biopipen 0.21.0__py3-none-any.whl → 0.34.26__py3-none-any.whl

{biopipen-0.21.0.dist-info → biopipen-0.34.26.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.8.1
+Generator: poetry-core 2.2.1
 Root-Is-Purelib: true
 Tag: py3-none-any

{biopipen-0.21.0.dist-info → biopipen-0.34.26.dist-info}/entry_points.txt

@@ -1,7 +1,8 @@
 [pipen_cli_run]
 bam=biopipen.ns.bam
-bcftools=biopipen.ns.bcftools
 bed=biopipen.ns.bed
+cellranger=biopipen.ns.cellranger
+cellranger_pipeline=biopipen.ns.cellranger_pipeline
 cnv=biopipen.ns.cnv
 cnvkit=biopipen.ns.cnvkit
 cnvkit_pipeline=biopipen.ns.cnvkit_pipeline
@@ -10,10 +11,13 @@ gene=biopipen.ns.gene
 gsea=biopipen.ns.gsea
 misc=biopipen.ns.misc
 plot=biopipen.ns.plot
+protein=biopipen.ns.protein
+regulatory=biopipen.ns.regulatory
 rnaseq=biopipen.ns.rnaseq
 scrna=biopipen.ns.scrna
-scrna_basic=biopipen.ns.scrna_basic
 scrna_metabolic_landscape=biopipen.ns.scrna_metabolic_landscape
+snp=biopipen.ns.snp
+stats=biopipen.ns.stats
 tcgamaf=biopipen.ns.tcgamaf
 tcr=biopipen.ns.tcr
 vcf=biopipen.ns.vcf

biopipen/ns/bcftools.py

@@ -1,111 +0,0 @@
-"""handling VCF files using bcftools"""
-from ..core.proc import Proc
-from ..core.config import config
-
-
-class BcftoolsAnnotate(Proc):
-    """Add or remove annotations from VCF files
-
-    Input:
-        infile: The input VCF file
-        annfile: The annotation file
-
-    Output:
-        outfile: The annotated VCF file
-
-    Envs:
-        bcftools: Path to bcftools
-        tabix: Path to tabix, used to index infile and annfile
-        annfile: The annotation file. If `in.annfile` is provided,
-            this is ignored
-        ncores: Number of cores (`--nthread`) to use
-        cols: Overwrite `-c/--columns`
-        header: Headers to be added
-        args: Other arguments for `bcftools annotate`
-    """
-    input = "infile:file, annfile:file"
-    output = "outfile:file:{{in.infile | basename}}"
-    lang = config.lang.python
-    envs = {
-        "bcftools": config.exe.bcftools,
-        "tabix": config.exe.tabix,
-        "annfile": "",
-        "cols": [],
-        "header": [],
-        "args": {},
-        "ncores": config.misc.ncores,
-    }
-    script = "file://../scripts/bcftools/BcftoolsAnnotate.py"
-
-
-class BcftoolsFilter(Proc):
-    """Apply fixed threshold filters to VCF files
-
-    Input:
-        infile: The input VCF file
-
-    Output:
-        outfile: The filtered VCF file. If the `in.infile` is gzipped, this is
-            gzipped as well.
-
-    Envs:
-        bcftools: Path to bcftools
-        ncores: Number of cores (`--nthread`) to use
-        keep: Whether we should keep the filtered variants or not.
-        args: Other arguments for `bcftools annotate`
-        ncores: `nthread`
-        tmpdir: Path to save the intermediate files
-            Since the filters need to be applied one by one by bcftools
-        includes: and
-        excludes: include/exclude only sites for which EXPRESSION is true.
-            See: https://samtools.github.io/bcftools/bcftools.html#expressions
-            If provided, `envs.args.include/exclude` will be ignored.
-            If `str`/`list` used, The filter names will be `Filter%d`
-            A dict is used when keys are filter names and values are expressions
-    """
-    input = "infile:file"
-    output = "outfile:file:{{in.infile | basename}}"
-    lang = config.lang.python
-    envs = {
-        "bcftools": config.exe.bcftools,
-        "keep": True,
-        "ncores": config.misc.ncores,
-        "includes": None,
-        "excludes": None,
-        "tmpdir": config.path.tmpdir,
-        "args": {},
-    }
-    script = "file://../scripts/bcftools/BcftoolsFilter.py"
-
-
-class BcftoolsSort(Proc):
-    """Sort VCF files
-
-    Input:
-        infile: The input VCF file
-
-    Output:
-        outfile: The sorted VCF file.
-
-    Envs:
-        bcftools: Path to bcftools
-        gz: Whether to gzip the output file
-        index: Whether to index the output file (tbi) (`envs.gz` forced to True)
-        tmpdir: Path to save the intermediate files
-        args: Other arguments for `bcftools sort`. For example `max-mem`.
-            See also https://samtools.github.io/bcftools/bcftools.html#sort
-    """
-    input = "infile:file"
-    output = (
-        "outfile:file:{{in.infile | stem0}}.vcf"
-        "{% if envs.gz or envs.index %}.gz{% endif %}"
-    )
-    lang = config.lang.python
-    envs = {
-        "bcftools": config.exe.bcftools,
-        "gz": True,
-        "index": True,
-        "tmpdir": config.path.tmpdir,
-        "args": {},
-    }
-    script = "file://../scripts/bcftools/BcftoolsSort.py"

