biopipen 0.28.1__py3-none-any.whl → 0.29.0__py3-none-any.whl

biopipen/ns/vcf.py

@@ -439,3 +439,199 @@ class TruvariConsistency(Proc):
     envs = {"truvari": config.exe.truvari, "heatmap": {}}
     script = "file://../scripts/vcf/TruvariConsistency.R"
     plugin_opts = {"report": "file://../reports/vcf/TruvariConsistency.svelte"}
+
+
+class BcftoolsAnnotate(Proc):
+    """Add or remove annotations from VCF files
+
+    See also: <https://samtools.github.io/bcftools/bcftools.html#annotate>
+
+    Input:
+        infile: The input VCF file
+        annfile: The annotation file.
+            Currently only VCF files are supported.
+
+    Output:
+        outfile: The VCF file with annotations added or removed.
+
+    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 (type=int): Number of cores (`--threads`) to use
+        columns (auto): Comma-separated or list of columns or tags to carry over from
+            the annotation file. Overrides `-c, --columns`
+        remove (auto): Remove the specified columns from the input file
+        header (type=list): Headers to be added
+        gz (flag): Whether to gzip the output file
+        index (flag): Whether to index the output file (tbi) (`envs.gz` forced to True)
+        <more>: Other arguments for `bcftools annotate`
+            See also <https://samtools.github.io/bcftools/bcftools.html#annotate>
+            Note that the underscore `_` will be replaced with dash `-` in the
+            argument name.
+    """
+    input = "infile:file, annfile:file"
+    output = (
+        "outfile:file:{{in.infile | stem: 'gz'}}.vcf"
+        "{{'.gz' if envs.index or envs.gz else ''}}"
+    )
+    lang = config.lang.python
+    envs = {
+        "bcftools": config.exe.bcftools,
+        "tabix": config.exe.tabix,
+        "annfile": None,
+        "columns": [],
+        "remove": [],
+        "header": [],
+        "gz": True,
+        "index": True,
+        "ncores": config.misc.ncores,
+    }
+    script = "file://../scripts/vcf/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
+        tabix: Path to tabix, used to index infile/outfile
+        ncores (type=int): Number of cores (`--threads`) to use
+        keep: Whether we should keep the filtered variants or not.
+            If True, the filtered variants will be kept in the output file, but
+            with a new FILTER.
+        includes: and
+        excludes: include/exclude only sites for which EXPRESSION is true.
+            See: <https://samtools.github.io/bcftools/bcftools.html#expressions>
+            If provided, `envs.include/exclude` will be ignored.
+            If `str`/`list` used, The filter names will be `Filter_<type>_<index>`.
+            A dict is used where keys are filter names and values are expressions
+        gz (flag): Whether to gzip the output file
+        index (flag): Whether to index the output file (tbi) (`envs.gz` forced to True)
+        <more>: Other arguments for `bcftools filter`
+            See also <https://samtools.github.io/bcftools/bcftools.html#filter>
+    """
+    input = "infile:file"
+    output = (
+        "outfile:file:{{in.infile | stem: 'gz'}}.vcf"
+        "{{'.gz' if envs.index or envs.gz else ''}}"
+    )
+    lang = config.lang.python
+    envs = {
+        "bcftools": config.exe.bcftools,
+        "tabix": config.exe.tabix,
+        "ncores": config.misc.ncores,
+        "keep": True,
+        "includes": None,
+        "excludes": None,
+        "gz": True,
+        "index": True,
+    }
+    script = "file://../scripts/vcf/BcftoolsFilter.py"
+
+
+class BcftoolsSort(Proc):
+    """Sort VCF files using `bcftools sort`.
+
+    `bcftools sort` is used to sort VCF files by chromosome and position based on the
+    order of contigs in the header.
+
+    Here we provide a chrsize file to first sort the contigs in the header and then
+    sort the VCF file using `bcftools sort`.
+
+    Input:
+        infile: The input VCF file
+
+    Output:
+        outfile: The sorted VCF file.
+
+    Envs:
+        bcftools: Path to bcftools
+        tabix: Path to tabix, used to index infile/outfile
+        ncores (type=int): Number of cores (`--threads`) to use
+        gz (flag): Whether to gzip the output file
+        index (flag): Whether to index the output file (tbi) (`envs.gz` forced to True)
+        chrsize: The chromosome size file, from which the chromosome order is used
+            to sort the contig in the header first.
+            If not provided, `bcftools sort` will be used directly.
+        notfound (choice): What if the contig in the VCF file is not found in the
+            `chrsize` file.
+            - error: Report error
+            - remove: Remove the contig from the header.
+                Note that if there are records with the removed contig, an error will
+                be raised by `bcftools sort`
+            - start: Move the contig to the start of the contigs from `chrsize`
+            - end: Move the contig to the end of the contigs from `chrsize`
+        <more>: 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 | stem: 'gz'}}.vcf"
+        "{{'.gz' if envs.index or envs.gz else ''}}"
+    )
+    lang = config.lang.python
+    envs = {
+        "bcftools": config.exe.bcftools,
+        "tabix": config.exe.tabix,
+        "ncores": config.misc.ncores,
+        "chrsize": config.ref.chrsize,
+        "notfound": "remove",
+        "gz": True,
+        "index": True,
+    }
+    script = "file://../scripts/vcf/BcftoolsSort.py"
+
+
+class BcftoolsView(Proc):
+    """View, subset and filter VCF files by position and filtering expression.
+
+    Also convert between VCF and BCF.
+
+    Input:
+        infile: The input VCF file
+        regions_file: The region file used to subset the input VCF file.
+        samples_file: The samples file used to subset the input VCF file.
+
+    Output:
+        outfile: The output VCF file.
+
+    Envs:
+        bcftools: Path to bcftools
+        tabix: Path to tabix, used to index infile/outfile
+        ncores (type=int): Number of cores (`--threads`) to use
+        regions_file: The region file used to subset the input VCF file.
+            If `in.regions_file` is provided, this is ignored.
+        samples_file: The samples file used to subset the input VCF file.
+            If `in.samples_file` is provided, this is ignored.
+        gz (flag): Whether to gzip the output file
+        index (flag): Whether to index the output file (tbi) (`envs.gz` forced to True)
+        <more>: Other arguments for `bcftools view`.
+            See also https://samtools.github.io/bcftools/bcftools.html#view
+            Note that the underscore `_` will be replaced with dash `-` in the
+            argument name.
+    """
+    input = "infile:file, regions_file:file, samples_file:file"
+    output = (
+        "outfile:file:{{in.infile | stem: 'gz'}}.vcf"
+        "{{'.gz' if envs.index or envs.gz else ''}}"
+    )
+    lang = config.lang.python
+    envs = {
+        "bcftools": config.exe.bcftools,
+        "tabix": config.exe.tabix,
+        "ncores": config.misc.ncores,
+        "regions_file": None,
+        "samples_file": None,
+        "gz": True,
+        "index": True,
+    }
+    script = "file://../scripts/vcf/BcftoolsView.py"

