biopipen 0.27.9__tar.gz → 0.28.1__tar.gz

{biopipen-0.27.9 → biopipen-0.28.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.27.9
+Version: 0.28.1
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

biopipen-0.28.1/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.28.1"

{biopipen-0.27.9 → biopipen-0.28.1}/biopipen/ns/cellranger.py

@@ -7,12 +7,15 @@ class CellRangerCount(Proc):
     """Run cellranger count
 
     to count gene expression and/or feature barcode reads
+    requires cellranger v7+.
 
     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.
+        id: The id defining output directory. If not provided, it is inferred
+            from the fastq files.
 
     Output:
         outdir: The output directory
@@ -23,21 +26,28 @@ class CellRangerCount(Proc):
         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.
+        include_introns (flag): Set to false to exclude intronic reads in count.
+        create_bam (flag): Enable or disable BAM file generation.
+            This is required by cellrange v8+. When using cellrange v8-, it will be
+            transformed to `--no-bam`.
         <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"
+    input = "fastqs:files, id"
     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 -}}
+        {%- if in.id -%}
+            {{in.id}}
+        {%- else -%}
+            {%- set id = commonprefix(*fastqs) |
+                regex_replace: "_L\\d+(:?_.*)?$", "" |
+                regex_replace: "_S\\d+$", "" -%}
+            {{- id -}}
+        {%- endif -%}
     """
     lang = config.lang.python
     envs = {
@@ -45,7 +55,8 @@ class CellRangerCount(Proc):
         "cellranger": config.exe.cellranger,
         "ref": config.ref.ref_cellranger_gex,
         "tmpdir": config.path.tmpdir,
-        "include_introns": "true",
+        "include_introns": True,
+        "create_bam": False,
     }
     script = "file://../scripts/cellranger/CellRangerCount.py"
     plugin_opts = {
@@ -57,13 +68,16 @@ class CellRangerCount(Proc):
 class CellRangerVdj(Proc):
     """Run cellranger vdj
 
-    to perform sequence assembly and paired clonotype calling
+    to perform sequence assembly and paired clonotype calling.
+    requires cellranger v7+.
 
     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.
+        id: The id determining the output directory. If not provided, it is inferred
+            from the fastq files.
 
     Output:
         outdir: The output directory
@@ -78,16 +92,20 @@ class CellRangerVdj(Proc):
             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"
+    input = "fastqs:files, id"
     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 -}}
+        {%- if in.id -%}
+            {{in.id}}
+        {%- else -%}
+            {%- set id = commonprefix(*fastqs) |
+                regex_replace: "_L\\d+(:?_.*)?$", "" |
+                regex_replace: "_S\\d+$", "" -%}
+            {{- id -}}
+        {%- endif -%}
     """
     lang = config.lang.python
     envs = {
@@ -129,4 +147,5 @@ class CellRangerSummary(Proc):
     envs = {"group": None}
     plugin_opts = {
         "report": "file://../reports/cellranger/CellRangerSummary.svelte",
+        "report_paging": 8,
     }

{biopipen-0.27.9 → biopipen-0.28.1}/biopipen/ns/cellranger_pipeline.py

@@ -7,6 +7,7 @@ from __future__ import annotations
 from typing import TYPE_CHECKING
 
 from diot import Diot
+from pipen.utils import mark, is_loading_pipeline
 from pipen_args.procgroup import ProcGroup
 
 if TYPE_CHECKING:
@@ -17,28 +18,43 @@ class CellRangerCountPipeline(ProcGroup):
     """The cellranger count pipeline
 
     Run cellranger count for multiple samples and summarize the metrics.
+
+    Args:
+        input (type=list): The list of lists of fastq files.
+            or the list of comma-separated string of fastq files.
+        ids (type=list): The list of ids for the samples.
     """
-    DEFAULTS = Diot(input=None)
+    DEFAULTS = Diot(input=None, ids=None)
 
     def post_init(self):
         """Check if the input is a list of fastq files"""
-        if (
+        if not is_loading_pipeline() and (
             not isinstance(self.opts.input, (list, tuple))
             or len(self.opts.input) == 0
-            or not isinstance(self.opts.input[0], (list, tuple))
         ):
             raise TypeError(
                 "The input of `CellRangerCountPipeline` should be a list of lists of "
                 "fastq files."
             )
 
+        if isinstance(self.opts.input, (list, tuple)):
+            self.opts.input = [
+                [y.strip() for y in x.split(",")]
+                if isinstance(x, str)
+                else x
+                for x in self.opts.input
+            ]
+
     @ProcGroup.add_proc
     def p_cellranger_count(self) -> Proc:
         """Build CellRangerCount process"""
         from .cellranger import CellRangerCount as _CellRangerCount
 
         class CellRangerCount(_CellRangerCount):
-            input_data = self.opts.input
+            if self.opts.ids:
+                input_data = list(zip(self.opts.input, self.opts.ids))
+            else:
+                input_data = self.opts.input
 
         return CellRangerCount
 
@@ -58,28 +74,43 @@ class CellRangerVdjPipeline(ProcGroup):
     """The cellranger vdj pipeline
 
