| Previous changeset 0:d89c09253c8d (2017-11-26) Next changeset 2:58a8ddd58dde (2018-03-07) |
|
Commit message:
planemo upload commit 5774fd6a5a746f36f6bf4671a51a39ea2b978300-dirty |
|
modified:
goprofiles.R goprofiles.xml |
|
added:
test-data/GO_Profile_diagram_outputs__profile.BP.pdf test-data/GO_Profile_diagram_outputs__profile.CC.pdf test-data/GO_Profile_diagram_outputs__profile.MF.pdf test-data/ID_Converter_FKW_Lacombe_et_al_2017_OK.txt |
|
removed:
test-data/UnipIDs.txt test-data/profile.BP.pdf test-data/profile.CC.pdf test-data/profile.MF.pdf |
| b |
| diff -r d89c09253c8d -r 1236ee08ccb8 goprofiles.R --- a/goprofiles.R Sun Nov 26 19:19:39 2017 -0500 +++ b/goprofiles.R Fri Feb 16 03:40:36 2018 -0500 |
| [ |
| b'@@ -5,16 +5,12 @@\n # Read file and return file content as data.frame?\n readfile = function(filename, header) {\n if (header == "true") {\n- # Read only the first two lines of the files as data (without headers):\n+ # Read only the first line of the files as data (without headers):\n headers <- read.table(filename, nrows = 1, header = FALSE, sep = "\\t", stringsAsFactors = FALSE, fill = TRUE)\n- #print("header")\n- #print(headers)\n- # Create the headers names with the two (or more) first rows, sappy allows to make operations over the columns (in this case paste) - read more about sapply here :\n- #headers_names <- sapply(headers, paste, collapse = "_")\n- #print(headers_names)\n- #Read the data of the files (skipping the first 2 rows):\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)\n- #print(file[1,])\n+ # Remove empty rows\n+ file <- file[!apply(is.na(file) | file == "", 1, all),]\n #And assign the headers of step two to the data:\n names(file) <- headers\n }\n@@ -24,10 +20,6 @@\n return(file)\n }\n \n-#filename = "/Users/LinCun/Documents/ProteoRE/usecase1/Check/HPA.Selection.134.txt"\n-#test = readfile(filename)\n-#str(test)\n-#str(test$Gene.names)\n getprofile = function(ids, id_type, level, duplicate) {\n ####################################################################\n # Arguments\n@@ -64,27 +56,6 @@\n print("IDs unable to convert to ENTREZID: ")\n print(NAs)\n }\n- #print(genes_ids)\n- # Convert Protein IDs into entrez ids\n- \n- # for (i in 1:length(id$UNIPROT)) {\n- # print(i)\n- # if (is.na(id[[2]][i])) {\n- # print(id[[2]][i])\n- # }\n- # }\n- # a = id[which(id$ENTREZID == "NA"),]\n- # print(a)\n- # print(a$UNIPROT)\n- #print(id[[1]][which(is.na(id$ENTREZID))])\n- #print(genes_ids)\n- # for (gene in genes) {\n- # #id = as.character(mget(gene, org.Hs.egALIAS2EG, ifnotfound = NA))\n- # id = select(org.Hs.eg.db, genes, "ENTREZID", "UNIPROT")\n- # print(id)\n- # genes_ids = append(genes_ids, id$ENTREZID)\n- # }\n- #print(genes_ids)\n \n # Create basic profiles\n profile.CC = basicProfile(genes_ids, onto=\'CC\', level=level, orgPackage="org.Hs.eg.db", empty.cats=F, ord=T, na.rm=T)\n@@ -172,103 +143,117 @@\n }\n \n goprofiles = function() {\n- args = commandArgs(trailingOnly = TRUE)\n- #print(args)\n- # arguments: