| Previous changeset 0:5f1cb4c28d73 (2023-06-01) Next changeset 2:d6b5fc94062c (2023-06-08) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/sleuth commit 6fbf73689708cfbdf3d9d783af4988bad7137f93 |
|
modified:
macros.xml sleuth.R sleuth.xml |
|
added:
test-data/design.tab test-data/test02_density.pdf test-data/test02_pca.pdf |
| b |
| diff -r 5f1cb4c28d73 -r d3e447dd52c8 macros.xml --- a/macros.xml Thu Jun 01 07:56:00 2023 +0000 +++ b/macros.xml Wed Jun 07 11:47:30 2023 +0000 |
| b |
| @@ -8,7 +8,7 @@ </requirements> </xml> <token name="@TOOL_VERSION@">0.30.1</token> - <token name="@SUFFIX_VERSION@">0</token> + <token name="@SUFFIX_VERSION@">1</token> <token name="@PROFILE@">20.01</token> <xml name="citations"> <citations> |
| b |
| diff -r 5f1cb4c28d73 -r d3e447dd52c8 sleuth.R --- a/sleuth.R Thu Jun 01 07:56:00 2023 +0000 +++ b/sleuth.R Wed Jun 07 11:47:30 2023 +0000 |
| [ |
| @@ -26,39 +26,67 @@ # Collect arguments from command line parser <- ArgumentParser(description = "Sleuth R script") -parser$add_argument("--factorLevel", action = "append", required = TRUE) +parser$add_argument("--factorLevel", action = "append", required = FALSE) parser$add_argument("--factorLevel_counts", action = "append", - required = TRUE) -parser$add_argument("--factorLevel_n", action = "append", required = TRUE) -parser$add_argument("--cores", type = "integer", required = TRUE) + required = FALSE) +parser$add_argument("--factorLevel_n", action = "append", required = FALSE) +parser$add_argument("--cores", type = "integer", required = FALSE) parser$add_argument("--normalize", action = "store_true", required = FALSE) -parser$add_argument("--nbins", type = "integer", required = TRUE) -parser$add_argument("--lwr", type = "numeric", required = TRUE) -parser$add_argument("--upr", type = "numeric", required = TRUE) +parser$add_argument("--nbins", type = "integer", required = FALSE) +parser$add_argument("--lwr", type = "numeric", required = FALSE) +parser$add_argument("--upr", type = "numeric", required = FALSE) +parser$add_argument("--metadata_file", + action = "append", + required = FALSE) +parser$add_argument("--experiment_design", required = FALSE) args <- parser$parse_args() -all_files <- args$factorLevel_counts +if (args$experiment_design == "complex") { + ## Complex experiment design + ############################ -conditions <- c() -for (x in seq_along(args$factorLevel)) { - temp <- append(conditions, rep(args$factorLevel[[x]])) - conditions <- temp -} + s2c <- + read.table(file = args$metadata_file, + header = TRUE, + sep = "\t") + paths <- c() + for (x in s2c$data_filename) { + paths <- c(paths, paste("./kallisto_outputs/", x, sep = "")) + } + for (f in paths) { + file.rename(f, gsub(".fastq.*", "", f)) + file.rename(f, paste(gsub(".fastq.*", "", f), ".h5", sep = "")) + } + s2c$path <- paste(gsub(".fastq.*", ".h5", paths), ".h5", sep = "") + + so <- sleuth_prep(s2c, full_model = ~ condition, num_cores = 1) + so <- sleuth_fit(so) -sample_names <- all_files %>% - str_replace(pattern = "\\.tab", "") +} else { + ## Simple experiment design + ########################### + + conditions <- c() + for (x in seq_along(args$factorLevel)) { + temp <- append(conditions, rep(args$factorLevel[[x]])) + conditions <- temp + } -design <- - data.frame(list( - sample = sample_names, - condition = conditions, - path = all_files - )) -so <- sleuth_prep(design, - cores = args$cores, - normalize = args$normalize) + sample_names <- + gsub(".fastq.+", "", basename(args$factorLevel_counts)) + + design <- + data.frame(list( + sample = sample_names, + condition = conditions, + path = args$factorLevel_counts + )) + so <- sleuth_prep(design, + cores = args$cores, + normalize = args$normalize) +} so <- sleuth_fit( so, |
| b |