biopipen/ns/scrna_basic.py

@@ -1,255 +0,0 @@
-"""Basic analysis for single cell RNA-seq data
-
-- QC
-- Clustering
-- Marker genes
-- Enrichment analysis
-"""
-from __future__ import annotations
-from pathlib import Path
-from typing import Type
-
-from pipen.utils import mark, is_loading_pipeline
-from pipen_annotate import annotate
-from pipen_args import ProcGroup
-
-from ..core.proc import Proc
-
-
-class ScrnaBasic(ProcGroup):
-    """Basic analysis for single cell RNA-seq data
-
-    Including QC, clustering, marker genes, and enrichment analysis.
-
-    See also the docs for details
-    <https://pwwang.github.io/biopipen/pipelines/scrna_basic/>
-
-    Args:
-        infile: The input file. Either a tab-delimited file containing
-            the information of metadata and paths to results of cellranger
-            or a seurat object has been saved as RDS file (with extension
-            `.rds` or `.RDS`), which QC is assumed to be done.
-            As for the tab-delimited file, it should have two columns:
-            `Sample` and `RNAData`. `Sample` should be the first column with
-            unique identifiers for the samples and `RNAData` indicates where the
-            barcodes, genes, expression matrices are.
-        is_seurat (flag): Whether the input file is a seurat object
-            in RDS format.
-            If this process group runs independently, this argument should
-            not be set. It will be recognized automatically by the extension
-            of `infile`. However, if this process group is run as a part of
-            a pipeline, this argument should be set manually since `infile`
-            should not be set in this case. It will be passed by other processes
-        clustering (choice;required): Which clustering method to use.
-            - supervised: Mapping the cells to given reference.
-                Using Seurat Reference Mapping procedure.
-                See: <https://satijalab.org/seurat/articles/multimodal_reference_mapping.html>
-            - unsupervised: Clustering the cells without reference.
-                Using Seurat FindClusters procedure.
-            - both: Both supervised and unsupervised clustering.
-                Performing both of the above procedures. The unsupervised
-                clustering will be added as `seurat_clusters_unsupervised`
-                to the metadata.
-        ref: The reference file for supervised clustering. It should be an
-            RDS file (with extension `.rds` or `.RDS`) containing a seurat
-            object, or a h5 file (with extension `.h5` or `.h5seurat`) that
-            can be loaded by `Seurat::LoadH5Seurat()`.
-    """  # noqa: E501
-
-    DEFAULTS = {
-        "infile": None,
-        "is_seurat": False,
-        "clustering": None,
-        "ref": None,
-    }
-
-    def post_init(self) -> None:
-        if self.opts.infile:
-            suffix = Path(self.opts.infile).suffix
-            self.opts.is_seurat = suffix in (".rds", ".RDS")
-
-    @ProcGroup.add_proc
-    def p_input(self) -> Type[Proc]:
-        """Build the input for the process group"""
-        from .misc import File2Proc
-
-        @mark(board_config_hidden=True)
-        class ScrnaBasicInput(File2Proc):
-            """Input file for scrna_basic process group
-
-            To specify the input file, use the `infile` argument of the
-            process group.
-            """
-
-            if self.opts.infile:
-                input_data = [self.opts.infile]
-
-        return ScrnaBasicInput
-
-    @ProcGroup.add_proc
-    def p_prepare(self) -> Type[Proc]:
-        """Prepare the input data into a Seurat object and do QC"""
-        if self.opts.is_seurat:
-            return self.p_input
-
-        from .scrna import SeuratPreparing
-
-        class ScrnaBasicPrepareAndQC(SeuratPreparing):
-            requires = self.p_input
-
-        return ScrnaBasicPrepareAndQC
-
-    @ProcGroup.add_proc
-    def p_supervised(self) -> Type[Proc]:
-        if (
-            self.opts.clustering == "unsupervised"
-            and not is_loading_pipeline()
-        ):
-            return None
-
-        from .scrna import SeuratMap2Ref
-
-        @annotate.format_doc(indent=3)
-        class ScrnaBasicSupervised(SeuratMap2Ref):
-            """{{Summary}}
-
-            **Only available when the group argument `clustering` is set to
-            `supervised` or `both`.**
-
-            Envs:
