biopipen 0.27.3__py3-none-any.whl → 0.27.5__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.27.3"
+__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/delim.py

@@ -113,7 +113,7 @@ class SampleInfo(Proc):
         "exclude_cols": None,
         "defaults": {
             "on": "Sample",
-            "distinct": None,
+            # "distinct": None,
             "group": None,
             "na_group": False,
             "each": None,

biopipen/ns/plot.py

@@ -114,3 +114,39 @@ class Heatmap(Proc):
         "globals": "",
     }
     script = "file://../scripts/plot/Heatmap.R"
+
+
+class ROC(Proc):
+    """Plot ROC curve using [`plotROC`](https://cran.r-project.org/web/packages/plotROC/vignettes/examples.html).
+
+    Input:
+        infile: The input file for data, tab-separated.
+            The first column should be ids of the records (this is optional if `envs.noids` is True).
+            The second column should be the labels of the records (1 for positive, 0 for negative).
+            If they are not binary, you can specify the positive label by `envs.pos_label`.
+            From the third column, it should be the scores of the different models.
+
+    Output:
+        outfile: The output figure file
+
+    Envs:
+        noids: Whether the input file has ids (first column) or not.
+        pos_label: The positive label.
+        ci: Whether to use `geom_rocci()` instead of `geom_roc()`.
+        devpars: The parameters for `png()`
+        args: Additional arguments for `geom_roc()` or `geom_rocci()` if `envs.ci` is True.
+        style_roc: Arguments for `style_roc()`
+    """  # noqa: E501
+    input = "infile:file"
+    output = "outfile:file:{{in.infile | stem}}.roc.png"
+    lang = config.lang.rscript
+    envs = {
+        "noids": False,
+        "pos_label": 1,
+        "ci": False,
+        "devpars": {"res": 100, "width": 750, "height": 600},
+        "args": {"labels": False},
+        "style_roc": {},
+        "show_auc": True,
+    }
+    script = "file://../scripts/plot/ROC.R"

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,
@@ -413,7 +417,7 @@ class SeuratClusterStats(Proc):
         nCells_All = { }
         ```
 
-        ![nCells_All](https://pwwang.github.io/immunopipe/processes/images/SeuratClusterStats_nCells_All.png){: width="80%" }
+        ![nCells_All](https://pwwang.github.io/immunopipe/latest/processes/images/SeuratClusterStats_nCells_All.png){: width="80%" }
 
         ### Number of cells in each cluster by groups
 
@@ -422,7 +426,7 @@ class SeuratClusterStats(Proc):
         nCells_Sample = { group-by = "Sample" }
         ```
 
-        ![nCells_Sample](https://pwwang.github.io/immunopipe/processes/images/SeuratClusterStats_nCells_Sample.png){: width="80%" }
+        ![nCells_Sample](https://pwwang.github.io/immunopipe/latest/processes/images/SeuratClusterStats_nCells_Sample.png){: width="80%" }
 
         ### Violin plots for the gene expressions
 
@@ -435,8 +439,8 @@ class SeuratClusterStats(Proc):
         vlnplots_1 = { features = ["FOXP3", "IL2RA"], pt-size = 0, kind = "vln" }
         ```
 
-        ![vlnplots](https://pwwang.github.io/immunopipe/processes/images/SeuratClusterStats_vlnplots.png){: width="80%" }
-        ![vlnplots_1](https://pwwang.github.io/immunopipe/processes/images/SeuratClusterStats_vlnplots_1.png){: width="80%" }
+        ![vlnplots](https://pwwang.github.io/immunopipe/latest/processes/images/SeuratClusterStats_vlnplots.png){: width="80%" }
+        ![vlnplots_1](https://pwwang.github.io/immunopipe/latest/processes/images/SeuratClusterStats_vlnplots_1.png){: width="80%" }
 
         ### Dimension reduction plot with labels
 
@@ -447,7 +451,7 @@ class SeuratClusterStats(Proc):
         repel = true
         ```
 
-        ![dimplots](https://pwwang.github.io/immunopipe/processes/images/SeuratClusterStats_dimplots.png){: width="80%" }
+        ![dimplots](https://pwwang.github.io/immunopipe/latest/processes/images/SeuratClusterStats_dimplots.png){: width="80%" }
 
     Input:
         srtobj: The seurat object loaded by `SeuratClustering`
@@ -857,7 +861,7 @@ class CellsDistribution(Proc):
         group_order = [ "Tumor", "Normal" ]
         ```
 