biopipen/reports/snp/PlinkCallRate.svelte

@@ -0,0 +1,24 @@
+{% from "utils/misc.liq" import report_jobs -%}
+<script>
+    import { Image, Descr } from "$libs";
+</script>
+
+{%- macro report_job(job, h=1) -%}
+    <h{{h+1}}>Sample Call Rate</h{{h+1}}>
+    {%- for pngfile in job.out.outdir | joinpaths: '*.samplecr.png' | glob -%}
+    <Descr>Cutoff: {{envs.samplecr}}</Descr>
+    <Image src="{{pngfile}}" />
+    {%- endfor -%}
+
+    <h{{h+1}}>Variant Call Rate</h{{h+1}}>
+    {%- for pngfile in job.out.outdir | joinpaths: '*.varcr.png' | glob -%}
+    <Descr>Cutoff: {{envs.varcr}}</Descr>
+    <Image src="{{pngfile}}" />
+    {%- endfor -%}
+{%- endmacro -%}
+
+{%- macro head_job(job) -%}
+<h1>Sample: {{job.in.cnrfile | stem0 }}</h1>
+{%- endmacro -%}
+
+{{ report_jobs(jobs, head_job, report_job) }}

biopipen/reports/snp/PlinkFreq.svelte

@@ -0,0 +1,18 @@
+{% from "utils/misc.liq" import report_jobs -%}
+<script>
+    import { Image, Descr } from "$libs";
+</script>
+
+{%- macro report_job(job, h=1) -%}
+    {%- for pngfile in job.out.outdir | joinpaths: '*.png' | glob -%}
+        {% set metric_col = pngfile | stem | ext0 %}
+        <h{{h+1}}>{{metric_col}} distribution</h{{h+1}}>
+        <Image src="{{pngfile}}" />
+    {%- endfor -%}
+{%- endmacro -%}
+
+{%- macro head_job(job) -%}
+<h1>Sample: {{job.in.cnrfile | stem0 }}</h1>
+{%- endmacro -%}
+
+{{ report_jobs(jobs, head_job, report_job) }}