-                ref (pgarg): {{Envs.ref.help | indent(20)}}.
-                    Defaults to the `ref` argument of the process group.
-            """
-            requires = self.p_prepare
-            envs = {
-                "ref": self.opts.ref,
-            }
-
-        return ScrnaBasicSupervised
-
-    @ProcGroup.add_proc
-    def p_supervised_stats(self) -> Type[Proc]:
-        if not self.p_supervised and not is_loading_pipeline():
-            return None
-
-        from .scrna import SeuratClusterStats
-
-        @annotate.format_doc(indent=3)
-        class ScrnaBasicSupervisedStats(SeuratClusterStats):
-            """{{Summary}}
-
-            **Only available when the group argument `clustering` is set to
-            `supervised` or `both`.**
-            """
-            requires = self.p_supervised
-
-        return ScrnaBasicSupervisedStats
-
-    @ProcGroup.add_proc
-    def p_unsupervised(self) -> Type[Proc]:
-        if (
-            self.opts.clustering == "supervised"
-            and not is_loading_pipeline()
-        ):
-            return None
-
-        from .scrna import SeuratClustering
-
-        class ScrnaBasicUnsupervised(SeuratClustering):
-            requires = self.p_prepare
-
-        return ScrnaBasicUnsupervised
-
-    @ProcGroup.add_proc
-    def p_unsupervised_anno(self) -> Type[Proc]:
-        if not self.p_unsupervised and not is_loading_pipeline():
-            return None
-
-        from .scrna import CellTypeAnnotation
-
-        class ScrnaBasicAnnotation(CellTypeAnnotation):
-            requires = self.p_unsupervised
-
-        return ScrnaBasicAnnotation
-
-    @ProcGroup.add_proc
-    def p_unsupervised_stats(self) -> Type[Proc]:
-        if not self.p_unsupervised_anno and not is_loading_pipeline():
-            return None
-
-        from .scrna import SeuratClusterStats
-
-        class ScrnaBasicUnsupervisedStats(SeuratClusterStats):
-            requires = self.p_unsupervised_anno
-
-        return ScrnaBasicUnsupervisedStats
-
-    @ProcGroup.add_proc
-    def p_merge(self) -> Type[Proc]:
-        if self.opts.clustering == "supervised" and not is_loading_pipeline():
-            return self.p_supervised
-
-        if self.opts.clustering == "unsupervised" and not is_loading_pipeline():
-            return self.p_unsupervised_anno
-
-        @mark(board_config_hidden=True)
-        class ScrnaBasicMerge(Proc):
-            """Merge the supervised and unsupervised clustering results
-
-            Add unsupervised clustering as metadata to the seurat object
-            with supervised clustering.
-
-            The unsupervised clustering results are stored in the metadata
-            `seurat_clusters_unsupervised`.
-
-            **Only available when the group argument `clustering` is set to
-            `both`.**
-            """
-            requires = [self.p_supervised, self.p_unsupervised_anno]
-            lang = self.p_supervised.lang
-            input = "sobjfile:file, uobjfile:file"
-            output = "outfile:file:{{in.sobjfile | stem}}.rds"
-            script = """
-                library(Seurat)
-                sobj <- readRDS({{in.sobjfile | quote}})
-                uobj <- readRDS({{in.uobjfile | quote}})
-                umeta <- as.list(uobj$seurat_clusters)
-                names(umeta) <- rownames(uobj)
-                sobj <- AddMetaData(
-                    sobj,
-                    metadata=umeta,
-                    col.name="seurat_clusters_unsupervised"
-                )
-                saveRDS(sobj, {{out.outfile | quote}})
-            """
-
-        return ScrnaBasicMerge
-
-    @ProcGroup.add_proc
-    def p_findmarkers(self) -> Type[Proc]:
-        from .scrna import MarkersFinder
-
-        @annotate.format_doc(indent=3)
-        class ScrnaBasicMarkers(MarkersFinder):
-            """{{Summary}}
-
-            If the group argument `clustering` is set to `"both"`,
-            you can set `group-by` to `"seurat_clusters_unsupervised"` in
-            a different case to find the markers for the unsupervised clusters.
-            """
-            requires = self.p_merge
-
-        return ScrnaBasicMarkers
-
-    @ProcGroup.add_proc
-    def p_scgsea(self) -> Type[Proc]:
-        from .scrna import ScFGSEA
-
-        class ScrnaBasicScGSEA(ScFGSEA):
-            requires = self.p_merge
-
-        return ScrnaBasicScGSEA
-
-
-if __name__ == "__main__":
-    ScrnaBasic().as_pipen().run()

