# HG changeset patch # User pavlo-lutsik # Date 1373025834 14400 # Node ID aad84663f9c2e1ee56dbcc3da821028fb7e5c7a8 # Parent afb06b3416d852e73efffc9ba144db422e3ae51b Uploaded diff -r afb06b3416d8 -r aad84663f9c2 .~lock.faq.section.doc# --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/.~lock.faq.section.doc# Fri Jul 05 08:03:54 2013 -0400 @@ -0,0 +1,1 @@ +Pavlo Lutsik,lutsik,ws.genetik.uni-sb.de,04.07.2013 21:51,file:///home/lutsik/.config/libreoffice/3; \ No newline at end of file diff -r afb06b3416d8 -r aad84663f9c2 RnBeadsGalaxy.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/RnBeadsGalaxy.R Fri Jul 05 08:03:54 2013 -0400 @@ -0,0 +1,198 @@ +#msg.file<-file("RnBeads.messages.out", open="w") +#sink(file=msg.file) + +suppressWarnings(suppressPackageStartupMessages(library(RnBeads))) +suppressWarnings(suppressPackageStartupMessages(library(getopt))) + +#all.opts<-names(rnb.options()) +opt.class<-RnBeads:::OPTION.TYPES[-28] +all.opts<-names(opt.class) +#all.opts<-paste("--", all.opts, sep="") +#all.opts<-gsub("\\.([a-z])", "\\U\\1", all.opts, perl=TRUE) +all.opts<-gsub("\\.","-", all.opts) +#opt.class<-sapply(rnb.options(), class) + +rnb.opt.spec<-data.frame( + Long=all.opts, + Short=as.character(1:length(all.opts)), + Mask=c(1,2)[as.integer((opt.class=="logical"))+1], + Type=opt.class) + +### automated xml file preparation +xml.strings<-apply(rnb.opt.spec,1, function(row){ + + opt.lab<-gsub("-", ".", row[1]) + opt.def.val<-rnb.getOption(opt.lab) + opt.name<-gsub("-([0-9a-z])", "\\U\\1", row[1], perl=TRUE) + tf.opt<-"\t\t\t\n\t\t\t" + opt.lab<-paste(opt.lab, gsub("\\."," ", row[4]), sep=", ") + if(row[4]=="logical"){ + opt.type<-'select' + if(!is.null(opt.def.val) && opt.def.val) + opt.def.val<-"1" else + opt.def.val<-"0" + string<-sprintf("\t\t\n%s\n\t\t\n", opt.name, opt.type, opt.lab, opt.def.val, tf.opt) + }else{ + opt.type<-'text' + if(!is.null(opt.def.val) && opt.def.val!="") + opt.def.val<-paste(opt.def.val, collapse=",") else + opt.def.val<-"" + string<-sprintf("\t\t\n", opt.name, opt.type, opt.lab, opt.def.val) + } + string + }) + +cat(xml.strings, sep="", file="automated.settings.xml.txt") + +opt.def.strings<-apply(rnb.opt.spec,1, function(row){ + + opt.name<-gsub("-([0-9a-z])", "\\U\\1", row[1], perl=TRUE) + opt.long<-row[1] + opt.short<-row[2] + + if(row[4]=="logical"){ + def.string<-sprintf("#if str( $options.%s ) == \"True\"\n\t--%s\n#end if\n", opt.name, opt.long) + }else{ + def.string<-sprintf("#if str( $options.%s ) != \"\"\n\t--%s=\"$options.%s\" \n#end if\n", opt.name, opt.long, opt.name) + } + def.string + + }) +cat(opt.def.strings, sep="", file="automated.option.assignments.txt") + + +rnb.opt.spec$Type<-gsub("\\.vector", "", rnb.opt.spec$Type) +rnb.opt.spec$Type<-gsub("numeric", "double", rnb.opt.spec$Type) +rnb.opt.spec<-rbind(data.frame( + Long=c("data-type", "pheno", "idat-dir","idat-files","bed-files", "gs-report", "geo-series", "betas", "pvals","output-file", "report-dir"), + Short=c("d","s","a","i","f","g","e","b","p","r","o"), + Mask=c(1,2,2,2,2,2,2,2,2,1,1), + Type=c("character","character","character","character","character","character","character","character","character","character", "character")), + rnb.opt.spec) + +opts<-getopt(as.matrix(rnb.opt.spec)) +#opts<-getopt(as.matrix(rnb.opt.spec), opt=list("--data-type=idats","--report-dir=dir", "--idats=file1\tfile2")) +print(opts) + +if(opts[["data-type"]]=="idatDir"){ + + data.source<-list() + data.type<-"idat.dir" + data.source[["idat.dir"]]<-opts[["idat-dir"]] + data.source[["sample.sheet"]]<-opts[["pheno"]] + +}else if(opts[["data-type"]]=="idatFiles"){ + + data.type<-"idat.dir" + file.string<-gsub(" ","", opts[["idat-files"]]) + files<-strsplit(file.string, ",")[[1]] + files<-files[files!=""] + bed.dir<-sprintf("%s_beds",opts[["report-dir"]]) + dir.create(bed.dir) + file.copy(files, bed.dir) + for(dat.file in list.files(bed.dir, full.names = TRUE)){ + file.rename(dat.file, gsub("\\.dat", ".bed", dat.file)) + } + data.source<-list() + data.source[["bed.dir"]]<-bed.dir + data.source[["sample.sheet"]]<-opts[["pheno"]] + + +}else if(opts[["data-type"]]=="GS.report"){ + + data.type<-"GS.report" + data.source<-opts[["gs-report"]] + +}else if(opts[["data-type"]]=="GEO"){ + + data.type<-"GEO" + data.source<-opts[["geo-series"]] + +}else if(opts[["data-type"]]=="data.files"){ + + data.type<-"GEO" + data.source<-opts[["geo-series"]] + +}else if(opts[["data-type"]]=="data.files"){ + + data.type<-"data.files" + data.source<-c(opts[["pheno"]], opts[["betas"]]) + if(!is.null(opts[["pvals"]])) + data.source<-c(data.source, opts[["pvals"]]) + +}else if(opts[["data-type"]]=="bed.dir"){ + + data.type<-"bed.dir" + file.string<-gsub(" ","", opts[["bed-files"]]) + files<-strsplit(file.string, ",")[[1]] + files<-files[files!