| diff -r 5f1cb4c28d73 -r d3e447dd52c8 sleuth.xml --- a/sleuth.xml Thu Jun 01 07:56:00 2023 +0000 +++ b/sleuth.xml Wed Jun 07 11:47:30 2023 +0000 |
| [ |
| b'@@ -21,23 +21,38 @@\n </stdio>\n <version_command><![CDATA[echo $(R --version | grep version | grep -v GNU)", sleuth version" $(R --vanilla --slave -e "library(sleuth); cat(sessionInfo()\\$otherPkgs\\$sleuth\\$Version)" 2> /dev/null | grep -v -i "WARNING: ")]]></version_command>\n <command><![CDATA[\n- #set $factor_levels = list()\n+ #import os\n+ mkdir -p \'./kallisto_outputs\' &&\n #set $cond_files = list()\n- #set $cond_n_files = list()\n- #for $level in $rep_factorLevel\n- $factor_levels.append(str($level.factorLevel))\n- $cond_n_files.append(len(str($level.countsFile).split(",")))\n- #for $i, $count in enumerate(str($level.countsFile).split(","))\n- #set $fname = str($level.factorLevel) + "_" + str($i) + \'.h5\'\n- ln -s \'${count}\' "${fname}" &&\n- $cond_files.append($fname)\n+ #if $experiment_design.selector == "single"\n+ #set $factor_levels = list()\n+ #set $cond_n_files = list()\n+ #for $level in $experiment_design.rep_factorLevel\n+ $factor_levels.append(str($level.factorLevel))\n+ $cond_n_files.append(len(str($level.countsFile).split(",")))\n+ #for $i, $count in enumerate(str($level.countsFile).split(","))\n+ #set $fname = str($level.factorLevel) + "_" + str($i) + \'.h5\'\n+ #set $output_path = "/".join([\'./kallisto_outputs\',$fname])\n+ ln -s \'${count}\' $output_path &&\n+ $cond_files.append($output_path)\n+ #end for\n #end for\n- #end for\n+ #else\n+ #for $count in $experiment_design.countsFile\n+ #set $output_path = "/".join([\'./kallisto_outputs\',$count.element_identifier])\n+ ln -s \'${count}\' $output_path &&\n+ $cond_files.append($output_path)\n+ #end for\n+ #end if\n Rscript \'${__tool_directory__}/sleuth.R\'\n- #for $i, $factor in enumerate($factor_levels)\n- --factorLevel $factor\n- --factorLevel_n $cond_n_files[$i]\n- #end for\n+ #if $experiment_design.selector == "single"\n+ #for $i, $factor in enumerate($factor_levels)\n+ --factorLevel $factor\n+ --factorLevel_n $cond_n_files[$i]\n+ #end for\n+ #else\n+ --metadata_file $experiment_design.metadata_file\n+ #end if\n #for $file in $cond_files\n --factorLevel_counts $file\n #end for\n@@ -46,17 +61,30 @@\n --nbins $advanced_options.nbins\n --lwr $advanced_options.lwr\n --upr $advanced_options.upr\n+ --experiment_design $experiment_design.selector\n ]]></command>\n <inputs>\n- <repeat name="rep_factorLevel" title="Factor level" min="2" default="2">\n- <param name="factorLevel" type="text" value="FactorLevel" label="Specify a factor level, typical values could be \'tumor\', \'normal\', \'treated\' or \'control\'"\n- help="Only letters, numbers and underscores will be retained in this field">\n- <sanitizer>\n- <valid initial="string.letters,string.digits"><add value="_" /></valid>\n- </sanitizer>\n+ <conditional name="experiment_design">\n+ <param name="selector" type="select" label="Experiment design" help="If you have multiple experimental conditions, you should use propably the complex design mode. In the help section you can find more information.">\n+ <option value="single">Simple design mode (one experimental factor)</option>\n+ <option value="complex">Complex design mode (two experimental factors)</option>\n </param>\n- <param name="countsFile" type="data" format="h5" multiple="true" label="Counts file(s)"/>\n- </repeat'..b'me="countsFile" type="data_collection" format="h5" multiple="true" label="Counts file(s)"/>\n+ <param argument="--metadata_file" type="data" format="txt" label="Input metadata file" help="You can find more details about it in the help section" />\n+ </when>\n+ </conditional>\n <section name="advanced_options" title="Advanced options" expanded="true">\n <param