biopipen 0.28.1__tar.gz → 0.29.1__tar.gz

{biopipen-0.28.1 → biopipen-0.29.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.28.1
+Version: 0.29.1
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang
@@ -16,7 +16,7 @@ Provides-Extra: runinfo
 Requires-Dist: datar[pandas] (>=0.15.6,<0.16.0)
 Requires-Dist: pipen-board[report] (>=0.15,<0.16)
 Requires-Dist: pipen-cli-run (>=0.13,<0.14)
-Requires-Dist: pipen-filters (>=0.12,<0.13)
+Requires-Dist: pipen-filters (>=0.13,<0.14)
 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)

biopipen-0.29.1/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.29.1"

{biopipen-0.28.1 → biopipen-0.29.1}/biopipen/core/config.toml

@@ -23,12 +23,16 @@ cnvpytor = "cnvpytor"
 cnvnator2vcf = "cnvnator2VCF.pl"
 # convert
 convert = "convert"
+# fimo from meme
+fimo = "fimo"
 # wget
 wget = "wget"
 # aria2c
 aria2c = "aria2c"
 # plink
 plink = "plink"
+# plink2
+plink2 = "plink2"
 # tabix
 tabix = "tabix"
 # sambamba
@@ -86,6 +90,10 @@ genome = ""
 # Database file for scType
 # https://github.com/IanevskiAleksandr/sc-type/
 sctype_db = ""
+# TF Motif database
+tf_motifdb = ""
+# TF motif pairs
+tf_motifs = ""
 
 [misc]
 # Number of cores used for each job

{biopipen-0.28.1 → biopipen-0.29.1}/biopipen/ns/bam.py

@@ -17,7 +17,6 @@ class CNVpytor(Proc):
 
     Envs:
         cnvpytor: Path to cnvpytor
-        cnvnator2vcf: Path to CNVnator2VCF.pl to convert the result to VCF file
         samtools: Path to samtools, used to index bam file in case it's not
         ncores: Number of cores to use (`-j` for cnvpytor)
         refdir: The directory containing the fasta file for each chromosome
@@ -41,7 +40,6 @@ class CNVpytor(Proc):
     lang = config.lang.python
     envs = {
         "cnvpytor": config.exe.cnvpytor,
-        "cnvnator2vcf": config.exe.cnvnator2vcf,
         "samtools": config.exe.samtools,
         "ncores": config.misc.ncores,
         "refdir": config.ref.refdir,

{biopipen-0.28.1 → biopipen-0.29.1}/biopipen/ns/bed.py

@@ -163,3 +163,38 @@ class BedtoolsMerge(Proc):
         "bedtools": config.exe.bedtools,
     }
     script = "file://../scripts/bed/BedtoolsMerge.py"
+
+
+class BedtoolsIntersect(Proc):
+    """Find the intersection of two BED files, using `bedtools intersect`
+
+    See <https://bedtools.readthedocs.io/en/latest/content/tools/intersect.html>
+
+    Input:
+        afile: The first BED file
+        bfile: The second BED file
+
+    Output:
+        outfile: The output BED file
+
+    Envs:
+        bedtools: The path to bedtools
+        sort: Sort `afile` and `bfile` before intersecting.
+            By default, `-sorted` is used, assuming the input files are sorted.
+            If error occurs, try to set `sort` to `True`.
+        chrsize: Alias for `g` in `bedtools intersect`.
+        postcmd: The command to be executed for the output file after intersecting.
+            You can use `$infile`, `$outfile`, and `$outdir` to refer to the input,
+            output, and output directory, respectively.
+        <more>: Other options to be passed to `bedtools intersect`
+    """  # noqa: E501
+    input = "afile:file", "bfile:file"
+    output = "outfile:file:{{in.afile | stem0}}_{{in.bfile | stem0}}-intersect.bt"
+    lang = config.lang.python
+    envs = {
+        "bedtools": config.exe.bedtools,
+        "sort": False,
+        "chrsize": config.ref.chrsize,
+        "postcmd": None,
+    }
+    script = "file://../scripts/bed/BedtoolsIntersect.py"

{biopipen-0.28.1 → biopipen-0.29.1}/biopipen/ns/cellranger_pipeline.py

@@ -7,7 +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.utils import is_loading_pipeline
 from pipen_args.procgroup import ProcGroup
 
 if TYPE_CHECKING:
@@ -20,9 +20,9 @@ class CellRangerCountPipeline(ProcGroup):
     Run cellranger count for multiple samples and summarize the metrics.
 