     Run cellranger vdj for multiple samples and summarize the metrics.
+
+    Args:
+        input (type=list): The list of lists of fastq files.
+            or the list of comma-separated string of fastq files.
+        ids (type=list): The list of ids for the samples.
     """
-    DEFAULTS = Diot(input=None)
+    DEFAULTS = Diot(input=None, ids=None)
 
     def post_init(self):
         """Check if the input is a list of fastq files"""
-        if (
+        if not is_loading_pipeline() and (
             not isinstance(self.opts.input, (list, tuple))
             or len(self.opts.input) == 0
-            or not isinstance(self.opts.input[0], (list, tuple))
         ):
             raise TypeError(
                 "The input of `CellRangerVdjPipeline` should be a list of lists of "
                 "fastq files."
             )
 
+        if isinstance(self.opts.input, (list, tuple)):
+            self.opts.input = [
+                [y.strip() for y in x.split(",")]
+                if isinstance(x, str)
+                else x
+                for x in self.opts.input
+            ]
+
     @ProcGroup.add_proc
     def p_cellranger_vdj(self) -> Proc:
         """Build CellRangerVdj process"""
         from .cellranger import CellRangerVdj as _CellRangerVdj
 
         class CellRangerVdj(_CellRangerVdj):
-            input_data = self.opts.input
+            if self.opts.ids:
+                input_data = list(zip(self.opts.input, self.opts.ids))
+            else:
+                input_data = self.opts.input
 
         return CellRangerVdj
 

{biopipen-0.27.9 → biopipen-0.28.1}/biopipen/ns/scrna.py

@@ -1689,11 +1689,11 @@ class CellTypeAnnotation(Proc):
             ///
 
         sccatch_args (ns): The arguments for `scCATCH::findmarkergene()` if `tool` is `sccatch`.
-            - species (choice): The specie of cells.
-                - Human: Human cells.
-                - Mouse: Mouse cells.
+            - species: The specie of cells.
             - cancer: If the sample is from cancer tissue, then the cancer type may be defined.
             - tissue: Tissue origin of cells must be defined.
+            - marker: The marker genes for cell type identification.
+            - if_use_custom_marker (flag): Whether to use custom marker genes. If `True`, no `species`, `cancer`, and `tissue` are needed.
             - <more>: Other arguments for [`scCATCH::findmarkergene()`](https://rdrr.io/cran/scCATCH/man/findmarkergene.html).
                 You can pass an RDS file to `sccatch_args.marker` to work as custom marker. If so,
                 `if_use_custom_marker` will be set to `TRUE` automatically.
@@ -1743,7 +1743,13 @@ class CellTypeAnnotation(Proc):
         "sctype_tissue": None,
         "sctype_db": config.ref.sctype_db,
         "cell_types": [],
-        "sccatch_args": {},
+        "sccatch_args": {
+            "species": None,
+            "cancer": "Normal",
+            "tissue": None,
+            "marker": None,
+            "if_use_custom_marker": False,
+        },
         "hitype_tissue": None,
         "hitype_db": None,
         "celltypist_args": {

{biopipen-0.27.9 → biopipen-0.28.1}/biopipen/scripts/cellranger/CellRangerCount.py

@@ -5,23 +5,17 @@ from biopipen.utils.misc import run_command
 
 fastqs = {{in.fastqs | repr}}  # pyright: ignore  # noqa
 outdir = {{out.outdir | quote}}  # pyright: ignore
+id = {{out.outdir | basename | 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
+include_introns = {{envs.include_introns | repr}}
+create_bam = {{envs.create_bam | repr}}
 
-{% 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 %}
+include_introns = str(include_introns).lower()
+create_bam = str(create_bam).lower()
 
 # create a temporary unique directory to store the soft-linked fastq files
 fastqdir = tmpdir / f"cellranger_count_{uuid.uuid4()}"
@@ -34,25 +28,35 @@ 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
+other_args = {{envs | dict_to_cli_args: dashify=True, exclude=['no_bam', 'create_bam', 'include_introns', 'cellranger', 'transcriptome', 'ref', 'tmpdir', 'id', 'ncores']}}  # pyright: ignore
 
 command = [
     cellranger,
     "count",
     "--id",
     id,
-    "--sample",
-    sample,
     "--fastqs",
     fastqdir,
     "--transcriptome",
-    ref,
+    Path(ref).resolve(),
     "--localcores",
     ncores,
     "--disable-ui",
+    "--include-introns",
+    include_introns,
     *other_args,
 ]
 