-        ![CellsDistribution_example](https://pwwang.github.io/immunopipe/processes/images/CellsDistribution_example.png)
+        ![CellsDistribution_example](https://pwwang.github.io/immunopipe/latest/processes/images/CellsDistribution_example.png)
 
     Input:
         srtobj: The seurat object in RDS format
@@ -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"
 
@@ -1870,7 +1877,7 @@ class RadarPlots(Proc):
 
         Then we will have a radar plots like this:
 
-        ![Radar plots](https://pwwang.github.io/immunopipe/processes/images/RadarPlots-default.png)
+        ![Radar plots](https://pwwang.github.io/immunopipe/latest/processes/images/RadarPlots-default.png)
 
         We can use `each` to separate the cells into different cases:
 
@@ -1882,7 +1889,7 @@ class RadarPlots(Proc):
 
         Then we will have two radar plots, one for `Pre` and one for `Post`:
 
-        ![Radar plots](https://pwwang.github.io/immunopipe/processes/images/RadarPlots-each.png)
+        ![Radar plots](https://pwwang.github.io/immunopipe/latest/processes/images/RadarPlots-each.png)
 
         Using `cluster_order` to change the order of the clusters and show only the first 3 clusters:
 
@@ -1893,7 +1900,7 @@ class RadarPlots(Proc):
         breaks = [0, 50, 100]  # also change the breaks
         ```
 
-        ![Radar plots cluster_order](https://pwwang.github.io/immunopipe/processes/images/RadarPlots-cluster_order.png)
+        ![Radar plots cluster_order](https://pwwang.github.io/immunopipe/latest/processes/images/RadarPlots-cluster_order.png)
 
 
         /// Attention

biopipen/ns/scrna_metabolic_landscape.py

@@ -22,11 +22,11 @@ class MetabolicPathwayActivity(Proc):
     For each subset, a heatmap and a violin plot will be generated.
     The heatmap shows the pathway activities for each group and each metabolic pathway
 
-    ![MetabolicPathwayActivity_heatmap](https://pwwang.github.io/immunopipe/processes/images/MetabolicPathwayActivity_heatmap.png){: width="80%"}
+    ![MetabolicPathwayActivity_heatmap](https://pwwang.github.io/immunopipe/latest/processes/images/MetabolicPathwayActivity_heatmap.png){: width="80%"}
 
     The violin plot shows the distribution of the pathway activities for each group
 
-    ![MetabolicPathwayActivity_violin](https://pwwang.github.io/immunopipe/processes/images/MetabolicPathwayActivity_violin.png){: width="45%"}
+    ![MetabolicPathwayActivity_violin](https://pwwang.github.io/immunopipe/latest/processes/images/MetabolicPathwayActivity_violin.png){: width="45%"}
 
     Envs:
         ntimes (type=int): Number of times to do the permutation
@@ -294,7 +294,7 @@ class MetabolicPathwayHeterogeneity(Proc):
     The heterogeneity can be reflected by the NES values and the p-values in
     different groups for the metabolic pathways.
 
-    ![MetabolicPathwayHeterogeneity](https://pwwang.github.io/immunopipe/processes/images/MetabolicPathwayHeterogeneity.png)
+    ![MetabolicPathwayHeterogeneity](https://pwwang.github.io/immunopipe/latest/processes/images/MetabolicPathwayHeterogeneity.png)
 
 
     Envs:

biopipen/ns/snp.py

@@ -71,3 +71,68 @@ class PlinkSimulation(Proc):
         "sample_prefix": None,
     }
     script = "file://../scripts/snp/PlinkSimulation.py"
+
+
+class MatrixEQTL(Proc):
+    """Run Matrix eQTL
+
+    See also <https://www.bios.unc.edu/research/genomic_software/Matrix_eQTL/>
+
+    Input:
+        geno: Genotype matrix file with rows representing SNPs and columns
+            representing samples.
+        expr: Expression matrix file with rows representing genes and columns
+            representing samples.
+        cov: Covariate matrix file with rows representing covariates and columns
+            representing samples.
+
+    Output:
+        alleqtls: Matrix eQTL output file
+        cisqtls: The cis-eQTL file if `snppos` and `genepos` are provided.
+            Otherwise it'll be empty.
+
+    Envs:
+        model (choice): The model to use.
+            - `linear`: Linear model
+            - `modelLINEAR`: Same as `linear`
+            - `anova`: ANOVA model
+            - `modelANOVA`: Same as `anova`
+        pval (type=float): P-value threshold for eQTLs
+        transp (type=float): P-value threshold for trans-eQTLs.
+            If cis-eQTLs are not enabled (`snppos` and `genepos` are not set),
+            this defaults to 1e-5.
+            If cis-eQTLs are enabled, this defaults to `None`, which will disable
+            trans-eQTL analysis.
+        fdr (flag): Do FDR calculation or not (save memory if not).
+        snppos: The path of the SNP position file.
+            It could be a BED, GFF, VCF or a tab-delimited file with
+            `snp`, `chr`, `pos` as the first 3 columns.
+        genepos: The path of the gene position file.
+            It could be a BED or GFF file.
+        dist (type=int): Distance threshold for cis-eQTLs.
+        transpose_geno (flag): If set, the genotype matrix (`in.geno`)
+            will be transposed.
+        transpose_expr (flag): If set, the expression matrix (`in.expr`)
+            will be transposed.
+        transpose_cov (flag): If set, the covariate matrix (`in.cov`)
+            will be transposed.
+    """
+    input = "geno:file, expr:file, cov:file"
+    output = [
+        "alleqtls:file:{{in.geno | stem}}.alleqtls.txt",
+        "cisqtls:file:{{in.geno | stem}}.cisqtls.txt",
+    ]
+    lang = config.lang.rscript
+    envs = {
+        "model": "linear",
+        "pval": 1e-3,
+        "transp": None,
+        "fdr": False,
+        "snppos": None,
+        "genepos": config.ref.refgene,
+        "dist": 250000,
+        "transpose_geno": False,
+        "transpose_expr": False,
+        "transpose_cov": False,
+    }
+    script = "file://../scripts/snp/MatrixEQTL.R"

biopipen/ns/tcr.py

@@ -923,7 +923,7 @@ class CloneResidency(Proc):
 
     - Residency plots showing the residency of clones in the two groups
 
-        ![CloneResidency_residency](https://pwwang.github.io/immunopipe/processes/images/CloneResidency.png)
+        ![CloneResidency_residency](https://pwwang.github.io/immunopipe/latest/processes/images/CloneResidency.png)
 
         The points in the plot are jittered to avoid overplotting. The x-axis is the residency in the first group and
         the y-axis is the residency in the second group. The size of the points are relative to the normalized size of
@@ -943,7 +943,7 @@ class CloneResidency(Proc):
 
     - Venn diagrams showing the overlap of the clones in the two groups
 
-        ![CloneResidency_venn](https://pwwang.github.io/immunopipe/processes/images/CloneResidency_venn.png){: width="60%"}
+        ![CloneResidency_venn](https://pwwang.github.io/immunopipe/latest/processes/images/CloneResidency_venn.png){: width="60%"}
 
     Input:
         immdata: The data loaded by `immunarch::repLoad()`
@@ -1259,7 +1259,7 @@ class TCRClusterStats(Proc):
         by = "Sample"
         ```
 
-        ![Cluster_size](https://pwwang.github.io/immunopipe/processes/images/TCRClusteringStats_cluster_size.png){: width="80%"}
+        ![Cluster_size](https://pwwang.github.io/immunopipe/latest/processes/images/TCRClusteringStats_cluster_size.png){: width="80%"}
 
         ### Shared clusters
 
@@ -1269,7 +1269,7 @@ class TCRClusterStats(Proc):
         heatmap_meta = ["region"]
         ```
 
-        ![Shared_clusters](https://pwwang.github.io/immunopipe/processes/images/TCRClusteringStats_shared_clusters.png){: width="80%"}
+        ![Shared_clusters](https://pwwang.github.io/immunopipe/latest/processes/images/TCRClusteringStats_shared_clusters.png){: width="80%"}
 
         ### Sample diversity
 
@@ -1278,11 +1278,11 @@ class TCRClusterStats(Proc):
         method = "gini"
         ```
 
-        ![Sample_diversity](https://pwwang.github.io/immunopipe/processes/images/TCRClusteringStats_sample_diversity.png){: width="80%"}
+        ![Sample_diversity](https://pwwang.github.io/immunopipe/latest/processes/images/TCRClusteringStats_sample_diversity.png){: width="80%"}
 
         Compared to the sample diversity using TCR clones:
 
-        ![Sample_diversity](https://pwwang.github.io/immunopipe/processes/images/Immunarch_sample_diversity.png){: width="80%"}
+        ![Sample_diversity](https://pwwang.github.io/immunopipe/latest/processes/images/Immunarch_sample_diversity.png){: width="80%"}
 