=""] + bed.dir<-sprintf("%s_beds",opts[["report-dir"]]) + dir.create(bed.dir) + file.copy(files, bed.dir) + for(dat.file in list.files(bed.dir, full.names = TRUE)){ + file.rename(dat.file, gsub("\\.dat", ".bed", dat.file)) + } + data.source<-list() + data.source[["bed.dir"]]<-bed.dir + + logger.start(fname="NA") + sample.sheet<-rnb.read.annotation(opts[["pheno"]]) + logger.close() + if(length(files) < nrow(sample.sheet)) + stop("Not all bed files are present") + + cn<-colnames(sample.sheet) + dat.files<-sapply(strsplit(files, "\\/"), function(el) el[length(el)]) + sample.sheet<-cbind(sample.sheet, gsub("\\.dat", ".bed", dat.files)) + colnames(sample.sheet)<-c(cn, "BED_files") + data.source[["sample.sheet"]]<-sample.sheet +} + +if("logging" %in% names(opts)){ # TODO create a cleaner way of checking whether the full options set was supplied + + dump<-sapply(names(opt.class), function(on){ + getoptname<-gsub("-", "\\.","-",on) + if(getoptname %in% names(opts)){ + if(opt.class[on]=="logical"){ + ov<-TRUE + }else if(opt.class %in% c("character","character.vector")){ + ov<-opts[[getoptname]] + ov<-gsub("\"", "", ov) + if(opt.class=="character.vector"){ + ov<-as.character(strsplit(ov,",")) + } + + }else if(opt.class %in% c("integer","numeric","integer.vector","numeric.vector")){ + ov<-opts[[getoptname]] + ov<-gsub("\"", "", ov) + if(opt.class %in% c("integer.vector","numeric.vector")){ + ov<-as.character(strsplit(ov,",")) + } + } + eval(parse(text=sprintf("rnb.options(%s=ov)",on))) + } + }) + + logical.opts<-names(opt.class[opt.class=="logical"]) + logical.opts.false<-logical.opts[!logical.opts %in% gsub("-",".",names(opts))] + + + dump<-sapply(logical.opts.false, function(on){ + eval(parse(text=sprintf("rnb.options(%s=FALSE)",on))) + }) +} + +print(rnb.options()) + +#report.out.dir<-sprintf("%s_rnbReport", tempdir()) +report.out.dir<-opts[["report-dir"]] +print("Starting RnBeads with the following inputs:") +print(data.source) +print(report.out.dir) +print(data.type) +rnb.run.analysis(data.source=data.source, dir.report=report.out.dir, data.type=data.type) + + +#sink(file=NULL) +#flush(msg.file) +#close(msg.file) \ No newline at end of file diff -r afb06b3416d8 -r aad84663f9c2 faq.section.doc Binary file faq.section.doc has changed diff -r afb06b3416d8 -r aad84663f9c2 galaxy.on.the.cloud Binary file galaxy.on.the.cloud has changed diff -r afb06b3416d8 -r aad84663f9c2 galaxy_faq.docx Binary file galaxy_faq.docx has changed diff -r afb06b3416d8 -r aad84663f9c2 install.rnbeads.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/install.rnbeads.R Fri Jul 05 08:03:54 2013 -0400 @@ -0,0 +1,1 @@ +source("http://rnbeads.mpi-inf.mpg.de/install.R") \ No newline at end of file diff -r afb06b3416d8 -r aad84663f9c2 rnb.cloud.4.07.analysis.log --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rnb.cloud.4.07.analysis.log Fri Jul 05 08:03:54 2013 -0400 @@ -0,0 +1,265 @@ +2013-07-04 12:48:18 STATUS STARTED RnBeads Pipeline +2013-07-04 12:48:18 INFO Initialized report index and saved to index.html +2013-07-04 12:48:18 STATUS STARTED Loading Data +2013-07-04 12:48:18 STATUS STARTED Loading GEO Data Series +2013-07-04 12:53:38 INFO Loaded 1 data series from GSE38268 +2013-07-04 12:53:38 INFO Extracted 6 samples from series 1 +2013-07-04 12:53:38 INFO Parsed characteristics_ch1 sample information +2013-07-04 12:53:38 STATUS COMPLETED Loading GEO Data Series +2013-07-04 12:54:49 STATUS Loaded data from GSE38268. Output object is of class RnBeadSet +2013-07-04 12:54:50 STATUS Added data loading section +2013-07-04 12:54:50 STATUS COMPLETED Loading Data +2013-07-04 12:54:50 STATUS STARTED Normalization +2013-07-04 12:54:50 WARNING Incompatible values for object and method. Changed the normalization method to "none" +2013-07-04 12:54:50 WARNING Incompatible values for object and background correction flag. Disabled the background correction +2013-07-04 12:54:50 STATUS Performed normalization with method "swan" +2013-07-04 12:54:53 STATUS Added normalization section +2013-07-04 12:54:53 STATUS COMPLETED Normalization +2013-07-04 12:54:54 INFO Initialized report index and saved to index.html +2013-07-04 12:54:54 STATUS STARTED Quality Control +2013-07-04 12:54:54 STATUS STARTED Quality Control Section +2013-07-04 12:54:54 INFO No quality information present in the dataset +2013-07-04 12:54:54 STATUS COMPLETED Quality Control Section +2013-07-04 12:54:54 STATUS COMPLETED Quality Control +2013-07-04 12:54:54 STATUS STARTED Visualizing Sample Mixups +2013-07-04 12:54:54 STATUS STARTED Mixups Visualization Section +2013-07-04 12:55:15 STATUS Added SNP heatmap +2013-07-04 12:55:15 STATUS COMPLETED Mixups Visualization Section +2013-07-04 12:55:15 STATUS COMPLETED Visualizing Sample Mixups +2013-07-04 12:55:15 INFO Initialized report index and saved to index.html +2013-07-04 12:55:15 STATUS STARTED Filtering +2013-07-04 12:55:23 STATUS STARTED Probe Context Removal +2013-07-04 12:56:00 STATUS Removed 3156 probe(s) out of context +2013-07-04 12:56:01 STATUS Saved removed sites to /mnt/galaxy/files/000/dataset_3_files/filtering_data/removed_sites_context.csv +2013-07-04 12:56:01 STATUS Added a