tNA\r\n+P14923\tJunction plakoglobin\t22\tENSG00000173801\tJUP\tJunction plakoglobin\tGroup enriched\tesophagus: 493.6;skin: 787.3\r\n+P02788\tLactotransferrin\t21\tENSG00000012223\tLTF\tLactotransferrin\tTissue enhanced\tbone marrow: 2808.6;cervix, uterine: 1024.2\r\n+Q9HC84\tMucin-5B\t21\tENSG00000117983\tMUC5B\tMucin 5B, oligomeric mucus/gel-forming\tGroup enriched\tcervix, uterine: 347.7;gallbladder: 346.8\r\n+P29508\tSerpin B3\t20\tENSG00000057149\tSERPINB3\tSerpin peptidase inhibitor, clade B (ovalbumin), member 3\tGroup enriched\tcervix, uterine: 297.6;esophagus: 851.2\r\n+P63261\tActin, cytoplasmic 2\t19\tENSG00000184009\tACTG1\tActin gamma 1\tExpressed in all\tNA\r\n+Q8N1N4\tKeratin, type II cytoskeletal 78\t18\tENSG00000170423\tKRT78\tKeratin 78, type II\tTissue enriched\tesophagus: 1058.9\r\n+Q04695\tKeratin, type I cytoskeletal 17\t18\tENSG00000128422\tKRT17\tKeratin 17, type I\tTissue enhanced\tbreast: 219.7;seminal vesicle: 223.4;urinary bladder: 334.2\r\n+P01876\tIg alpha-1 chain C region\t16\tENSG00000211895; ENSG00000282633\tNA\tNA\tNA\tNA\r\n+Q01469\tFatty acid-binding protein 5, epidermal\t15\tENSG00000164687\tFABP5\tFatty acid binding protein 5 (psoriasis-associated)\tExpressed in all\tNA\r\n+P31944\tCaspase-14\t15\tENSG00000105141\tCASP14\tCaspase 14, apoptosis-related cysteine peptidase\tTissue enriched\tskin: 560.0\r\n+P01833\tPolymeric immunoglobulin receptor\t15\tENSG00000162896\tPIGR\tPolymeric immunoglobulin receptor\tTissue enhanced\tcolon: 1721.7;duodenum: 2732.8\r\n+P06733\tAlpha-enolase\t15\tENSG00000074800\tENO1\tEnolase 1, (alpha)\tExpressed in all\tNA\r\n+Q15149\tPlectin\t15\tENSG00000178209\tPLEC\tPlectin\tExpressed in all\tNA\r\n+P19013\tKeratin, type II cytoskeletal 4\t13\tENSG00000170477\tKRT4\tKeratin 4, type II\tTissue enriched\tesophagus: 14911.0\r\n+Q6KB66\tKeratin, type II cytoskeletal 80\t13\tENSG00000167767\tKRT80\tKeratin 80, type II\tTissue enhanced\tskin: 125.3\r\n+Q08188\tProtein-glutamine gamma-glutamyltransferase E\t12\tENSG00000125780\tTGM3\tTransglutaminase 3\tTissue enriched\tesophagus: 1519.7\r\n+P13646\tKeratin, type I cytoskeletal 13\t11\tENSG00000171401\tKRT13\tKeratin 13, type I\tTissue enriched\tesophagus: 35268.3\r\n+Q86YZ3\tHornerin\t11\tENSG00000197915\tHRNR\tHornerin\tNot detected\tNA\r\n+P04259\tKeratin, type II cytoskeletal 6B\t10\tENSG00000185479\tKRT6B\tKeratin 6B, type II\tTissue enriched\tesophagus: 673.4\r\n+P02545\tPrelamin-A/C;Lamin-A/C\t10\tENSG00000160789\tLMNA\tLamin A/C\tExpressed in all\tNA\r\n+P04083\tAnnexin A1\t10\tENSG00000135046\tANXA1\tAnnexin A1\tTissue enriched\tesophagus: 7577.8\r\n+P11021\t78 kDa glucose-regulated