biopipen/reports/snp/PlinkHWE.svelte

@@ -0,0 +1,18 @@
+{% from "utils/misc.liq" import report_jobs -%}
+<script>
+    import { Image, Descr } from "$libs";
+</script>
+
+{%- macro report_job(job, h=1) -%}
+    {%- for pngfile in job.out.outdir | joinpaths: '*.png' | glob -%}
+    <h{{h+1}}>Distribution</h{{h+1}}>
+    <Descr>Cutoff: {{envs.cutoff}}</Descr>
+    <Image src="{{pngfile}}" />
+    {%- endfor -%}
+{%- endmacro -%}
+
+{%- macro head_job(job) -%}
+<h1>Sample: {{job.in.cnrfile | stem0 }}</h1>
+{%- endmacro -%}
+
+{{ report_jobs(jobs, head_job, report_job) }}

biopipen/reports/snp/PlinkHet.svelte

@@ -0,0 +1,18 @@
+{% from "utils/misc.liq" import report_jobs -%}
+<script>
+    import { Image, Descr } from "$libs";
+</script>
+
+{%- macro report_job(job, h=1) -%}
+    {%- for pngfile in job.out.outdir | joinpaths: '*.png' | glob -%}
+    <h{{h+1}}>Distribution</h{{h+1}}>
+    <Descr>Cutoff: [mean - {{envs.cutoff}} x sd, mean + {{envs.cutoff}} x sd]</Descr>
+    <Image src="{{pngfile}}" />
+    {%- endfor -%}
+{%- endmacro -%}
+
+{%- macro head_job(job) -%}
+<h1>Sample: {{job.in.cnrfile | stem0 }}</h1>
+{%- endmacro -%}
+
+{{ report_jobs(jobs, head_job, report_job) }}

biopipen/reports/snp/PlinkIBD.svelte

@@ -0,0 +1,18 @@
+{% from "utils/misc.liq" import report_jobs -%}
+<script>
+    import { Image, Descr } from "$libs";
+</script>
+
+{%- macro report_job(job, h=1) -%}
+    {%- for pngfile in job.out.outdir | joinpaths: '*.png' | glob -%}
+    <h{{h+1}}>Heatmap</h{{h+1}}>
+    <Descr>PI_HAT threshold = {{envs.pihat}}</Descr>
+    <Image src="{{pngfile}}" />
+    {%- endfor -%}
+{%- endmacro -%}
+
+{%- macro head_job(job) -%}
+<h1>Sample: {{job.in.cnrfile | stem0 }}</h1>
+{%- endmacro -%}
+
+{{ report_jobs(jobs, head_job, report_job) }}

biopipen/scripts/bam/CNVpytor.py

@@ -1,15 +1,15 @@
 from pathlib import Path
 
+import warnings
 import pandas
-from biopipen.scripts.vcf.VcfFix_utils import HeaderContig, fix_vcffile
+from datetime import datetime
 from biopipen.utils.reference import bam_index
-from biopipen.utils.misc import run_command, dict_to_cli_args
+from biopipen.utils.misc import run_command, dict_to_cli_args, logger
 
-bamfile = {{in.bamfile | quote}}  # pyright: ignore
+bamfile = {{in.bamfile | quote}}  # pyright: ignore # noqa
 snpfile = {{in.snpfile | repr}}  # pyright: ignore
 outdir = Path({{out.outdir | quote}})  # pyright: ignore
 cnvpytor = {{envs.cnvpytor | quote}}  # pyright: ignore
-cnvnator2vcf = {{envs.cnvnator2vcf | quote}}  # pyright: ignore
 samtools = {{envs.samtools | quote}}  # pyright: ignore
 ncores = {{envs.ncores | int}}  # pyright: ignore
 refdir = {{envs.refdir | quote}}  # pyright: ignore
@@ -20,7 +20,6 @@ args = {{envs | repr}}  # pyright: ignore
 
 del args['cnvpytor']
 del args['ncores']
-del args['cnvnator2vcf']
 del args['samtools']
 del args['refdir']
 del args['genome']
@@ -236,47 +235,138 @@ def load_chrsize():
                 yield chrom, int(size)
 