     Input:
         immfile: The immunarch object with TCR clusters attached

biopipen/scripts/delim/SampleInfo.R

@@ -113,14 +113,14 @@ for (name in names(stats)) {
     if (stat$plot == "boxplot" || stat$plot == "box") {
         p <- ggplot(data, aes(x=!!group, y=!!sym(stat$on), fill=!!group)) +
             geom_boxplot(position = "dodge") +
-            scale_fill_biopipen() +
+            scale_fill_biopipen(alpha = .6) +
             xlab("")
     } else if (stat$plot == "violin" ||
                stat$plot == "violinplot" ||
                stat$plot == "vlnplot") {
         p <- ggplot(data, aes(x = !!group, y = !!sym(stat$on), fill=!!group)) +
             geom_violin(position = "dodge") +
-            scale_fill_biopipen() +
+            scale_fill_biopipen(alpha = .6) +
             xlab("")
     } else if (
         (grepl("violin", stat$plot) || grepl("vln", stat$plot)) &&
@@ -129,12 +129,12 @@ for (name in names(stats)) {
         p <- ggplot(data, aes(x = !!group, y = !!sym(stat$on), fill = !!group)) +
             geom_violin(position = "dodge") +
             geom_boxplot(width = 0.1, position = position_dodge(0.9), fill="white") +
-            scale_fill_biopipen() +
+            scale_fill_biopipen(alpha = .6) +
             xlab("")
     } else if (stat$plot == "histogram" || stat$plot == "hist") {
         p <- ggplot(data, aes(x = !!sym(stat$on), fill = !!group)) +
             geom_histogram(bins = 10, position = "dodge", alpha = 0.8, color = "white") +
-            scale_fill_biopipen()
+            scale_fill_biopipen(alpha = .6)
     } else if (stat$plot == "pie" || stat$plot == "piechart") {
         if (is.null(stat$each)) {
             data <- data %>% distinct(!!group, .keep_all = TRUE)
@@ -157,7 +157,7 @@ for (name in names(stats)) {
                 fill="#EEEEEE",
                 size=4
             ) +
-            scale_fill_biopipen(name = group) +
+            scale_fill_biopipen(alpha = .6, name = group) +
             ggtitle(paste0("# ", stat$on))
     } else if (stat$plot == "bar" || stat$plot == "barplot") {
         if (is.null(stat$each)) {
@@ -169,7 +169,7 @@ for (name in names(stats)) {
             data,
             aes(x = !!group, y = !!sym(count_on), fill = !!group)) +
             geom_bar(stat = "identity") +
-            scale_fill_biopipen() +
+            scale_fill_biopipen(alpha = .6) +
             ylab(paste0("# ", stat$on))
     } else {
         stop("Unknown plot type: ", stat$plot)

biopipen/scripts/plot/ROC.R

@@ -0,0 +1,88 @@
+
+source("{{biopipen_dir}}/utils/misc.R")
+
+library(rlang)
+library(ggplot2)
+library(plotROC)
+
+infile <- {{in.infile | r}}
+outfile <- {{out.outfile | r}}
+joboutdir <- {{job.outdir | r}}
+noids <- {{envs.noids | r}}
+pos_label <- {{envs.pos_label | r}}
+ci <- {{envs.ci | r}}
+devpars <- {{envs.devpars | r}}
+show_auc <- {{envs.show_auc | r}}
+args <- {{envs.args | r: todot="-"}}
+style_roc_args <- {{envs.style_roc | r: todot="-"}}
+if (!is.null(style_roc_args$theme)) {
+    style_roc_args$theme <- eval(parse(text=style_roc_args$theme))
+}
+
+data <- read.table(infile, header=TRUE, sep="\t", row.names = NULL, check.names = FALSE, stringsAsFactors=FALSE)
+if (!noids) {
+    data <- data[, -1]
+}
+
+# Normalize the first column (labels) into 0 and 1.
+# If they are not 0/1, use pos_label to determine the positive class.
+label_col <- colnames(data)[1]
+if (is.character(data[[label_col]])) {
+    data[[label_col]] <- as.numeric(data[[label_col]] == pos_label)
+}
+
+models <- colnames(data)[2:ncol(data)]
+
+if (length(models) > 1) {
+    # pivot longer the models, and put the model names into the column 'model'
+    data <- melt_roc(data, label_col, colnames(data)[2:ncol(data)])
+} else {
+    data <- data.frame(
+        D = data[[label_col]],
+        M = data[[models]],
+        name = rep(models, nrow(data))
+    )
+}
+
+# Plot the ROC curve
+p <- ggplot(data, aes(d = D, m = M, color = name))
+
+if (isTRUE(ci)) {
+    p <- p + do.call(geom_rocci, args)
+} else {
+    p <- p + do.call(geom_roc, args)
+}
+
+p <- p + do.call(style_roc, style_roc_args)
+p <- p + scale_color_biopipen()
+
+if (length(models) > 1) {
+    p <- p + theme(legend.title = element_blank())
+} else {
+    p <- p + theme(legend.position = "none")
+}
+
+aucs = calc_auc(p)
+write.table(aucs, file=file.path(joboutdir, "aucs.tsv"), sep="\t", quote=FALSE, row.names=FALSE)
+
+if (show_auc) {
+    aucs = split(aucs$AUC, aucs$name)
+    if (length(aucs) > 1) {
+        # Add AUC values to the legend items
+        p <- p +
+            scale_color_manual(
+                values = pal_biopipen()(length(models)),
+                labels = sapply(models, function(m) paste(m, " (AUC =", round(aucs[[m]], 2), ")")),
+                breaks = models)
+    } else {
+        p <- p +
+            geom_text(
+                x = 0.8, y = 0.2, label = paste("AUC =", round(unlist(aucs), 2)),
+                color = "black", size = 4)
+    }
+}
+
+devpars$filename <- outfile
+do.call(png, devpars)
+print(p)
+dev.off()