corresponding section to the report +2013-07-04 12:56:01 STATUS COMPLETED Probe Context Removal +2013-07-04 12:56:03 STATUS STARTED Removal of SNP-enriched Sites +2013-07-04 12:56:38 STATUS Removed 18987 sites that overlap sites with more than 2 SNP(s) +2013-07-04 12:56:38 STATUS Saved removed sites to /mnt/galaxy/files/000/dataset_3_files/filtering_data/removed_sites_snp.csv +2013-07-04 12:56:38 STATUS Added a corresponding section to the report +2013-07-04 12:56:38 STATUS COMPLETED Removal of SNP-enriched Sites +2013-07-04 12:56:39 INFO Omitting Greedycut because detection p-values are missing +2013-07-04 12:56:42 STATUS STARTED Summary of Filtering Procedures +2013-07-04 12:56:46 STATUS Added summary table of removed and retained values +2013-07-04 12:57:47 STATUS Added comparison between removed and retained beta values +2013-07-04 12:57:47 STATUS COMPLETED Summary of Filtering Procedures +2013-07-04 12:57:47 STATUS COMPLETED Filtering +2013-07-04 12:57:47 INFO Initialized report index and saved to index.html +2013-07-04 12:57:47 STATUS STARTED Dimension Reduction Techniques +2013-07-04 12:57:48 WARNING Removed 4301 loci ( sites ) because they contain missing values +2013-07-04 12:57:49 STATUS Calculated PCA coordinates +2013-07-04 12:57:49 STATUS Calculated MDS coordinates using manhattan distance +2013-07-04 12:57:49 STATUS Calculated MDS coordinates using euclidean distance +2013-07-04 12:57:50 WARNING Removed 491 loci ( tiling ) because they contain missing values +2013-07-04 12:57:50 STATUS Calculated PCA coordinates +2013-07-04 12:57:50 STATUS Calculated MDS coordinates using manhattan distance +2013-07-04 12:57:50 STATUS Calculated MDS coordinates using euclidean distance +2013-07-04 12:57:50 WARNING Removed 25 loci ( genes ) because they contain missing values +2013-07-04 12:57:50 STATUS Calculated PCA coordinates +2013-07-04 12:57:50 STATUS Calculated MDS coordinates using manhattan distance +2013-07-04 12:57:50 STATUS Calculated MDS coordinates using euclidean distance +2013-07-04 12:57:50 WARNING Removed 30 loci ( promoters ) because they contain missing values +2013-07-04 12:57:50 STATUS Calculated PCA coordinates +2013-07-04 12:57:50 STATUS Calculated MDS coordinates using manhattan distance +2013-07-04 12:57:50 STATUS Calculated MDS coordinates using euclidean distance +2013-07-04 12:57:51 WARNING Removed 15 loci ( cpgislands ) because they contain missing values +2013-07-04 12:57:51 STATUS Calculated PCA coordinates +2013-07-04 12:57:51 STATUS Calculated MDS coordinates using manhattan distance +2013-07-04 12:57:51 STATUS Calculated MDS coordinates using euclidean distance +2013-07-04 12:57:51 INFO Mapping 2 traits to point colors and types +2013-07-04 13:14:59 INFO Principal components that explain at least 95 % of the total variance: 5 +2013-07-04 13:14:59 INFO Saved percentage of total variance to pca_variance_explained_1.csv +2013-07-04 13:15:03 INFO Principal components that explain at least 95 % of the total variance: 5 +2013-07-04 13:15:03 INFO Saved percentage of total variance to pca_variance_explained_2.csv +2013-07-04 13:15:08 INFO Principal components that explain at least 95 % of the total variance: 5 +2013-07-04 13:15:08 INFO Saved percentage of total variance to pca_variance_explained_3.csv +2013-07-04 13:15:12 INFO Principal components that explain at least 95 % of the total variance: 5 +2013-07-04 13:15:12 INFO Saved percentage of total variance to pca_variance_explained_4.csv +2013-07-04 13:15:16 INFO Principal components that explain at least 95 % of the total variance: 5 +2013-07-04 13:15:16 INFO Saved percentage of total variance to pca_variance_explained_5.csv +2013-07-04 13:15:20 STATUS Created scatter plots and CDFs summarizing the reduced dimensional representations +2013-07-04 13:15:20 STATUS COMPLETED Dimension Reduction Techniques +2013-07-04 13:15:20 STATUS STARTED Tests for Associations +2013-07-04 13:15:20 INFO Testing the following traits for associations: tumour site; tissue +2013-07-04 13:15:20 STATUS Computed correlations between principal components and traits. +2013-07-04 13:15:20 STATUS Computed pairwise correlations between traits. +2013-07-04 13:15:20 STATUS COMPLETED Tests for Associations +2013-07-04 13:15:48 STATUS STARTED Quality-associated Batch Effects +2013-07-04 13:15:48 WARNING No quality information available +2013-07-04 13:15:48 STATUS COMPLETED Quality-associated Batch Effects +2013-07-04 13:15:48 INFO Initialized report index and saved to index.html +2013-07-04 13:15:49 STATUS STARTED Methylation Profiles +2013-07-04 13:15:49 INFO Designed color mappings for probe type and CGI status +2013-07-04 13:15:57 STATUS STARTED Methylation Value Distributions - Sample Groups +2013-07-04 13:19:31 STATUS COMPLETED Methylation Value Distributions - Sample Groups +2013-07-04 13:19:31 STATUS STARTED Methylation Value Distributions - Probe Categories +2013-07-04 13:22:46 STATUS COMPLETED Methylation Value Distributions - Probe