filename.R inputfile ncol "CC,MF,BP,ALL" "PNG,JPEG,PDF" level "TRUE"(percentage) "Title"\n- if (length(args) != 9) {\n- stop("Not enough/Too many arguments", call. = FALSE)\n+ args <- commandArgs(TRUE)\n+ if(length(args)<1) {\n+ args <- c("--help")\n }\n- else {\n- input_type = args[2]\n- if (input_type == "text") {\n- input = strsplit(args[1], "\\\\s+")[[1]]\n- }\n- else if (input_type == "file") {\n- filename = strsplit(args[1], ",")[[1]][1]\n- ncol = strsplit(args[1], ",")[[1]][2]\n- # Check ncol\n- if (! as.numeric(gsub("c", "", ncol)) %% 1 == 0) {\n- stop("Please enter an integer for level")\n- }\n- else {\n- ncol = as.numeric(gsub("c", "", ncol))\n- }\n- header = strsplit(args[1], ",")[[1]][3]\n- # Get file content\n- file = readfile(filename, header)\n- # Extract Protein IDs list\n- input = c()\n- for (row in as.character(file[,ncol])) {\n- input = c(input, strsplit(row, ";")[[1]][1])\n- }\n- }\n- id_type = args[3]\n- ontoopt = strsplit(args[4], ",")[[1]]\n- #print(ontoopt)\n- #plotopt = strsplit(args[3], ",")\n- plotopt = args[5]\n- level = args[6]\n- per = as.logical(args[7])\n- title = args[8]\n- duplicate = args[9]\n-\n- profiles = getprofile(input, id_type, level, duplicate)\n- profile.CC = profiles[1]\n- #print(profile.CC)\n- profile.MF = profiles[2]\n- #print(profile.MF)\n- profile.BP = profiles[3]\n- #print(profile.BP)\n- profile.ALL = profiles[-3:-1]\n- #print(profile.ALL)\n- #c(profile.ALL, profil'..b'- plotPDF(profile.BP = profile.BP, per=per, title=title)\n- }\n- }\n- \n- #if (grepl("PNG", plotopt)) {\n- # plotPNG(profile.ALL = profile.ALL, per=per, title=title)\n- #}\n- #if (grepl("JPEG", plotopt)) {\n- # plotJPEG(profile.ALL = profile.ALL, per=per, title=title)\n- #}\n- #if (grepl("PDF", plotopt)) {\n- # plotPDF(profile.ALL = profile.ALL, per=per, title=title)\n- #}\n+ \n+ # Help section\n+ if("--help" %in% args) {\n+ cat("Selection and Annotation HPA\n+ Arguments:\n+ --input_type: type of input (list of id or filename)\n+ --input: input\n+ --ncol: the column number which you would like to apply...\n+ --header: true/false if your file contains a header\n+ --id_type: the type of input IDs (UniProt/EntrezID)\n+ --onto_opt: ontology options\n+ --plot_opt: plot extension options (PDF/JPEG/PNG)\n+ --level: 1-3\n+ --per\n+ --title: title of the plot\n+ --duplicate: remove dupliate input IDs (true/false)\n+ --text_output: text output filename \\n")\n+ q(save="no")\n }\n \n+ # Parse arguments\n+ parseArgs <- function(x) strsplit(sub("^--", "", x), "=")\n+ argsDF <- as.data.frame(do.call("rbind", parseArgs(args)))\n+ args <- as.list(as.character(argsDF$V2))\n+ names(args) <- argsDF$V1\n+\n+ input_type = args$input_type\n+ if (input_type == "text") {\n+ input = strsplit(args$input, " ")[[1]]\n+ }\n+ else if (input_type == "file") {\n+ filename = args$input\n+ ncol = args$ncol\n+ # Check ncol\n+ if (! as.numeric(gsub("c", "", ncol)) %% 1 == 0) {\n+ stop("Please enter an integer for level")\n+ }\n+ else {\n+ ncol = as.numeric(gsub("c", "", ncol))\n+ }\n+ header = args$header\n+ # Get file content\n+ file = readfile(filename, header)\n+ # Extract Protein IDs list\n+ input = c()\n+ for (row in as.character(file[,ncol])) {\n+ input = c(input, strsplit(row, ";")[[1]][1])\n+ }\n+ }\n+ id_type = args$id_type\n+ ontoopt = strsplit(args$onto_opt, ",")[[1]]\n+ #print(ontoopt)\n+ #plotopt = strsplit(args[3], ",")\n+ plotopt = args$plot_opt\n+ level = args$level\n+ per = as.logical(args$per)\n+ title = args$title\n+ duplicate = args$duplicate\n+ text_output = args$text_output\n+\n+ profiles = getprofile(input, id_type, level, duplicate)\n+ profile.CC = profiles[1]\n+ #print(profile.CC)\n+ profile.MF = profiles[2]\n+ #print(profile.MF)\n+ profile.BP = profiles[3]\n+ #print(profile.BP)\n+ profile.ALL = profiles[-3:-1]\n+ #print(profile.ALL)\n+ #c(profile.ALL, profile.CC, profile.MF, profile.BP)\n+ \n+ if ("CC" %in% ontoopt) {\n+ write.table(profile.CC, text_output, append = TRUE, sep="\\t", row.names = FALSE, quote=FALSE)\n+ if (grepl("PNG", plotopt)) {\n+ plotPNG(profile.CC=profile.CC, per=per, title=title)\n+ }\n+ if (grepl("JPEG", plotopt)) {\n+ plotJPEG(profile.CC = profile.CC, per=per, title=title)\n+ }\n+ if (grepl("PDF", plotopt)) {\n+ plotPDF(profile.CC = profile.CC, per=per, title=title)\n+ }\n+ }\n+ if ("MF" %in% ontoopt) {\n+ write.table(profile.MF, text_output, append = TRUE, sep="\\t", row.names = FALSE, quote=FALSE)\n+ if (grepl("PNG", plotopt)) {\n+ plotPNG(profile.MF = profile.MF, per=per, title=title)\n+ }\n+ if (grepl("JPEG", plotopt)) {\n+ plotJPEG(profile.MF = profile.MF, per=per, title=title)\n+ }\n+ if (grepl("PDF", plotopt)) {\n+ plotPDF(profile.MF = profile.MF, per=per, title=title)\n+ }\n+ }\n+ if ("BP" %in% ontoopt) {\n+ write.table(profile.BP, text_output, append = TRUE, sep="\\t", row.names = FALSE, quote=FALSE)\n+ if (grepl("PNG", plotopt)) {\n+ plotPNG(profile.BP = profile.BP, per=per, title=title)\n+ }\n+ if (grepl("JPEG", plotopt)) {\n+ plotJPEG(profile.BP = profile.BP, per=per, title=title)\n+ }\n+ if (grepl("PDF", plotopt)) {\n+ plotPDF(profile.BP = profile.BP, per=per, title=title)\n+ }\n+ }\n }\n \n goprofiles()\n-\n-#Rscript go.R ../proteinGroups_Maud.txt "1" "CC" "PDF" 2 "TRUE" "Title"\n' |
| b |
| diff -r d89c09253c8d -r 1236ee08ccb8 goprofiles.xml --- a/goprofiles.xml Sun Nov 26 19:19:39 2017 -0500 +++ b/goprofiles.xml Fri Feb 16 03:40:36 2018 -0500 |
| [ |
| @@ -5,7 +5,7 @@ <requirement type="package" version="3.4.1">R</requirement> <requirement type="package" version="3.3.0">bioconductor-org.hs.eg.db</requirement> <requirement type="package" version="1.38.0">bioconductor-annotationdbi</requirement> - <requirement type="package" version="2.34.0">bioconductor-biobase</requirement> + <requirement type="package" version="2.38.0">bioconductor-biobase</requirement> <requirement type="package" version="1.38.0">goprofiles</requirement> </requirements> <stdio> @@ -14,29 +14,35 @@ <command><![CDATA[ Rscript $__tool_directory__/goprofiles.R #if $input.ids == "text" - "$input.text" "text" - #else - "$input.file,$input.ncol,$input.header" "file" + --input_type="text" + --input="$input.text" + #else + --input_type="file" + --input="$input.file" + --ncol="$input.ncol" + --header="$input.header" #end if - $input.id_type + --id_type="$input.id_type" + + --onto_opt="$onto_opt" - $onto_opt + --plot_opt="$opt.plot_opt" - $opt.plot_opt + --level="$level" - $level + --per="$per" - $per + --title="$title" - "$title" - - $duplicate + --duplicate="$duplicate" + + --text_output="$text_output" ]]></command> <inputs> <conditional name="input" > - <param name="ids" type="select" label="Provide your Entrez Gene or UniProt identifiers" help="Copy/paste or ID list from a file (e.g. table)" > + <param name="ids" type="select" label="Enter your ID list (only Entrez Gene ID or UniProt accession number allowed" help="Copy/paste or ID list from a file (e.g. table)" > <option value="text">Copy/paste your identifiers</option> <option value="file">Input file containing your identifiers</option> </param> @@ -53,7 +59,7 @@ </param> <param name="id_type" type="select" label="Please select the type of your IDs list" > <option value="Entrez">Entrez Gene ID</option> - <option value="UniProt">UniProt protein ID</option> + <option value="UniProt">UniProt protein acession number</option> </param> </when> <when value="file" > @@ -93,16 +99,18 @@ <discover_datasets pattern="(?P<designation>.+\.jpeg)" ext="jpg" /> <discover_datasets pattern="(?P<designation>.+\.pdf)" ext="pdf" /> </collection> + <data name="text_output" format="tabular" label="GO Profile text output" /> </outputs> <tests> <test> <conditional name="input"> <param name="ids" value="file" /> - <param name="file" value="UnipIDs.txt" /> + <param name="file" value="ID_Converter_FKW_Lacombe_et_al_2017_OK.txt" /> <param name="ncol" value="c1" /> - <param name="header" value="false" /> + <param name="header" value="talse" /> <param name="id_type" value="UniProt" /> </conditional> + <param name="duplicate" value="false"/> <param name="onto_opt" value="CC,MF,BP" /> <param name="level" value="2" /> <param name="per" value="true" /> @@ -111,14 +119,15 @@ <param name="plot_opt" value="PDF" /> </section> <output_collection name="output" type="list" > - <element name="profile.BP.pdf" file="profile.BP.pdf" ftype="pdf" /> - <element name="profile.MF.pdf" file="profile.MF.pdf" ftype="pdf" /> - <element name="profile.CC.pdf" file="profile.CC.pdf" ftype="pdf" /> + <element name="GO_Profile_diagram_outputs__profile.BP.pdf" file="GO_Profile_diagram_outputs__profile.BP.pdf" ftype="pdf" /> + <element name="GO_Profile_diagram_outputs__profile.CC.pdf" file="GO_Profile_diagram_outputs__profile.CC.pdf" ftype="pdf" /> + <element name="GO_Profile_diagram_outputs__profile.MF.pdf" file="GO_Profile_diagram_outputs__profile.MF.pdf" ftype="pdf" /> </output_collection> + <output name="text_output" file="GO_Profile_text_output.txt"/> </test> </tests> <help><![CDATA[ -This tool, based on the goProfiles R package, performs statistical