protein\t10\tENSG00000044574\tHSPA5\tHeat shock 70kDa protein 5 (glucose-regulated protein, 78kDa)\tExpressed in all\tNA\r\n+P02787\tSerotransferrin\t9\tENSG00000091513\tTF\tTransferrin\tTissue enriched\tliver: 5384.6\r\n+P04040\tCatalase\t9\tENSG00000121691\tCAT\tCatalase\tExpressed in all\tNA\r\n+P31151\tProtein S100-A7\t9\tENSG00000143556\tS100A7\tS100 calcium binding protein A7\tGroup enriched\tskin: 325.1;tonsil: 921.8\r\n+P31947\t14-3-3 protein sigma\t9\tENSG00000175793\tSFN\tStratifin\tGroup enriched\tesophagus: 1094.4;skin: 1158.9\r\n+Q96P63\tSerpin B12\t9\tENSG00000166634\tSERPINB12\tSerpin peptidase inhibitor, clade B (ovalbumin), member 12\tTissue enriched\tskin: 78.4\r\n+P14618\tPyruvate kinase PKM\t9\tENSG00000067225\tPKM\tPyruvate kinase, muscle\tExpressed in all\tNA\r\n+P60174\tTriosep'..b'riched\tesophagus: 221.1;skin: 262.5\r\n+P40926\tMalate dehydrogenase, mitochondrial\t3\tENSG00000146701\tMDH2\tMalate dehydrogenase 2, NAD (mitochondrial)\tExpressed in all\tNA\r\n+Q9Y6R7\tIgGFc-binding protein\t3\tENSG00000281123\tNA\tNA\tNA\tNA\r\n+O95274\tLy6/PLAUR domain-containing protein 3\t2\tENSG00000124466\tLYPD3\tLY6/PLAUR domain containing 3\tGroup enriched\tesophagus: 676.5;skin: 594.5\r\n+P00491\tPurine nucleoside phosphorylase\t2\tENSG00000198805\tPNP\tPurine nucleoside phosphorylase\tExpressed in all\tNA\r\n+P04080\tCystatin-B\t2\tENSG00000160213\tCSTB\tCystatin B (stefin B)\tTissue enriched\tesophagus: 1836.3\r\n+P09972\tFructose-bisphosphate aldolase C\t2\tENSG00000109107\tALDOC\tAldolase C, fructose-bisphosphate\tTissue enriched\tcerebral cortex: 768.7\r\n+P19012\tKeratin, type I cytoskeletal 15\t2\tENSG00000171346\tKRT15\tKeratin 15, type I\tGroup enriched\tbreast: 320.0;esophagus: 787.5;skin: 1012.3\r\n+P20930\tFilaggrin\t2\tENSG00000143631\tFLG\tFilaggrin\tTissue enriched\tskin: 549.7\r\n+Q96FX8\tp53 apoptosis effector related to PMP-22\t2\tENSG00000112378\tPERP\tPERP, TP53 apoptosis effector\tGroup enriched\tesophagus: 574.1;skin: 1238.6\r\n+Q9UIV8\tSerpin B13\t2\tENSG00000197641\tSERPINB13\tSerpin peptidase inhibitor, clade B (ovalbumin), member 13\tTissue enriched\tesophagus: 185.3\r\n+P01625\tIg kappa chain V-IV region Len\t2\tNA\tNA\tNA\tNA\tNA\r\n+P01765\tIg heavy chain V-III region TIL\t2\tNA\tNA\tNA\tNA\tNA\r\n+P01766\tIg heavy chain V-III region BRO\t2\tENSG00000211942; ENSG00000282286\tNA\tNA\tNA\tNA\r\n+P01860\tIg gamma-3 chain C region\t2\tNA\tNA\tNA\tNA\tNA\r\n+P01871\tIg mu chain C region\t2\tENSG00000211899; ENSG00000282657\tNA\tNA\tNA\tNA\r\n+P05090\tApolipoprotein D\t2\tENSG00000189058\tAPOD\tApolipoprotein D\tTissue enriched\tbreast: 4546.8\r\n+P07858\tCathepsin