Categories +2013-07-04 13:22:47 STATUS STARTED Scatter Plots of Mean Beta vs Variance +2013-07-04 13:22:47 INFO Sample subgroups are defined by: tumour site; tissue +2013-07-04 13:22:48 WARNING Removed 10 loci with missing values in group all samples +2013-07-04 13:31:43 WARNING Removed 1448 loci with missing values in group base of tongue (based on tumour site) +2013-07-04 13:40:36 WARNING Removed 26 loci with missing values in group tonsil (based on tumour site) +2013-07-04 13:49:33 WARNING Removed 56 loci with missing values in group HPV+ HNSCC tumor (based on tissue) +2013-07-04 13:58:28 WARNING Removed 78 loci with missing values in group HPV- HNSCC tumor (based on tissue) +2013-07-04 14:07:20 STATUS Created 20 scatter plots of methylation variance on the site level +2013-07-04 14:07:21 WARNING Removed 1 loci with missing values in group all samples +2013-07-04 14:08:44 WARNING Removed 159 loci with missing values in group base of tongue (based on tumour site) +2013-07-04 14:10:05 WARNING Removed 2 loci with missing values in group tonsil (based on tumour site) +2013-07-04 14:11:26 WARNING Removed 4 loci with missing values in group HPV+ HNSCC tumor (based on tissue) +2013-07-04 14:12:48 WARNING Removed 7 loci with missing values in group HPV- HNSCC tumor (based on tissue) +2013-07-04 14:14:34 WARNING Removed 9 loci with missing values in group base of tongue (based on tumour site) +2013-07-04 14:16:42 WARNING Removed 8 loci with missing values in group base of tongue (based on tumour site) +2013-07-04 14:17:34 WARNING Removed 1 loci with missing values in group HPV+ HNSCC tumor (based on tissue) +2013-07-04 14:18:49 WARNING Removed 2 loci with missing values in group base of tongue (based on tumour site) +2013-07-04 14:20:26 STATUS Created 40 scatter plots of methylation variance on the region level +2013-07-04 14:20:26 STATUS COMPLETED Scatter Plots of Mean Beta vs Variance +2013-07-04 14:20:26 STATUS STARTED Deviation Plots +2013-07-04 14:49:08 STATUS Created 15 deviation plots on the site level +2013-07-04 15:04:01 STATUS Created 20 deviation plots on the region level +2013-07-04 15:04:02 STATUS Added summary table of variabilities +2013-07-04 15:04:02 STATUS COMPLETED Deviation Plots +2013-07-04 15:04:02 STATUS STARTED Sample Clustering +2013-07-04 15:04:02 STATUS STARTED Agglomerative Hierarchical Clustering +2013-07-04 15:04:02 STATUS Performed clustering on sites using correlation as a distance metric +2013-07-04 15:04:02 STATUS Performed clustering on sites using manhattan as a distance metric +2013-07-04 15:04:03 STATUS Performed clustering on sites using euclidean as a distance metric +2013-07-04 15:04:03 STATUS Performed clustering on tiling using correlation as a distance metric +2013-07-04 15:04:03 STATUS Performed clustering on tiling using manhattan as a distance metric +2013-07-04 15:04:03 STATUS Performed clustering on tiling using euclidean as a distance metric +2013-07-04 15:04:03 STATUS Completed clustering for tiling +2013-07-04 15:04:03 STATUS Performed clustering on genes using correlation as a distance metric +2013-07-04 15:04:03 STATUS Performed clustering on genes using manhattan as a distance metric +2013-07-04 15:04:03 STATUS Performed clustering on genes using euclidean as a distance metric +2013-07-04 15:04:03 STATUS Completed clustering for genes +2013-07-04 15:04:03 STATUS Performed clustering on promoters using correlation as a distance metric +2013-07-04 15:04:03 STATUS Performed clustering on promoters using manhattan as a distance metric +2013-07-04 15:04:03 STATUS Performed clustering on promoters using euclidean as a distance metric +2013-07-04 15:04:03 STATUS Completed clustering for promoters +2013-07-04 15:04:03 STATUS Performed clustering on cpgislands using correlation as a distance metric +2013-07-04 15:04:03 STATUS Performed clustering on cpgislands using manhattan as a distance metric +2013-07-04 15:04:04 STATUS Performed clustering on cpgislands using euclidean as a distance metric +2013-07-04 15:04:04 STATUS Completed clustering for cpgislands +2013-07-04 15:04:04 STATUS COMPLETED Agglomerative Hierarchical Clustering +2013-07-04 15:04:04 STATUS STARTED Clustering Section +2013-07-04 15:04:05 STATUS STARTED Generating Heatmaps +2013-07-04 15:04:05 STATUS STARTED Region type: sites +2013-07-04 15:12:40 STATUS COMPLETED Region type: sites +2013-07-04 15:12:40 STATUS STARTED Region type: tiling +2013-07-04 15:21:19 STATUS COMPLETED Region type: tiling +2013-07-04 15:21:19 STATUS STARTED Region type: genes +2013-07-04 15:29:56 STATUS COMPLETED Region type: genes +2013-07-04 15:29:56 STATUS STARTED Region type: promoters +2013-07-04 15:38:33 STATUS COMPLETED Region type: promoters +2013-07-04 15:38:33 STATUS STARTED Region type: cpgislands +2013-07-04 15:47:09 STATUS COMPLETED Region type: cpgislands +2013-07-04 15:47:10 STATUS Created 360 heatmaps based on the clustering results +2013-07-04 15:47:10 STATUS COMPLETED Generating