biopipen 0.32.3__py3-none-any.whl → 0.33.1__py3-none-any.whl

biopipen/ns/snp.py

@@ -183,7 +183,7 @@ class PlinkFromVcf(Proc):
         vcf_idspace_to: convert all spaces in sample IDs to this character.
         set_missing_var_ids: update variant IDs using a template string,
             with a '@' where the chromosome code should go, and a '#' where the
-            base-pair position belongs. You can also specify `\$r` and `\$a` for
+            base-pair position belongs. You can also specify `\\$r` and `\\$a` for
             the reference and alternate alleles, respectively.
             See <https://www.cog-genomics.org/plink/2.0/data#set_all_var_ids>
         max_alleles (type=int): Maximum number of alleles per variant.
@@ -191,7 +191,7 @@ class PlinkFromVcf(Proc):
             Note that `_` will be replaced by `-` in the argument names.
     """  # noqa: E501
     input = "invcf:file"
-    output = "outdir:dir:{{in.invcf | regex_replace: '\\.gz$', '' | stem}}"
+    output = "outdir:dir:{{in.invcf.stem | regex_replace: '\\.gz$', ''}}"
     lang = config.lang.python
     envs = {
         "plink": config.exe.plink2,
@@ -217,7 +217,14 @@ class Plink2GTMat(Proc):
 
     The allelic dosage is used as the values of genotype matrix.
     "--keep-allele-order" is used to keep the allele order consistent with the
-    reference allele first.
+    reference allele first. This way, the genotype of homozygous reference alleles
+    will be encoded as 2, heterozygous as 1, and homozygous alternate alleles as 0.
+    This is the PLINK dosage encoding. If you want to use this encoding, you can
+    set `envs.gtcoding` to `plink`. Otherwise, the default encoding is `vcf`, which
+    will encode the genotype as 0, 1, and 2 for homozygous reference, heterozygous,
+    and homozygous alternate alleles, respectively.
+
+    Note that `envs.gtcoding = "vcf"` only works for biallelic variants for now.
 
     Input:
         indir: Input directory containing the PLINK files.
@@ -241,6 +248,11 @@ class Plink2GTMat(Proc):
             respectively.
         trans_chr: A dictionary to translate chromosome numbers to chromosome names.
         missing_id: what to use as the rs if missing.
+        gtcoding (choice): The genotype coding to use.
+            - vcf: 0/1/2 for homozygous reference, heterozygous, and homozygous
+                alternate alleles, respectively.
+            - plink: 2/1/0 for homozygous reference, heterozygous, and homozygous
+                alternate alleles, respectively.
     """
     input = "indir:dir"
     output = "outfile:file:{{in.indir | stem}}-gtmat.txt"
@@ -253,6 +265,7 @@ class Plink2GTMat(Proc):
         "varid": "{chr}_{pos}_{varid}_{ref}_{alt}",
         "trans_chr": {"23": "X", "24": "Y", "25": "XY", "26": "M"},
         "missing_id": "NA",
+        "gtcoding": "vcf",
     }
     script = "file://../scripts/snp/Plink2GTMat.py"
 

biopipen/ns/tcr.py

@@ -39,7 +39,8 @@ class ImmunarchLoading(Proc):
             information.
 
     Output:
-        rdsfile: The RDS file with the data and metadata
+        rdsfile: The RDS file with the data and metadata, which can be processed by
+            other `immunarch` functions.
         metatxt: The meta data at cell level, which can be used to attach to the Seurat object
 
