biopipen 0.22.1__py3-none-any.whl → 0.22.2__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.22.1"
+__version__ = "0.22.2"

biopipen/core/config.toml

@@ -4,6 +4,8 @@
 bedtools = "bedtools"
 # bcftools to handle bcf/vcf files
 bcftools = "bcftools"
+# cellranger
+cellranger = "cellranger"
 # Control-FREEC to call cnvs
 freec = "freec"
 # liftover coordinates across genomes
@@ -59,6 +61,10 @@ liftover_chain = ""
 # tmpdir = ""
 
 [ref]
+# The reference for cellranger gex
+ref_cellranger_gex = ""
+# The reference for cellranger vdj
+ref_cellranger_vdj = ""
 # The reference genome
 reffa = ""
 # The directory with reference for each chromosome

biopipen/core/filters.py

@@ -15,6 +15,7 @@ filtermanager = FilterManager()
 @filtermanager.register
 def dict_to_cli_args(
     dic: Mapping[str, Any],
+    exclude: List[str] = None,
     prefix: str | None = None,
     sep: str | None = " ",
     dup_key: bool = True,
@@ -27,6 +28,7 @@ def dict_to_cli_args(
 
     Args:
         dic: The dict to convert
+        exclude: The keys to exclude
         prefix: The prefix of the keys after conversion
             Defaults to `None`, mean `-` for short keys and `--` for long keys
         sep: The separator between key and value
@@ -37,6 +39,13 @@ def dict_to_cli_args(
             If `sep` is `None` or `=`, this must be True, otherwise an error
             will be raised
         join: Whether to join the arguments into a single string
+        start_key: The key to start the arguments
+            This is useful when you want to put some arguments at the beginning
+            of the command line
+        end_key: The key to end the arguments
+            This is useful when you want to put some arguments at the end
+            of the command line
+        dashify: Whether to replace `_` with `-` in the keys
 
     Returns:
         The converted string or list of strings
@@ -44,6 +53,9 @@ def dict_to_cli_args(
     if sep in [None, "="] and not dup_key:
         raise ValueError("`dup_key` must be True when sep is `None` or `=`")
 
+    if exclude:
+        dic = {k: v for k, v in dic.items() if k not in exclude}
+
     starts = []
     ends = []
     out = []

biopipen/ns/cellranger.py

@@ -0,0 +1,101 @@
+"""Cellranger pipeline module for BioPipen"""
+from ..core.proc import Proc
+from ..core.config import config
+
+
+class CellRangerCount(Proc):
+    """Run cellranger count
+
+    to count gene expression and/or feature barcode reads
+
+    Input:
+        fastqs: The input fastq files
+            Either a list of fastq files or a directory containing fastq files
+            If a directory is provided, it should be passed as a list with one
+            element.
+
+    Output:
+        outdir: The output directory
+
+    Envs:
+        ncores: Number of cores to use
+        cellranger: Path to cellranger
+        ref: Path of folder containing 10x-compatible transcriptome reference
+        tmpdir: Path to temporary directory, used to save the soft-lined fastq files
+            to pass to cellranger
+        include_introns: Set to false to exclude intronic reads in count.
+        <more>: Other environment variables required by `cellranger count`
+            See `cellranger count --help` for more details or
+            https://www.10xgenomics.com/support/software/cell-ranger/advanced/cr-command-line-arguments#count
+    """  # noqa: E501
+    input = "fastqs:files"
+    output = """outdir:dir:
+        {%- set fastqs = in.fastqs -%}
+        {%- if len(fastqs) == 1 and isdir(fastqs[0]) -%}
+            {%- set fastqs = fastqs[0] | glob: "*.fastq.gz" -%}
+        {%- endif -%}
+        {%- set sample = commonprefix(*fastqs) |
+            regex_replace: "_L\\d+_$", "" |
+            regex_replace: "_S\\d+$", "" -%}
+        {{- sample -}}
+    """
+    lang = config.lang.python
+    envs = {
+        "ncores": config.misc.ncores,
+        "cellranger": config.exe.cellranger,
+        "ref": config.ref.ref_cellranger_gex,
+        "tmpdir": config.path.tmpdir,
+        "include_introns": "true",
+    }
+    script = "file://../scripts/cellranger/CellRangerCount.py"
+    plugin_opts = {
+        "report": "file://../reports/cellranger/CellRangerCount.svelte",
+    }
+
+
+class CellRangerVdj(Proc):
+    """Run cellranger vdj
+
+    to perform sequence assembly and paired clonotype calling
+
+    Input:
+        fastqs: The input fastq files
+            Either a list of fastq files or a directory containing fastq files
+            If a directory is provided, it should be passed as a list with one
+            element.
+
+    Output:
+        outdir: The output directory
+
+    Envs:
+        ncores: Number of cores to use
+        cellranger: Path to cellranger
+        ref: Path of folder containing 10x-compatible transcriptome reference
+        tmpdir: Path to temporary directory, used to save the soft-lined fastq files
+            to pass to cellranger
+        <more>: Other environment variables required by `cellranger vdj`
+            See `cellranger vdj --help` for more details or
+            https://www.10xgenomics.com/support/software/cell-ranger/advanced/cr-command-line-arguments#vdj
+    """  # noqa: E501
+    input = "fastqs:files"
+    output = """outdir:dir:
+        {%- set fastqs = in.fastqs -%}
+        {%- if len(fastqs) == 1 and isdir(fastqs[0]) -%}
+            {%- set fastqs = fastqs[0] | glob: "*.fastq.gz" -%}
+        {%- endif -%}
+        {%- set sample = commonprefix(*fastqs) |
+            regex_replace: "_L\\d+_$", "" |
+            regex_replace: "_S\\d+$", "" -%}
+        {{- sample -}}
+    """
+    lang = config.lang.python
+    envs = {
+        "ncores": config.misc.ncores,
+        "cellranger": config.exe.cellranger,
+        "ref": config.ref.ref_cellranger_vdj,
+        "tmpdir": config.path.tmpdir,
+    }
+    script = "file://../scripts/cellranger/CellRangerVdj.py"
+    plugin_opts = {
+        "report": "file://../reports/cellranger/CellRangerVdj.svelte",
+    }

biopipen/ns/scrna.py

@@ -1422,6 +1422,8 @@ class CellTypeAnnotation(Proc):
             If the length of `cell_types` is shorter than the number of
             clusters, the remaining clusters will be kept as the original cell
             types.
+            You can also use `NA` to remove the clusters from downstream analysis. This
+            only works when `envs.newcol` is not specified.
 