biopipen/reports/delim/SampleInfo.svelte

@@ -1,36 +0,0 @@
-{% from "utils/misc.liq" import report_jobs, table_of_images -%}
-
-<script>
-    import { Image, DataTable } from "$libs";
-</script>
-
-{%- macro report_job(job, h=1) -%}
-
-    {% if envs.stats %}
-    <h{{h}}>Sample Information</h{{h}}>
-    {% endif %}
-    {% if envs.exclude_cols and isinstance(envs.exclude_cols, str) %}
-        {% set excluded_cols = envs.exclude_cols | replace: " ", "" | split: "," %}
-    {% else %}
-        {% set excluded_cols = envs.exclude_cols %}
-    {% endif %}
-
-    <DataTable
-        data={ {{ job.out.outfile | datatable: sep="\t", excluded=excluded_cols }} }
-        pageSize={50}
-        />
-
-    {% if envs.stats %}
-        <h{{h}}>Statistics</h{{h}}>
-        {%- set stat_imgs = job.outdir | glob: "*.png" -%}
-        {{- table_of_images(stat_imgs) -}}
-    {% endif %}
-
-{%- endmacro -%}
-
-{%- macro head_job(job) -%}
-    <h1>{{job.in.infile | stem | escape }}</h1>
-{%- endmacro -%}
-
-{{ report_jobs(jobs, head_job, report_job) }}
-

biopipen/reports/scrna/GeneExpressionInvistigation.svelte

@@ -1,32 +0,0 @@
-{% from_ os import path %}
-{% from "utils/misc.liq" import report_jobs, table_of_images -%}
-
-<script>
-    import { Image } from "$libs";
-</script>
-
-{%- macro report_job(job, h=1) -%}
-
-{% assign boxplotpng = job.out.outdir | joinpaths: "boxplot.png" %}
-{% assign heatmappng = job.out.outdir | joinpaths: "heatmap.png" %}
-
-{% if path.exists(boxplotpng) %}
-<Image src={{boxplotpng | quote}} />
-{% endif %}
-
-{% if path.exists(heatmappng) %}
-<Image src={{heatmappng | quote}} />
-{% endif %}
-
-{%- endmacro -%}
-
-{%- macro head_job(job) -%}
-{% if job.in.configfile %}
-{%  assign name = job.in.configfile | toml_load | attr: "name" %}
-{% else %}
-{%  assign name = job.ennvs.config | attr: "name" %}
-{% endif %}
-<h1>{{name | escape}}</h1>
-{%- endmacro -%}
-
-{{ report_jobs(jobs, head_job, report_job) }}