Heatmaps +2013-07-04 15:47:10 STATUS STARTED Adding Color Legends +2013-07-04 15:50:15 STATUS COMPLETED Adding Color Legends +2013-07-04 15:50:15 STATUS STARTED Estimating Optimal Numbers of Clusters +2013-07-04 15:51:21 STATUS Estimated number of clusters based on mean silhouette value +2013-07-04 15:51:21 STATUS COMPLETED Estimating Optimal Numbers of Clusters +2013-07-04 15:51:21 STATUS STARTED Overlapping Clusters with Sample Traits +2013-07-04 15:51:21 STATUS Computed adjusted rand indices and saved to profiles_data/adjusted_rand_indices_1.csv +2013-07-04 15:51:21 STATUS Computed adjusted rand indices and saved to profiles_data/adjusted_rand_indices_2.csv +2013-07-04 15:51:21 STATUS Computed adjusted rand indices and saved to profiles_data/adjusted_rand_indices_3.csv +2013-07-04 15:51:21 STATUS Computed adjusted rand indices and saved to profiles_data/adjusted_rand_indices_4.csv +2013-07-04 15:51:21 STATUS Computed adjusted rand indices and saved to profiles_data/adjusted_rand_indices_5.csv +2013-07-04 15:52:26 STATUS COMPLETED Overlapping Clusters with Sample Traits +2013-07-04 15:52:26 STATUS COMPLETED Clustering Section +2013-07-04 15:52:26 STATUS COMPLETED Sample Clustering +2013-07-04 15:52:26 STATUS STARTED Regional Methylation Profiling +2013-07-04 15:52:26 STATUS STARTED Computing Regional Profiles Based on Binning +2013-07-04 15:52:26 STATUS STARTED Processing Region Type: genes +2013-07-04 16:03:01 STATUS Set region annotation and site membership +2013-07-04 16:04:02 STATUS Computed binned methylation values +2013-07-04 16:04:02 STATUS COMPLETED Processing Region Type: genes +2013-07-04 16:04:02 STATUS STARTED Processing Region Type: promoters +2013-07-04 16:14:38 STATUS Set region annotation and site membership +2013-07-04 16:15:29 STATUS Computed binned methylation values +2013-07-04 16:15:29 STATUS COMPLETED Processing Region Type: promoters +2013-07-04 16:15:29 STATUS STARTED Processing Region Type: cpgislands +2013-07-04 16:25:46 STATUS Set region annotation and site membership +2013-07-04 16:26:38 STATUS Computed binned methylation values +2013-07-04 16:26:38 STATUS COMPLETED Processing Region Type: cpgislands +2013-07-04 16:26:38 STATUS COMPLETED Computing Regional Profiles Based on Binning +2013-07-04 16:26:38 STATUS STARTED Creating a Corresponding Section in the Report +2013-07-04 16:26:38 STATUS Plotting region profiles for region genes and column tumour site ... +2013-07-04 16:28:31 STATUS Plotting region profiles for region genes and column tissue ... +2013-07-04 16:29:44 STATUS Plotting region profiles for region promoters and column tumour site ... +2013-07-04 16:30:31 STATUS Plotting region profiles for region promoters and column tissue ... +2013-07-04 16:31:15 STATUS Plotting region profiles for region cpgislands and column tumour site ... +2013-07-04 16:32:16 STATUS Plotting region profiles for region cpgislands and column tissue ... +2013-07-04 16:33:13 STATUS COMPLETED Creating a Corresponding Section in the Report +2013-07-04 16:33:13 STATUS COMPLETED Regional Methylation Profiling +2013-07-04 16:33:13 STATUS COMPLETED Methylation Profiles +2013-07-04 16:33:13 INFO Initialized report index and saved to index.html +2013-07-04 16:33:14 STATUS STARTED Differential Methylation - Analysis +2013-07-04 16:33:14 INFO Using 0 permutation tests +2013-07-04 16:33:14 INFO Using columns: title,geo_accession,status,submission_date,last_update_date,type,channel_count,source_name_ch1,organism_ch1,molecule_ch1,extract_protocol_ch1,label_ch1,label_protocol_ch1,taxid_ch1,hyb_protocol,scan_protocol,description,data_processing,platform_id,contact_name,contact_email,contact_laboratory,contact_department,contact_institute,contact_address,contact_city,contact_zip/postal_code,contact_country,supplementary_file,data_row_count,tumour site,tissue +2013-07-04 16:33:14 INFO Using region types: tiling,genes,promoters,cpgislands +2013-07-04 16:33:14 STATUS STARTED Comparison Information: tumour site +2013-07-04 16:33:14 STATUS STARTED Comparing base of tongue-tonsil +2013-07-04 16:33:14 STATUS STARTED Computing Differential Methylation Table (Site Level) +2013-07-04 16:33:21 INFO Some t-test p-values are NA. They are treated as 1 in FDR adjustment +2013-07-04 16:33:28 STATUS COMPLETED Computing Differential Methylation Table (Site Level) +2013-07-04 16:33:28 STATUS STARTED Computing Differential Methylation Tables (Region Level) +2013-07-04 16:45:21 INFO Some p-values are NA. They are treated as 1 in FDR adjustment +2013-07-04 16:45:21 STATUS Computed table for tiling +2013-07-04 16:48:07 INFO Some p-values are NA. They are treated as 1 in FDR adjustment +2013-07-04 16:48:07 STATUS Computed table for genes +2013-07-04 16:50:48 INFO Some p-values are NA. They are treated as 1 in FDR adjustment +2013-07-04 16:50:48 STATUS Computed table for promoters +2013-07-04 16:53:07 INFO Some p-values are NA. They are treated as 1 in FDR adjustment +2013-07-04 16:53:07 STATUS Computed