biopipen 0.27.4__py3-none-any.whl → 0.27.5__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.27.4"
+__version__ = "0.27.5"

biopipen/core/testing.py

@@ -51,15 +51,16 @@ class PipelineSucceeded:
         pipen._succeeded = succeeded
 
 
-def get_pipeline(testfile, loglevel="debug", **kwargs):
+def get_pipeline(testfile, loglevel="debug", enable_report=False, **kwargs):
     """Get a pipeline for a test file"""
     name, workdir, outdir = _get_test_dirs(testfile, False)
+    report_plugin_prefix = "+" if enable_report else "-"
     kws = {
         "name": name,
         "workdir": workdir,
         "outdir": outdir,
         "loglevel": loglevel,
-        "plugins": [PipelineSucceeded, "-report"],
+        "plugins": [PipelineSucceeded, f"{report_plugin_prefix}report"],
     }
     kws.update(kwargs)
     return Pipen(**kws)

biopipen/ns/scrna.py

@@ -122,6 +122,9 @@ class SeuratPreparing(Proc):
             genes.
             ///
 
+        cell_qc_per_sample (flag): Whether to perform cell QC per sample or not.
+            If `True`, the cell QC will be performed per sample, and the QC will be
+            applied to each sample before merging.
         gene_qc (ns): Filter genes.
             `gene_qc` is applied after `cell_qc`.
             - min_cells: The minimum number of cells that a gene must be
@@ -222,6 +225,7 @@ class SeuratPreparing(Proc):
     envs = {
         "ncores": config.misc.ncores,
         "cell_qc": None,  # "nFeature_RNA > 200 & percent.mt < 5",
+        "cell_qc_per_sample": False,
         "gene_qc": {"min_cells": 0, "excludes": []},
         "use_sct": False,
         "no_integration": False,
@@ -1483,14 +1487,17 @@ class SeuratTo10X(Proc):
         srtobj: The seurat object in RDS
 
     Output:
-        outdir: The output directory
+        outdir: The output directory.
+            When `envs.split_by` is specified, the subdirectories will be
+            created for each distinct value of the column.
+            Otherwise, the matrices will be written to the output directory.
 
     Envs:
         version: The version of 10X format
     """
     input = "srtobj:file"
     output = "outdir:dir:{{in.srtobj | stem}}"
-    envs = {"version": "3"}
+    envs = {"version": "3", "split_by": None}
     lang = config.lang.rscript
     script = "file://../scripts/scrna/SeuratTo10X.R"
 

biopipen/scripts/scrna/SeuratClusterStats-features.R

@@ -81,7 +81,7 @@ do_one_features = function(name) {
     if (case$kind %in% c("ridge", "ridgeplot")) {
         case$kind = "ridge"
         if (is.null(case$cols)) {
-            case$cols = pal_biopipen()(32)
+            case$cols = pal_biopipen()(n_uidents)
         }
         excluded_args = c(excluded_args, "split.by", "reduction")
         fn = RidgePlot

biopipen/scripts/scrna/SeuratPreparing.R

@@ -4,6 +4,7 @@ library(Seurat)
 library(future)
 library(bracer)
 library(ggplot2)
+library(dplyr)
 library(tidyseurat)
 
 metafile = {{in.metafile | quote}}
@@ -49,6 +50,19 @@ if (!"RNAData" %in% meta_cols) {
     stop("Error: Column `RNAData` is not found in metafile.")
 }
 
+samples = as.character(metadata$Sample)
+
+# used for plotting
+cell_qc_df = NULL
+
+plotsdir = file.path(joboutdir, "plots")
+dir.create(plotsdir, showWarnings = FALSE, recursive = TRUE)
+
+# features for cell QC
+feats = c(
+    "nFeature_RNA", "nCount_RNA",
+    "percent.mt", "percent.ribo", "percent.hb", "percent.plat"
+)
 
 rename_files = function(e, sample, path) {
     tmpdatadir = file.path(joboutdir, "renamed", sample)
@@ -74,6 +88,143 @@ rename_files = function(e, sample, path) {
     Read10X(data.dir = tmpdatadir)
 }
 