biopipen/reports/scrna/ScFGSEA.svelte

@@ -1,35 +0,0 @@
-{% from "utils/gsea.liq" import fgsea_report -%}
-{% from "utils/misc.liq" import report_jobs -%}
-<script>
-    import { Image, DataTable } from "$libs";
-</script>
-
-{%- macro report_job(job, h=1) -%}
-    {%- set secdirs = job.out.outdir | glob: "*" -%}
-    {%- if len(secdirs) == 1 -%}
-        {%- set secname = secdirs | first | basename -%}
-        {%- for casedir in secdirs | first | glob: "*" -%}
-            {%- if secname == "DEFAULT" -%}
-                <h{{h}}>{{ casedir | basename | escape }}</h{{h}}>
-            {%- else -%}
-                <h{{h}}>{{secname | escape }} - {{ casedir | basename | escape }}</h{{h}}>
-            {%- endif -%}
-            {{ fgsea_report(casedir, h + 1) }}
-        {%- endfor -%}
-    {%- else -%}
-        {%- for secdir in secdirs -%}
-            {%- set sec = secdir | basename -%}
-            <h{{h}}>{{sec | escape}}</h{{h}}>
-            {%- for casedir in secdir | glob: "*" -%}
-                <h{{h+1}}>{{casedir | basename | escape}}</h{{h+1}}>
-                {{ fgsea_report(casedir, h + 2) }}
-            {%- endfor -%}
-        {%- endfor -%}
-    {%- endif -%}
-{%- endmacro -%}
-
-{%- macro head_job(job) -%}
-<h1>{{job.in.srtobj | stem0 | escape}}</h1>
-{%- endmacro -%}
-
-{{ report_jobs(jobs, head_job, report_job) }}

biopipen/reports/scrna/SeuratClusterStats.svelte

@@ -1,82 +0,0 @@
-{% from "utils/misc.liq" import report_jobs, table_of_images -%}
-{% from_ os import path %}
-<script>
-    import { DataTable, Image } from "$libs";
-    import { Tabs, Tab, TabContent } from "$ccs";
-</script>
-
-{%- macro report_job(job, h=1) -%}
-    {%- set stats_reports_file = job.out.outdir | joinpaths: "stats", "report_toc.json" -%}
-    {%- set features_reports_file = job.out.outdir | joinpaths: "features", "report_toc.json" -%}
-    {%- set dimplots_reports_file = job.out.outdir | joinpaths: "dimplots", "report_toc.json" -%}
-
-    {%- if stats_reports_file | exists -%}
-        {%- set stats = stats_reports_file | config: "json" -%}
-        {% for key, value in stats.items() -%}
-            <h{{h}}>{{key | escape}}</h{{h}}>
-            <Tabs>
-                {% if 'bar' in value -%}
-                    <Tab label="Bar plot" />
-                {% endif -%}
-                {% if 'pie' in value -%}
-                    <Tab label="Pie chart" />
-                {% endif -%}
-                {% if 'table' in value -%}
-                    <Tab label="Table" />
-                {% endif -%}
-                <svelte:fragment slot="content">
-                    {% if 'bar' in value -%}
-                        <TabContent>
-                            <Image src="{{job.out.outdir}}/stats/{{value.bar}}" />
-                        </TabContent>
-                    {% endif -%}
-                    {% if 'pie' in value -%}
-                        <TabContent>
-                            <Image src="{{job.out.outdir}}/stats/{{value.pie}}" />
-                        </TabContent>
-                    {% endif -%}
-                    {% if 'table' in value -%}
-                        <TabContent>
-                            <DataTable src="{{job.out.outdir}}/stats/{{value.table}}"
-                                data={ {{job.out.outdir | joinpaths: "stats", value.table | datatable: sep="\t", nrows=100 }} }
-                                />
-                        </TabContent>
-                    {% endif -%}
-                </svelte:fragment>
-            </Tabs>
-        {%- endfor -%}
-    {%- endif -%}
-
-    {%- if features_reports_file | exists -%}
-        {%- set features = features_reports_file | config: "json" %}
-        {% for key, value in features.items() -%}
-            <h{{h}}>{{key | escape}}</h{{h}}>
-            {% for val in value -%}
-                {% if "name" in val -%}
-                    <h{{h+1}}>{{val.name | escape}}</h{{h+1}}>
-                {%- endif -%}
-                {% if val.kind == "table" -%}
-                    <DataTable src="{{job.out.outdir}}/features/{{val.file}}"
-                        data={ {{job.out.outdir | joinpaths: "features", val.file | datatable: sep="\t", nrows=100 }} }
-                        />
-                {% else -%}
-                    <Image src="{{job.out.outdir}}/features/{{val.file}}" />
-                {% endif -%}
-            {%- endfor -%}
-        {%- endfor -%}
-    {%- endif -%}
-
-    {%- if dimplots_reports_file | exists -%}
-        {%- set dimplots = dimplots_reports_file | config: "json" %}
-        {% for key, value in dimplots.items() -%}
-            <h{{h}}>{{key | escape}}</h{{h}}>
-            <Image src="{{job.out.outdir}}/dimplots/{{value}}" />
-        {%- endfor -%}
-    {%- endif -%}
-{%- endmacro -%}
-
-{%- macro head_job(job) -%}
-<h1>{{job.in.srtobj | stem}}</h1>
-{%- endmacro -%}
-
-{{ report_jobs(jobs, head_job, report_job) }}