B\t2\tENSG00000164733\tCTSB\tCathepsin B\tExpressed in all\tNA\r\n+P08865\t40S ribosomal protein SA\t2\tENSG00000168028\tRPSA\tRibosomal protein SA\tExpressed in all\tNA\r\n+P11279\tLysosome-associated membrane glycoprotein 1\t2\tENSG00000185896\tLAMP1\tLysosomal-associated membrane protein 1\tExpressed in all\tNA\r\n+P13473\tLysosome-associated membrane glycoprotein 2\t2\tENSG00000005893\tLAMP2\tLysosomal-associated membrane protein 2\tExpressed in all\tNA\r\n+P19971\tThymidine phosphorylase\t2\tENSG00000025708\tTYMP\tThymidine phosphorylase\tTissue enhanced\tappendix: 103.2\r\n+P23284\tPeptidyl-prolyl cis-trans isomerase B\t2\tENSG00000166794\tPPIB\tPeptidylprolyl isomerase B (cyclophilin B)\tExpressed in all\tNA\r\n+P23396\t40S ribosomal protein S3\t2\tENSG00000149273\tRPS3\tRibosomal protein S3\tExpressed in all\tNA\r\n+P25705\tATP synthase subunit alpha, mitochondrial\t2\tENSG00000152234\tATP5A1\tATP synthase, H+ transporting, mitochondrial F1 complex, alpha subunit 1, cardiac muscle\tExpressed in all\tNA\r\n+P27482\tCalmodulin-like protein 3\t2\tENSG00000178363\tCALML3\tCalmodulin-like 3\tTissue enhanced\tesophagus: 166.4;skin: 42.7\r\n+P31949\tProtein S100-A11\t2\tENSG00000163191\tS100A11\tS100 calcium binding protein A11\tExpressed in all\tNA\r\n+P40121\tMacrophage-capping protein\t2\tENSG00000042493\tCAPG\tCapping protein (actin filament), gelsolin-like\tExpressed in all\tNA\r\n+P42357\tHistidine ammonia-lyase\t2\tENSG00000084110\tHAL\tHistidine ammonia-lyase\tGroup enriched\tliver: 51.0;skin: 72.6\r\n+P47756\tF-actin-capping protein subunit beta\t2\tENSG00000077549\tCAPZB\tCapping protein (actin filament) muscle Z-line, beta\tExpressed in all\tNA\r\n+P48637\tGlutathione synthetase\t2\tENSG00000100983\tGSS\tGlutathione synthetase\tExpressed in all\tNA\r\n+P49720\tProteasome subunit beta type-3\t2\tENSG00000277791; ENSG00000275903\tPSMB3\tProteasome subunit beta 3\tExpressed in all\tNA\r\n+P50395\tRab GDP dissociation inhibitor beta\t2\tENSG00000057608\tGDI2\tGDP dissociation inhibitor 2\tExpressed in all\tNA\r\n+P59998\tActin-related protein 2/3 complex subunit 4\t2\tENSG00000241553\tARPC4\tActin related protein 2/3 complex, subunit 4, 20kDa\tExpressed in all\tNA\r\n+P61160\tActin-related protein 2\t2\tENSG00000138071\tACTR2\tARP2 actin-related protein 2 homolog (yeast)\tExpressed in all\tNA\r\n+P61916\tEpididymal secretory protein E1\t2\tENSG00000119655\tNPC2\tNiemann-Pick disease, type C2\tTissue enriched\tepididymis: 16057.0\r\n'
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/mouse_geneID.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/mouse_geneID.txt Tue Dec 18 09:21:32 2018 -0500
b