+
+perform_cell_qc <- function(sobj, per_sample = FALSE) {
+    log_prefix = ifelse(per_sample, "  ", "- ")
+    log_info("{log_prefix}Adding metadata for QC ...")
+    sobj$percent.mt = PercentageFeatureSet(sobj, pattern = "^MT-")
+    sobj$percent.ribo = PercentageFeatureSet(sobj, pattern = "^RP[SL]")
+    sobj$percent.hb = PercentageFeatureSet(sobj, pattern = "^HB[^(P)]")
+    sobj$percent.plat = PercentageFeatureSet(sobj, pattern = "PECAM1|PF4")
+
+    if (is.null(envs$cell_qc) || length(envs$cell_qc) == 0) {
+        log_warn("{log_prefix}No cell QC criteria is provided. All cells will be kept.")
+        cell_qc = "TRUE"
+    } else {
+        cell_qc = envs$cell_qc
+    }
+
+    sobj = sobj %>% mutate(.QC = !!rlang::parse_expr(cell_qc))
+
+    if (is.null(cell_qc_df)) {
+        cell_qc_df <<- sobj@meta.data[, c("Sample", ".QC", feats), drop = FALSE]
+    } else {
+        cell_qc_df <<- rbind(cell_qc_df, sobj@meta.data[, c("Sample", ".QC", feats), drop = FALSE])
+    }
+
+    # Do the filtering
+    log_info("{log_prefix}Filtering cells using QC criteria ...")
+    sobj = sobj %>% filter(.QC)
+    sobj$.QC = NULL
+
+    return(sobj)
+}
+
+report_cell_qc = function(ngenes) {
+    # uses cell_qc_df
+
+    # Violin plots
+    log_info("- Plotting violin plots ...")
+    add_report(
+        list(
+            kind = "descr",
+            content = paste(
+                "The violin plots for each feature. The cells are grouped by sample.",
+                "The cells that fail the QC criteria are colored in red, and",
+                "the cells that pass the QC criteria are colored in black.",
+                "The cells that fail the QC criteria are filtered out in the returned Seurat object."
+            )
+        ),
+        h1 = "Violin Plots"
+    )
+    for (feat in feats) {
+        log_info("  For feature: {feat}")
+        vln_p <- ggplot(cell_qc_df, aes(x = Sample, y = !!sym(feat), color = .QC)) +
+            geom_violin(fill = "white", width = 0.5) +
+            geom_jitter(width = 0.2, height = 0, alpha = 0.5) +
+            scale_color_manual(values = c("#181818", pal_biopipen()(1)), breaks = c(TRUE, FALSE)) +
+            labs(x = "Sample", y = feat) +
+            theme_minimal()
+
+        vlnplot = file.path(plotsdir, paste0(slugify(feat), ".vln.png"))
+        png(
+            vlnplot,
+            width = 800 + length(samples) * 15, height = 600, res = 100
+        )
+        print(vln_p)
+        dev.off()
+
+        add_report(
+            list(
+                src = vlnplot,
+                name = feat,
+                descr = paste0("Distribution of ", feat, " for each sample.")
+            ),
+            h1 = "Violin Plots",
+            ui = "table_of_images"
+        )
+    }
+
+    # Scatter plots against nCount_RNA
+    log_info("- Plotting scatter plots ...")
+    add_report(
+        list(
+            kind = "descr",
+            content = paste(
+                "The scatter plots for each feature against nCount_RNA. ",
+                "The cells that fail the QC criteria are colored in red, and",
+                "the cells that pass the QC criteria are colored in black.",
+                "The cells that fail the QC criteria are filtered out in the returned Seurat object."
+            )
+        ),
+        h1 = "Scatter Plots"
+    )
+    for (feat in setdiff(feats, "nCount_RNA")) {
+        log_info("  For feature: {feat}, against nCount_RNA")
+        scat_p <- ggplot(cell_qc_df, aes(x = nCount_RNA, y = !!sym(feat), color = .QC)) +
+            geom_point() +
+            scale_color_manual(values = c("#181818", pal_biopipen()(1)), breaks = c(TRUE, FALSE)) +
+            labs(x = "nCount_RNA", y = feat) +
+            theme_minimal()
+
+        scatfile = file.path(plotsdir, paste0(slugify(feat), "-nCount_RNA.scatter.png"))
+        png(scatfile, width = 800, height = 600, res = 100)
+        print(scat_p)
+        dev.off()
+
+        add_report(
+            list(
+                src = scatfile,
+                name = paste0(feat, " vs nCount_RNA"),
+                descr = paste0("Scatter plot for ", feat, " against nCount_RNA")
+            ),
+            h1 = "Scatter Plots",
+            ui = "table_of_images"
+        )
+    }
+
+    # return the dim_df calculated from the cell_qc_df
+    rbind(
+        cell_qc_df %>%
+            # group_by(Sample) %>%
+            summarise(
+                when = "Before_Cell_QC",
+                nCells = dplyr::n(),
+                nGenes = ngenes
+            ) %>%
+            ungroup(),
+        cell_qc_df %>%
+            filter(.QC) %>%
+            # group_by(Sample) %>%
+            summarise(
+                when = "After_Cell_QC",
+                nCells = dplyr::n(),
+                nGenes = ngenes
+            ) %>%
+            ungroup()
+    )
+}
+
 load_sample = function(sample) {
     log_info("- Loading sample: {sample} ...")
     mdata = as.data.frame(metadata)[metadata$Sample == sample, , drop=TRUE]
@@ -114,6 +265,11 @@ load_sample = function(sample) {
         obj[[mname]] = mdt
     }
 