+# check cellranger version
+#   cellranger cellranger-7.2.0
+version = run_command([cellranger, "--version"], stdout = "RETURN")
+version = version.replace("cellranger", "").replace("-", "").strip()
+version = list(map(int, version.split(".")))
+if version[0] >= 8:
+    command += ["--create-bam", create_bam]
+elif not create_bam:
+    command += ["--no-bam"]
+
 run_command(command, fg=True, cwd=str(Path(outdir).parent))
 
 web_summary_html = Path(outdir) / "outs" / "web_summary.html"
@@ -68,7 +72,7 @@ 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)
+    regex = re.compile(r"<script>(.+)</script>", re.DOTALL)
     web_summary_html.write_text(regex.sub(
         '<script src="web_summary.js"></script>',
         web_summary_content,

{biopipen-0.27.9 → biopipen-0.28.1}/biopipen/scripts/cellranger/CellRangerVdj.py

@@ -5,24 +5,13 @@ from biopipen.utils.misc import run_command
 
 fastqs = {{in.fastqs | repr}}  # pyright: ignore  # noqa
 outdir = {{out.outdir | quote}}  # pyright: ignore
+id = {{out.outdir | basename | 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)
@@ -34,19 +23,17 @@ 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
+other_args = {{envs | dict_to_cli_args: dashify=True, exclude=['cellranger', 'reference', 'ref', 'tmpdir', 'id', 'ncores']}}  # pyright: ignore
 
 command = [
     cellranger,
     "vdj",
     "--id",
     id,
-    "--sample",
-    sample,
     "--fastqs",
     fastqdir,
     "--reference",
-    ref,
+    Path(ref).resolve(),
     "--localcores",
     ncores,
     "--disable-ui",
@@ -68,7 +55,7 @@ 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)
+    regex = re.compile(r"<script>(.+)</script>", re.DOTALL)
     web_summary_html.write_text(regex.sub(
         '<script src="web_summary.js"></script>',
         web_summary_content,

{biopipen-0.27.9 → biopipen-0.28.1}/biopipen/scripts/scrna/CellTypeAnnotation-sccatch.R

@@ -7,19 +7,12 @@ outfile = {{out.outfile | r}}
 sccatch_args = {{envs.sccatch_args | r}}
 newcol = {{envs.newcol | r}}
 
-if (is.null(sccatch_args$tissue)) { stop("`envs.sccatch_args.tissue` origin of cells must be defined.") }
-if (is.null(sccatch_args$species)) {
-    sccatch_args$species = "Human"
-}
 if (!is.null(sccatch_args$marker)) {
     cellmatch = readRDS(sccatch_args$marker)
     sccatch_args$if_use_custom_marker = TRUE
 }
 sccatch_args$marker = cellmatch
 
-if (is.null(sccatch_args$cancer)) {
-    sccatch_args$cancer = "Normal"
-}
 if (is.integer(sccatch_args$use_method)) {
     sccatch_args$use_method = as.character(sccatch_args$use_method)
 }
@@ -30,6 +23,8 @@ obj = createscCATCH(data = GetAssayData(sobj), cluster = as.character(Idents(sob
 sccatch_args$object = obj
 
 obj = do_call(findmarkergene, sccatch_args)
+obj = findcelltype(object = obj)
+
 write.table(
     obj@celltype,
     file = file.path(dirname(outfile), "cluster2celltype.tsv"),

{biopipen-0.27.9 → biopipen-0.28.1}/biopipen/scripts/scrna/CellsDistribution.R

@@ -360,6 +360,7 @@ do_case <- function(name, case) {
     }
 
     log_info("  Merging and saving pie charts ...")
+    devpars = case$devpars
     # assemble and save pie chart plots
     res <- devpars$res %||% 100
     #                         legend, cells_by names
@@ -405,6 +406,7 @@ do_case <- function(name, case) {
     }
 
     col_fun <- colorRamp2(c(0, max(hmdata, na.rm = T)), c("lightyellow", "purple"))
+    hm_devpars <- case$hm_devpars
     hm_res <- hm_devpars$res %||% 100
     hm_width <- hm_devpars$width %||% (600 + 15 * length(unique(meta$seurat_clusters)) + extra_width)
     hm_height <- hm_devpars$height %||% (450 + 15 * cells_rows + extra_height)

{biopipen-0.27.9 → biopipen-0.28.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "biopipen"
-version = "0.27.9"
+version = "0.28.1"
 description = "Bioinformatics processes/pipelines that can be run from `pipen run`"
 authors = ["pwwang <pwwang@pwwang.com>"]
 license = "MIT"

{biopipen-0.27.9 → biopipen-0.28.1}/setup.py

@@ -81,7 +81,7 @@ entry_points = \
 
 setup_kwargs = {
     'name': 'biopipen',
-    'version': '0.27.9',
+    'version': '0.28.1',
     'description': 'Bioinformatics processes/pipelines that can be run from `pipen run`',
     'long_description': 'None',
     'author': 'pwwang',

biopipen-0.27.9/biopipen/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.27.9"