argument="normalization" type="boolean" truevalue="--normalize" falsevalue="" checked="true" label="Normalize data" \n help="If this is set to false, bootstraps will not be read and transformation of the data will not be done. This should \n@@ -68,6 +96,7 @@\n <param argument="upr" type="float" min="0" max="1" value="0.75" label="UPR" help="The upper range of variances within each \n bin that should be included for the shrinkage procedure." />\n </section>\n+\n </inputs>\n <outputs>\n <data name="sleuth_table" from_work_dir="sleuth_table.tab" format="tabular" label="${tool.name} on ${on_string}: DE table">\n@@ -104,6 +133,35 @@\n <output name="pca_plot" file="test01_pca.pdf" ftype="pdf" compare="sim_size"/>\n <output name="density_plot" file="test01_density.pdf" ftype="pdf" compare="sim_size"/>\n </test>\n+ <test expect_num_outputs="3">\n+ <conditional name="experiment_design">\n+ <param name="selector" value="complex"/>\n+ <param name="countsFile">\n+ <collection type="list">\n+ <element name="kallisto_output_01.h5" ftype="h5" value="kallisto_output_01.h5"/>\n+ <element name="kallisto_output_02.h5" ftype="h5" value="kallisto_output_02.h5"/>\n+ <element name="kallisto_output_03.h5" ftype="h5" value="kallisto_output_03.h5"/>\n+ <element name="kallisto_output_04.h5" ftype="h5" value="kallisto_output_04.h5"/>\n+ </collection>\n+ </param>\n+ <param name="metadata_file" value="design.tab"/>\n+ </conditional>\n+ <section name="advanced_options">\n+ <param name="normalization" value="true"/>\n+ <param name="nbins" value="100"/>\n+ <param name="lwr" value="0.25"/>\n+ <param name="upr" value="0.75"/>\n+ </section>\n+ <output name="sleuth_table" ftype="tabular">\n+ <assert_contents>\n+ <has_size value="756310" delta="100"/>\n+ <has_text text="ENST00000394894.8"/>\n+ <has_text text="ENST00000524187.1"/>\n+ </assert_contents>\n+ </output>\n+ <output name="pca_plot" file="test02_pca.pdf" ftype="pdf" compare="sim_size"/>\n+ <output name="density_plot" file="test02_density.pdf" ftype="pdf" compare="sim_size"/>\n+ </test>\n </tests>\n <help><![CDATA[\n \n@@ -123,6 +181,24 @@\n These can serve as proxies for technical replicates, allowing for an ascertainment of the variability in estimates due to the random \n processes underlying RNA-Seq as well as the statistical procedure of read assignment. \n \n+.. class:: infomark\n+\n+**Experimental design tabular input for complex experimental designs**\n+\n+The experimental design input should have this format:\n+\n+ ::\n+ \n+ data_filename\tcondition\tsample\n+ finename_01.fastq.gz\tcondition1\treplicate1\n+ filename_02.fastq.gz\tcondition1\treplicate2\n+ filename_03.fastq.gz\tcondition2\treplicate1\n+ filename_04.fastq.gz\tcondition2\treplicate2\n+\n+\n+The tabular file **requires to have the same column names** as the example (data_file, condition, sample). The data file column correspond to original FASTQ filenames uploaded to Galaxy. \n+Condition includes the information about the first factor, and sample includes information about the second factor. **Only alphanumeric characters, undescores and dots are allowed**.\n+\n ]]></help>\n <expand macro="citations" />\n </tool>\n' |
| b |
| diff -r 5f1cb4c28d73 -r d3e447dd52c8 test-data/design.tab --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/design.tab Wed Jun 07 11:47:30 2023 +0000 |
| b |
| @@ -0,0 +1,5 @@ +sample condition data_filename +CAM_01 CAM kallisto_output_01.h5 +CAM_02 CAM kallisto_output_02.h5 +reC3_01 reC3 kallisto_output_03.h5 +reC3_02 reC3 kallisto_output_04.h5 |
| b |
| diff -r 5f1cb4c28d73 -r d3e447dd52c8 test-data/test02_density.pdf |
| b |
| Binary file test-data/test02_density.pdf has changed |
| b |
| diff -r 5f1cb4c28d73 -r d3e447dd52c8 test-data/test02_pca.pdf |
| b |
| Binary file test-data/test02_pca.pdf has changed |