biopipen 0.27.4__tar.gz → 0.27.6__tar.gz

{biopipen-0.27.4 → biopipen-0.27.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.27.4
+Version: 0.27.6
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

biopipen-0.27.6/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.27.6"

{biopipen-0.27.4 → biopipen-0.27.6}/biopipen/core/testing.py

@@ -3,7 +3,7 @@ import tempfile
 from functools import wraps
 from pathlib import Path
 
-from pipen import Pipen, plugin
+from pipen import Pipen
 
 TESTING_INDEX_INIT = 1
 TESTING_PARENT_DIR = Path(tempfile.gettempdir())
@@ -40,26 +40,16 @@ def _get_test_dirs(testfile, new):
     return name, workdir, outdir
 
 
-class PipelineSucceeded:
-    """A plugin to check if the pipeline succeeded"""
-
-    name = "succeeded"
-    version = "0.1.0"
-
-    @plugin.impl
-    async def on_complete(pipen, succeeded):
-        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": [f"{report_plugin_prefix}report"],
     }
     kws.update(kwargs)
     return Pipen(**kws)

{biopipen-0.27.4 → biopipen-0.27.6}/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-0.27.4 → biopipen-0.27.6}/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-0.27.4 → biopipen-0.27.6}/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-0.27.6/biopipen/scripts/scrna/SeuratTo10X.R

@@ -0,0 +1,27 @@
+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 {
+    counts = GetAssayData(object = srtobj, layer = "counts")
+    write10xCounts(outdir, counts, version = version, overwrite = TRUE)
+}

{biopipen-0.27.4 → biopipen-0.27.6}/biopipen/scripts/scrna_metabolic_landscape/MetabolicFeatures.R

@@ -52,12 +52,13 @@ do_one_group <- function(obj, features, group, outputdir, h1) {
     if (any(table(classes) < 5)) {
         msg <- paste("Group", group, "has less than 5 cells, or only 5 cells left.")
         log_warn(msg)
-        add_report(
-            list(kind = "error", content = msg),
-            h1 = ifelse(is.null(h1), groupname, h1),
-            h2 = ifelse(is.null(h1), "#", groupname)
+        return(
+            list(
+                list(kind = "error", content = msg),
+                h1 = ifelse(is.null(h1), groupname, h1),
+                h2 = ifelse(is.null(h1), "#", groupname)
+            )
         )
-        return()
     }
 
     exprs = GetAssayData(obj)[features, , drop = FALSE]

{biopipen-0.27.4 → biopipen-0.27.6}/biopipen/utils/gsea.R

@@ -172,12 +172,12 @@ runFGSEA = function(
 
     tablefig = file.path(outdir, "gsea_table.png")
     png(tablefig, res=100, width=1000, height=200 + 40 * length(topPathways))
-    print(plotGseaTable(
+    plotGseaTable(
         envs$pathways[topPathways],
         ranks,
         gsea_res,
         gseaParam = if (!is.null(envs$gseaParam)) envs$gseaParam else 1
-    ))
+    )
     dev.off()
 
     for (pathway in topPathways) {

{biopipen-0.27.4 → biopipen-0.27.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "biopipen"
-version = "0.27.4"
+version = "0.27.6"
 description = "Bioinformatics processes/pipelines that can be run from `pipen run`"
 authors = ["pwwang <pwwang@pwwang.com>"]
 license = "MIT"

{biopipen-0.27.4 → biopipen-0.27.6}/setup.py

@@ -81,7 +81,7 @@ entry_points = \
 
 setup_kwargs = {
     'name': 'biopipen',
-    'version': '0.27.4',
+    'version': '0.27.6',
     'description': 'Bioinformatics processes/pipelines that can be run from `pipen run`',
     'long_description': 'None',
     'author': 'pwwang',

biopipen-0.27.4/biopipen/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.27.4"

biopipen-0.27.4/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)