@@ -0,0 +1,231 @@
+27053
+20860
+217845
+17748
+74568
+17750
+56150
+102502
+225884
+227620
+67103
+12856
+110078
+16069
+22240
+107569
+20753
+22218
+105298
+11636
+17975
+12332
+192176
+76650
+234663
+16765
+74551
+12580
+68441
+15381
+15507
+16181
+114774
+22323
+21810
+76281
+67144
+238055
+217069
+98415
+53415
+72275
+68219
+242687
+104759
+14864
+54138
+66144
+19656
+19659
+11853
+50915
+14114
+12798
+12028
+230753
+17524
+22350
+66395
+27357
+226654
+65964
+19039
+13821
+107589
+17931
+69694
+19240
+11677
+NA
+67290
+239217
+67938
+15463
+100042295
+67092
+18104
+110052
+211666
+69787
+66060
+105348
+225884
+17068
+74122
+216350
+NA
+17075
+72303
+231655
+445007
+12796
+13086
+12490
+27053
+22350
+15388
+217845
+66120
+11647
+242291
+68556
+56215
+13211
+72657
+223921
+77106
+21985
+13118
+384009
+20218
+17149
+14548
+72787
+54138
+225027
+14105
+81898
+68981
+331401
+100038882
+56857
+83701
+19383
+223672
+20637
+20823
+110809
+NA
+20860
+19223
+72082
+29875
+19192
+68693
+68087
+67938
+230257
+57278
+386612
+19659
+72027
+236539
+21681
+239017
+434080
+20630
+17476
+142980
+13046
+20624
+66184
+67068
+53607
+21838
+20384
+11677
+15463
+18054
+107686
+331487
+230908
+50926
+15384
+72040
+15381
+20462
+67465
+11766
+17304
+71960
+246730
+30934
+12293
+11852
+20336
+80860
+100317
+17184
+74326
+13179
+20773
+66395
+245688
+77134
+112417
+75062
+66058
+53379
+71733
+229279
+19656
+74558
+17063
+28000
+226101
+14999
+105298
+17454
+29816
+16414
+219158
+17079
+68953
+56705
+67040
+74125
+20719
+67657
+21767
+109815
+192159
+15211
+13204
+105501
+71660
+67144
+68565
+29864
+53357
+67103
+227620
+269774
+66585
+67996
+11991
+224045
+69150
+99889
+71514
+16852
b
diff -r 5e16cec55146 -r 4609346d8108 test-data/universe.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/universe.csv Tue Dec 18 09:21:32 2018 -0500
b
b'@@ -0,0 +1,14624 @@\n+Gene\tGene.name\tTissue\tCell.type\tLevel\tReliability\tUniProt.AC\n+ENSG00000001167\tNFYA\tepididymis\tglandular cells\tMedium\tEnhanced\tP23511\n+ENSG00000001167\tNFYA\tprostate\tglandular cells\tMedium\tEnhanced\tP23511\n+ENSG00000001167\tNFYA\tseminal vesicle\tglandular cells\tMedium\tEnhanced\tP23511\n+ENSG00000001167\tNFYA\ttestis\tcells in seminiferous ducts\tMedium\tEnhanced\tP23511\n+ENSG00000001167\tNFYA\ttestis\tLeydig cells\tMedium\tEnhanced\tP23511\n+ENSG00000001497\tLAS1L\tepididymis\tglandular cells\tHigh\tSupported\tQ9Y4W2\n+ENSG00000001497\tLAS1L\tprostate\tglandular cells\tMedium\tSupported\tQ9Y4W2\n+ENSG00000001497\tLAS1L\tseminal vesicle\tglandular cells\tHigh\tSupported\tQ9Y4W2\n+ENSG00000001497\tLAS1L\ttestis\tcells in seminiferous