             /// Note
             If `tool` is `direct` and `cell_types` is not specified or an empty list,

biopipen/reports/cellranger/CellRangerCount.svelte

@@ -0,0 +1,16 @@
+{% from "utils/misc.liq" import report_jobs, table_of_images -%}
+
+{%- macro report_job(job, h=1) -%}
+    <h{{h}}>{{job.out.outdir | basename | escape}}</h{{h}}>
+    <iframe
+        src="{{job.out.outdir}}/outs/web_summary.html"
+        width="100%"
+        frameborder="0"
+        style="min-height: 80vh"></iframe>
+{%- endmacro -%}
+
+{%- macro head_job(job) -%}
+    <h1>{{job.out.outdir | basename | escape}}</h1>
+{%- endmacro -%}
+
+{{ report_jobs(jobs, head_job, report_job) }}

biopipen/reports/cellranger/CellRangerVdj.svelte

@@ -0,0 +1,16 @@
+{% from "utils/misc.liq" import report_jobs, table_of_images -%}
+
+{%- macro report_job(job, h=1) -%}
+    <h{{h}}>{{job.out.outdir | basename | escape}}</h{{h}}>
+    <iframe
+        src="{{job.out.outdir}}/outs/web_summary.html"
+        width="100%"
+        frameborder="0"
+        style="min-height: 80vh"></iframe>
+{%- endmacro -%}
+
+{%- macro head_job(job) -%}
+    <h1>{{job.out.outdir | basename | escape}}</h1>
+{%- endmacro -%}
+
+{{ report_jobs(jobs, head_job, report_job) }}

biopipen/scripts/cellranger/CellRangerCount.py

@@ -0,0 +1,79 @@
+import uuid
+import re
+from pathlib import Path
+from biopipen.utils.misc import run_command
+
+fastqs = {{in.fastqs | repr}}  # pyright: ignore  # noqa
+outdir = {{out.outdir | quote}}  # pyright: ignore
+
+cellranger = {{envs.cellranger | quote}}  # pyright: ignore
+tmpdir = Path({{envs.tmpdir | quote}})  # pyright: ignore
+ref = {{envs.ref | quote}}  # pyright: ignore
+ncores = {{envs.ncores | int}}  # pyright: ignore
+
+{% if "id" in envs -%}
+id = {{envs.id | quote}}  # pyright: ignore
+{%- else -%}
+id = {{out.outdir | basename | quote}}  # pyright: ignore
+{%- endif %}
+
+{% if "sample" in envs -%}
+sample = {{envs.sample | quote}}  # pyright: ignore
+{%- else -%}
+sample = {{out.outdir | basename | quote}}  # pyright: ignore
+{%- endif %}
+
+# create a temporary unique directory to store the soft-linked fastq files
+fastqdir = tmpdir / f"cellranger_count_{uuid.uuid4()}"
+fastqdir.mkdir(parents=True, exist_ok=True)
+if len(fastqs) == 1 and fastqs[0].is_dir():
+    fastqs = list(fastqs[0].glob("*.fastq.gz"))
+
+# soft-link the fastq files to the temporary directory
+for fastq in fastqs:
+    fastq = Path(fastq)
+    (fastqdir / fastq.name).symlink_to(fastq)
+
+other_args = {{envs | dict_to_cli_args: dashify=True, exclude=['cellranger', 'transcriptome', 'ref', 'tmpdir', 'id', 'sample', 'ncores']}}  # pyright: ignore
+
+command = [
+    cellranger,
+    "count",
+    "--id",
+    id,
+    "--sample",
+    sample,
+    "--fastqs",
+    fastqdir,
+    "--transcriptome",
+    ref,
+    "--localcores",
+    ncores,
+    "--disable-ui",
+    *other_args,
+]
+
+run_command(command, fg=True, cwd=str(Path(outdir).parent))
+
+web_summary_html = Path(outdir) / "outs" / "web_summary.html"
+if not web_summary_html.exists():
+    raise RuntimeError(
+        f"web_summary.html does not exist in {outdir}/outs. "
+        "cellranger count failed."
+    )
+
+# Modify web_summary.html to move javascript to a separate file
+# to void vscode live server breaking the page by injecting some code
+print("# Modify web_summary.html to move javascript to a separate file")
+try:
+    web_summary_js = Path(outdir) / "outs" / "web_summary.js"
+    web_summary_content = web_summary_html.read_text()
+    regex = re.compile(r"<script>(?=/\*! For license)(.+)</script>", re.DOTALL)
+    web_summary_html.write_text(regex.sub(
+        '<script src="web_summary.js"></script>',
+        web_summary_content,
+    ))
+    web_summary_js.write_text(regex.search(web_summary_content).group(1))
+except Exception as e:
+    print(f"Error modifying web_summary.html: {e}")
+    raise e

biopipen/scripts/cellranger/CellRangerVdj.py

@@ -0,0 +1,79 @@
+import uuid
+import re
+from pathlib import Path
+from biopipen.utils.misc import run_command
+
+fastqs = {{in.fastqs | repr}}  # pyright: ignore  # noqa
+outdir = {{out.outdir | quote}}  # pyright: ignore
+
+cellranger = {{envs.cellranger | quote}}  # pyright: ignore
+tmpdir = Path({{envs.tmpdir | quote}})  # pyright: ignore
+ref = {{envs.ref | quote}}  # pyright: ignore
+ncores = {{envs.ncores | int}}  # pyright: ignore
+
+{% if "id" in envs -%}
+id = {{envs.id | quote}}  # pyright: ignore
+{%- else -%}
+id = {{out.outdir | basename | quote}}  # pyright: ignore
+{%- endif %}
+
+{% if "sample" in envs -%}
+sample = {{envs.sample | quote}}  # pyright: ignore
+{%- else -%}
+sample = {{out.outdir | basename | quote}}  # pyright: ignore
+{%- endif %}
+
+# create a temporary unique directory to store the soft-linked fastq files
+fastqdir = tmpdir / f"cellranger_count_{uuid.uuid4()}"
+fastqdir.mkdir(parents=True, exist_ok=True)
+if len(fastqs) == 1 and fastqs[0].is_dir():
+    fastqs = list(fastqs[0].glob("*.fastq.gz"))
+
+# soft-link the fastq files to the temporary directory
+for fastq in fastqs:
+    fastq = Path(fastq)
+    (fastqdir / fastq.name).symlink_to(fastq)
+
+other_args = {{envs | dict_to_cli_args: dashify=True, exclude=['cellranger', 'reference', 'ref', 'tmpdir', 'id', 'sample', 'ncores']}}  # pyright: ignore
+
+command = [
+    cellranger,
+    "vdj",
+    "--id",
+    id,
+    "--sample",
+    sample,
+    "--fastqs",
+    fastqdir,
+    "--reference",
+    ref,
+    "--localcores",
+    ncores,
+    "--disable-ui",
+    *other_args,
+]
+
+run_command(command, fg=True, cwd=str(Path(outdir).parent))
+
+web_summary_html = Path(outdir) / "outs" / "web_summary.html"
+if not web_summary_html.exists():
+    raise RuntimeError(
+        f"web_summary.html does not exist in {outdir}/outs. "
+        "cellranger vdj failed."
+    )
+
+# Modify web_summary.html to move javascript to a separate file
+# to void vscode live server breaking the page by injecting some code
+print("# Modify web_summary.html to move javascript to a separate file")
+try:
+    web_summary_js = Path(outdir) / "outs" / "web_summary.js"
+    web_summary_content = web_summary_html.read_text()
+    regex = re.compile(r"<script>(?=/\*! For license)(.+)</script>", re.DOTALL)
+    web_summary_html.write_text(regex.sub(
+        '<script src="web_summary.js"></script>',
+        web_summary_content,
+    ))
+    web_summary_js.write_text(regex.search(web_summary_content).group(1))
+except Exception as e:
+    print(f"Error modifying web_summary.html: {e}")
+    raise e

biopipen/scripts/scrna/CellTypeAnnotation-direct.R

@@ -1,47 +1,54 @@
 source("{{biopipen_dir}}/utils/misc.R")
 library(Seurat)
 
-sobjfile = {{in.sobjfile | r}}
-outfile = {{out.outfile | r}}
-celltypes = {{envs.cell_types | r}}
-newcol = {{envs.newcol | r}}
+sobjfile <- {{in.sobjfile | r}}
+outfile <- {{out.outfile | r}}
+celltypes <- {{envs.cell_types | r}}
+newcol <- {{envs.newcol | r}}
 
 if (is.null(celltypes) || length(celltypes) == 0) {
-    warning("No cell types are given!")
+    log_warn("No cell types are given!")
 