table for cpgislands +2013-07-04 16:53:07 STATUS COMPLETED Computing Differential Methylation Tables (Region Level) +2013-07-04 16:53:07 STATUS COMPLETED Comparing base of tongue-tonsil +2013-07-04 16:53:07 STATUS COMPLETED Comparison Information: tumour site +2013-07-04 16:53:07 STATUS STARTED Comparison Information: tissue +2013-07-04 16:53:07 STATUS STARTED Comparing HPV+ HNSCC tumor-HPV- HNSCC tumor +2013-07-04 16:53:07 STATUS STARTED Computing Differential Methylation Table (Site Level) +2013-07-04 16:53:12 INFO Some t-test p-values are NA. They are treated as 1 in FDR adjustment +2013-07-04 16:53:17 STATUS COMPLETED Computing Differential Methylation Table (Site Level) +2013-07-04 16:53:17 STATUS STARTED Computing Differential Methylation Tables (Region Level) +2013-07-04 17:04:12 INFO Some p-values are NA. They are treated as 1 in FDR adjustment +2013-07-04 17:04:13 STATUS Computed table for tiling +2013-07-04 17:06:56 STATUS Computed table for genes +2013-07-04 17:09:29 INFO Some p-values are NA. They are treated as 1 in FDR adjustment +2013-07-04 17:09:29 STATUS Computed table for promoters +2013-07-04 17:11:43 STATUS Computed table for cpgislands +2013-07-04 17:11:43 STATUS COMPLETED Computing Differential Methylation Tables (Region Level) +2013-07-04 17:11:43 STATUS COMPLETED Comparing HPV+ HNSCC tumor-HPV- HNSCC tumor +2013-07-04 17:11:43 STATUS COMPLETED Comparison Information: tissue +2013-07-04 17:11:43 INFO Skipping enrichment analysis of differentially methylated regions +2013-07-04 17:11:43 STATUS COMPLETED Differential Methylation - Analysis +2013-07-04 17:11:43 STATUS STARTED Differential Methylation - Report Generation +2013-07-04 17:11:43 STATUS Added introductory section +2013-07-04 17:11:43 STATUS STARTED Adding Site Level Information +2013-07-04 18:03:20 STATUS COMPLETED Adding Site Level Information +2013-07-04 18:03:20 STATUS STARTED Adding Region Level Information +2013-07-04 18:31:24 STATUS COMPLETED Adding Region Level Information +2013-07-04 18:31:24 STATUS COMPLETED Differential Methylation - Report Generation +2013-07-04 18:31:25 INFO Initialized report index and saved to index.html +2013-07-04 18:31:25 STATUS STARTED Data Export +2013-07-04 18:31:25 STATUS STARTED Exporting RnBSet +2013-07-04 18:31:25 STATUS STARTED Exporting sites +2013-07-04 18:31:25 STATUS STARTED Creating UCSC Track Hub -- bigBed +2013-07-04 18:31:25 STATUS STARTED Conversion to BED +2013-07-04 18:33:46 STATUS COMPLETED Conversion to BED +2013-07-04 18:33:46 STATUS STARTED Creating UCSC Track Hub +2013-07-04 18:34:06 STATUS COMPLETED Creating UCSC Track Hub +2013-07-04 18:34:06 STATUS COMPLETED Creating UCSC Track Hub -- bigBed +2013-07-04 18:34:06 STATUS STARTED Creating UCSC Track Hub -- bigWig +2013-07-04 18:34:06 STATUS STARTED Conversion to bedGraph +2013-07-04 18:36:10 STATUS COMPLETED Conversion to bedGraph +2013-07-04 18:36:10 STATUS STARTED Creating UCSC Track Hub +2013-07-04 18:36:28 STATUS COMPLETED Creating UCSC Track Hub +2013-07-04 18:36:28 STATUS COMPLETED Creating UCSC Track Hub -- bigWig +2013-07-04 18:36:28 STATUS COMPLETED Exporting sites +2013-07-04 18:36:28 STATUS COMPLETED Exporting RnBSet +2013-07-04 18:36:28 STATUS STARTED Writing export report +2013-07-04 18:36:28 STATUS COMPLETED Writing export report +2013-07-04 18:36:28 STATUS COMPLETED Data Export +2013-07-04 18:36:28 INFO Initialized report index and saved to index.html +2013-07-04 18:36:29 STATUS COMPLETED RnBeads Pipeline + diff -r afb06b3416d8 -r aad84663f9c2 rnbeads.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rnbeads.xml Fri Jul 05 08:03:54 2013 -0400 @@ -0,0 +1,506 @@ + + + Performs RnBeads analysis for the selected set of + + R_SCRIPTS_PATH + R + + rnbeads_galaxy_wrapper.sh + --report-dir="$html_file.extra_files_path" + --output-file="$html_file" + #if str( $inputDataSelector.dataType ) == "idats" + --pheno="$inputDataSelector.sampleAnnotations" + #end if + #if str( $inputDataSelector.dataType ) != "idats" + #pass + #else if str( $inputDataSelector.idatSelector.idatSource ) == "history" + --data-type="idatFiles" + #set $idatList="" + #for $input_file in $inputDataSelector.idatSelector.idatSeries: + #set $idatList+=str( $input_file.idatFile ) + #set $idatList+="," + #end for + --idat-files="$idatList" + #else: + --data-type="idatDir" + --idat-dir="$inputDataSelector.idatSelector.idatRepo.fields.path" + #end if + #if str( $inputDataSelector.dataType ) == "gsreport" + --data-type="GS.report" + --gs-report="$inputDataSelector.gsReportFile" + #end if + #if str( $inputDataSelector.dataType ) == "geo" + --data-type="GEO" + --geo-series=$inputDataSelector.geoSeries + #end if + #if str( $inputDataSelector.dataType ) == "tables" + --data-type="data.files" + --pheno="$inputDataSelector.sampleAnnotations" + #end if + #if str( $inputDataSelector.dataType ) == "tables" + --data-type="data.files" + --pheno="$inputDataSelector.sampleAnnotations" + --betas="$inputDataSelector.betaTable" + --pvals="$inputDataSelector.pvalTable" + #end