+    if (isTRUE(envs$cell_qc_per_sample)) {
+        log_info("- Perform cell QC for sample: {sample} ...")
+        obj = perform_cell_qc(obj, TRUE)
+    }
+
     if (isTRUE(envs$use_sct)) {
         # so that we have data and scale.data layers on RNA assay
         # useful for visualization in case some genes are not in
@@ -126,125 +282,20 @@ load_sample = function(sample) {
 }
 
 # Load data
-samples = as.character(metadata$Sample)
-
 log_info("Reading samples individually ...")
 obj_list = lapply(samples, load_sample)
 
 log_info("Merging samples ...")
 sobj = Reduce(merge, obj_list)
 
-log_info("Adding metadata for QC ...")
-sobj$percent.mt = PercentageFeatureSet(sobj, pattern = "^MT-")
-sobj$percent.ribo = PercentageFeatureSet(sobj, pattern = "^RP[SL]")
-sobj$percent.hb = PercentageFeatureSet(sobj, pattern = "^HB[^(P)]")
-sobj$percent.plat = PercentageFeatureSet(sobj, pattern = "PECAM1|PF4")
-
-dim_df = data.frame(When = "Before_QC", nCells = ncol(sobj), nGenes = nrow(sobj))
-
-if (is.null(envs$cell_qc) || length(envs$cell_qc) == 0) {
-    log_warn("No cell QC criteria is provided. All cells will be kept.")
-    envs$cell_qc = "TRUE"
-}
-
-sobj = sobj %>% mutate(.QC = !!rlang::parse_expr(envs$cell_qc))
-feats = c("nFeature_RNA", "nCount_RNA", "percent.mt", "percent.ribo", "percent.hb", "percent.plat")
-plotsdir = file.path(joboutdir, "plots")
-dir.create(plotsdir, showWarnings = FALSE)
-
-# Violin plots
-log_info("Plotting violin plots ...")
-add_report(
-    list(
-        kind = "descr",
-        content = paste(
-            "The violin plots for each feature. The cells are grouped by sample.",
-            "The cells that fail the QC criteria are colored in red, and",
-            "the cells that pass the QC criteria are colored in black.",
-            "The cells that fail the QC criteria are filtered out in the returned Seurat object."
-        )
-    ),
-    h1 = "Violin Plots"
-)
-for (feat in feats) {
-    log_info("- For feature: {feat}")
-    vln_p = VlnPlot(
-        sobj,
-        cols = rep("white", length(samples)),
-        group.by = "Sample",
-        features = feat,
-        pt.size = 0) + NoLegend()
-    vln_p$data$.QC = sobj@meta.data$.QC
-    vln_p = vln_p + geom_jitter(
-            aes(color = .QC),
-            data = vln_p$data,
-            position = position_jitterdodge(jitter.width = 0.4, dodge.width = 0.9)
-        ) + scale_color_manual(values = c("#181818", pal_biopipen()(1)), breaks = c(TRUE, FALSE))
-
-    vlnplot = file.path(plotsdir, paste0(slugify(feat), ".vln.png"))
-    png(
-        vlnplot,
-        width = 800 + length(samples) * 15, height = 600, res = 100
-    )
-    print(vln_p)
-    dev.off()
-
-    add_report(
-        list(
-            src = vlnplot,
-            name = feat,
-            descr = paste0("Distribution of ", feat, " for each sample.")
-        ),
-        h1 = "Violin Plots",
-        ui = "table_of_images"
-    )
-}
-
-# Scatter plots against nCount_RNA
-log_info("Plotting scatter plots ...")
-add_report(
-    list(
-        kind = "descr",
-        content = paste(
-            "The scatter plots for each feature against nCount_RNA. ",
-            "The cells that fail the QC criteria are colored in red, and",
-            "the cells that pass the QC criteria are colored in black.",
-            "The cells that fail the QC criteria are filtered out in the returned Seurat object."
-        )
-    ),
-    h1 = "Scatter Plots"
-)
-for (feat in setdiff(feats, "nCount_RNA")) {
-    log_info("- For feature: {feat}, against nCount_RNA")
-    scat_p = FeatureScatter(
-        sobj,
-        feature1 = "nCount_RNA",
-        feature2 = feat,
-        group.by = ".QC"
-    ) +
-    NoLegend() +
-    scale_color_manual(values = c("#181818", pal_biopipen()(1)), breaks = c(TRUE, FALSE))
-
-    scatfile = file.path(plotsdir, paste0(slugify(feat), "-nCount_RNA.scatter.png"))
-    png(scatfile, width = 800, height = 600, res = 100)
-    print(scat_p)
-    dev.off()
-
-    add_report(
-        list(
-            src = scatfile,
-            name = paste0(feat, " vs nCount_RNA"),
-            descr = paste0("Scatter plot for ", feat, " against nCount_RNA")
-        ),
-        h1 = "Scatter Plots",
-        ui = "table_of_images"
-    )
+if (!envs$cell_qc_per_sample) {
+    log_info("Performing cell QC ...")
+    sobj = perform_cell_qc(sobj)
 }
 