     # create a symbolic link to the input file
     file.symlink(sobjfile, outfile)
 } else {
-    sobj = readRDS(sobjfile)
-    idents = as.character(unique(Idents(sobj)))
-    idents = idents[order(as.numeric(idents))]
+    log_info("Loading Seurat object ...")
+    sobj <- readRDS(sobjfile)
+    idents <- as.character(unique(Idents(sobj)))
+    idents <- idents[order(as.numeric(idents))]
 
     if (length(celltypes) < length(idents)) {
-        celltypes = c(celltypes, idents[(length(celltypes) + 1):length(idents)])
+        celltypes <- c(celltypes, idents[(length(celltypes) + 1):length(idents)])
     } else if (length(celltypes) > length(idents)) {
-        celltypes = celltypes[1:length(idents)]
-        warning(
-            "The length of cell types is longer than the number of clusters!",
-            immediate. = TRUE
-        )
+        celltypes <- celltypes[1:length(idents)]
+        log_warn("The length of cell types is longer than the number of clusters!")
     }
     for (i in seq_along(celltypes)) {
         if (celltypes[i] == "-" || celltypes[i] == "") {
-            celltypes[i] = idents[i]
+            celltypes[i] <- idents[i]
         }
     }
-    names(celltypes) = idents
+    names(celltypes) <- idents
 
+    log_info("Renaming cell types ...")
     if (is.null(newcol)) {
-        sobj$seurat_clusters_id = Idents(sobj)
-        celltypes$object = sobj
-        sobj = do_call(RenameIdents, celltypes)
-        sobj$seurat_clusters = Idents(sobj)
+        has_na <- "NA" %in% unlist(celltypes) || anyNA(unlist(celltypes))
+        sobj$seurat_clusters_id <- Idents(sobj)
+        celltypes$object <- sobj
+        sobj <- do_call(RenameIdents, celltypes)
+        sobj$seurat_clusters <- Idents(sobj)
+        if (has_na) {
+            log_info("Filtering clusters if NA ...")
+            sobj <- subset(
+                sobj,
+                subset = seurat_clusters != "NA" & !is.na(seurat_clusters)
+            )
+        }
     } else {
-        celltypes$object = sobj
-        sobj = do_call(RenameIdents, celltypes)
-        sobj[[newcol]] = Idents(sobj)
-        Idents(sobj) = "seurat_clusters"
+        celltypes$object <- sobj
+        sobj <- do_call(RenameIdents, celltypes)
+        sobj[[newcol]] <- Idents(sobj)
+        Idents(sobj) <- "seurat_clusters"
     }
 
     saveRDS(sobj, outfile)

biopipen/scripts/scrna/CellsDistribution.R

@@ -142,13 +142,8 @@ do_case <- function(name, case) {
     info <- casename_info(name, create = TRUE)
     cells_by <- trimws(strsplit(case$cells_by, ",")[[1]])
 
-    sec_case_names <- strsplit(name, ":")[[1]]
-    sec_dir <- file.path(outdir, sec_case_names[1])
-    casename <- paste(sec_case_names[-1], collapse = ":")
-    dir.create(sec_dir, showWarnings = FALSE, recursive = TRUE)
-
-    outfile <- file.path(info$sec_dir, paste0("case-", info$case_slug, ".png"))
-    txtfile <- file.path(info$sec_dir, paste0("case-", info$case_slug, ".txt"))
+    outfile <- file.path(info$sec_dir, paste0(info$case_slug, ".png"))
+    txtfile <- file.path(info$sec_dir, paste0(info$case_slug, ".txt"))
 
     # subset the seurat object
     meta <- srtobj@meta.data
@@ -242,7 +237,7 @@ do_case <- function(name, case) {
         ),
         txtfile,
         sep = "\t",
-        row.names = TRUE,
+        row.names = FALSE,
         col.names = TRUE,
         quote = FALSE
     )

biopipen/scripts/scrna/MarkersFinder.R

@@ -143,11 +143,13 @@ for (name in names(cases)) {
     } else if (is.null(case$each)) {
         # is.null(case$ident.1)
         sections <- c(sections, name)
-        idents <- srtobj@meta.data %>% pull(case$group.by) %>% unique() %>% na.omit()
-        for (ident in idents) {
-            newcases[[paste0(name, ":", ident)]] <- case
-            newcases[[paste0(name, ":", ident)]]$ident.1 <- ident
-        }
+        newcases[[name]] <- case
+        newcases[[name]]$findall <- TRUE
+        # idents <- srtobj@meta.data %>% pull(case$group.by) %>% unique() %>% na.omit()
+        # for (ident in idents) {
+        #     newcases[[paste0(name, ":", ident)]] <- case
+        #     newcases[[paste0(name, ":", ident)]]$ident.1 <- ident
+        # }
     } else {
         eachs <- srtobj@meta.data %>% pull(case$each) %>% unique() %>% na.omit()
         for (each in eachs) {
@@ -160,18 +162,22 @@ for (name in names(cases)) {
                 )
             )
             if (is.null(case$ident.1)) {
-                idents <- srtobj@meta.data %>% pull(case$group.by) %>% unique() %>% na.omit()
-                for (ident in idents) {
-                    kname <- if (name == "DEFAULT") "" else paste0(" - ", name)
-                    sections <- c(sections, paste0(each, kname))
-                    key <- paste0(each, kname, ":", ident)
-                    if (case$prefix_each) {
-                        key <- paste0(case$each, " - ", key)
-                    }
-                    newcases[[key]] <- case
-                    newcases[[key]]$ident.1 <- ident
-                    newcases[[key]]$group.by <- by
-                }
+                kname <- if (name == "DEFAULT") "" else paste0(" - ", name)
+                sections <- c(sections, paste0(each, kname))
+                key <- paste0(each, kname)
+                newcases[[key]] <- case
+                newcases[[key]]$group.by <- by
+                newcases[[key]]$findall <- TRUE
+                # idents <- srtobj@meta.data %>% pull(case$group.by) %>% unique() %>% na.omit()
+                # for (ident in idents) {
+                #     key <- paste0(each, kname, ":", ident)
+                #     if (case$prefix_each) {
+                #         key <- paste0(case$each, " - ", key)
+                #     }
+                #     newcases[[key]] <- case
+                #     newcases[[key]]$ident.1 <- ident
+                #     newcases[[key]]$group.by <- by
+                # }
             } else {
                 sections <- c(sections, case$each)
                 key <- paste0(case$each, ":", each)
@@ -312,11 +318,11 @@ do_enrich <- function(info, markers, sig, volgenes) {
 }
 