ducts\tHigh\tSupported\tQ9Y4W2\n+ENSG00000001497\tLAS1L\ttestis\tLeydig cells\tHigh\tSupported\tQ9Y4W2\n+ENSG00000001630\tCYP51A1\ttestis\tLeydig cells\tHigh\tEnhanced\tQ16850\n+ENSG00000002549\tLAP3\tepididymis\tglandular cells\tMedium\tEnhanced\tP28838\n+ENSG00000002549\tLAP3\tprostate\tglandular cells\tMedium\tEnhanced\tP28838\n+ENSG00000002549\tLAP3\tseminal vesicle\tglandular cells\tMedium\tEnhanced\tP28838\n+ENSG00000002549\tLAP3\ttestis\tcells in seminiferous ducts\tMedium\tEnhanced\tP28838\n+ENSG00000002549\tLAP3\ttestis\tLeydig cells\tLow\tEnhanced\tP28838\n+ENSG00000002586\tCD99\tepididymis\tglandular cells\tLow\tSupported\tP14209\n+ENSG00000002586\tCD99\tprostate\tglandular cells\tHigh\tSupported\tP14209\n+ENSG00000002586\tCD99\tseminal vesicle\tglandular cells\tMedium\tSupported\tP14209\n+ENSG00000002586\tCD99\ttestis\tcells in seminiferous ducts\tHigh\tSupported\tP14209\n+ENSG00000002822\tMAD1L1\tepididymis\tglandular cells\tHigh\tSupported\tQ9Y6D9\n+ENSG00000002822\tMAD1L1\tprostate\tglandular cells\tMedium\tSupported\tQ9Y6D9\n+ENSG00000002822\tMAD1L1\tseminal vesicle\tglandular cells\tMedium\tSupported\tQ9Y6D9\n+ENSG00000002822\tMAD1L1\ttestis\tcells in seminiferous ducts\tHigh\tSupported\tQ9Y6D9\n+ENSG00000002822\tMAD1L1\ttestis\tLeydig cells\tMedium\tSupported\tQ9Y6D9\n+ENSG00000003436\tTFPI\tepididymis\tglandular cells\tMedium\tSupported\tP10646\n+ENSG00000003436\tTFPI\tprostate\tglandular cells\tMedium\tSupported\tP10646\n+ENSG00000003436\tTFPI\tseminal vesicle\tglandular cells\tMedium\tSupported\tP10646\n+ENSG00000003436\tTFPI\ttestis\tcells in seminiferous ducts\tLow\tSupported\tP10646\n+ENSG00000003436\tTFPI\ttestis\tLeydig cells\tMedium\tSupported\tP10646\n+ENSG00000004468\tCD38\tprostate\tglandular cells\tHigh\tEnhanced\tP28907\n+ENSG00000004468\tCD38\tseminal vesicle\tglandular cells\tHigh\tEnhanced\tP28907\n+ENSG00000004478\tFKBP4\tepididymis\tglandular cells\tMedium\tEnhanced\tQ02790\n+ENSG00000004478\tFKBP4\tprostate\tglandular cells\tMedium\tEnhanced\tQ02790\n+ENSG00000004478\tFKBP4\ttestis\tcells in seminiferous ducts\tMedium\tEnhanced\tQ02790\n+ENSG00000004478\tFKBP4\ttestis\tLeydig cells\tLow\tEnhanced\tQ02790\n+ENSG00000004487\tKDM1A\tepididymis\tglandular cells\tMedium\tSupported\tO60341\n+ENSG00000004487\tKDM1A\tseminal vesicle\tglandular cells\tMedium\tSupported\tO60341\n+ENSG00000004487\tKDM1A\ttestis\tcells in seminiferous ducts\tMedium\tSupported\tO60341\n+ENSG00000004534\tRBM6\tepididymis\tglandular cells\tHigh\tEnhanced\tP78332\n+ENSG00000004534\tRBM6\tprostate\tglandular cells\tHigh\tEnhanced\tP78332\n+ENSG00000004534\tRBM6\tseminal vesicle\tglandular cells\tLow\tEnhanced\tP78332\n+ENSG00000004534\tRBM6\ttestis\tcells