-# Do the filtering
-log_info("Filtering cells using QC criteria ...")
-sobj = sobj %>% filter(.QC)
-sobj$.QC = NULL
+# plot and report the QC
+log_info("Plotting and reporting QC ...")
+dim_df = report_cell_qc(nrow(sobj))
 
 log_info("Filtering genes ...")
 if (is.list(envs$gene_qc)) {
@@ -271,7 +322,7 @@ if (is.list(envs$gene_qc)) {
 dim_df = rbind(
     dim_df,
     data.frame(
-        When = "After_Gene_QC",
+        when = "After_Gene_QC",
         nCells = ncol(sobj),
         nGenes = nrow(sobj)
     )

biopipen/scripts/scrna/SeuratTo10X.R

@@ -1,84 +1,27 @@
-library(Matrix)
-
-indir = {{in.indir | quote}}
-outdir = {{out.outdir | quote}}
-envs = {{envs | r}}
-
-set.seed(envs$seed)
-setwd(outdir)
-
-logger <- function(...) {
-  cat(paste(..., "\n"), file=stderr())
-}
-
-# Find the data files
-mtx_file = Sys.glob(file.path(indir, "*matrix.mtx.gz"))
-feat_file = c(
-    Sys.glob(file.path(indir, "*genes.tsv.gz")),
-    Sys.glob(file.path(indir, "*features.tsv.gz"))
-)
-barcode_file = Sys.glob(file.path(indir, "*barcodes.tsv.gz"))
-if (length(mtx_file) == 0) {
-    stop("No matrix file found in", indir)
-}
-if (length(mtx_file) > 1) {
-    warning(paste("Multiple matrix files found in", indir, ", using the first one."))
-}
-if (length(feat_file) == 0) {
-    stop("No feature file found in", indir)
-}
-if (length(feat_file) > 1) {
-    warning(paste("Multiple feature files found in", indir, ", using the first one."))
-}
-if (length(barcode_file) == 0) {
-    stop("No barcode file found in", indir)
-}
-if (length(barcode_file) > 1) {
-    warning(paste("Multiple barcode files found in", indir, ", using the first one."))
-}
-
-mtx = readMM(mtx_file)
-n_feats = nrow(mtx)
-n_cells = ncol(mtx)
-logger("- Dimension: Features:", n_feats, ", Cells:", n_cells)
-
-if (envs$nfeats <= 1) {
-    nfeats = as.integer(n_feats * envs$nfeats)
+library(DropletUtils)
+library(Seurat)
+
+srtobjfile = {{in.srtobj | r}}
+outdir = {{out.outdir | r}}
+version = {{envs.version | r}}
+split_by = {{envs.split_by | r}}
+
+srtobj = readRDS(srtobjfile)
+if (!is.null(split_by)) {
+    # check if split_by is a valid column
+    if (is.null(srtobj[[split_by]])) {
+        stop(paste0("Column ", split_by, " not found in Seurat object"))
+    }
+
+    # split Seurat object by split_by column
+    objs <- SplitObject(srtobj, split.by = split_by)
+    for (s in names(objs)) {
+        counts <- GetAssayData(object = objs[[s]], layer = "counts")
+        odir <- file.path(outdir, s)
+        dir.create(odir, recursive = TRUE, showWarnings = FALSE)
+        write10xCounts(odir, counts, version = version, overwrite = TRUE)
+    }
 } else {
-    nfeats = envs$nfeats
-}
-if (envs$ncells <= 1) {
-    ncells = as.integer(n_cells * envs$ncells)
-} else {
-    ncells = envs$ncells
-}
-
-logger("- Identifying features to keep ...")
-feats = read.table(feat_file, header=FALSE, row.names=NULL, check.names=FALSE)
-feats_to_keep = c()
-if (length(envs$feats_to_keep) > 0) {
-    feats_to_keep = match(envs$feats_to_keep, feats[,2])
+    counts = GetAssayData(object = srtobj, layer = "counts")
+    write10xCounts(outdir, counts, version = version, overwrite = TRUE)
 }
-
-out_feats = unique(c(sample(1:n_feats, nfeats), feats_to_keep))
-out_cells = sample(1:n_cells, ncells)
-logger("- Resulting in", length(out_feats), "features and", ncells, "cells")
-
-logger("- Subsetting matrix and saving it ...")
-out_mtx = mtx[out_feats, out_cells, drop=FALSE]
-out_mtx_file = file.path(outdir, "matrix.mtx")
-writeMM(out_mtx, out_mtx_file)
-system(paste("gzip", out_mtx_file))
-
-logger("- Subsetting features and saving it ...")
-out_feats = feats[out_feats, , drop=FALSE]
-out_feats_file = gzfile(file.path(outdir, "features.tsv.gz"), "w")
-write.table(out_feats, out_feats_file, sep="\t", row.names=FALSE, col.names=FALSE, quote=FALSE)
-close(out_feats_file)
-
-logger("- Subsetting barcodes and saving it ...")
-barcodes = read.table(barcode_file, header=FALSE, row.names=NULL, check.names=FALSE)
-out_barcodes = barcodes[out_cells, , drop=FALSE]
-out_barcodes_file = gzfile(file.path(outdir, "barcodes.tsv.gz"), "w")
-write.table(out_barcodes, out_barcodes_file, sep="\t", row.names=FALSE, col.names=FALSE, quote=FALSE)
-close(out_barcodes_file)