biopipen/reports/scrna/SeuratMap2Ref.svelte

@@ -1,20 +0,0 @@
-{% from "utils/misc.liq" import report_jobs, table_of_images -%}
-<script>
-    import { Image } from "$libs";
-</script>
-
-{%- macro report_job(job, h=1) -%}
-<h{{h}}>Reference UMAP</h{{h}}>
-{% set imgs = job.outdir | glob: "Reference_UMAP_*.png" %}
-{{ table_of_images(imgs) }}
-
-<h{{h}}>Query UMAP</h{{h}}>
-{% set imgs = job.outdir | glob: "Query_UMAP_*.png" %}
-{{ table_of_images(imgs) }}
-{%- endmacro -%}
-
-{%- macro head_job(job) -%}
-<h1>{{job.in.sobjfile | stem0 | escape}}</h1>
-{%- endmacro -%}
-
-{{ report_jobs(jobs, head_job, report_job) }}

biopipen/reports/scrna/SeuratPreparing.svelte

@@ -1,38 +0,0 @@
-{% from "utils/misc.liq" import report_jobs, table_of_images -%}
-{% from_ os import path %}
-<script>
-    import { Image, DataTable } from "$libs";
-    import { Tile } from "$ccs";
-</script>
-
-{%- macro report_job(job, h=1) -%}
-    <h{{h}}>Applied filters</h{{h}}>
-    <Tile>
-        <p>Cell filters: {{envs.cell_qc | str | escape}}</p>
-        <p>Gene filters: {{
-            proc.envs.gene_qc
-            | str
-            | replace: "{", "&#123"
-            | replace: "}", "&#125"
-        }}</p>
-
-        <DataTable
-            src={{job.outdir | joinpaths: 'plots', 'dim.txt' | quote}}
-            data={ {{job.outdir | joinpaths: 'plots', 'dim.txt' | datatable: sep="\t"}} } />
-    </Tile>
-
-    <h{{h}}>Violin plots</h{{h}}>
-    {% set qcimgs = job.outdir | glob: "plots", "*.vln.png" %}
-    {{ table_of_images(qcimgs) }}
-
-    <h{{h}}>Scatter plots</h{{h}}>
-    {% set qcimgs = job.outdir | glob: "plots", "*.scatter.png" %}
-    {{ table_of_images(qcimgs) }}
-
-{%- endmacro -%}
-
-{%- macro head_job(job) -%}
-    <h1>{{job.in.metafile | stem}}</h1>
-{%- endmacro -%}
-
-{{ report_jobs(jobs, head_job, report_job) }}