     Args:
-        input (type=list): The list of lists of fastq files.
+        input (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.
+        ids (list): The list of ids for the samples.
     """
     DEFAULTS = Diot(input=None, ids=None)
 
@@ -76,9 +76,9 @@ class CellRangerVdjPipeline(ProcGroup):
     Run cellranger vdj for multiple samples and summarize the metrics.
 
     Args:
-        input (type=list): The list of lists of fastq files.
+        input (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.
+        ids (list): The list of ids for the samples.
     """
     DEFAULTS = Diot(input=None, ids=None)
 

{biopipen-0.28.1 → biopipen-0.29.1}/biopipen/ns/cnv.py

@@ -12,7 +12,15 @@ class AneuploidyScore(Proc):
 
     Input:
         segfile: The seg file, generally including chrom, start, end and
-            seg.mean (the log2 ratio)
+            seg.mean (the log2 ratio).
+            It is typically a tab-delimited file or a BED file.
+            If so, envs.chrom_col, envs.start_col, envs.end_col and envs.seg_col
+            are the 1st, 2nd, 3rd and 5th columns, respectively.
+            It can also be a VCF file. If so, envs.chrom_col and envs.start_col
+            are not required.
+            `end_col` and `envs.seg_col` will be a field in the INFO column.
+            [`VariantAnnotation`](https://rdrr.io/bioc/VariantAnnotation/)
+            is required to extract the INFO field.
 
     Output:
         outdir: The output directory containing the CAAs, AS and a histogram
@@ -122,7 +130,15 @@ class TMADScore(Proc):
     Input:
         segfile: The seg file, two columns are required:
             * chrom: The chromosome name, used for filtering
-            * seg.mean: The log2 ratio
+            * seg.mean: The log2 ratio.
+            It is typically a tab-delimited file or a BED file.
+            If so, envs.chrom_col and envs.seg_col
+            are the 1st and 5th columns, respectively.
+            It can also be a VCF file. If so, envs.chrom_col and envs.start_col
+            are not required.
+            `end_col` and `envs.seg_col` will be a field in the INFO column.
+            [`VariantAnnotation`](https://rdrr.io/bioc/VariantAnnotation/)
+            is required to extract the INFO field.
 
     Output:
         outfile: The output file containing the TMAD score

{biopipen-0.28.1 → biopipen-0.29.1}/biopipen/ns/cnvkit_pipeline.py

@@ -487,7 +487,8 @@ class CNVkitPipeline(ProcGroup):
                 target_file = None
                 antitarget_file = None
                 if self.col.sex in metadf:
-                    sample_sex = ",".join(metadf[self.col.sex][control_masks])
+                    all_sex = metadf[self.col.sex][control_masks].unique()
+                    sample_sex = [None] if len(all_sex) > 1 else all_sex[0]
                 else:
                     sample_sex = [None]
             else:
@@ -774,13 +775,15 @@ class CNVkitPipeline(ProcGroup):
             else:
                 tumor_masks = metadf[self.col.group] == self.opts.case
 
+            if self.col.sex in metadf:
+                all_sex = metadf[self.col.sex][tumor_masks].unique()
+                sample_sex = [None] if len(all_sex) > 1 else all_sex[0]
+            else:
+                sample_sex = [None]
+
             return tibble(
                 segfiles=[ch2.outfile.tolist()],
-                sample_sex=(
-                    ",".join(metadf[self.col.sex][tumor_masks])
-                    if self.col.sex in metadf
-                    else [None]
-                ),
+                sample_sex=sample_sex,
             )
 
         @annotate.format_doc(indent=3)
@@ -823,13 +826,15 @@ class CNVkitPipeline(ProcGroup):
             else:
                 tumor_masks = metadf[self.col.group] == self.opts.case
 
+            if self.col.sex in metadf:
+                all_sex = metadf[self.col.sex][tumor_masks].unique()
+                sample_sex = [None] if len(all_sex) > 1 else all_sex[0]
+            else:
+                sample_sex = [None]
+
             return tibble(
                 segfiles=[ch2.outfile.tolist()],
-                sample_sex=(
-                    ",".join(metadf[self.col.sex][tumor_masks])
-                    if self.col.sex in metadf
-                    else [None]
-                ),
+                sample_sex=sample_sex,
             )
 