in seminiferous ducts\tHigh\tEnhanced\tP78332\n+ENSG00000004534\tRBM6\ttestis\tLeydig cells\tHigh\tEnhanced\tP78332\n+ENSG00000004700\tRECQL\tepididymis\tglandular cells\tMedium\tEnhanced\tP46063\n+ENSG00000004700\tRECQL\tseminal vesicle\tglandular cells\tLow\tEnhanced\tP46063\n+ENSG00000004700\tRECQL\ttestis\tcells in seminiferous ducts\tMedium\tEnhanced\tP46063\n+ENSG00000004700\tRECQL\ttestis\tLeydig cells\tMedium\tEnhanced\tP46063\n+ENSG00000004776\tHSPB6\ttestis\tLeydig cells\tHigh\tEnhanced\tO14558\n+ENSG00000004777\tARHGAP33\tepididymis\tglandular cells\tMedium\tSupported\tO14559\n+ENSG00000004777\tARHGAP33\tprostate\tglandular cells\tMedium\tSupported\tO14559\n+ENSG00000004777\tARHGAP33\tseminal vesicle\tglandular cells\tLow\tSupported\tO14559\n+ENSG00000004777\tARHGAP33\ttestis\tcells in seminiferous ducts\tMedium\tSupported\tO14559\n+ENSG00000004777\tARHGAP33\ttes'..b'in seminiferous ducts\tHigh\tSupported\tNA\n+ENSG00000278272\tHIST1H3C\ttestis\tLeydig cells\tHigh\tSupported\tNA\n+ENSG00000278289\tCT45A6\ttestis\tcells in seminiferous ducts\tHigh\tSupported\tP0DMU7\n+ENSG00000278463\tHIST1H2AB\tepididymis\tglandular cells\tMedium\tSupported\tNA\n+ENSG00000278463\tHIST1H2AB\tprostate\tglandular cells\tLow\tSupported\tNA\n+ENSG00000278463\tHIST1H2AB\tseminal vesicle\tglandular cells\tMedium\tSupported\tNA\n+ENSG00000278463\tHIST1H2AB\ttestis\tcells in seminiferous ducts\tHigh\tSupported\tNA\n+ENSG00000278463\tHIST1H2AB\ttestis\tLeydig cells\tLow\tSupported\tNA\n+ENSG00000278535\tDHRS11\ttestis\tcells in seminiferous ducts\tLow\tEnhanced\tNA\n+ENSG00000278535\tDHRS11\ttestis\tLeydig cells\tLow\tEnhanced\tNA\n+ENSG00000278588\tHIST1H2BI\tepididymis\tglandular cells\tHigh\tSupported\tNA\n+ENSG00000278588\tHIST1H2BI\tprostate\tglandular cells\tHigh\tSupported\tNA\n+ENSG00000278588\tHIST1H2BI\tseminal vesicle\tglandular cells\tHigh\tSupported\tNA\n+ENSG00000278588\tHIST1H2BI\ttestis\tcells in seminiferous ducts\tHigh\tSupported\tNA\n+ENSG00000278588\tHIST1H2BI\ttestis\tLeydig cells\tHigh\tSupported\tNA\n+ENSG00000278619\tMRM1\tepididymis\tglandular cells\tLow\tSupported\tNA\n+ENSG00000278619\tMRM1\tprostate\tglandular cells\tLow\tSupported\tNA\n+ENSG00000278619\tMRM1\tseminal vesicle\tglandular cells\tMedium\tSupported\tNA\n+ENSG00000278619\tMRM1\ttestis\tcells in seminiferous ducts\tLow\tSupported\tNA\n+ENSG00000278619\tMRM1\ttestis\tLeydig cells\tMedium\tSupported\tNA\n+ENSG00000278637\tHIST1H4A\tepididymis\tglandular cells\tMedium\tSupported\tNA\n+ENSG00000278637\tHIST1H4A\tprostate\tglandular cells\tMedium\tSupported\tNA\n+ENSG00000278637\tHIST1H4A\tseminal