     Envs:
@@ -1675,3 +1676,126 @@ class TCRDock(Proc):
         "data_dir": None,
     }
     script = "file://../scripts/tcr/TCRDock.py"
+
+
+class ScRepLoading(Proc):
+    """Load the single cell TCR/BCR data into a `scRepertoire` compatible object
+
+    This process loads the single cell TCR/BCR data into a `scRepertoire`
+    compatible object. Later, `scRepertoire::combineExpression` can be used to
+    combine the expression data with the TCR/BCR data.
+
+    For the data path specified at `TCRData` in the input file, we will first find
+    `filtered_contig_annotations.csv` and `filtered_config_annotations.csv.gz` in the
+    path. If neighter of them exists, we will find `all_contig_annotations.csv` and
+    `all_contig_annotations.csv.gz` in the path and a warning will be raised
+    (You can find it at `./.pipen/<pipeline-name>/ImmunarchLoading/<job.index>/job.stderr`).
+
+    If none of the files exists, an error will be raised.
+
+    Input:
+        metafile: The meta data of the samples
+            A tab-delimited file
+            Two columns are required:
+            * `Sample` to specify the sample names.
+            * `TCRData` to assign the path of the data to the samples,
+            and this column will be excluded as metadata.
+            Immunarch is able to fetch the sample names from the names of
+            the target files. However, 10x data yields result like
+            `filtered_contig_annotations.csv`, which doesn't have any name
+            information.
+
+    Output:
+        outfile: The `scRepertoire` compatible object in RDS format
+
+    Envs:
+        combineTCR (type=json): The extra arguments for `scRepertoire::combineTCR` function.
+            See also <https://www.borch.dev/uploads/screpertoire/reference/combinetcr>
+        exclude (auto): The columns to exclude from the metadata to add to the object.
+            A list of column names to exclude or a string with column names separated by `,`.
+            By default, `TCRData` and `RNAData` will be excluded.
+
+    """  # noqa: E501
+    input = "metafile:file"
+    output = "outfile:file:{{in.metafile | stem}}.scRep.RDS"
+    lang = config.lang.rscript
+    envs = {"combineTCR": {"samples": True}, "exclude": ["TCRData", "RNAData"]}
+    script = "file://../scripts/tcr/ScRepLoading.R"
+
+
+class ClonalStats(Proc):
+    """Visualize the clonal information.
+
+    Using [`scplotter`](https://github.com/pwwang/scplotter) to visualize the clonal
+    information.
+
+    Input:
+        screpfile: The `scRepertoire` object in RDS format
+
+    Output:
+        outdir: The output directory containing the plots
+
+    Envs:
+        mutaters (type=json;order=-9): The mutaters passed to `dplyr::mutate()` to add new variables.
+            When the object loaded form `in.screpfile` is a list, the mutaters will be applied to each element.
+            The keys are the names of the new variables, and the values are the expressions.
+            When it is a `Seurat` object, typically an output of `scRepertoire::combineExpression()`,
+            the mutaters will be applied to the `meta.data`.
+        viz_type (choice): The type of visualization to generate.
+            - volume: The volume of the clones using [`ClonalVolumePlot`](https://pwwang.github.io/scplotter/reference/ClonalVolumePlot.html)
+            - abundance: The abundance of the clones using [`ClonalAbundancePlot`](https://pwwang.github.io/scplotter/reference/ClonalAbundancePlot.html)
+            - length: The length of the CDR3 sequences using [`ClonalLengthPlot`](https://pwwang.github.io/scplotter/reference/ClonalLengthPlot.html)
+            - residency: The residency of the clones using [`ClonalResidencyPlot`](https://pwwang.github.io/scplotter/reference/ClonalResidencyPlot.html)
+            - dynamics: The dynamics of the clones using [`ClonalDynamicsPlot`](https://pwwang.github.io/scplotter/reference/ClonalDynamicsPlot.html)
+            - composition: The composition of the clones using [`ClonalCompositionPlot`](https://pwwang.github.io/scplotter/reference/ClonalCompositionPlot.html)
+            - overlap: The overlap of the clones using [`ClonalOverlapPlot`](https://pwwang.github.io/scplotter/reference/ClonalOverlapPlot.html)
+            - diversity: The diversity of the clones using [`ClonalDiversityPlot`](https://pwwang.github.io/scplotter/reference/ClonalDiversityPlot.html)
+            - geneusage: The gene usage of the clones using [`ClonalGeneUsagePlot`](https://pwwang.github.io/scplotter/reference/ClonalGeneUsagePlot.html)
+            - positional: The positional information of the clones using [`ClonalPositionalPlot`](https://pwwang.github.io/scplotter/reference/ClonalPositionalPlot.html)
+            - kmer: The kmer information of the clones using [`ClonalKmerPlot`](https://pwwang.github.io/scplotter/reference/ClonalKmerPlot.html)
+            - rarefaction: The rarefaction curve of the clones using [`ClonalRarefactionPlot`](https://pwwang.github.io/scplotter/reference/ClonalRarefactionPlot.html)
+        subset: An expression to subset the data before plotting.
+            Similar to `mutaters`, it will be applied to each element by `dplyr::filter()` if the object
+            loaded form `in.screpfile` is a list; otherwise, it will be applied to
+            `subset(sobj, subset = <expr>)` if the object is a `Seurat` object.
+        devpars (ns): The parameters for the plotting device.
+            - width (type=int): The width of the device
+            - height (type=int): The height of the device
+            - res (type=int): The resolution of the device
+        more_formats (list): The extra formats to save the plots in, other than PNG.
+        save_code (flag): Whether to save the code used to generate the plots
+            Note that the data directly used to generate the plots will also be saved in an `rda` file.
+            Be careful if the data is large as it may take a lot of disk space.
+        descr: The description of the plot, used to show in the report.
+        <more>: The arguments for the plot function
+            See the documentation of the corresponding plot function for the details
+        cases (type=json): The cases to generate the plots if we have multiple cases.
+            The keys are the names of the cases, and the values are the arguments for the plot function.
+            The arguments in `envs` will be used if not specified in `cases`, except for `mutaters`.
+            Sections can be specified as the prefix of the case name, separated by `::`.
+            For example, if you have a case named `Clonal Volume::Case1`, the plot will be put in the
+            section `Clonal Volume`. By default, when there are multiple cases for the same 'viz_type', the name of the 'viz_type' will be used
+            as the default section name (for example, when 'viz_type' is 'volume', the section name will be 'Clonal Volume').
+            When there is only a single case, the section name will default to 'DEFAULT', which will not be shown
+            in the report.
+    """  # noqa: E501
+    input = "screpfile:file"
+    output = "outdir:dir:{{in.screpfile | stem}}.clonalstats"
+    lang = config.lang.rscript
+    envs = {
+        "mutaters": {},
+        "subset": None,
+        "viz_type": None,
+        "devpars": {"width": None, "height": None, "res": 100},
+        "more_formats": [],
+        "save_code": False,
+        "descr": None,
+        "cases": {
+            "Clonal Volume": {"viz_type": "volume"},
+            "Clonal Abundance": {"viz_type": "abundance"},
+            "CDR3 Length": {"viz_type": "length"},
+            "Clonal Diversity": {"viz_type": "diversity"},
+        }
+    }
+    script = "file://../scripts/tcr/ClonalStats.R"
+    plugin_opts = {"report": "file://../reports/tcr/ClonalStats.svelte"}