         @annotate.format_doc(indent=3)

biopipen-0.29.1/biopipen/ns/gene.py

@@ -0,0 +1,99 @@
+"""Gene related processes"""
+
+from ..core.proc import Proc
+from ..core.config import config
+
+
+class GeneNameConversion(Proc):
+    """Convert gene names back and forth using MyGeneInfo
+
+    Input:
+        infile: The input file with original gene names
+            It should be a tab-separated file with header
+
+    Output:
+        outfile: The output file with converted gene names
+
+    Envs:
+        notfound (choice): What to do if a conversion cannot be done.
+            - use-query: Ignore the conversion and use the original name
+            - skip: Ignore the conversion and skip the entire row in input file
+            - ignore: Same as skip
+            - error: Report error
+            - na: Use NA
+        dup (choice): What to do if a conversion results in multiple names.
+            - first: Use the first name, sorted by matching score descendingly (default)
+            - last: Use the last name, sorted by matching score descendingly
+            - combine: Combine all names using `;` as separator
+        genecol: The index (1-based) or name of the column where genes are present
+        output (choice): How to output.
+            - append: Add the converted names as new columns at the end using `envs.outfmt`
+                as the column name.
+            - replace: Drop the original name column, and insert
+                the converted names at the original position.
+            - converted: Only keep the converted names.
+            - with-query: Output 2 columns with original and converted names.
+        infmt: What's the original gene name format
+            Available fields
+            https://docs.mygene.info/en/latest/doc/query_service.html#available-fields
+        outfmt: What's the target gene name format. Currently only a single format
+            is supported.
+        species: Limit gene query to certain species.
+            Supported: human, mouse, rat, fruitfly, nematode, zebrafish,
+            thale-cress, frog and pig
+    """  # noqa: E501
+    input = "infile:file"
+    output = "outfile:file:{{in.infile | basename}}"
+    lang = config.lang.rscript
+    envs = {
+        "notfound": "error",
+        "genecol": 1,
+        "dup": "first",
+        "output": "append",
+        "infmt": ["symbol", "alias"],
+        "outfmt": "symbol",
+        "species": "human",
+    }
+    script = "file://../scripts/gene/GeneNameConversion.R"
+
+
+class GenePromoters(Proc):
+    """Get gene promoter regions by specifying the flanking regions of TSS
+
+    Input:
+        infile: The input file with gene ids/names
+
+    Output:
+        outfile: The output file with promoter regions in BED format
+
+    Envs:
+        up (type=int): The upstream distance from TSS
+        down (type=int): The downstream distance from TSS
+            If not specified, the default is `envs.up`
+        notfound (choice): What to do if a gene is not found.
+            - skip: Skip the gene
+            - error: Report error
+        refgene: The reference gene annotation file in GTF format
+        header (flag): Whether the input file has a header
+        genecol (type=int): The index (1-based) of the gene column
+        match_id (flag): Should we match the genes in `in.infile` by `gene_id`
+            instead of `gene_name` in `envs.refgene`
+        sort (flag): Sort the output by chromosome and start position
+        chrsize: The chromosome size file, from which the chromosome order is
+            used to sort the output
+    """
+    input = "infile:file"
+    output = "outfile:file:{{in.infile | stem}}-promoters.bed"
+    lang = config.lang.rscript
+    envs = {
+        "up": 2000,
+        "down": None,
+        "notfound": "error",
+        "refgene": config.ref.refgene,
+        "header": True,
+        "genecol": 1,
+        "match_id": False,
+        "sort": False,
+        "chrsize": config.ref.chrsize,
+    }
+    script = "file://../scripts/gene/GenePromoters.R"

{biopipen-0.28.1 → biopipen-0.29.1}/biopipen/ns/misc.py

@@ -80,7 +80,7 @@ class Str2File(Proc):
         name: The name of the output file
     """
     input = "str, name"
-    output = "outfile:file:{{in.name}}"
+    output = "outfile:file:{{in.name | default: 'unnamed.txt'}}"
     lang = config.lang.python
     envs = {"name": None}
     script = "file://../scripts/misc/Str2File.py"
@@ -105,17 +105,4 @@ class Shell(Proc):
     output = "outfile:file:{{in.infile | basename}}"
     envs = {"cmd": "", "outdir": False}
     lang = config.lang.bash
-    script = """
-        infile={{in.infile | quote}}
-        outfile={{out.outfile | quote}}
-        is_outdir={{envs.outdir | int}}
-        cmd={{envs.cmd | quote}}
-        if [[ -z "$cmd" ]]; then
-            echo "No command given." 1>&2
-            exit 1
-        fi
-        if [[ $is_outdir -eq 1 ]]; then
-            mkdir -p "$outfile"
-        fi
-        eval "$cmd"
-    """
+    script = "file://../scripts/misc/Shell.sh"