biopipen/scripts/scrna/Subset10X.R

@@ -0,0 +1,84 @@
+library(Matrix)
+
+indir = {{in.indir | quote}}
+outdir = {{out.outdir | quote}}
+envs = {{envs | r}}
+
+set.seed(envs$seed)
+setwd(outdir)
+
+logger <- function(...) {
+  cat(paste(..., "\n"), file=stderr())
+}
+
+# Find the data files
+mtx_file = Sys.glob(file.path(indir, "*matrix.mtx.gz"))
+feat_file = c(
+    Sys.glob(file.path(indir, "*genes.tsv.gz")),
+    Sys.glob(file.path(indir, "*features.tsv.gz"))
+)
+barcode_file = Sys.glob(file.path(indir, "*barcodes.tsv.gz"))
+if (length(mtx_file) == 0) {
+    stop("No matrix file found in", indir)
+}
+if (length(mtx_file) > 1) {
+    warning(paste("Multiple matrix files found in", indir, ", using the first one."))
+}
+if (length(feat_file) == 0) {
+    stop("No feature file found in", indir)
+}
+if (length(feat_file) > 1) {
+    warning(paste("Multiple feature files found in", indir, ", using the first one."))
+}
+if (length(barcode_file) == 0) {
+    stop("No barcode file found in", indir)
+}
+if (length(barcode_file) > 1) {
+    warning(paste("Multiple barcode files found in", indir, ", using the first one."))
+}
+
+mtx = readMM(mtx_file)
+n_feats = nrow(mtx)
+n_cells = ncol(mtx)
+logger("- Dimension: Features:", n_feats, ", Cells:", n_cells)
+
+if (envs$nfeats <= 1) {
+    nfeats = as.integer(n_feats * envs$nfeats)
+} else {
+    nfeats = envs$nfeats
+}
+if (envs$ncells <= 1) {
+    ncells = as.integer(n_cells * envs$ncells)
+} else {
+    ncells = envs$ncells
+}
+
+logger("- Identifying features to keep ...")
+feats = read.table(feat_file, header=FALSE, row.names=NULL, check.names=FALSE)
+feats_to_keep = c()
+if (length(envs$feats_to_keep) > 0) {
+    feats_to_keep = match(envs$feats_to_keep, feats[,2])
+}
+
+out_feats = unique(c(sample(1:n_feats, nfeats), feats_to_keep))
+out_cells = sample(1:n_cells, ncells)
+logger("- Resulting in", length(out_feats), "features and", ncells, "cells")
+
+logger("- Subsetting matrix and saving it ...")
+out_mtx = mtx[out_feats, out_cells, drop=FALSE]
+out_mtx_file = file.path(outdir, "matrix.mtx")
+writeMM(out_mtx, out_mtx_file)
+system(paste("gzip", out_mtx_file))
+
+logger("- Subsetting features and saving it ...")
+out_feats = feats[out_feats, , drop=FALSE]
+out_feats_file = gzfile(file.path(outdir, "features.tsv.gz"), "w")
+write.table(out_feats, out_feats_file, sep="\t", row.names=FALSE, col.names=FALSE, quote=FALSE)
+close(out_feats_file)
+
+logger("- Subsetting barcodes and saving it ...")
+barcodes = read.table(barcode_file, header=FALSE, row.names=NULL, check.names=FALSE)
+out_barcodes = barcodes[out_cells, , drop=FALSE]
+out_barcodes_file = gzfile(file.path(outdir, "barcodes.tsv.gz"), "w")
+write.table(out_barcodes, out_barcodes_file, sep="\t", row.names=FALSE, col.names=FALSE, quote=FALSE)
+close(out_barcodes_file)

{biopipen-0.27.4.dist-info → biopipen-0.27.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.27.4
+Version: 0.27.5
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