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/scripts/snp/MatrixEQTL.R

@@ -0,0 +1,157 @@
+source("{{biopipen_dir}}/utils/misc.R")
+library(rlang)
+library(MatrixEQTL)
+
+snpfile = {{in.geno | r}}
+expfile = {{in.expr | r}}
+covfile = {{in.cov | r}}
+joboutdir = {{job.outdir | r}}
+alleqtl = {{out.alleqtls | r}}
+outfile = {{out.cisqtls | r}}
+
+model = {{envs.model | r}}
+pval = {{envs.pval | r}}
+transp = {{envs.transp | r}}
+fdr = {{envs.fdr | r}}
+snppos = {{envs.snppos | r}}
+genepos = {{envs.genepos | r}}
+dist = {{envs.dist | r}}
+
+transpose_geno = {{envs.transpose_geno | r}}
+transpose_expr = {{envs.transpose_expr | r}}
+transpose_cov = {{envs.transpose_cov | r}}
+
+arg_match(model, c("modelANOVA", "modelLINEAR", "linear", "anova"))
+if (model == "linear") model = "modelLINEAR"
+if (model == "anova") model = "modelANOVA"
+model = get(model)
+
+trans_enabled = !is.null(transp)
+cis_enabled = !is.null(snppos) && !is.null(genepos) && dist > 0
+
+# if trans is disabled, all files needed for cis should be provided
+if (!trans_enabled && !cis_enabled) {
+    log_warn("Using `envs.transp = 1e-5` since cis-eQTL is disabled.")
+    trans_enabled <- TRUE
+    transp <- 1e-5
+}
+
+transpose_file <- function(file) {
+    out <- file.path(joboutdir, paste0(
+        tools::file_path_sans_ext(basename(file)),
+        ".transposed.",
+        tools::file_ext(file))
+    )
+    data <- read.table(file, header=TRUE, stringsAsFactors=FALSE, row.names=1, sep="\t", quote="", check.names=FALSE)
+    write.table(t(data), file=out, sep="\t", quote=FALSE, row.names=TRUE, col.names=TRUE)
+    out
+}
+
+if (transpose_geno) snpfile = transpose_file(snpfile)
+if (transpose_expr) expfile = transpose_file(expfile)
+if (transpose_cov) covfile = transpose_file(covfile)
+
+snps = SlicedData$new();
+snps$fileDelimiter = "\t";       # the TAB character
+snps$fileOmitCharacters = "NA";  # denote missing values;
+snps$fileSkipRows = 1;           # one row of column labels
+snps$fileSkipColumns = 1;        # one column of row labels
+snps$fileSliceSize = 10000;      # read file in pieces of 2,000 rows
+snps$LoadFile( snpfile );
+
+gene = SlicedData$new();
+gene$fileDelimiter = "\t";       # the TAB character
+gene$fileOmitCharacters = "NA";  # denote missing values;
+gene$fileSkipRows = 1;           # one row of column labels
+gene$fileSkipColumns = 1;        # one column of row labels
+gene$fileSliceSize = 10000;      # read file in pieces of 2,000 rows
+gene$LoadFile( expfile );
+
+cvrt = SlicedData$new();
+if (!is.null(covfile) && file.exists(covfile)) {
+    covmatrix = t(read.table.inopts(covfile, list(cnames=TRUE, rnames=TRUE)))
+    cvrt$CreateFromMatrix( as.matrix(covmatrix) )
+}
+
+engine_params = list()
+engine_params$snps = snps
+engine_params$gene = gene
+engine_params$cvrt = cvrt
+engine_params$output_file_name = ifelse(trans_enabled, alleqtl, NULL)
+engine_params$pvOutputThreshold = ifelse(trans_enabled, transp, 0)
+engine_params$useModel = model
+engine_params$errorCovariance = numeric()
+engine_params$verbose = TRUE
+engine_params$noFDRsaveMemory = !fdr