 
-do_dotplot <- function(info, siggenes, case, args) {
-    dotplot_devpars <- case$dotplot$devpars
+do_dotplot <- function(info, siggenes, dotplot, args) {
+    dotplot_devpars <- dotplot$devpars
     if (is.null(args$ident.2)) {
-        case$dotplot$object <- args$object
-        case$dotplot$object@meta.data <- case$dotplot$object@meta.data %>%
+        dotplot$object <- args$object
+        dotplot$object@meta.data <- dotplot$object@meta.data %>%
             mutate(
                 !!sym(args$group.by) := if_else(
                     !!sym(args$group.by) == args$ident.1,
@@ -329,17 +335,16 @@ do_dotplot <- function(info, siggenes, case, args) {
                 )
             )
     } else {
-        case$dotplot$object <- args$object %>%
+        dotplot$object <- args$object %>%
             filter(!!sym(args$group.by) %in% c(args$ident.1, args$ident.2)) %>%
             mutate(!!sym(args$group.by) := factor(
                 !!sym(args$group.by),
                 levels = c(args$ident.1, args$ident.2)
             ))
     }
-    case$dotplot$devpars <- NULL
-    case$dotplot$features <- siggenes
-    case$dotplot$group.by <- args$group.by
-    case$dotplot$assay <- case$assay
+    dotplot$devpars <- NULL
+    dotplot$features <- siggenes
+    dotplot$group.by <- args$group.by
     dotplot_width = ifelse(
         is.null(dotplot_devpars$width),
         if (length(siggenes) <= 20) length(siggenes) * 60 else length(siggenes) * 30,
@@ -351,7 +356,7 @@ do_dotplot <- function(info, siggenes, case, args) {
     png(dotplot_file, res = dotplot_res, width = dotplot_height, height = dotplot_width)
     # rotate x axis labels
     print(
-        do_call(DotPlot, case$dotplot) +
+        do_call(DotPlot, dotplot) +
         theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
         coord_flip()
     )
@@ -456,9 +461,79 @@ add_case_report <- function(info, sigmarkers, siggenes) {
 }
 
 
+do_case_findall <- function(casename) {
+    log_info("- Using FindAllMarkers for case: {casename}...")
+
+    case = cases[[casename]]
+    args <- case$rest
+    args$group.by <- case$group.by
+    if (is.null(args$logfc.threshold)) {
+        args$locfc.threshold <- 0
+    }
+    if (is.null(args$min.cells.group)) {
+        args$min.cells.group <- 1
+    }
+    if (is.null(args$min.cells.feature)) {
+        args$min.cells.feature <- 1
+    }
+    if (is.null(args$min.pct)) {
+        args$min.pct <- 0
+    }
+    if (!is.null(case$subset)) {
+        args$object <- srtobj %>% filter(!!parse_expr(case$subset) & filter(!is.na(!!sym(case$group.by))))
+    } else {
+        args$object <- srtobj %>% filter(!is.na(!!sym(case$group.by)))
+    }
+    Idents(args$object) <- case$group.by
+    markers <- tryCatch({
+        do_call(FindAllMarkers, args)
+        # gene, p_val, avg_log2FC, pct.1, pct.2, p_val_adj, cluster
+    }, error = function(e) {
+        log_warn(e$message)
+        data.frame(
+            gene = character(),
+            p_val = numeric(),
+            avg_log2FC = numeric(),
+            pct.1 = numeric(),
+            pct.2 = numeric(),
+            p_val_adj=numeric(),
+            cluster = character()
+        )
+    })
+
+    if (is.null(case$dotplot$assay)) {
+        case$dotplot$assay <- assay
+    }
+    idents <- unique(markers$cluster)
+    for (ident in idents) {
+        log_info("- Dealing with ident: {ident}...")
+        info <- casename_info(paste0(casename, ":", ident), create = TRUE)
+        siggenes <- do_enrich(info, markers %>% filter(cluster == ident), case$sigmarkers, case$volcano_genes)
+
+        if (length(siggenes) > 0) {
+            args$ident.1 <- as.character(ident)
+            do_dotplot(info, siggenes, case$dotplot, args)
+        }
+        add_case_report(info, case$sigmarkers, siggenes)
+
+        if (info$section %in% overlap) {
+            if (is.null(overlaps[[info$section]])) {
+                overlaps[[info$section]] <<- list()
+            }
+            overlaps[[info$section]][[info$case]] <<- siggenes
+        }
+    }
+}
+
+
 do_case <- function(casename) {
     log_info("Dealing with case: {casename}...")
 
+    if (isTRUE(cases[[casename]]$findall)) {
+        do_case_findall(casename)
+        return()
+    }
+
     info <- casename_info(casename, create = TRUE)
     case <- cases[[casename]]
     # ident1
@@ -507,7 +582,10 @@ do_case <- function(casename) {
     siggenes <- do_enrich(info, markers, case$sigmarkers, case$volcano_genes)
 
     if (length(siggenes) > 0) {
-        do_dotplot(info, siggenes, case, args)
+        if (is.null(case$dotplot$assay)) {
+            case$dotplot$assay <- assay
+        }
+        do_dotplot(info, siggenes, case$dotplot, args)
     }
 
     if (info$section %in% overlap) {

biopipen/scripts/scrna/SeuratClusterStats-features.R

@@ -173,8 +173,8 @@ do_one_features = function(name) {
             rownames_to_column("Feature") %>%
             select(Feature, everything())
 
-        exprfile = paste0(slugify(name), ".txt")
-        write.table(expr, file.path(odir, exprfile), sep="\t", quote=FALSE, row.names=FALSE)
+        exprfile = file.path(odir, paste0(slugify(name), ".txt"))
+        write.table(expr, exprfile, sep="\t", quote=FALSE, row.names=FALSE)
 
         add_report(
             list(

biopipen/utils/common_docstrs.py

@@ -46,11 +46,14 @@ Those functions take following arguments:
 * `group-by`: The column name in metadata to group the cells.
 * `idents`: The first group or both groups of cells to compare (value in `group-by` column). If only the first group is given, the rest of the cells (with non-NA in `group-by` column) will be used as the second group.
 * `subset`: An expression to subset the cells, will be passed to `dplyr::filter()`. Default is `TRUE` (no filtering).
+* `each`: A column name (without quotes) in metadata to split the cells.
+    Each comparison will be done for each value in this column.
 * `id`: The column name in metadata for the group ids (i.e. `CDR3.aa`).
 * `compare`: Either a (numeric) column name (i.e. `Clones`) in metadata to compare between groups, or `.n` to compare the number of cells in each group.
     If numeric column is given, the values should be the same for all cells in the same group.
     This will not be checked (only the first value is used).
 * `uniq`: Whether to return unique ids or not. Default is `TRUE`. If `FALSE`, you can mutate the meta data frame with the returned ids. For example, `df |> mutate(expanded = expanded(...))`.
+* `debug`: Return the data frame with intermediate columns instead of the ids. Default is `FALSE`.
 * `order`: The order of the returned ids. It could be `sum` or `diff`, which is the sum or diff of the `compare` between idents.
     Two kinds of modifiers can be added, including `desc` and `abs`.
     For example, `sum,desc` means the sum of `compare` between idents in descending order.