{biopipen-0.27.4.dist-info → biopipen-0.27.5.dist-info}/RECORD

@@ -1,11 +1,11 @@
-biopipen/__init__.py,sha256=FRehirBY8kLByuBXp81U_RUAg8WYLFropNPtg2RpV2w,23
+biopipen/__init__.py,sha256=E1FuUUku2gzKP9EaIByX13BXhDU2SYE99gN_s2YdX7s,23
 biopipen/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/core/config.py,sha256=edK5xnDhM8j27srDzsxubi934NMrglLoKrdcC8qsEPk,1069
 biopipen/core/config.toml,sha256=20RCI30Peee1EQdfb_UbV3Hf74XUPndJnYZlUThytsw,1781
 biopipen/core/defaults.py,sha256=yPeehPLk_OYCf71IgRVCWuQRxLAMixDF81Ium0HtPKI,344
 biopipen/core/filters.py,sha256=HLrjXGsvvjRtTWIAmg_f4IMymWaRD769HlDwsCTh170,12424
 biopipen/core/proc.py,sha256=60lUP3PcUAaKbDETo9N5PEIoeOYrLgcSmuytmrhcx8g,912
-biopipen/core/testing.py,sha256=6BaHm8C7oHdnC5q14DBd0Qp1wqNxSexSFc5vUtHZjsw,3565
+biopipen/core/testing.py,sha256=fZ8lzLwM5AhYapx0LDdYZPumqC0dj7GZpQuabhlqyGI,3665
 biopipen/ns/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/ns/bam.py,sha256=5AsYrB0mtr_mH6mCL6gjJ5rC4NywpjFkpFjUrBGp7Fk,9301
 biopipen/ns/bcftools.py,sha256=puCDfIL-1z6cz2y1Rlz-ESNIr8xJgeIjEQ440qicCvM,3467
@@ -21,7 +21,7 @@ biopipen/ns/gsea.py,sha256=EsNRAPYsagaV2KYgr4Jv0KCnZGqayM209v4yOGGTIOI,7423
 biopipen/ns/misc.py,sha256=fzn0pXvdghMkQhu-e3MMapPNMyO6IAJbtTzVU3GbFa0,3246
 biopipen/ns/plot.py,sha256=fzJAKKl4a_tsVkLREGCQTFVHP049m33LdWgeYRb6v7M,5483
 biopipen/ns/rnaseq.py,sha256=bKAa6friFWof4yDTWZQahm1MS-lrdetO1GqDKdfxXYc,7708
-biopipen/ns/scrna.py,sha256=u0p2eVqB2T7vpg-19NN0277QKChTsv9yxM6xQA6pJHg,103464
+biopipen/ns/scrna.py,sha256=7Gs1xxQoGM3TKxaQvbgKNyMDEsgatFopImzC-RcOEoA,103946
 biopipen/ns/scrna_metabolic_landscape.py,sha256=EhOtHQyoH-jRpzDoOI_06UbjEg6mhvbDEHKhek01bPk,28334
 biopipen/ns/snp.py,sha256=EQ2FS0trQ7YThPmBVTpS66lc2OSfgQ6lCh6WnyP-C2g,5499
 biopipen/ns/stats.py,sha256=yJ6C1CXF84T7DDs9mgufqUOr89Rl6kybE5ji8Vnx6cw,13693
@@ -138,7 +138,7 @@ biopipen/scripts/scrna/SCImpute.R,sha256=dSJOHhmJ3x_72LBRXT72dbCti5oiB85CJ-OjWtq
