| Previous changeset 5:cdf4443d5625 (2020-01-29) Next changeset 7:2c1200fba922 (2021-01-07) |
|
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/dropletutils/ commit ed0625fe59342d14a08745996e3e32c6f922a738" |
|
modified:
dropletutils.xml scripts/dropletutils.Rscript test-data/defs_defaultdrops.h5 test-data/defs_emptydrops_150_0002.h5 test-data/defs_emptydrops_150_0002.png test-data/defs_emptydrops_150_0002a.h5 test-data/defs_emptydrops_150_0002a.png |
| b |
| diff -r cdf4443d5625 -r 8855361fcfc5 dropletutils.xml --- a/dropletutils.xml Wed Jan 29 15:07:38 2020 -0500 +++ b/dropletutils.xml Thu Dec 10 13:50:06 2020 +0000 |
| [ |
| @@ -1,9 +1,22 @@ <?xml version="1.0" encoding="utf-8"?> -<tool id="dropletutils" name="DropletUtils" version="@PACKAGE_VERSION@+@GALAXY_VERSION@" > +<tool id="dropletutils" name="DropletUtils" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" > <description>Utilities for handling droplet-based single-cell RNA-seq data</description> + <xrefs> + <xref type="bio.tools">dropletutils</xref> + </xrefs> + <edam_topics> + <edam_topic>topic_0203</edam_topic> + <edam_topic>topic_3168</edam_topic> + <edam_topic>topic_3170</edam_topic> + <edam_topic>topic_3308</edam_topic> + </edam_topics> + <edam_operations> + <edam_operation>operation_1812</edam_operation> + <edam_operation>operation_3200</edam_operation> + </edam_operations> <macros> - <token name="@PACKAGE_VERSION@" >1.2.1</token> - <token name="@GALAXY_VERSION@" >galaxy6</token> + <token name="@TOOL_VERSION@">1.10.0</token> + <token name="@VERSION_SUFFIX@">0</token> <token name="@TXIN@">tenx.input</token> <token name="@TXOUT@">tenx.output</token> <xml name="test_dirin" > @@ -16,9 +29,10 @@ </xml> </macros> <requirements> - <requirement type="package" version="@PACKAGE_VERSION@">bioconductor-dropletutils</requirement> - <requirement type="package" version="1.2_17" >r-matrix</requirement> - <requirement type="package" version="1.10.1" >bioconductor-scater</requirement> + <requirement type="package" version="@TOOL_VERSION@">bioconductor-dropletutils</requirement> + <requirement type="package" version="1.18.0" >bioconductor-scater</requirement> + <requirement type="package" version="4.0">r-base</requirement> + <requirement type="package" version="1.2_18">r-matrix</requirement> <requirement type="package" version="1">fonts-conda-ecosystem</requirement> </requirements> <version_command><![CDATA[ @@ -45,14 +59,14 @@ <configfiles> <configfile name="droplet_conf" > ## defaults -empty.fdr_threshold = 0.01 -eparams=formals(emptyDrops) -dparams=formals(defaultDrops) -bparams=formals(barcodeRanks) +empty_fdr_threshold = 0.01 +eparams = formals(emptyDrops) +dparams = formals(defaultDrops) +bparams = formals(barcodeRanks) ## File params -in.type='$tenx_format.use' -out.type=NULL +intype='$tenx_format.use' +outtype=NULL files=list() files\$table='$table' @@ -74,10 +88,10 @@ #else if str($operation.method.use) == 'emptydrops': do.method="emptyDrops" eparams\$lower=as.integer('$operation.method.lower') -empty.fdr_threshold=as.numeric('$operation.method.fdr_thresh') +empty_fdr_threshold=as.numeric('$operation.method.fdr_thresh') #end if -out.type='$operation.outformat' +outtype='$operation.outformat' #if str($operation.outformat) == 'directory': files\$out='@TXOUT@' #else if str($operation.outformat) == 'h5': @@ -172,8 +186,8 @@ </outputs> <tests> <!-- Directory input tests --> - <!-- ::: Default Drops --> <test expect_num_outputs="1"> + <!-- ::: Default Drops --> <expand macro="test_dirin" /> <conditional name="operation"> <param name="use" value="filter" /> @@ -196,17 +210,17 @@ </assert_contents> </output> </test> - <!