if + #if str( $inputDataSelector.dataType ) == "bed" + --data-type="bed.dir" + --pheno="$inputDataSelector.sampleAnnotations" + #set $bedList="" + #for $input_file in $inputDataSelector.bedSeries: + #set $bedList+=str( $input_file.bedFile ) + #set $bedList+="," + #end for + --bed-files="$bedList" + #end if + #if str( $options.optionSet ) == "full" + #if str( $options.analysisName ) != "" + --analysis-name="$options.analysisName" + #end if + #if str( $options.logging ) == "True" + --logging + #end if + #if str( $options.email ) != "" + --email="$options.email" + #end if + #if str( $options.assembly ) != "" + --assembly="$options.assembly" + #end if + #if str( $options.columnsPairing ) != "" + --columns-pairing="$options.columnsPairing" + #end if + #if str( $options.analyzeSites ) == "True" + --analyze-sites + #end if + #if str( $options.regionTypes ) != "" + --region-types="$options.regionTypes" + #end if + #if str( $options.identifiersColumn ) != "" + --identifiers-column="$options.identifiersColumn" + #end if + #if str( $options.pointsCategory ) != "" + --points-category="$options.pointsCategory" + #end if + #if str( $options.colorsCategory ) != "" + --colors-category="$options.colorsCategory" + #end if + #if str( $options.colorsGradient ) != "" + --colors-gradient="$options.colorsGradient" + #end if + #if str( $options.minGroupSize ) != "" + --min-group-size="$options.minGroupSize" + #end if + #if str( $options.maxGroupCount ) != "" + --max-group-count="$options.maxGroupCount" + #end if + #if str( $options.gzLargeFiles ) == "True" + --gz-large-files + #end if + #if str( $options.strandSpecific ) == "True" + --strand-specific + #end if + #if str( $options.replicateIdColumn ) != "" + --replicate-id-column="$options.replicateIdColumn" + #end if + #if str( $options.loadingNormalization ) == "True" + --loading-normalization + #end if + #if str( $options.loadingDefaultDataType ) != "" + --loading-default-data-type="$options.loadingDefaultDataType" + #end if + #if str( $options.loadingTableSeparator ) != "" + --loading-table-separator="$options.loadingTableSeparator" + #end if + #if str( $options.loadingBedStyle ) != "" + --loading-bed-style="$options.loadingBedStyle" + #end if + #if str( $options.loadingBedColumns ) != "" + --loading-bed-columns="$options.loadingBedColumns" + #end if + #if str( $options.loadingBedFrameShift ) != "" + --loading-bed-frame-shift="$options.loadingBedFrameShift" + #end if + #if str( $options.normalizationMethod ) != "" + --normalization-method="$options.normalizationMethod" + #end if + #if str( $options.normalizationBackgroundMethod ) != "" + --normalization-background-method="$options.normalizationBackgroundMethod" + #end if + #if str( $options.qc ) == "True" + --qc + #end if + #if str( $options.qcBoxplots ) == "True" + --qc-boxplots + #end if + #if str( $options.qcBarplots ) == "True" + --qc-barplots + #end if + #if str( $options.qcSnpHeatmap ) == "True" + --qc-snp-heatmap + #end if + #if str( $options.qcSnpHeatmap ) == "True" + --qc-snp-heatmap + #end if + #if str( $options.qcSnpBoxplot ) == "True" + --qc-snp-boxplot + #end if + #if str( $options.qcSnpBarplot ) == "True" + --qc-snp-barplot + #end if + #if str( $options.qcSampleBatchSize ) != "" + --qc-sample-batch-size="$options.qcSampleBatchSize" + #end if + #if str( $options.filteringContextRemoval ) != "" + --filtering-context-removal="$options.filteringContextRemoval" + #end if + #if str( $options.filteringSnp ) == "True" + --filtering-snp + #end if + #if str( $options.filteringSnpFrequency ) != "" + --filtering-snp-frequency="$options.filteringSnpFrequency" + #end if + #if str( $options.filteringSnpAccepted ) != "" + --filtering-snp-accepted="$options.filteringSnpAccepted" + #end if + #if str( $options.filteringSexChromosomesRemoval ) == "True" + --filtering-sex-chromosomes-removal + #end if + #if str( $options.filteringMissingValueQuantile ) != "" + --filtering-missing-value-quantile="$options.filteringMissingValueQuantile" + #end if + #if str( $options.filteringCoverageThreshold ) != "" + --filtering-coverage-threshold="$options.filteringCoverageThreshold" + #end if + #if str( $options.filteringLowCoverageMasking ) == "True" + --filtering-low-coverage-masking + #end if + #if str( $options.filteringHighCoverageOutliers ) == "True" + --filtering-high-coverage-outliers + #end if + #if str( $options.filteringGreedycut ) == "True" + --filtering-greedycut + #end if + #if str( $options.filteringGreedycutPvalueThreshold ) != "" + --filtering-greedycut-pvalue-threshold="$options.filteringGreedycutPvalueThreshold" + #end if + #if str( $options.filteringGreedycutRcTies ) != "" + --filtering-greedycut-rc-ties="$options.filteringGreedycutRcTies" + #end if + #if str( $options.filteringDeviationThreshold ) != "" + --filtering-deviation-threshold="$options.filteringDeviationThreshold" + #end if + #if str( $options.batch ) == "True" + --batch + #end if + #if