 biopipen/scripts/scrna/ScFGSEA.R,sha256=2UCTCIydVkPGvn7WP-_fcE7857iKKDxY56-j-ruyO8o,6254
 biopipen/scripts/scrna/Seurat2AnnData.R,sha256=qz4u-B5J3GMwttubnNnByJXreziFbrP5Mak0L0q7eG0,1557
 biopipen/scripts/scrna/SeuratClusterStats-dimplots.R,sha256=gViDgQ8NorYD64iK0FgcODOrDOw0tExZmhuPRuLNp4g,2354
-biopipen/scripts/scrna/SeuratClusterStats-features.R,sha256=SaKTJloP1fttRXZQeb2ApX0ej7al13wOoEYkthSk13k,15489
+biopipen/scripts/scrna/SeuratClusterStats-features.R,sha256=W7iYhaFsC5EMZLO50QukYPLYGK4bq9kQc1VT5FwvI68,15496
 biopipen/scripts/scrna/SeuratClusterStats-hists.R,sha256=YhuD-GePjJPSkR0iLRgV_hiGHD_bnOIKp-LB6GCwquo,5037
 biopipen/scripts/scrna/SeuratClusterStats-ngenes.R,sha256=GVKIXFNS_syCuSN8oxoBkjxxAeI5LdSxh-qLVkUsbDA,2146
 biopipen/scripts/scrna/SeuratClusterStats-stats.R,sha256=TxQ0OcLwXwIgwL1mTLArboK0ATJIJhxWiv9DV_jBlhE,9255
@@ -148,13 +148,13 @@ biopipen/scripts/scrna/SeuratFilter.R,sha256=BrYK0MLdaTtQvInMaQsmOt7oH_hlks0M1zy
 biopipen/scripts/scrna/SeuratLoading.R,sha256=ekWKnHIqtQb3kHVQiVymAHXXqiUxs6KKefjZKjaykmk,900
 biopipen/scripts/scrna/SeuratMap2Ref.R,sha256=Xn3VnvKqShuC0Ju05380wjuLVSdW0uWVzntdxjme244,4359
 biopipen/scripts/scrna/SeuratMetadataMutater.R,sha256=Pp4GsF3hZ6ZC2vroC3LSBmVa4B1p2L3hbh981yaAIeQ,1093
-biopipen/scripts/scrna/SeuratPreparing.R,sha256=c_aBM0mugBNyYJ5OjNVDR_Cj0sGqkiJZXCOk3pesFDk,16990
+biopipen/scripts/scrna/SeuratPreparing.R,sha256=t6GOcc9ZNwpRLeES7uBWja9RF6u6k5I_TXcdK4Ve7d0,18683
 biopipen/scripts/scrna/SeuratSplit.R,sha256=vdK11V39_Uo_NaOh76QWCtxObGaEr5Ynxqq0hTiSvsU,754
 biopipen/scripts/scrna/SeuratSubClustering.R,sha256=L1SwKhNNKvsQGrcj0ZjScW9BLuvdO2pg7U48Ospsot8,6096
 biopipen/scripts/scrna/SeuratSubset.R,sha256=yVA11NVE2FSSw-DhxQcJRapns0tNNHdyDYi5epO6SKM,1776
-biopipen/scripts/scrna/SeuratTo10X.R,sha256=T2nJBTwOe12AIKC2FZsMSv6xx3s-67CYZokpz5wshqY,2679
+biopipen/scripts/scrna/SeuratTo10X.R,sha256=1mh1R0Qlo1iHVrpMLUXyLDOA92QKJ4GzTMURTFRqsWg,901