-- :: Barcode Ranks --> <test expect_num_outputs="1"> + <!-- :: Barcode Ranks --> <expand macro="test_dirin" /> <conditional name="operation"> <param name="use" value="barcode_rank" /> <param name="lower" value="120" /> </conditional> - <output name="plot" value="defs_barcoderankings.png" compare="sim_size" delta="400"/> + <output name="plot" value="defs_barcoderankings.png" compare="sim_size" delta="600"/> </test> - <!-- ::: Empty Drops --> <test expect_num_outputs="3"> + <!-- ::: Empty Drops --> <expand macro="test_dirin" /> <conditional name="operation"> <param name="use" value="filter" /> @@ -221,16 +235,16 @@ <output name="table" > <assert_contents> <has_n_columns n="9" /> - <has_line_matching expression="^\sbar.names\sTotal\sLogProb\sPValue\sLimited\sFDR\sis.Cell\sis.CellAndLimited" /> - <has_line_matching expression="^994\sGGCATTACAA\s338\s-246.922772388055\s9.99900009999e-05\sTRUE\s9.99900009999e-05\sTRUE\sTRUE" /> - <has_line_matching expression="^998\sCATGAAGCAA\s151\s-166.644236503983\s9.99900009999e-05\sTRUE\s9.99900009999e-05\sTRUE\sTRUE" /> + <has_line_matching expression="^\sbar_names\sTotal\sLogProb\sPValue\sLimited\sFDR\sis_cell\sis_cellandlimited" /> + <has_line_matching expression="^994\sGGCATTACAA\s338\s-246\.(.*TRUE){3}$" /> + <has_line_matching expression="^998\sCATGAAGCAA\s151\s-166\.(.*TRUE){3}$" /> </assert_contents> </output> <output name="plot" value="defs_emptydrops_150_0002.png" compare="sim_size" delta="400" /> </test> <!-- Other format input tests --> - <!-- ::: Empty Drops, same as above but input is h5 --> <test expect_num_outputs="3"> + <!-- ::: Empty Drops, same as above but input is h5 --> <conditional name="tenx_format" > <param name="use" value="h5" /> <param name="input" value="in_matrix.h5" /> @@ -248,9 +262,9 @@ <output name="table" > <assert_contents> <has_n_columns n="9" /> - <has_line_matching expression="^\sbar.names\sTotal\sLogProb\sPValue\sLimited\sFDR\sis.Cell\sis.CellAndLimited" /> - <has_line_matching expression="^1100\sCCGGAAGCAA\s169\s-198.117943099773\s9.99900009999e-05\sTRUE\s0.000126279506880773\sTRUE\sTRUE" /> - <has_line_matching expression="^1114\sTCCGAAGCAA\s182\s-196.181449214729\s9.99900009999e-05\sTRUE\s0.000126279506880773\sTRUE\sTRUE" /> + <has_line_matching expression="^\sbar_names\sTotal\sLogProb\sPValue\sLimited\sFDR\sis_cell\sis_cellandlimited" /> + <has_line_matching expression="^1100\sCCGGAAGCAA\s169\s-198\.(.*TRUE){3}$" /> + <has_line_matching expression="^1114\sTCCGAAGCAA\s182\s-196\.(.*TRUE){3}$" /> </assert_contents> </output> <output name="plot" value="defs_emptydrops_150_0002a.png" compare="sim_size" delta="400" /> |
| b |
| diff -r cdf4443d5625 -r 8855361fcfc5 scripts/dropletutils.Rscript --- a/scripts/dropletutils.Rscript Wed Jan 29 15:07:38 2020 -0500 +++ b/scripts/dropletutils.Rscript Thu Dec 10 13:50:06 2020 +0000 |
| [ |
| b'@@ -1,6 +1,6 @@\n ## Load in data\n-args = commandArgs(trailingOnly = T)\n-if (length(args) != 1){\n+args <- commandArgs(trailingOnly = T)\n+if (length(args) != 1) {\n stop("Please provide the config file")\n }\n \n@@ -11,57 +11,60 @@\n source(args[1])\n \n ## Helper functions\n-setSparse <- function(obj){\n+set_sparse <- function(obj) {\n return(as(obj, "dgCMatrix"))\n }\n \n-writeTSV <- function(fileout, obj){\n- write.table(as.matrix(obj), file=fileout, col.names=NA, sep=\'\\t\', quote=FALSE)\n+write_tsv <- function(fileout, obj) {\n+ write.table(as.matrix(obj), file = fileout,\n+ col.names = NA, sep = "\\t", quote = FALSE)\n }\n \n-determineGeneIDs <- function(object){\n- if (!is.null(rowData(object)$Symbol)){\n+determine_geneids <- function(object) {\n+ if (!is.null(rowData(object)$Symbol)) {\n return(rowData(object)$Symbol)\n }\n return(rownames(object))\n }\n \n-getCounts <- function(object){\n- return(Matrix(counts(object), sparse=TRUE))\n+get_counts <- function(object) {\n+ return(Matrix(counts(object), sparse = TRUE))\n }\n \n-writeOut <- function(object, fileout, typeout){\n- if (typeout == "tsv"){\n- writeTSV(fileout, getCounts(object))\n+write_out <- function(object, fileout, typeout) {\n+ if (typeout == "tsv") {\n+ write_tsv(fileout, get_counts(object))\n }\n- else if (typeout == "h5"){\n- write10xCounts(fileout, getCounts(object),\n- type="HDF5",\n- gene.symbol=determineGeneIDs(object),\n- overwrite=TRUE)\n+ else if (typeout == "h5") {\n+ write10xCounts(fileout, get_counts(object),\n+ type = "HDF5",\n+ gene.symbol = determine_geneids(object),\n+ overwrite = TRUE)\n }\n- else if (typeout == "directory"){\n- write10xCounts(fileout, getCounts(object),\n- type="sparse",\n- gene.symbol=determineGeneIDs(object),\n- overwrite=TRUE)\n+ else if (typeout == "directory") {\n+ write10xCounts(fileout, get_counts(object),\n+ type = "sparse",\n+ gene.symbol = determine_geneids(object),\n+ overwrite = TRUE)\n }\n }\n \n-read10xFiles <- function(filein, typein){\n+read_10x_files <- function(filein, typein) {\n sce <- NULL\n- if (typein == "tsv"){\n+ if (typein == "tsv") {\n ## Exploding memory problems occured here\n ## - solution is to use the readSparseCounts function from scater\n- sce <- SingleCellExperiment(assays = list(counts = readSparseCounts(filein)))\n- }\n- else if (typein == "h5"){\n- sce <- read10xCounts(filein, col.names=T, type="HDF5") # use barcodes.tsv as column names\n+ sce <- SingleCellExperiment(assays =\n+ list(counts = readSparseCounts(filein)))\n }\n- else if (typein == "directory"){\n- sce <- read10xCounts(filein, col.names=T, type="sparse")\n+ else if (typein == "h5") {\n+ # use barcodes.tsv as column names\n+ sce <- read10xCounts(filein, col.names = T, type = "HDF5")\n }\n- counts(sce) <- setSparse(counts(sce))\n+ else if (typein == "directory") {\n+ sce <- read10xCounts(filein, col.names = T, type = "sparse")\n+ }\n+ counts(sce) <- set_sparse(counts(sce))\n return(sce)\n }\n \n@@ -69,97 +72,113 @@\n ## Methods\n \n \n-doEmptyDrops <- function(files, eparams, in.type="directory", out.type="h5", fdr_threshold = 0.01){\n- sce <- read10xFiles(files$infile, in.type)\n+do_empty_drops <- function(files, eparams, intype = "directory",\n+ outtype = "h5", fdr_threshold = 0.01) {\n+ sce <- read_10x_files(files$infile, intype)\n+\n+ eparams$... <- NULL ## hack to remove other parameters from being\n+ eparams$m <- Matrix(counts(sce), sparse = TRUE)\n+\n+ ## Determine sensible lowerbound\n+ m_stats <- summary(colSums(counts(sce)))\n+ print("Cell Li'..b'e.out[complete.cases(e.out),])\n+ write_tsv(files$table, e_out[complete.cases(e_out), ])\n \n png(files$plot)\n- plot(e.out$Total, -e.out$LogProb, col=ifelse(e.out$is.Cell, "red", "black"),\n- xlab="Total UMI count", ylab="-Log Probability",\n- xlim=c(min(xlim.dat),max(xlim.dat)))\n+ plot(e_out$Total, -e_out$LogProb, col = ifelse(e_out$is_cell,\n+ "red", "black"),\n+ xlab = "Total UMI count", ylab = "-Log Probability",\n+ xlim = c(min(xlim_dat), max(xlim_dat)))\n dev.off()\n \n ## Filtered\n called <- NULL\n- if (fdr_threshold != 0){\n- called <- e.out$is.CellAndLimited\n+ if (fdr_threshold != 0) {\n+ called <- e_out$is_cellandlimited\n } else {\n- called <- e.out$is.Cell\n+ called <- e_out$is_cell\n }\n called[is.na(called)] <- FALSE # replace NA\'s with FALSE\n- sce.filtered <- sce[,called]\n+ sce_filtered <- sce[, called]\n \n- writeOut(sce.filtered, files$out, out.type)\n+ write_out(sce_filtered, files$out, outtype)\n \n- message(paste("Cells:", sum(na.omit(e.out$is.Cell))))\n- message(paste("Cells and Limited:", sum(na.omit(e.out$is.CellAndLimited))))\n+ message(paste("Cells:", sum(na.omit(e_out$is_cell))))\n+ message(paste("Cells and Limited:", sum(na.omit(e_out$is_cellandlimited))))\n }\n \n \n-doDefaultDrops <- function(files, dparams, in.type="directory", out.type="h5"){\n- sce <- read10xFiles(files$infile, in.type)\n+do_default_drops <- function(files, dparams,\n+ intype = "directory", outtype = "h5") {\n+ sce <- read_10x_files(files$infile, intype)\n \n- dparams$m = counts(sce)\n+ dparams$m <- counts(sce)\n called <- do.call(defaultDrops, c(dparams))\n \n # Filtered\n- sce.filtered <- sce[,called]\n+ sce_filtered <- sce[, called]\n \n- writeOut(sce.filtered, files$out, out.type)\n+ write_out(sce_filtered, files$out, outtype)\n \n message(paste("Cells:", sum(called)))\n }\n \n-\n-doBarcodeRankings <- function(files, bparams, in.type="directory"){\n- sce <- read10xFiles(files$infile, in.type)\n+do_barcode_rankings <- function(files, bparams, intype = "directory") {\n+ sce <- read_10x_files(files$infile, intype)\n \n bparams$... <- NULL ## hack\n- bparams$m = counts(sce)\n+ bparams$m <- counts(sce)\n \n- br.out <- do.call(barcodeRanks, c(bparams))\n+ brout <- do.call(barcodeRanks, c(bparams))\n \n png(files$plot)\n- plot(br.out$rank, br.out$total, log="xy", xlab="(log) Rank", ylab="(log) Total Number of Barcodes")\n- o <- order(br.out$rank)\n- lines(br.out$rank[o], br.out$fitted[o], col="red")\n+ plot(brout$rank, brout$total, log = "xy",\n+ xlab = "(log) Rank", ylab = "(log) Total Number of Barcodes")\n+ o <- order(brout$rank)\n+ lines(brout$rank[o], brout$fitted[o], col = "red")\n \n- abline(h=br.out$knee, col="dodgerblue", lty=2)\n- abline(h=br.out$inflection, col="forestgreen", lty=2)\n- legend("bottomleft", lty=2, col=c("dodgerblue", "forestgreen"), legend=c("knee", "inflection"))\n+ abline(h = brout$knee, col = "dodgerblue", lty = 2)\n+ abline(h = brout$inflection, col = "forestgreen", lty = 2)\n+ legend("bottomleft", lty = 2, col = c("dodgerblue", "forestgreen"),\n+ legend = c("knee", "inflection"))\n dev.off()\n \n- print(paste("knee =", br.out$knee, ", inflection = ", br.out$inflection))\n+ print(paste("knee =", brout$knee, ", inflection = ", brout$inflection))\n }\n \n ## Main\n set.seed(seed.val)\n \n if (do.method == "barcodeRankings") {\n- doBarcodeRankings(files, bparams, in.type)\n+ do_barcode_rankings(files, bparams, intype)\n \n } else if (do.method == "defaultDrops") {\n- doDefaultDrops(files, dparams, in.type, out.type)\n+ do_default_drops(files, dparams, intype, outtype)\n \n } else if (do.method == "emptyDrops") {\n- doEmptyDrops(files, eparams, in.type, out.type, empty.fdr_threshold)\n+ do_empty_drops(files, eparams, intype, outtype, empty_fdr_threshold)\n }\n' |
| b |
| diff -r cdf4443d5625 -r 8855361fcfc5 test-data/defs_defaultdrops.h5 |
| b |
| Binary file test-data/defs_defaultdrops.h5 has changed |
| b |
| diff -r cdf4443d5625 -r 8855361fcfc5 test-data/defs_emptydrops_150_0002.h5 |
| b |
| Binary file test-data/defs_emptydrops_150_0002.h5 has changed |
| b |
| diff -r cdf4443d5625 -r 8855361fcfc5 test-data/defs_emptydrops_150_0002.png |
| b |
| Binary file test-data/defs_emptydrops_150_0002.png has changed |
| b |
| diff -r cdf4443d5625 -r 8855361fcfc5 test-data/defs_emptydrops_150_0002a.h5 |
| b |
| Binary file test-data/defs_emptydrops_150_0002a.h5 has changed |
| b |
| diff -r cdf4443d5625 -r 8855361fcfc5 test-data/defs_emptydrops_150_0002a.png |
| b |
| Binary file test-data/defs_emptydrops_150_0002a.png has changed |