biopipen/utils/mutate_helpers.R

@@ -1,6 +1,7 @@
 suppressPackageStartupMessages(library(rlang))
 suppressPackageStartupMessages(library(tidyselect))
 suppressPackageStartupMessages(library(dplyr))
+suppressPackageStartupMessages(library(tidyr))
 
 #' Get expanded, collapsed, emerged or vanished clones from a meta data frame
 #'
@@ -15,6 +16,8 @@ suppressPackageStartupMessages(library(dplyr))
 #'  be used as `ident_2`.
 #' @param subset An expression to subset the cells, will be passed to
 #'  `dplyr::filter()`. Default is `TRUE` (no filtering).
+#' @param each A column name (without quotes) in metadata to split the cells.
+#'  Each comparison will be done for each value in this column.
 #' @param id The column name (without quotes) in metadata for the
 #'  group ids (i.e. `CDR3.aa`)
 #' @param compare Either a (numeric) column name (i.e. `Clones`, without quotes)
@@ -25,6 +28,7 @@ suppressPackageStartupMessages(library(dplyr))
 #' @param uniq Whether to return unique ids or not. Default is `TRUE`.
 #'  If `FALSE`, you can mutate the meta data frame with the returned ids.
 #'  For example, `df %>% mutate(expanded = expanded(...))`.
+#' @param debug Return the transformed data frame with counts, predicates, sum, and diff.
 #' @param order The order of the returned ids. It could be `sum` or `diff`,
 #'  which is the sum or diff of the `compare` between idents. Two kinds of
 #'  modifiers can be added, including `desc` and `abs`. For example,
@@ -82,8 +86,10 @@ suppressPackageStartupMessages(library(dplyr))
     id,
     compare,
     fun,
+    each,
     uniq,
-    order
+    order,
+    debug
 ) {
     if (length(idents) == 1) {
         ident_1 <- idents[1]
@@ -119,100 +125,82 @@ suppressPackageStartupMessages(library(dplyr))
 
     if (!compare_is_count && !compare_label %in% colnames(df)) {
         stop(paste0(
-            "`compare` must be either a column name in df, or 'count'/'n'. ",
+            "`compare` must be either a column name in df, or 'count'/'.n'. ",
             'Got "',
             compare_label,
             '"'
         ))
     }
 
-    predicate <- function(comp) {
+    predicate <- function(ident_1, ident_2) {
         if (fun == "expanded") {
-            comp[1] > comp[2] && comp[2] > 0
+            ident_1 > ident_2 && ident_2 > 0
         } else if (fun == "expanded+") {
-            comp[1] > comp[2]
+            ident_1 > ident_2
         } else if (fun == "collapsed") {
-            comp[1] < comp[2] && comp[1] > 0
+            ident_1 < ident_2 && ident_1 > 0
         } else if (fun == "collapsed+") {
-            comp[1] < comp[2]
+            ident_1 < ident_2
         } else if (fun == "emerged") {
-            comp[1] > 0 && comp[2] == 0
+            ident_1 > 0 && ident_2 == 0
         } else if (fun == "vanished") {
-            comp[1] == 0 && comp[2] > 0
+            ident_1 == 0 && ident_2 > 0
         }
     }
 
     # subset the data frame
-    trans <- df %>% dplyr::filter(!!subset) %>%
-        # remove NA values in group.by column
-        dplyr::filter(!is.na(!!group.by)) %>%
-        # mark the group.by column (as ..group) as ident_1 or ident_2 or NA
+    trans <- df %>%
+        dplyr::filter(!!subset) %>%
+        drop_na(!!id) %>%
+        # # remove NA values in group.by column
+        # dplyr::filter(!is.na(!!group.by)) %>%
+        # mark the group.by column (as .group) as ident_1 or ident_2 or NA
         mutate(
-            ..group = if_else(
+            .group = if_else(
                 !!group.by == ident_1,
                 "ident_1",
                 if_else(ident_2 != "<NULL>" & !!group.by != ident_2, NA, "ident_2")
             )
         ) %>%
         # remove NA values in ..group column
-        dplyr::filter(!is.na(..group)) %>%
-        # for each clone and group (ident_1 and ident_2)
-        group_by(!!id, ..group) %>%
-        # summarise the number of cells in each clone and group
-        # so that we can compare between groups later
-        summarise(
-            ..compare = ifelse(compare_is_count, n(), first(!!compare)),
-            .groups = "drop"
-        ) %>%
-        # for each clone, either compare Clones or ..count between groups
-        # (ident_1 and ident_2)
-        group_by(!!id) %>%
-        # add missing group (either ident_1 or ident_2)
-        group_modify(function(d, ...) {
-            if (nrow(d) == 1) {
-                d <- d %>% add_row(
-                    ..group = ifelse(
-                        d$..group == "ident_1", "ident_2", "ident_1"
-                    ),
-                    ..compare = 0
-                )
-            }
-            d
-        }) %>%
-        # make sure ident_1 and ident_2 are in order
-        arrange(..group, .by_group = TRUE) %>%
+        drop_na(.group)
+
+    if (is.null(each)) {
+        trans <- trans %>% group_by(!!id, .group)
+    } else {
+        trans <- trans %>% group_by(!!each, !!id, .group)
+    }
+
+    if (compare_is_count) {
+        trans <- trans %>% summarise(.n = n(), .groups = "drop")
+    } else {
+        trans <- trans %>% summarise(.n = first(!!compare), .groups = "drop")
+    }
+
+    trans <- trans %>% pivot_wider(names_from = .group, values_from = .n) %>%
+        replace_na(list(ident_1 = 0, ident_2 = 0)) %>%
+        rowwise() %>%
         # add the predicates, sums and diffs
-        summarise(
-            ..predicate = predicate(..compare),
-            ..sum = sum(..compare),
-            ..diff = ..compare[1] - ..compare[2]
+        mutate(
+            .predicate = predicate(ident_1, ident_2),
+            .sum = ident_1 + ident_2,
+            .diff = ident_1 - ident_2
         ) %>%
-        # filter the clones
-        dplyr::filter(..predicate)
+        ungroup() %>%
+        arrange(!!order)
 
-    order_sum <- grepl("sum", order)
-    order_diff <- grepl("diff", order)
-    order_desc <- grepl("desc", order)
-    order_abs <- grepl("abs", order)
-    if (order_sum && !order_desc) {
-        out <- trans %>% arrange(..sum) %>% pull(!!id)
-    } else if (order_sum) {
-        out <- trans %>% arrange(desc(..sum)) %>% pull(!!id)
-    } else if (order_diff && !order_desc && !order_abs) {
-        out <- trans %>% arrange(..diff) %>% pull(!!id)
-    } else if (order_diff && !order_desc && order_abs) {
-        out <- trans %>% arrange(abs(..diff)) %>% pull(!!id)
-    } else if (order_diff && order_desc && !order_abs) {
-        out <- trans %>% arrange(desc(..diff)) %>% pull(!!id)
-    } else if (order_diff && order_desc && order_abs) {
-        out <- trans %>% arrange(desc(abs(..diff))) %>% pull(!!id)
-    } else {
-        out <- trans %>% pull(!!id)
+    if (debug) {
+        return(trans)
     }
 