+biopipen/scripts/scrna/Subset10X.R,sha256=T2nJBTwOe12AIKC2FZsMSv6xx3s-67CYZokpz5wshqY,2679
 biopipen/scripts/scrna/TopExpressingGenes.R,sha256=kXMCYHVytgVgO_Uq66fKKFCFV2PPXE8VREy_0yYPLpU,7475
-biopipen/scripts/scrna/Write10X.R,sha256=OMhXvJwvaH-aWsMpijKrvXQVabc1qUu5ZEwiLAhkDeY,285
 biopipen/scripts/scrna/celltypist-wrapper.py,sha256=f5M8f4rU5nC7l17RS0YVmUPpLLz4D6PIcgWtA77UExM,1722
 biopipen/scripts/scrna/sctype.R,sha256=NaUJkABwF5G1UVm1CCtcMbwLSj94Mo24mbYCKFqo1Bw,6524
 biopipen/scripts/scrna_metabolic_landscape/MetabolicFeatures.R,sha256=b77yG5FeRse3bNfFgLIEYGHNZzydAn1OeyyR_n5Ju60,4790
@@ -240,7 +240,7 @@ biopipen/utils/reference.py,sha256=6bPSwQa-GiDfr7xLR9a5T64Ey40y24yn3QfQ5wDFZkU,4
 biopipen/utils/rnaseq.R,sha256=Ro2B2dG-Z2oVaT5tkwp9RHBz4dp_RF-JcizlM5GYXFs,1298
 biopipen/utils/single_cell.R,sha256=pJjYP8bIZpNAtTQ32rOXhZxaM1Y-6D-xUcK3pql9tbk,4316
 biopipen/utils/vcf.py,sha256=ajXs0M_QghEctlvUlSRjWQIABVF02wPdYd-0LP4mIsU,9377
-biopipen-0.27.4.dist-info/METADATA,sha256=jBHr-0G03oeihg4W1XgeY5gVb4rI-4chXNOt6wWhbJE,882
-biopipen-0.27.4.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-biopipen-0.27.4.dist-info/entry_points.txt,sha256=wu70aoBcv1UahVbB_5237MY-9M9_mzqmWjDD-oi3yz0,621
-biopipen-0.27.4.dist-info/RECORD,,
+biopipen-0.27.5.dist-info/METADATA,sha256=V-P-6i9I4Q1OE-KDY39Nkki_Iv_5jpP-65kxeUuCc88,882
+biopipen-0.27.5.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+biopipen-0.27.5.dist-info/entry_points.txt,sha256=wu70aoBcv1UahVbB_5237MY-9M9_mzqmWjDD-oi3yz0,621
+biopipen-0.27.5.dist-info/RECORD,,

biopipen/scripts/scrna/Write10X.R

@@ -1,11 +0,0 @@
-library(DropletUtils)
-library(Seurat)
-
-srtobjfile = {{in.srtobj | r}}
-outdir = {{out.outdir | r}}
-version = {{envs.version | r}}
-
-srtobj = readRDS(srtobjfile)
-counts = GetAssayData(object = srtobj, layer = "counts")
-
-write10xCounts(outdir, counts, version = version, overwrite = TRUE)