biopipen/ns/vcf.py

@@ -595,6 +595,40 @@ class BcftoolsSort(Proc):
     script = "file://../scripts/vcf/BcftoolsSort.py"
 
 
+class BcftoolsMerge(Proc):
+    """Merge multiple VCF files using `bcftools merge`.
+
+    Input:
+        infiles: The input VCF files
+
+    Output:
+        outfile: The merged 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)
+        <more>: Other arguments for `bcftools merge`.
+            See also <https://samtools.github.io/bcftools/bcftools.html#merge>
+    """
+    input = "infiles:files"
+    output = (
+        "outfile:file:{{in.infiles | first | stem | append: '_etc_merged'}}.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,
+        "gz": True,
+        "index": True,
+    }
+    script = "file://../scripts/vcf/BcftoolsMerge.py"
+
+
 class BcftoolsView(Proc):
     """View, subset and filter VCF files by position and filtering expression.
 

biopipen/ns/web.py

@@ -32,7 +32,11 @@ class Download(Proc):
     input = "url"
     output = (
         "outfile:file:"
-        "{{in.url | basename | replace: '%2E', '.' | slugify: separator='.'}}"
+        """{{in.url
+            | basename
+            | url_decode
+            | slugify: separator='.', lowercase=False, regex_pattern='[^-a-zA-Z0-9_]+'
+        }}"""
     )
     lang = config.lang.python
     envs = {

biopipen/reports/scrna/SeuratClusterStats.svelte

@@ -1,7 +1,7 @@
 {% from "utils/misc.liq" import report_jobs, table_of_images -%}
 {% from_ os import path %}
 <script>
-    import { DataTable, Image, Descr } from "$libs";
+    import { DataTable, Image, Descr, Plotly } from "$libs";
     import { Tabs, Tab, TabContent } from "$ccs";
 </script>
 

biopipen/reports/scrna/SeuratMap2Ref.svelte

@@ -6,8 +6,21 @@
 {%- macro report_job(job, h=1) -%}
 
 <h{{h}}>UMAPs</h{{h}}>
-{% set imgs = job.outdir | glob: "UMAPs-*.png" %}
-{{ table_of_images(imgs) }}
+{% set imgs = [] %}
+{% set caps = [] %}
+{% for png in job.outdir | glob: "UMAPs-*.png" %}
+    {% set pdf = png | regex_replace: "\\.png$", ".pdf" %}
+    {% set stm = png | stem %}
+    {% set _ = imgs.append({"src": png, "download": pdf}) %}
+    {% set _ = caps.append(stm | replace: "UMAPs-", "") %}
+{% endfor %}
+{{ table_of_images(imgs, caps) }}
+
+<h{{h}}>Mapping Score</h{{h}}>
+<Image
+    src="{{job.outdir | joinpath: 'mapping_score.png'}}"
+    download="{{job.outdir | joinpath: 'mapping_score.pdf'}}"
+    />
 