 
-def cnvpytor2vcf(infile, snp, fix=True):
-    unfixedfile = Path(infile).with_suffix(f".unfixed.vcf")
-    outfile = Path(infile).with_suffix(f".vcf")
-    stdout = run_command(
-        dict_to_cli_args(
-            {
-                "": cnvpytor2vcf,
-                "reference": genome,
-                "_": [infile, refdir],
-            },
-            prefix="-",
-        ),
-        stdout="return",
-    )
-    if fix:
-        unfixedfile.write_text(stdout)
+def parse_chrom(chrom, chromdir):
+    file = Path(chromdir) / f"{chrom}.fa"
+    if not file.exists():
+        warnings.warn(f"Chromosome file not found in refdir: {chrom}")
+        return ""
 
-        fixes = [
-            {
-                "kind": "format",
-                "id": "PE",
-                "fix": lambda obj: setattr(obj, 'Type', 'String')
-            },
-            {
-                "kind": "fields",
-                "fix": lambda items: items.__setitem__(-1, Path(bamfile).stem)
-            }
-        ]
+    seq = ""
+    with open(file) as f:
+        for line in f:
+            line = line.strip()
+            if not line:
+                continue
+            if line.startswith(">"):
+                seq = ""
+            else:
+                seq += line
+    return seq
+
+
+def cnvpytor2vcf(infile, snp):
+    # snp: in case to be used in the future
+    outfile = Path(infile).with_suffix(f".vcf")
+    # stdout = run_command(
+    #     dict_to_cli_args(
+    #         {
+    #             "": cnvnator2vcf,
+    #             "reference": genome,
+    #             "_": [infile, refdir],
+    #         },
+    #         prefix="-",
+    #     ),
+    #     stdout="return",
+    # )
+    ## command hangs
+    with open(infile) as fin, open(outfile, "w") as fout:
+        fout.write("##fileformat=VCFv4.2\n")
+        fout.write(f"##fileDate={datetime.now().strftime('%Y%m%d')}\n")
+        fout.write(f"##reference={genome}\n")
+        fout.write(f"##source=CNVpytor\n")
         for chrom, size in load_chrsize():
-            fixes.append({
-                "kind": "contig",
-                "append": True,
-                "fix": (
-                    lambda obj, chrom=chrom, size=size:
-                    HeaderContig(ID=chrom, length=size)
-                )
-            })
+            fout.write(f"##contig=<ID={chrom},length={size}>\n")
+        fout.write('##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant described in this record">\n')
+        fout.write('##INFO=<ID=IMPRECISE,Number=0,Type=Flag,Description="Imprecise structural variation">\n')
+        fout.write('##INFO=<ID=SVLEN,Number=1,Type=Integer,Description="Difference in length between REF and ALT alleles">\n')
+        fout.write('##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">\n')
+        fout.write('##INFO=<ID=natorRD,Number=1,Type=Float,Description="Normalized RD">\n')
+        fout.write('##INFO=<ID=natorP1,Number=1,Type=Float,Description="e-val by t-test">\n')
+        fout.write('##INFO=<ID=natorP2,Number=1,Type=Float,Description="e-val by Gaussian tail">\n')
+        fout.write('##INFO=<ID=natorP3,Number=1,Type=Float,Description="e-val by t-test (middle)">\n')
+        fout.write('##INFO=<ID=natorP4,Number=1,Type=Float,Description="e-val by Gaussian tail (middle)">\n')
+        fout.write('##INFO=<ID=natorQ0,Number=1,Type=Float,Description="Fraction of reads with 0 mapping quality">\n')
+        fout.write('##INFO=<ID=natorPE,Number=1,Type=Integer,Description="Number of paired-ends support the event">\n')
+        fout.write('##INFO=<ID=SAMPLES,Number=.,Type=String,Description="Sample genotyped to have the variant">\n')
+        fout.write('##ALT=<ID=DEL,Description="Deletion">\n')
+        fout.write('##ALT=<ID=DUP,Description="Duplication">\n')
+        fout.write('##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n')
+        fout.write('##FORMAT=<ID=CN,Number=1,Type=Integer,Description="Copy number genotype for imprecise events">\n')
+        fout.write('##FORMAT=<ID=PE,Number=1,Type=String,Description="Number of paired-ends that support the event">\n')
+        fout.write(f"#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t{Path(bamfile).stem}\n")
+        prev_chrom, chrom_seq, count = "", "", 0
+        for line in fin:
+            # type, coor, length, rd, p1, p2, p3, p4, q0, pe = line.strip("\n").split()
+            items = line.strip("\n").split()
+            type, coor, length = items[:3]
+            rd = float(items[3]) if len(items) > 3 else False
+            p1 = items[4] if len(items) > 4 else ""
+            p2 = items[5] if len(items) > 5 else ""
+            p3 = items[6] if len(items) > 6 else ""
+            p4 = items[7] if len(items) > 7 else ""
+            q0 = items[8] if len(items) > 8 else ""
+            pe = items[9] if len(items) > 9 else ""
+            chrom, pos = coor.split(":")
+            start, end = pos.split("-")
+            start, end = int(start), int(end)
+            is_del = type == "deletion"
+            is_dup = type == "duplication"
+
+            if not is_del and not is_dup:
+                warnings.warn(f"Skipping unrecognized CNV type: {type}")
+                continue
 