+
+noq = function(s) {
+    gsub('^\"|\"$', "", s)
+}
+
+if (cis_enabled) {
+    if (endsWith(snppos, ".bed")) {
+        snppos_data = read.table.inopts(snppos,
+                                        list(cnames=FALSE, rnames=FALSE))
+        snppos_data = snppos_data[, c(4, 1, 2)]
+        colnames(snppos_data) = c("snp", "chr", "pos")
+    } else if (endsWith(snppos, ".gff") || endsWith(snppos, ".gtf")) {
+        snppos_data = read.table.inopts(snppos,
+                                        list(cnames=FALSE, rnames=FALSE));
+        snppos_data = snppos_data[, c(9, 1, 4)]
+        colnames(snppos_data) = c("snp", "chr", "pos")
+        snppos_data$snp = unlist(lapply(snppos_data$snp, function(x) {
+            for (s in unlist(strsplit(x, '; ', fixed=T))) {
+                if (startsWith(s, "snp_id "))
+                    return(noq(substring(s, 8)))
+                else if (startsWith(s, "rs_id "))
+                    return(noq(substring(s, 7)))
+                else if (startsWith(s, "rs "))
+                    return(noq(substring(s, 4)))
+            }
+        }))
+    } else if (endsWith(snppos, ".vcf") || endsWith(snppos, ".vcf.gz")) {
+        snppos_data = read.table.inopts(snppos,
+                                        list(cnames=FALSE, rnames=FALSE))
+        snppos_data = snppos_data[, c(3, 1, 2)]
+        colnames(snppos_data) = c("snp", "chr", "pos")
+    } else {
+        snppos_data = read.table.inopts(snppos, list(cnames=TRUE))
+        colnames(snppos_data) = c("snp", "chr", "pos")
+    }
+
+    if (endsWith(genepos, ".bed")) {
+        genepos_data = read.table.inopts(genepos,
+                                         list(cnames=FALSE, rnames=FALSE))
+        genepos_data = genepos_data[, c(4, 1:3)]
+        colnames(genepos_data) = c("geneid", "chr", "s1", "s2")
+    } else if (endsWith(genepos, ".gff") || endsWith(genepos, ".gtf")) {
+        genepos_data = read.table.inopts(genepos,
+                                         list(cnames=FALSE, rnames=FALSE))
+        genepos_data = genepos_data[, c(9, 1, 4, 5)]
+        colnames(genepos_data) = c("geneid", "chr", "s1", "s2")
+        genepos_data$geneid = noquote(unlist(lapply(genepos_data$geneid, function(x) {
+            for (s in unlist(strsplit(x, '; ', fixed=T))) {
+                if (startsWith(s, "gene_id "))
+                    return(noq(substring(s, 9)))
+            }
+        })))
+    } else {
+        genepos_data = read.table(genepos, header = TRUE, stringsAsFactors = FALSE);
+        colnames(genepos_data) = c("geneid", "chr", "s1", "s2")
+    }
+
+    engine_params$output_file_name.cis = outfile
+    engine_params$pvOutputThreshold.cis = pval
+    engine_params$cisDist = dist
+    engine_params$snpspos = snppos_data
+    engine_params$genepos = genepos_data
+    do_call(Matrix_eQTL_main, engine_params)
+} else {
+    do_call(Matrix_eQTL_engine, engine_params)
+    file.create(outfile)
+}
+
+if (pval == 0) {
+    if (!file.exists(outfile)) file.create(outfile)
+    if (!file.exists(alleqtl)) file.create(alleqtl)
+}