-    if (uniq) { return(out) }
+    uniq_ids <- trans %>% filter(.predicate) %>% pull(!!id) %>% as.vector() %>% unique()
+    if (uniq) {
+        return(uniq_ids)
+    }
 
-    df %>% mutate(..out = if_else(!!id %in% out, !!id, NA)) %>% pull(..out)
+    out <- df %>% pull(!!id)
+    out[!out %in% uniq_ids] <- NA
+    out
 }
 
 #' @export
@@ -221,10 +209,12 @@ expanded <- function(
     group.by, # nolint
     idents,
     subset = TRUE,
+    each = NULL,
     id = CDR3.aa,
-    compare = Clones,
+    compare = .n,
     uniq = TRUE,
-    order = "diff+desc",
+    debug = FALSE,
+    order = desc(.sum),
     include_emerged = FALSE
 ) {
     lbl <- as_label(enquo(df))
@@ -233,15 +223,17 @@ expanded <- function(
     }
     fun = if (include_emerged) "expanded+" else "expanded"
     .size_compare(
-        df,
-        enquo(group.by),
-        idents,
-        enquo(subset),
-        enquo(id),
-        enquo(compare),
-        fun,
+        df = df,
+        group.by = enquo(group.by),
+        idents = idents,
+        subset = enquo(subset),
+        id = enquo(id),
+        compare = enquo(compare),
+        fun = fun,
+        each = tryCatch(enquo(each), error = function(e) NULL),
         uniq = uniq,
-        order = order
+        order = enexpr(order),
+        debug = debug
     )
 }
 
@@ -251,10 +243,12 @@ collapsed <- function(
     group.by, # nolint
     idents,
     subset = TRUE,
+    each = NULL,
     id = CDR3.aa,
-    compare = Clones,
+    compare = .n,
     uniq = TRUE,
-    order = "diff+desc",
+    debug = FALSE,
+    order = desc(.sum),
     include_vanished = FALSE
 ) {
     lbl <- as_label(enquo(df))
@@ -263,15 +257,17 @@ collapsed <- function(
     }
     fun = if (include_vanished) "collapsed+" else "collapsed"
     .size_compare(
-        df,
-        enquo(group.by),
-        idents,
-        enquo(subset),
-        enquo(id),
-        enquo(compare),
-        fun,
+        df = df,
+        group.by = enquo(group.by),
+        idents = idents,
+        subset = enquo(subset),
+        id = enquo(id),
+        compare = enquo(compare),
+        fun = fun,
+        each = tryCatch(enquo(each), error = function(e) NULL),
         uniq = uniq,
-        order = order
+        order = enexpr(order),
+        debug = debug
     )
 }
 
@@ -281,25 +277,29 @@ emerged <- function(
     group.by, # nolint
     idents,
     subset = TRUE,
+    each = NULL,
     id = CDR3.aa,
-    compare = Clones,
+    compare = .n,
     uniq = TRUE,
-    order = "diff+desc"
+    debug = FALSE,
+    order = desc(.sum)
 ) {
     lbl <- as_label(enquo(df))
     if (length(lbl) == 1 && lbl == ".") {
         df <- across(everything())
     }
     .size_compare(
-        df,
-        enquo(group.by),
-        idents,
-        enquo(subset),
-        enquo(id),
-        enquo(compare),
-        "emerged",
+        df = df,
+        group.by = enquo(group.by),
+        idents = idents,
+        subset = enquo(subset),
+        id = enquo(id),
+        compare = enquo(compare),
+        fun = "emerged",
+        each = tryCatch(enquo(each), error = function(e) NULL),
         uniq = uniq,
-        order = order
+        order = enexpr(order),
+        debug = debug
     )
 }
 
@@ -309,25 +309,29 @@ vanished <- function(
     group.by, # nolint
     idents,
     subset = TRUE,
+    each = NULL,
     id = CDR3.aa,
-    compare = Clones,
+    compare = .n,
     uniq = TRUE,
-    order = "diff+desc"
+    debug = FALSE,
+    order = desc(.sum)
 ) {
     lbl <- as_label(enquo(df))
     if (length(lbl) == 1 && lbl == ".") {
         df <- across(everything())
     }
     .size_compare(
-        df,
-        enquo(group.by),
-        idents,
-        enquo(subset),
-        enquo(id),
-        enquo(compare),
-        "vanished",
+        df = df,
+        group.by = enquo(group.by),
+        idents = idents,
+        subset = enquo(subset),
+        id = enquo(id),
+        compare = enquo(compare),
+        fun = "vanished",
+        each = tryCatch(enquo(each), error = function(e) NULL),
         uniq = uniq,
-        order = order
+        order = enexpr(order),
+        debug = debug
     )
 }
 

{biopipen-0.22.1.dist-info → biopipen-0.22.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.22.1
+Version: 0.22.2
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