-        fix_vcffile(unfixedfile, outfile, fixes)
-    else:
-        outfile.write_text(stdout)
+            if chrom != prev_chrom:
+                chrom_seq = parse_chrom(chrom, refdir)
+                prev_chrom = chrom
+
+            count += 1
+            info = f"END={end}"
+            info += f";SVTYPE=DEL;SVLEN=-{length}" if is_del else f";SVTYPE=DUP;SVLEN={length}"
+            info += ";IMPRECISE"
+            info += f";natorRD={rd}" if rd is not False else ""
+            info += f";natorP1={p1}" if p1 else ""
+            info += f";natorP2={p2}" if p2 else ""
+            info += f";natorP3={p3}" if p3 else ""
+            info += f";natorP4={p4}" if p4 else ""
+            info += f";natorQ0={q0}" if q0 else ""
+            info += f";natorPE={pe}" if pe else ""
+
+            gt = "GT"
+            if rd is not False:
+                gt += ":CN"
+                gt += ":PE" if pe else ""
+                gt += "\t"
+                if is_del and rd < 0.25:
+                    gt += "1/1:0"
+                elif is_del and rd >= 0.25:
+                    gt += "0/1:1"
+                elif rd <= 1.75:
+                    gt += "0/1:2"
+                elif rd > 1.75 and rd <= 2.25:
+                    gt += "1/1:2"
+                elif rd > 2.25:
+                    gt += f"./2:{rd:.0f}"
+                else:
+                    gt = "GT:PE\t./." if pe else "GT\t./."
+
+                gt += f":{pe}" if pe else ""
+            else:
+                gt += "\t./."
+
+            fout.write("\t".join(
+                [
+                    chrom,
+                    str(start),
+                    f"CNVpytor_{'del_' if is_del else 'dup_'}{count}",
+                    chrom_seq[start - 1] if start < len(chrom_seq) else "N",
+                    "<DEL>" if is_del else "<DUP>",
+                    ".",
+                    "PASS",
+                    info,
+                    gt,
+                ]
+            ) + "\n")
 
 
 def do_case():
@@ -290,7 +380,7 @@ def do_case():
     rootfile = outdir / "file.pytor"
     case["j"] = case.get("j", ncores)
 
-    # read depth signal
+    logger.info("Reading depth signals ...")
     run_command(
         dict_to_cli_args(
             {
@@ -305,7 +395,7 @@ def do_case():
         fg=True,
     )
 
-    # predicting cnv
+    logger.info("Predicting CNVs ...")
     run_command(
         dict_to_cli_args(
             {
@@ -314,6 +404,7 @@ def do_case():
                 "his": binsizes,
             },
             prefix="-",
+            dup_key=False,
         ),
         fg=True,
     )
@@ -326,6 +417,7 @@ def do_case():
                 "partition": binsizes,
             },
             prefix="-",
+            dup_key=False,
         ),
         fg=True,
     )
@@ -336,6 +428,7 @@ def do_case():
         mask_snps = snp.pop("mask_snps", True)
         baf_nomask = snp.pop("baf_nomask", False)
 