analysis of functional profiles. It is based on GO ontology and considers either a gene set ('Entrez’ Identifiers) or a protein set (Uniprot ID) as input. +This tool, based on the goProfiles R package, performs statistical analysis of functional profiles. It is based on GO ontology and considers either a gene set ('Entrez’ Identifiers) or a protein set (Uniprot accession number) as input. You can choose one or more GO categories: @@ -126,11 +135,11 @@ * Cellular Component (CC) * Molecular Function (MF) -Functional profile at a given GO level is obtained by counting the number of identifiers having a hit in each category of this level (2 by default). Results are displayed as bar plots (with absolute or relative frequencies) and can be exported in pdf, png and jpeg formats. +Functional profile at a given GO level is obtained by counting the number of identifiers having a hit in each category of this level (2 by default). Results are displayed as bar plots (with absolute or relative frequencies) and can be exported in pdf, png and jpeg formats; textual output with GO terms and their computed frequencies is also provided. For more details about GoProfiles, please read: Salicrú et al. Comparison of lists of genes based on functional profiles. BMC Bioinformatics. 2011;12:401.(https://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-12-401) -If your type of identifiers is not supported (i.e. different form Uniprot and Entrez), please use the **ID Converter** component in the ProteoRE section to convert your list of IDs first. +If your type of identifiers is not supported (i.e. different from Uniprot and Entrez), please use the **ID Converter** tool in the ProteoRE section to convert your list of IDs first. ----- |
| b |
| diff -r d89c09253c8d -r 1236ee08ccb8 test-data/GO_Profile_diagram_outputs__profile.BP.pdf |
| b |
| Binary file test-data/GO_Profile_diagram_outputs__profile.BP.pdf has changed |
| b |
| diff -r d89c09253c8d -r 1236ee08ccb8 test-data/GO_Profile_diagram_outputs__profile.CC.pdf |
| b |
| Binary file test-data/GO_Profile_diagram_outputs__profile.CC.pdf has changed |
| b |
| diff -r d89c09253c8d -r 1236ee08ccb8 test-data/GO_Profile_diagram_outputs__profile.MF.pdf |
| b |
| Binary file test-data/GO_Profile_diagram_outputs__profile.MF.pdf has changed |
| b |
| diff -r d89c09253c8d -r 1236ee08ccb8 test-data/ID_Converter_FKW_Lacombe_et_al_2017_OK.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/ID_Converter_FKW_Lacombe_et_al_2017_OK.txt Fri Feb 16 03:40:36 2018 -0500 |
| b |
| b'@@ -0,0 +1,152 @@\n+Protein accession number (UniProt)\tProtein name\tNumber of peptides (razor + unique)\tneXtProt_ID\tUniProt.ID\tGeneID\tMIM\tEnsembl\n+P15924\tDesmoplakin\t69\tNX_P15924\tDESP_HUMAN\t1832\t125647; 605676; 607450; 607655; 609638; 612908; 615821\tENSG00000096696\n+P02538\tKeratin, type II cytoskeletal 6A\t53\tNX_P02538\tK2C6A_HUMAN\t3853\t148041; 615726\tENSG00000205420\n+P02768\tSerum albumin\t44\tNX_P02768\tALBU_HUMAN\t213\t103600; 615999; 