{biopipen-0.27.3.dist-info → biopipen-0.27.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.27.3
+Version: 0.27.5
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang
@@ -20,4 +20,3 @@ Requires-Dist: pipen-filters (>=0.12,<0.13)
 Requires-Dist: pipen-poplog (>=0.1.2,<0.2.0)
 Requires-Dist: pipen-runinfo (>=0.6,<0.7) ; extra == "runinfo"
 Requires-Dist: pipen-verbose (>=0.11,<0.12)
-Requires-Dist: pyyaml-include (==1.*)

{biopipen-0.27.3.dist-info → biopipen-0.27.5.dist-info}/RECORD

@@ -1,11 +1,11 @@
-biopipen/__init__.py,sha256=lxhjPOOCzhlHB02EzaqTtDdBFZSOLV3WLWw2HC0DYvo,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
@@ -15,18 +15,18 @@ biopipen/ns/cellranger_pipeline.py,sha256=D6gvIeasHjDCdro7f4wjomxRYTtsJT77Ld47Xz
 biopipen/ns/cnv.py,sha256=vq6dZfEOyuVuqg3nP6FQtNmQ-JocpBJMX9IYlZ0OPD0,6803
 biopipen/ns/cnvkit.py,sha256=5mA2Q8-YDs4g1HoxtpB_NWnyZYwEThNr3s3wlubLQrQ,31130
 biopipen/ns/cnvkit_pipeline.py,sha256=2fJLn70L2jJ81ZMNdnU84Sf3HoKA2CSnHuDzLGR8jmw,36854
-biopipen/ns/delim.py,sha256=cmGy82_Cjyf1anBPSzqEUcZCzZqMLdNY-w5uJLE-H6c,5610
+biopipen/ns/delim.py,sha256=fejsh4KW1TG5oMZzAC238LvQhBz7brXkfl3BHfnLK5M,5612
 biopipen/ns/gene.py,sha256=Q5FzRByfnRITXRNRZR65ApG09FRyiihRC3TcIXxufzE,2228
 biopipen/ns/gsea.py,sha256=EsNRAPYsagaV2KYgr4Jv0KCnZGqayM209v4yOGGTIOI,7423
 biopipen/ns/misc.py,sha256=fzn0pXvdghMkQhu-e3MMapPNMyO6IAJbtTzVU3GbFa0,3246
-biopipen/ns/plot.py,sha256=yguxmErUOH-hOM10JfuI_sXw2p49XF8yGR_gXfbd5yQ,4066
+biopipen/ns/plot.py,sha256=fzJAKKl4a_tsVkLREGCQTFVHP049m33LdWgeYRb6v7M,5483
 biopipen/ns/rnaseq.py,sha256=bKAa6friFWof4yDTWZQahm1MS-lrdetO1GqDKdfxXYc,7708
-biopipen/ns/scrna.py,sha256=i9h0xNOII3SqJ_cJOZ5epn8breAsc-yXH_Us04DoZvg,103401
-biopipen/ns/scrna_metabolic_landscape.py,sha256=9s1NvH3aMaNDXyfwy9TdzGcSP_lIW4JqhLgknNZcIKE,28313
-biopipen/ns/snp.py,sha256=Nq20NJzQ9YiqE9mhtCUH6dfs7528o1e4N-j9PewjAsQ,3016
+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
 biopipen/ns/tcgamaf.py,sha256=AFbUJIxiMSvsVY3RcHgjRFuMnNh2DG3Mr5slLNEyz6o,1455
-biopipen/ns/tcr.py,sha256=5bMnxhbeB08UrAw8YSh2BkA3AUFeoOajhE6DhHt74K4,87863
+biopipen/ns/tcr.py,sha256=7F_FulZ3UGouuvgH_ylZwJybr_310f9BTz_kouO1SjY,87905
 biopipen/ns/vcf.py,sha256=cdkKroii0_nl_bSP2cnO09qESUAhHqu6btOiTSKS79Y,15314
 biopipen/ns/web.py,sha256=3zucrDo-IVsSnIvlw-deoScuxqWa6OMTm8Vo-R4E44Q,2224
 biopipen/reports/bam/CNAClinic.svelte,sha256=D4IxQcgDCPQZMbXog-aZP5iJEQTK2N4i0C60e_iXyfs,213
@@ -102,7 +102,7 @@ biopipen/scripts/cnvkit/CNVkitScatter.py,sha256=7DhTiXPHEHbdXn0VFcDOR-wTP6sks08N
 biopipen/scripts/cnvkit/CNVkitSegment.py,sha256=q5iGAjY6-yIehPcJpi3hX6EuGre0YgWTPkG_d5LEV48,1629