+        logger.info("Importing SNP data ...")
         run_command(
             dict_to_cli_args(
                 {
@@ -350,6 +443,7 @@ def do_case():
         )
 
         if mask_snps:
+            logger.info("Masking 1000 Genome SNPs ...")
             run_command(
                 dict_to_cli_args(
                     {
@@ -362,6 +456,7 @@ def do_case():
                 fg=True,
             )
 
+        logger.info("Calculating BAF histograms ...")
         run_command(
             dict_to_cli_args(
                 {
@@ -375,8 +470,9 @@ def do_case():
             fg=True,
         )
 
-    # call
+    logger.info("Predicting CNV regions using joint caller ...")
     for binsize in binsizes:
+        logger.info(f"- binsize: {binsize}")
         outfile = outdir / f"calls{'.combined' if snp is not False else ''}.{binsize}.tsv"
         outfile_filtered = outdir / f"calls{'.combined' if snp is not False else ''}.{binsize}.filtered.tsv"
         run_command(
@@ -392,6 +488,7 @@ def do_case():
             stdout=outfile,
         )
 
+        logger.info("  Converting to other formats ...")
         cnvpytor2other(outfile, bool(snp), "gff")
         cnvpytor2other(outfile, bool(snp), "bed")
         cnvpytor2vcf(outfile, bool(snp))
@@ -424,6 +521,7 @@ def do_case():
         cnvpytor2vcf(outfile_filtered, bool(snp))
 
         # plots
+        logger.info("  Plotting ...")
         manplot = outdir / f"manhattan.{binsize}.png"
         run_command(
             dict_to_cli_args(

biopipen/scripts/bed/BedtoolsIntersect.py

@@ -0,0 +1,54 @@
+from pathlib import Path
+from biopipen.utils.misc import run_command, dict_to_cli_args, logger
+
+afile = Path({{in.afile | repr}})  # pyright: ignore # noqa: #999
+bfile = Path({{in.bfile | repr}})  # pyright: ignore
+outfile = {{out.outfile | repr}}  # pyright: ignore
+envs = {{envs | repr}}  # pyright: ignore
+
+bedtools = envs.pop("bedtools")
+sort = envs.pop("sort")
+chrsize = envs.pop("chrsize")
+postcmd = envs.pop("postcmd", None)
+outdir = Path(outfile).parent
+
+if chrsize and "g" in envs:
+    logger.warning("Ignoring envs.g because envs.chrsize is provided.")
+    envs["g"] = Path(chrsize).expanduser()
+elif chrsize:
+    envs["g"] = Path(chrsize).expanduser()
+
+if sort:
+    afile_sorted = outdir / f"{afile.stem}_sorted{afile.suffix}"
+    bfile_sorted = outdir / f"{bfile.stem}_sorted{bfile.suffix}"
+    run_command(
+        [bedtools, "sort", "-g", envs["g"], "-i", afile],
+        stdout=afile_sorted,
+    )
+    run_command(
+        [bedtools, "sort", "-g", envs["g"], "-i", bfile],
+        stdout=bfile_sorted,
+    )
+    afile = afile_sorted
+    bfile = bfile_sorted
+
+envs[""] = [bedtools, "intersect"]
+envs["a"] = afile
+envs["b"] = bfile
+envs.setdefault("sorted", True)
+
+if envs["sorted"] and not "g" in envs:
+    raise ValueError("envs.g is required or manullay set envs.sorted to False.")
+
+if postcmd:
+    ofile = Path(outfile).with_suffix(".prior.bt")
+    run_command(dict_to_cli_args(envs, prefix="-"), stdout=ofile)
+    postcmd_file = outdir / "_postcmd.sh"
+    postcmd_file.write_text(postcmd)
+    run_command(
+        ["bash", postcmd_file],
+        env={"infile": ofile, "outfile": outfile, "outdir": outdir},
+        fg=True,
+    )
+else:
+    run_command(dict_to_cli_args(envs, prefix="-"), stdout=outfile)

biopipen/scripts/bed/BedtoolsMerge.py

@@ -1,6 +1,6 @@
 from biopipen.utils import run_command, dict_to_cli_args
 
-inbed = {{in.inbed | repr}}  # pyright: ignore
+inbed = {{in.inbed | repr}}  # pyright: ignore # noqa: #999
 outbed = {{out.outbed | repr}}  # pyright: ignore
 envs = {{envs | repr}}  # pyright: ignore
 bedtools = envs.pop("bedtools", "bedtools")