616000\tENSG00000163631\n+P08779\tKeratin, type I cytoskeletal 16\t29\tNX_P08779\tK1C16_HUMAN\t3868\t148067; 167200; 613000\tENSG00000186832\n+Q02413\tDesmoglein-1\t24\tNX_Q02413\tDSG1_HUMAN\t1828\t125670; 148700; 615508\tENSG00000134760\n+P07355\tAnnexin A2;Putative annexin A2-like protein\t22\tNX_P07355\tANXA2_HUMAN\t302\t151740\tENSG00000182718\n+P14923\tJunction plakoglobin\t22\tNX_P14923\tPLAK_HUMAN\t3728\t173325; 601214; 611528\tENSG00000173801\n+P02788\tLactotransferrin\t21\tNX_P02788\tTRFL_HUMAN\t4057\t150210\tENSG00000012223\n+Q9HC84\tMucin-5B\t21\tNX_Q9HC84\tMUC5B_HUMAN\t727897\t178500; 600770\tENSG00000117983\n+P29508\tSerpin B3\t20\tNX_P29508\tSPB3_HUMAN\t6317\t600517\tENSG00000057149\n+P63261\tActin, cytoplasmic 2\t19\tNX_P63261\tACTG_HUMAN\t71\t102560; 604717; 614583\tENSG00000184009\n+Q8N1N4\tKeratin, type II cytoskeletal 78\t18\tNX_Q8N1N4\tK2C78_HUMAN\t196374\t611159\tENSG00000170423\n+Q04695\tKeratin, type I cytoskeletal 17\t18\tNX_Q04695\tK1C17_HUMAN\t3872\t148069; 167210; 184500\tENSG00000128422\n+P01876\tIg alpha-1 chain C region\t16\tNX_P01876\tIGHA1_HUMAN\tNA\t146900\tENSG00000211895; ENSG00000282633\n+Q01469\tFatty acid-binding protein 5, epidermal\t15\tNX_Q01469\tFABP5_HUMAN\t2171\t605168\tENSG00000164687\n+P31944\tCaspase-14\t15\tNX_P31944\tCASPE_HUMAN\t23581\t605848; 617320\tENSG00000105141\n+P01833\tPolymeric immunoglobulin receptor\t15\tNX_P01833\tPIGR_HUMAN\t5284\t173880\tENSG00000162896\n+P06733\tAlpha-enolase\t15\tNX_P06733\tENOA_HUMAN\t2023\t172430\tENSG00000074800\n+P25311\tZinc-alpha-2-glycoprotein\t15\tNX_P25311\tZA2G_HUMAN\t563\t194460\tENSG00000160862\n+Q15149\tPlectin\t15\tNX_Q15149\tPLEC_HUMAN\t5339\t131950; 226670; 601282; 612138; 613723; 616487\tENSG00000178209\n+P19013\tKeratin, type II cytoskeletal 4\t13\tNX_P19013\tK2C4_HUMAN\tNA\t123940; 193900\tENSG00000170477\n+Q6KB66\tKeratin, type II cytoskeletal 80\t13\tNX_Q6KB66\tK2C80_HUMAN\t144501\t611161\tENSG00000167767\n+Q08188\tProtein-glutamine gamma-glutamyltransferase E\t12\tNX_Q08188\tTGM3_HUMAN\t7053\t600238; 617251\tENSG00000125780\n+P13646\tKeratin, type I cytoskeletal 13\t11\tNX_P13646\tK1C13_HUMAN\t3860\t148065; 615785\tENSG00000171401\n+Q86YZ3\tHornerin\t11\tNX_Q86YZ3\tHORN_HUMAN\t388697\t616293\tENSG00000197915\n+P04259\tKeratin, type II cytoskeletal 6B\t10\tNX_P04259\tK2C6B_HUMAN\t3854\t148042; 615728\tENSG00000185479\n+P02545\tPrelamin-A/C;Lamin-A/C\t10\tNX_P02545\tLMNA_HUMAN\t4000\t115200; 150330; 151660; 159001; 176670; 181350; 212112; 248370; 275210; 605588; 610140; 613205; 616516\tENSG00000160789\n+P04083\tAnnexin A1\t10\tNX_P04083\tANXA1_HUMAN\t301\t151690\tENSG00000135046\n+P11021\t78 kDa glucose-regulated protein\t10\tNX_P11021\tGRP78_HUMAN\t3309\t138120\tENSG00000044574\n+P02787\tSerotransferrin\t9\tNX_P02787\tTRFE_HUMAN\t7018\t190000; 209300\tENSG00000091513\n+P04040\tCatalase\t9\tNX_P04040\tCATA_HUMAN\t847\t115500; 614097\tENSG00000121691\n+P31151\tProtein S100-A7\t9\tNX_P31151\tS10A7_HUMAN\t6278\t600353\tENSG00000143556\n+P31947\t14-3-3 protein