{biopipen-0.22.1.dist-info → biopipen-0.22.2.dist-info}/RECORD

@@ -1,15 +1,16 @@
-biopipen/__init__.py,sha256=mjWPUw5WSKjOdLE532eMicR6Gvc0AStLxFjzYGRWcns,23
+biopipen/__init__.py,sha256=Bh5Z0gPzleot68P4r2qTs7W0HNi5DFO8t_uKNyCoA94,23
 biopipen/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/core/config.py,sha256=edK5xnDhM8j27srDzsxubi934NMrglLoKrdcC8qsEPk,1069
-biopipen/core/config.toml,sha256=JALO2S7TfmV3gIRPJ0cLTFWncPXXheQJS3vYQlyX6wQ,1600
+biopipen/core/config.toml,sha256=Rn7Cta7WsMtmQkKGC4h9d5dU_STaIVBgR8UliiGgL6o,1757
 biopipen/core/defaults.py,sha256=yPeehPLk_OYCf71IgRVCWuQRxLAMixDF81Ium0HtPKI,344
-biopipen/core/filters.py,sha256=5Qi7do0JT8_mwd80ddf4TgsX7yZh__ZpOex270Jjrbc,11037
+biopipen/core/filters.py,sha256=bsH5an2Wfk4JaEEYpa5xFLy9-QVN3fdA_nl7_ceSM68,11562
 biopipen/core/proc.py,sha256=7TsjBM7EEtMMB-w4jbxV_CSRY8J970gM8320Ga1YeHU,717
 biopipen/core/testing.py,sha256=5vR15kkCjfXM7Bx0HBzabNLtDLAEX4uU94TskCkPni8,1447
 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
 biopipen/ns/bed.py,sha256=UN38qUChDeE-ipuSBY8RVLwvJqM2wxSRmlhOiDo4JG0,5395
+biopipen/ns/cellranger.py,sha256=0A6pCpBLg1zKm2Ve2cXvGvNNK4lMqdsek2iTer5X_TI,3679
 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
@@ -19,7 +20,7 @@ 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/rnaseq.py,sha256=l4vFeRasGhkexopGTM_VfSyIFewOxg-9L5niFzhWUNA,565
-biopipen/ns/scrna.py,sha256=F5j1TmjsS2swwm-uDyT6sTys5pldIJ_M2hNITAQdflc,82728
+biopipen/ns/scrna.py,sha256=jLK_K90B36ZbmDZcR8PT2x1ntBpvxKHzeNhWYkrexhM,82876
 biopipen/ns/scrna_basic.py,sha256=Py90IveDI5Alm6FUeC89xp3W79VPRvAQctQpc5JtO2M,8639
 biopipen/ns/scrna_metabolic_landscape.py,sha256=dSL-y1Gx1fcgebX7vk3wcSbm9aBALfCZKz0vjcDxQ_8,28139
 biopipen/ns/tcgamaf.py,sha256=AFbUJIxiMSvsVY3RcHgjRFuMnNh2DG3Mr5slLNEyz6o,1455
@@ -29,6 +30,8 @@ biopipen/ns/web.py,sha256=3zucrDo-IVsSnIvlw-deoScuxqWa6OMTm8Vo-R4E44Q,2224
 biopipen/reports/bam/CNAClinic.svelte,sha256=D4IxQcgDCPQZMbXog-aZP5iJEQTK2N4i0C60e_iXyfs,213
 biopipen/reports/bam/CNVpytor.svelte,sha256=s03SlhbEPd8-_44Dy_cqE8FSErhUdqStLK39te5o7ZE,1364
 biopipen/reports/bam/ControlFREEC.svelte,sha256=OwN96RW0dN-gtQ1zWKbXYZCYkkrOC0RQmP3UG4x7zqU,837
+biopipen/reports/cellranger/CellRangerCount.svelte,sha256=oR7WzqY_FcjeCi5rir0qyUdUe09mkYBgg4-V1dB9ph4,478
+biopipen/reports/cellranger/CellRangerVdj.svelte,sha256=oR7WzqY_FcjeCi5rir0qyUdUe09mkYBgg4-V1dB9ph4,478
 biopipen/reports/cnv/AneuploidyScore.svelte,sha256=x0LbhqjauZpqMzmzDWmYgx-rEh5Tzo8qBrXcLcM0h78,1020
 biopipen/reports/cnv/AneuploidyScoreSummary.svelte,sha256=AWlns70mChJGhH3z8r5uXuI4tc7VbVN_cOUdqBr3ZKg,4414
 biopipen/reports/cnv/TMADScoreSummary.svelte,sha256=tJutaMOqeXxKroAosOIqOJVyhTTFet-soMwuOYVHTYU,2060
@@ -76,6 +79,8 @@ biopipen/scripts/bed/Bed2Vcf.py,sha256=u0mp_2Y4UtEA839zq9UENesH6Gyiwd4sZQW9wFnBV
 biopipen/scripts/bed/BedConsensus.py,sha256=gfAxuIalvCEpS0tiOyAJGPYGgHN0L-hm0K37Iteh5yw,2386
 biopipen/scripts/bed/BedLiftOver.sh,sha256=Y4gBsz9w4zhE29UmWojO6F4PXMMMWC1uCzjrxa19eOs,256
 biopipen/scripts/bed/BedtoolsMerge.py,sha256=TjKO5MpUzDj931bQAWku2660MVSiZzdMHt_v2Xbt0IE,355
+biopipen/scripts/cellranger/CellRangerCount.py,sha256=ZDcry8suLhulXiTsl01LGKmSJkewJ-TgHazLtfsBr6U,2516
+biopipen/scripts/cellranger/CellRangerVdj.py,sha256=-QbhPKqFBZ15Es6NJaU7Lwf1KQW_3Lyv0aISh-Urk2M,2504
 biopipen/scripts/cnv/AneuploidyScore.R,sha256=liAN8u8_lj8voJ01oBW9Dw09yi388KF5f_gwPOv0wdE,8437
 biopipen/scripts/cnv/AneuploidyScoreSummary.R,sha256=9Zni5zqYfzevs5XSAt3fqD9WZ_RWr_ByUnXReKLLWoY,12337
 biopipen/scripts/cnv/TMADScore.R,sha256=uCLHQR6sMt-4uVUAEJlJxYXlai9ZE5J7xBl0sl-EkjU,1065
@@ -105,26 +110,26 @@ biopipen/scripts/misc/Str2File.py,sha256=99oQNxChxChNJ9vmD77b48cu-r_P_heSpx7A5wi
 biopipen/scripts/plot/Heatmap.R,sha256=4v_oRME8ZiwczIlBIp-OP_YPWLAvBKzbHiwNBCZ0Xog,1982
 biopipen/scripts/plot/VennDiagram.R,sha256=GVc-kyHqnXrbXZvy-evcxI1XGtlLSChBiVnMjPywNMA,731
 biopipen/scripts/rnaseq/UnitConversion.R,sha256=9etSQ6ivtlrgSg4mLjViZAl8nUtCxfEROxXvFCpN9sg,1928
-biopipen/scripts/scrna/CellTypeAnnotation-direct.R,sha256=jBEc2OTjC4hbVCJJXzZ4KC9Db5W-7kfJ3N5U5rE05AQ,1449
+biopipen/scripts/scrna/CellTypeAnnotation-direct.R,sha256=Qp8w3-Xh67F6QHYzpTjWdSDdCVlhcjGjgoAi7PGUbmI,1797
 biopipen/scripts/scrna/CellTypeAnnotation-hitype.R,sha256=6_DBAlLKcHqaMyWGZWvTd4gFfHymfz9s2XLja8aj1qA,1869
 biopipen/scripts/scrna/CellTypeAnnotation-sccatch.R,sha256=1ejye0hs-EOwzzdP9gFWSLPcF6dOAA6VmNKXEjmS11E,1654
 biopipen/scripts/scrna/CellTypeAnnotation-sctype.R,sha256=u1eQsBWv1GKTbkwp6OFyiPuMFFcgwoa4-VI-d4q8nM4,3877
 biopipen/scripts/scrna/CellTypeAnnotation.R,sha256=6Le1SvZcKI8D0SLkFZ5SibGsW9ZWqirnBl3Q1BNZOuU,513