vesicle\tglandular cells\tMedium\tSupported\tNA\n+ENSG00000278637\tHIST1H4A\ttestis\tcells in seminiferous ducts\tHigh\tSupported\tNA\n+ENSG00000278637\tHIST1H4A\ttestis\tLeydig cells\tMedium\tSupported\tNA\n+ENSG00000278646\tRP1-321E8.5\ttestis\tcells in seminiferous ducts\tMedium\tSupported\tA0A087WWU0\n+ENSG00000278677\tHIST1H2AM\tepididymis\tglandular cells\tMedium\tSupported\tNA\n+ENSG00000278677\tHIST1H2AM\tprostate\tglandular cells\tLow\tSupported\tNA\n+ENSG00000278677\tHIST1H2AM\tseminal vesicle\tglandular cells\tMedium\tSupported\tNA\n+ENSG00000278677\tHIST1H2AM\ttestis\tcells in seminiferous ducts\tHigh\tSupported\tNA\n+ENSG00000278677\tHIST1H2AM\ttestis\tLeydig cells\tLow\tSupported\tNA\n+ENSG00000278705\tHIST1H4B\tepididymis\tglandular cells\tLow\tSupported\tNA\n+ENSG00000278705\tHIST1H4B\tprostate\tglandular cells\tLow\tSupported\tNA\n+ENSG00000278705\tHIST1H4B\tseminal vesicle\tglandular cells\tMedium\tSupported\tNA\n+ENSG00000278705\tHIST1H4B\ttestis\tcells in seminiferous ducts\tMedium\tSupported\tNA\n+ENSG00000278828\tHIST1H3H\tepididymis\tglandular cells\tHigh\tSupported\tNA\n+ENSG00000278828\tHIST1H3H\tprostate\tglandular cells\tHigh\tSupported\tNA\n+ENSG00000278828\tHIST1H3H\tseminal vesicle\tglandular cells\tHigh\tSupported\tNA\n+ENSG00000278828\tHIST1H3H\ttestis\tcells in seminiferous ducts\tHigh\tSupported\tNA\n+ENSG00000278828\tHIST1H3H\ttestis\tLeydig cells\tHigh\tSupported\tNA\n+ENSG00000278845\tMRPL45\tepididymis\tglandular cells\tMedium\tEnhanced\tA0A087X2D5\n+ENSG00000278845\tMRPL45\tprostate\tglandular cells\tMedium\tEnhanced\tA0A087X2D5\n+ENSG00000278845\tMRPL45\tseminal vesicle\tglandular cells\tMedium\tEnhanced\tA0A087X2D5\n+ENSG00000278845\tMRPL45\ttestis\tcells in seminiferous ducts\tMedium\tEnhanced\tA0A087X2D5\n+ENSG00000278845\tMRPL45\ttestis\tLeydig cells\tHigh\tEnhanced\tA0A087X2D5\n+ENSG00000280987\tMATR3\tepididymis\tglandular cells\tHigh\tSupported\tA8MXP9\n+ENSG00000280987\tMATR3\tprostate\tglandular cells\tHigh\tSupported\tA8MXP9\n+ENSG00000280987\tMATR3\tseminal vesicle\tglandular cells\tHigh\tSupported\tA8MXP9\n+ENSG00000280987\tMATR3\ttestis\tcells in seminiferous ducts\tHigh\tSupported\tA8MXP9\n+ENSG00000280987\tMATR3\ttestis\tLeydig cells\tHigh\tSupported\tA8MXP9\n+ENSG00000283706\tPRSS50\ttestis\tcells in seminiferous ducts\tHigh\tSupported\tNA\n+ENSG00000283706\tPRSS50\ttestis\telongated or late spermatids\tMedium\tSupported\tNA\n+ENSG00000283706\tPRSS50\ttestis\tpachytene spermatocytes\tHigh\tSupported\tNA\n+ENSG00000283706\tPRSS50\ttestis\tround or early spermatids\tMedium\tSupported\tNA\n+ENSG00000284308\tC2orf81\ttestis\tLeydig cells\tLow\tEnhanced\tA6NN90\n'