sigma\t9\tNX_P31947\t1433S_HUMAN\t2810\t601290\tENSG00000175793\n+Q96P63\tSerpin B12\t9\tNX_Q96P63\tSPB12_HUMAN\t89777\t615662\tENSG00000166634\n+P14618\tPyruvate kinase PKM\t9\tNX_P14618\tKPYM_HUMAN\t5315\t179050\tENSG00000067225\n+P60174\tTriosephosphate isomerase\t9\tNX_P60174\tTPIS_HUMAN\t7167\t190450; 615512\tENSG00000111669\n+Q06830\tPeroxiredoxin-1\t9\tNX_Q06830\tPRDX1_HUMAN\t5052\t176763\tENSG00000117450\n+P01040\tCystatin-A\t8\tNX_P01040\tCYTA_HUMAN\t1475\t184600; 607936\tENSG00000121552\n+P05089\tArginase-1\t8\tNX_P05089\tARGI1_HUMAN\t383\t207800; 608313\tENSG00000118520\n+P01834\tIg kappa chain C region\t8\tNX_P01834\tIGKC_HUMAN\tNA\t147200; 614102\tNA\n+P04406\tGlyceraldehyde-3-phosphate dehydrogenase\t8\tNX_P04406\tG3P_HUMAN\t2597\t138400\tENSG00000111640\n+P0DMV9\tHeat shock 70 kDa protein 1B\t8\tNX_P0DMV9\tHS71B_HUMAN\t3303; 3304\t140550; '..b'X_P36952\tSPB5_HUMAN\t5268\t154790\tENSG00000206075\n+P40926\tMalate dehydrogenase, mitochondrial\t3\tNX_P40926\tMDHM_HUMAN\t4191\t154100; 617339\tENSG00000146701\n+Q9Y6R7\tIgGFc-binding protein\t3\tNX_Q9Y6R7\tFCGBP_HUMAN\t8857\t617553\tENSG00000281123\n+O95274\tLy6/PLAUR domain-containing protein 3\t2\tNX_O95274\tLYPD3_HUMAN\t27076\t609484\tENSG00000124466\n+P00491\tPurine nucleoside phosphorylase\t2\tNX_P00491\tPNPH_HUMAN\t4860\t164050; 613179\tENSG00000198805\n+P04080\tCystatin-B\t2\tNX_P04080\tCYTB_HUMAN\t1476\t254800; 601145\tENSG00000160213\n+P09972\tFructose-bisphosphate aldolase C\t2\tNX_P09972\tALDOC_HUMAN\t230\t103870\tENSG00000109107\n+P19012\tKeratin, type I cytoskeletal 15\t2\tNX_P19012\tK1C15_HUMAN\t3866\t148030\tENSG00000171346\n+P20930\tFilaggrin\t2\tNX_P20930\tFILA_HUMAN\t2312\t135940; 146700; 605803\tENSG00000143631\n+Q96FX8\tp53 apoptosis effector related to PMP-22\t2\tNX_Q96FX8\tPERP_HUMAN\t64065\t609301\tENSG00000112378\n+Q9UIV8\tSerpin B13\t2\tNX_Q9UIV8\tSPB13_HUMAN\t5275\t604445\tENSG00000197641\n+P01625\tIg kappa chain V-IV region Len\t2\tNA\tNA\tNA\tNA\tNA\n+P01765\tIg heavy chain V-III region TIL\t2\tNA\tNA\tNA\tNA\tNA\n+P01766\tIg heavy chain V-III region BRO\t2\tNX_P01766\tHV313_HUMAN\tNA\tNA\tENSG00000211942; ENSG00000282286\n+P01860\tIg gamma-3 chain C region\t2\tNX_P01860\tIGHG3_HUMAN\tNA\t147120\tNA\n+P01871\tIg mu chain C region\t2\tNX_P01871\tIGHM_HUMAN\tNA\t147020; 601495\tENSG00000211899; ENSG00000282657\n+P05090\tApolipoprotein D\t2\tNX_P05090\tAPOD_HUMAN\t347\t107740\tENSG00000189058\n+P06870\tKallikrein-1\t2\tNX_P06870\tKLK1_HUMAN\t3816\t147910; 615953\tENSG00000167748\n+P07858\tCathepsin B\t2\tNX_P07858\tCATB_HUMAN\t1508\t116810\tENSG00000164733\n+P08865\t40S ribosomal protein SA\t2\tNX_P08865\tRSSA_HUMAN\t3921\t150370; 271400\tENSG00000168028\n+P11279\tLysosome-associated membrane glycoprotein 1\t2\tNX_P11279\tLAMP1_HUMAN\t3916\t153330\tENSG00000185896\n+P13473\tLysosome-associated membrane glycoprotein 2\t2\tNX_P13473\tLAMP2_HUMAN\t3920\t300257; 309060\tENSG00000005893\n+P19971\tThymidine phosphorylase\t2\tNX_P19971\tTYPH_HUMAN\t1890\t131222; 