-biopipen/scripts/scrna/CellsDistribution.R,sha256=8bDwA1xQHCHnGRBW5XfW35BOpNLydxbWX93TId9vRa8,12908
+biopipen/scripts/scrna/CellsDistribution.R,sha256=shfgljiveRMrMM9GAbvemn9vSUCL9vNwTxH2Hiq9Yyk,12669
 biopipen/scripts/scrna/DimPlots.R,sha256=-mXOTMnpPxvR30XLjwcohFfFx7xTqWKKiICwJiD6yEo,1554
 biopipen/scripts/scrna/ExprImpution-alra.R,sha256=8wcyZk1Whf45SXsYOM_ykl8m-iBxr27KEjtslbl2JQQ,782
 biopipen/scripts/scrna/ExprImpution-rmagic.R,sha256=yYnkyVfqIaNynsbaZZLGS6DrAJ_XhVQj1Ox598w8yOY,651
 biopipen/scripts/scrna/ExprImpution-scimpute.R,sha256=mg40qCUW7-nP5oHPvARq7dmtoahM0GRFWXQpum0BXVk,1082
 biopipen/scripts/scrna/ExprImpution.R,sha256=7768ezrr59xUZDXq8lO9jj2XhnkSsx-xxBmOD9_DO7c,313
 biopipen/scripts/scrna/GeneExpressionInvistigation.R,sha256=FI5MWic3xRml2DN7ONcyT7pbceOnL30Zd4nBHRZRFNQ,3800
-biopipen/scripts/scrna/MarkersFinder.R,sha256=mPyKZcYcrhTjLqqp406-wkGZzpTUSBUQnDSsGJe-SL4,18669
+biopipen/scripts/scrna/MarkersFinder.R,sha256=v_PIhg-QcuaY_6F_sNGMkNohLmlZL_BkGNiXNPxRn6I,21137
 biopipen/scripts/scrna/MetaMarkers.R,sha256=3gZdMjO4sGQLq0XvlLooMrQUKEAIYUCTsxVHrkYe7HM,11119
 biopipen/scripts/scrna/ModuleScoreCalculator.R,sha256=0mLGoTvJRpTbCnmuYbYKqZnP3ZdJQkTn6getJddBKRs,2495
 biopipen/scripts/scrna/RadarPlots.R,sha256=1oicly0wxLaQDrDUojKtyCD052cYnMrBcW8TpbFY7wE,8535
 biopipen/scripts/scrna/SCImpute.R,sha256=dSJOHhmJ3x_72LBRXT72dbCti5oiB85CJ-OjWtqONbk,2958
 biopipen/scripts/scrna/ScFGSEA.R,sha256=wePSQYGjGv_InJEmi0Hf0zNt1gmqhkItjFqYE-wiYec,5999
 biopipen/scripts/scrna/SeuratClusterStats-dimplots.R,sha256=BknWb-5Vc_LHB3hlOgsAEooHObG6xoU1JV2KeNVrEGk,1623
-biopipen/scripts/scrna/SeuratClusterStats-features.R,sha256=NLdv5un_mntsNSukChUCXY3u41GARrNMqM4Ko0kN384,7705
+biopipen/scripts/scrna/SeuratClusterStats-features.R,sha256=ft1sSF2pXuDb4H2vSkPYuzcDgOOpXpCZGv9_17DdZN8,7705
 biopipen/scripts/scrna/SeuratClusterStats-stats.R,sha256=KSD4GSssj-UZeMlWPbHbCLyonACGhSvVwAD4jeoJ_60,4099
 biopipen/scripts/scrna/SeuratClusterStats.R,sha256=SO4AGgF95YoLvjGMiC6fb3OIQkXne2Lqt5G7n50JYJo,616
 biopipen/scripts/scrna/SeuratClustering.R,sha256=JBJkwZmdjMsWzHaa_WvYCN1tXQimgclmgAOj3VJ1b3A,9114
@@ -200,20 +205,20 @@ biopipen/scripts/vcf/VcfSplitSamples.py,sha256=GraKi7WluzDAvVVGljwd3Yif6MriniF8s
 biopipen/scripts/web/Download.py,sha256=WKC_t5ZEeJoKFyY9XwksHARcMbKmHMcxNEUDLMGJ0Cc,924
 biopipen/scripts/web/DownloadList.py,sha256=cZvdi3LVzlATiTvAXe0uuDDXGqB5jcR2zHrMLCEb2U8,1130
 biopipen/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-biopipen/utils/common_docstrs.py,sha256=7jnUhJ0GKV9YR6-wZYqycenGoQIz8Nol5auhKYuIGMM,3060
+biopipen/utils/common_docstrs.py,sha256=77whqrhTg6kA7XHW5s7RJT3tGLo-d0XzgPc3LriBdgI,3296
 biopipen/utils/gene.R,sha256=BzAwlLA8hO12vF-3t6IwEuTEeLa_jBll4zm_5qe3qoE,1243
 biopipen/utils/gene.py,sha256=qE_BqTayrJWxRdniffhcz6OhZcw9GUoOrj2EtFWH9Gw,2246
 biopipen/utils/gsea.R,sha256=o3RC-wejsfFXPXzRIpFw22F-aif27qnuKEPavvXIlkc,5794
 biopipen/utils/io.R,sha256=jIYdqdn0iRWfQYAZa5CjXi3fikqmYvPPLIXhobRe8sw,537
 biopipen/utils/misc.R,sha256=nkjiAsEsilq0AeiKRDNqrhTx-1Grqg-rFlkjOEOEDYg,5224
 biopipen/utils/misc.py,sha256=Pmh3CBiKJ3vC_RqorfOfRAvTVKXrGDJT8DMLfYbTivs,3055
-biopipen/utils/mutate_helpers.R,sha256=E4OcaMC7aqb6D6m3dXSDLdHhTZb8RUksjtFwHweMGF8,13219
+biopipen/utils/mutate_helpers.R,sha256=F_DYYjmmlPp2FppNIFUI1cNKsR2vUCwDn7NlvinasBQ,13068
 biopipen/utils/plot.R,sha256=pzl37PomNeUZPxohHZ2w93j3Fc4T0Qrc62FF-9MTKdw,4417
 biopipen/utils/reference.py,sha256=6bPSwQa-GiDfr7xLR9a5T64Ey40y24yn3QfQ5wDFZkU,4420
 biopipen/utils/rnaseq.R,sha256=Ro2B2dG-Z2oVaT5tkwp9RHBz4dp_RF-JcizlM5GYXFs,1298
 biopipen/utils/single_cell.R,sha256=bKduqOQjSC8BtZJuwfUShR49omoEMbB57n3Gi6dYlqA,4147
 biopipen/utils/vcf.py,sha256=ajXs0M_QghEctlvUlSRjWQIABVF02wPdYd-0LP4mIsU,9377
-biopipen-0.22.1.dist-info/METADATA,sha256=0PvmDBQ2Ffe1tvlcVMcEz5AdFbhLhPrswGpxHYXB5KM,886
-biopipen-0.22.1.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-biopipen-0.22.1.dist-info/entry_points.txt,sha256=sfI6oDEEuMvAg0KNujE9uu-c29y7IwQQA1_A2sUjPhc,527
-biopipen-0.22.1.dist-info/RECORD,,
+biopipen-0.22.2.dist-info/METADATA,sha256=vtGP0R0JZ3mSaEgRjhGbqNuLnbmYp1Rc7XoErM1JCxo,886
+biopipen-0.22.2.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+biopipen-0.22.2.dist-info/entry_points.txt,sha256=-rKo4gInvzqlh7_2oEVmEo9gKO9y1ba3rHWTWOM5xP4,561
+biopipen-0.22.2.dist-info/RECORD,,

{biopipen-0.22.1.dist-info → biopipen-0.22.2.dist-info}/entry_points.txt

@@ -2,6 +2,7 @@
 bam=biopipen.ns.bam
 bcftools=biopipen.ns.bcftools
 bed=biopipen.ns.bed
+cellranger=biopipen.ns.cellranger
 cnv=biopipen.ns.cnv
 cnvkit=biopipen.ns.cnvkit
 cnvkit_pipeline=biopipen.ns.cnvkit_pipeline