 biopipen/scripts/cnvkit/guess_baits.py,sha256=7OCMtSMHIJWWZv9qEYVXnB0N4hU_JaGEesKdkr6tvJc,10586
 biopipen/scripts/delim/RowsBinder.R,sha256=yp960u7Ui_jFCL8WDvODa-0vhJvyLo64ll35PzXYUbI,1444
-biopipen/scripts/delim/SampleInfo.R,sha256=aYMaQR6klV8rVshqkaML9mnVpCfuGTvd_D5iUbPRzJA,6335
+biopipen/scripts/delim/SampleInfo.R,sha256=1EYlqoVpIEl9l2eBaCLETuI_Ma3HjihS9tRbGmOPiBk,6397
 biopipen/scripts/gene/GeneNameConversion.py,sha256=2RveardTsLv2K1XSj3G0ERYLiln9bcR74bjkRdKcChc,1880
 biopipen/scripts/gsea/Enrichr.R,sha256=tr4vInlVIeiGXumh22ARuTQmy0-Qq869RiX7d7ERqCg,661
 biopipen/scripts/gsea/FGSEA.R,sha256=RLqDgrqnYEacHfzEEuZ3d29lxNqWehigOnGuu248SRg,1483
@@ -111,6 +111,7 @@ biopipen/scripts/gsea/PreRank.R,sha256=onZK1FQa6yDO0Fz4juy56XQjpzyw3zBdZv7edY9ac
 biopipen/scripts/misc/Config2File.py,sha256=NUio0uOEuZtUBpuByDSItYu9Kwu5mosb4pdPq5-QAmE,440
 biopipen/scripts/misc/Str2File.py,sha256=99oQNxChxChNJ9vmD77b48cu-r_P_heSpx7A5wi3qTE,212
 biopipen/scripts/plot/Heatmap.R,sha256=4v_oRME8ZiwczIlBIp-OP_YPWLAvBKzbHiwNBCZ0Xog,1982
+biopipen/scripts/plot/ROC.R,sha256=Cr-mHQx6c748fQYkOWO2xIKWwiVAUxGuxn6lYEhNH78,2430
 biopipen/scripts/plot/VennDiagram.R,sha256=GVc-kyHqnXrbXZvy-evcxI1XGtlLSChBiVnMjPywNMA,731
 biopipen/scripts/rnaseq/Simulation-ESCO.R,sha256=68cEHDdJclX8P8Q7ey9yBOfK09M_kxlL6zgYXsEL2Rs,6378
 biopipen/scripts/rnaseq/Simulation-RUVcorr.R,sha256=6C6Ke5RLF0fC2V9WQPoFEdqoDabCnhslZBIyB6zhIxc,1155
@@ -137,7 +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
@@ -147,19 +148,20 @@ 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
 biopipen/scripts/scrna_metabolic_landscape/MetabolicFeaturesIntraSubset.R,sha256=ic8Fy8QqYDGh_izmvZVJ3KL66podg_CSF5ITL3FZsvo,5196
 biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayActivity.R,sha256=95DLX1Rz0tobOuDZ8V9YdGgO0KiNthhccoeeOK21tno,16216
 biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayHeterogeneity.R,sha256=rQ9iwGh9FNRZlJJzM4QItdyXmebfzLAq05ZAjb1kGUw,9831
+biopipen/scripts/snp/MatrixEQTL.R,sha256=zOR_mhn_sUXuxqgV82TPvDp-E1i5aJVA45QixyRP8no,5930
 biopipen/scripts/snp/PlinkSimulation.py,sha256=mSSoGGG6sbEPBcUGdHgbebUrg4DiHeyNyc7jLPjV5pY,4169
 biopipen/scripts/stats/ChowTest.R,sha256=4p7NULmfOZSfeBSQ04els0h3cXOK5yeCJJ4-gEBPOGk,3617
 biopipen/scripts/stats/DiffCoexpr.R,sha256=5hQDV2_7bKdKUsOGMZUa0GS5rc7kFspxonNyFEPmtbc,4516
@@ -238,7 +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-0.27.3.dist-info/METADATA,sha256=4DeAjhBZHdg7pZXoTNPiQkzGsx6hSm7VwgWgyYKMY18,920
-biopipen-0.27.3.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-biopipen-0.27.3.dist-info/entry_points.txt,sha256=wu70aoBcv1UahVbB_5237MY-9M9_mzqmWjDD-oi3yz0,621
-biopipen-0.27.3.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)