str( $options.batchDreductionColumns ) != "" + --batch-dreduction-columns="$options.batchDreductionColumns" + #end if + #if str( $options.batchPrincipalComponents ) != "" + --batch-principal-components="$options.batchPrincipalComponents" + #end if + #if str( $options.batchCorrelationColumns ) != "" + --batch-correlation-columns="$options.batchCorrelationColumns" + #end if + #if str( $options.batchCorrelationPvalueThreshold ) != "" + --batch-correlation-pvalue-threshold="$options.batchCorrelationPvalueThreshold" + #end if + #if str( $options.batchCorrelationPermutations ) != "" + --batch-correlation-permutations="$options.batchCorrelationPermutations" + #end if + #if str( $options.batchCorrelationQc ) == "True" + --batch-correlation-qc + #end if + #if str( $options.profiles ) == "True" + --profiles + #end if + #if str( $options.profilesBetaDistribution ) == "True" + --profiles-beta-distribution + #end if + #if str( $options.profilesIntersample ) == "True" + --profiles-intersample + #end if + #if str( $options.profilesDeviationPlots ) == "True" + --profiles-deviation-plots + #end if + #if str( $options.profilesColumns ) != "" + --profiles-columns="$options.profilesColumns" + #end if + #if str( $options.profilesClustering ) == "True" + --profiles-clustering + #end if + #if str( $options.profilesClusteringTopProbes ) != "" + --profiles-clustering-top-probes="$options.profilesClusteringTopProbes" + #end if + #if str( $options.regionProfilesTypes ) != "" + --region-profiles-types="$options.regionProfilesTypes" + #end if + #if str( $options.differential ) == "True" + --differential + #end if + #if str( $options.differentialPermutations ) != "" + --differential-permutations="$options.differentialPermutations" + #end if + #if str( $options.differentialComparisonColumns ) != "" + --differential-comparison-columns="$options.differentialComparisonColumns" + #end if + #if str( $options.differentialComparisonColumnsAllPairwise ) != "" + --differential-comparison-columns-all-pairwise="$options.differentialComparisonColumnsAllPairwise" + #end if + #if str( $options.differentialEnrichment ) == "True" + --differential-enrichment + #end if + #if str( $options.exportToUcsc ) != "" + --export-to-ucsc="$options.exportToUcsc" + #end if + #if str( $options.exportToBed ) == "True" + --export-to-bed + #end if + #if str( $options.exportToCsv ) == "True" + --export-to-csv + #end if + #if str( $options.exportTypes ) != "" + --export-types="$options.exportTypes" + #end if + #if str( $options.colors3Gradient ) != "" + --colors-3-gradient="$options.colors3Gradient" + #end if + #if str( $options.loggingMemory ) == "True" + --logging-memory + #end if + #end if + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + RnBeads is an R-package for comprehensive analysis of Illumina Infinium HumanMethylation450 BeadChip data. It extends previous approaches for this type of data analysis by high throughput capabilities, as well as presenting results in a comprehensive, highly interpretable fashion. + + + \ No newline at end of file diff -r afb06b3416d8 -r aad84663f9c2 rnbeads_galaxy_wrapper.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rnbeads_galaxy_wrapper.sh Fri Jul 05 08:03:54 2013 -0400 @@ -0,0 +1,25 @@ +#!/bin/bash +Rscript --no-save $(dirname $(readlink -f $0))/RnBeadsGalaxy.R $* > /tmp/rnbeads.stdout 2>/tmp/rnbeads.stderr +#Rscript --no-save \$R_SCRIPTS_PATH/RnBeadsGalaxy.R $* +outfile=`echo $* | cut -d\ -f2 | sed -e "s/--output-file=//g"` +echo $outfile +#outdir=`echo $* | sed -e "s/.*--report-dir=\(.*\)[[:blank:]].*/\1/g"` + + +if [ -s /tmp/rnbeads.stderr ] +then + cat /tmp/rnbeads.stdout >&2 + #cat $outdir/analysis.log >&2 + cat /tmp/rnbeads.stderr >&2 + exit 3 +else + echo "" >> $outfile + echo "RnBeads report" >> $outfile + echo "

Output was generated during the execution:
" >> $outfile + echo "
" >> outfile
+	cat /tmp/rnbeads.stdout |sed -e "s/$//g" >> $outfile
+	echo "
" >> outfile + echo "

" >> $outfile + echo "" >> $outfile + exit 0 +fi \ No newline at end of file diff -r afb06b3416d8 -r aad84663f9c2 rnbeads_repos.txt.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rnbeads_repos.txt.sample Fri Jul 05 08:03:54 2013 -0400 @@ -0,0 +1,1 @@ +repo1 Repository1 /data/iscan/idats \ No newline at end of file diff -r afb06b3416d8 -r aad84663f9c2 tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Fri Jul 05 08:03:54 2013 -0400 @@ -0,0 +1,6 @@ + + + id, name, value + +
+
\ No newline at end of file diff -r afb06b3416d8 -r aad84663f9c2 tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Fri Jul 05 08:03:54 2013 -0400 @@ -0,0 +1,22 @@ + + + + $REPOSITORY_INSTALL_DIR + + + + + http://CRAN.R-project.org/src/base/R-3/R-3.0.0.tar.gz + ./configure --prefix=$INSTALL_DIR --with-x=no + make + + $INSTALL_DIR/bin + + R --no-save <<< "install.packages("getopt"); source('http://rnbeads.mpi-inf.mpg.de')" + + + + You need a FORTRAN compiler or perhaps f2c in addition to a C compiler to build R. + + + \ No newline at end of file