603041\tENSG00000025708\n+P23284\tPeptidyl-prolyl cis-trans isomerase B\t2\tNX_P23284\tPPIB_HUMAN\t5479\t123841; 259440\tENSG00000166794\n+P23396\t40S ribosomal protein S3\t2\tNX_P23396\tRS3_HUMAN\t6188\t600454\tENSG00000149273\n+P25705\tATP synthase subunit alpha, mitochondrial\t2\tNX_P25705\tATPA_HUMAN\t498\t164360; 615228; 616045\tENSG00000152234\n+P27482\tCalmodulin-like protein 3\t2\tNX_P27482\tCALL3_HUMAN\t810\t114184\tENSG00000178363\n+P31949\tProtein S100-A11\t2\tNX_P31949\tS10AB_HUMAN\t6282\t603114\tENSG00000163191\n+P40121\tMacrophage-capping protein\t2\tNX_P40121\tCAPG_HUMAN\t822\t153615\tENSG00000042493\n+P42357\tHistidine ammonia-lyase\t2\tNX_P42357\tHUTH_HUMAN\t3034\t235800; 609457\tENSG00000084110\n+P47756\tF-actin-capping protein subunit beta\t2\tNX_P47756\tCAPZB_HUMAN\t832\t601572\tENSG00000077549\n+P48637\tGlutathione synthetase\t2\tNX_P48637\tGSHB_HUMAN\t2937\t231900; 266130; 601002\tENSG00000100983\n+P49720\tProteasome subunit beta type-3\t2\tNX_P49720\tPSB3_HUMAN\t5691\t602176\tENSG00000277791; ENSG00000275903\n+P50395\tRab GDP dissociation inhibitor beta\t2\tNX_P50395\tGDIB_HUMAN\t2665\t600767\tENSG00000057608\n+P59998\tActin-related protein 2/3 complex subunit 4\t2\tNX_P59998\tARPC4_HUMAN\t10093\t604226\tENSG00000241553\n+P61160\tActin-related protein 2\t2\tNX_P61160\tARP2_HUMAN\t10097\t604221\tENSG00000138071\n+P61916\tEpididymal secretory protein E1\t2\tNX_P61916\tNPC2_HUMAN\t10577\t601015; 607625\tENSG00000119655\n+P04745\tAlpha-amylase 1\t23\tNX_P04745\tAMY1_HUMAN\t276; 277; 278\t104700; 104701; 104702\tENSG00000174876; ENSG00000187733; ENSG00000237763\n+Q9NZT1\tCalmodulin-like protein 5\t8\tNX_Q9NZT1\tCALL5_HUMAN\t51806\t605183\tENSG00000178372\n+P12273\tProlactin-inducible protein\t6\tNX_P12273\tPIP_HUMAN\t5304\t176720\tENSG00000159763\n+Q96DA0\tZymogen granule protein 16 homolog B\t5\tNX_Q96DA0\tZG16B_HUMAN\t124220\tNA\tENSG00000162078; ENSG00000283056\n+P01036\tCystatin-S\t5\tNX_P01036\tCYTS_HUMAN\t1472\t123857\tENSG00000101441\n+Q8TAX7\tMucin-7\t2\tNX_Q8TAX7\tMUC7_HUMAN\t4589\t158375; 600807\tENSG00000171195\n+P01037\tCystatin-SN\t2\tNX_P01037\tCYTN_HUMAN\t1469\t123855\tENSG00000170373\n+P09228\tCystatin-SA\t2\tNX_P09228\tCYTT_HUMAN\t1470\t123856\tENSG00000170369\n' |
| b |
| diff -r d89c09253c8d -r 1236ee08ccb8 test-data/UnipIDs.txt --- a/test-data/UnipIDs.txt Sun Nov 26 19:19:39 2017 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,25 +0,0 @@ -P04637 -P08246 -P63244 -P10275 -P00533 -Q14524 -P05067 -P35555 -P35222 -O95273 -P00451 -P38398 -Q05086 -Q12802 -P68871 -P04585 -Q96EB6 -Q9NYL2 -P31749 -P01137 -Q5S007 -Q08379 -P02649 -P35498 -P12931 |
| b |
| diff -r d89c09253c8d -r 1236ee08ccb8 test-data/profile.BP.pdf |
| b |
| Binary file test-data/profile.BP.pdf has changed |
| b |
| diff -r d89c09253c8d -r 1236ee08ccb8 test-data/profile.CC.pdf |
| b |
| Binary file test-data/profile.CC.pdf has changed |
| b |
| diff -r d89c09253c8d -r 1236ee08ccb8 test-data/profile.MF.pdf |
| b |
| Binary file test-data/profile.MF.pdf has changed |