 <h{{h}}>Stats</h{{h}}>
 {% for stfile in job.outdir | glob: "stats-*.txt" %}

biopipen/reports/tcr/ClonalStats.svelte

@@ -0,0 +1,15 @@
+{% from "utils/misc.liq" import report_jobs, table_of_images -%}
+
+<script>
+    import { Image, DataTable, Descr } from "$libs";
+</script>
+
+{%- macro report_job(job, h=1) -%}
+    {{ job | render_job: h=h }}
+{%- endmacro -%}
+
+{%- macro head_job(job) -%}
+    <h1>{{job.in.screpfile | stem | escape }}</h1>
+{%- endmacro -%}
+
+{{ report_jobs(jobs, head_job, report_job) }}

biopipen/reports/utils/misc.liq

@@ -25,7 +25,14 @@ import { Image } from "$libs";
 {% for batch_srcs in srcs | batch: col, "" %}
 {% set outer_loop = loop %}
 <tr>
-    {% for src in batch_srcs %}
+    {% for srcinfo in batch_srcs %}
+        {% if srcinfo | isinstance: str %}
+            {% set src = srcinfo %}
+            {% set download = None %}
+        {% else %}
+            {% set src = srcinfo['src'] %}
+            {% set download = srcinfo.get('download', None) %}
+        {% endif %}
         {% set i = col * outer_loop.index0 + loop.index0 %}
         {% if i >= len(srcs) %}
             <td style="width: {{table_width / col}}%"></td>
@@ -33,21 +40,27 @@ import { Image } from "$libs";
         <td style="width: {{table_width / col}}%; vertical-align:top;">
             {% if caps is none %}
             <div
-                style="padding-left: 28px; font-weight: bold; padding-top: 10px; margin-bottom: -10px;">
+                style="padding-left: 28px; font-weight: bold; padding-top: 16px;">
                 {{ src | stem }}
             </div>
             {% elif caps is false %}
             {% else %}
             <div
-                style="padding-left: 28px; font-weight: bold; padding-top: 10px; margin-bottom: -10px;">
+                style="padding-left: 28px; font-weight: bold; padding-top: 16px;">
                 {{ caps[i] }}
             </div>
             {% endif %}
-            {% if src | replace: ".png", ".pdf" | exists %}
-                <Image style="max-width: 90%" src={{src | quote}}
-                    download={{src | replace: ".png", ".pdf" | quote}} />
+            {% if download %}
+                <Image
+                    style="max-width: 90%"
+                    src={{src | quote}}
+                    download={ {{download | json}} }
+                />
             {% else %}
-                <Image style="max-width: 90%" src={{src | quote}} />
+                <Image
+                    style="max-width: 90%"
+                    src={{src | quote}}
+                />
             {% endif %}
         </td>
         {% endif %}

biopipen/scripts/bam/BamMerge.py

@@ -1,8 +1,8 @@
 from pathlib import Path
 from biopipen.utils.misc import run_command, logger
 
-bamfiles = {{in.bamfiles | repr}}  # pyright: ignore # noqa
-outfile = Path({{out.outfile | repr}})  # pyright: ignore
+bamfiles = {{in.bamfiles | default: [] | each: str}}  # pyright: ignore # noqa
+outfile = Path({{out.outfile | quote}})  # pyright: ignore
 ncores = {{envs.ncores | int}}  # pyright: ignore
 tool = {{envs.tool | quote}}  # pyright: ignore
 samtools = {{envs.samtools | quote}}  # pyright: ignore

biopipen/scripts/bam/BamSampling.py

@@ -4,12 +4,12 @@ from biopipen.utils.misc import run_command, logger
 # using:
 # samtools view --subsample 0.1 --subsample-seed 1234 --threads 4 -b -o out.bam in.bam
 
-bamfile = {{ in.bamfile | repr }} # pyright: ignore # noqa
-outfile = Path({{ out.outfile | repr }}) # pyright: ignore
+bamfile = {{ in.bamfile | quote }} # pyright: ignore # noqa
+outfile = Path({{ out.outfile | quote }}) # pyright: ignore
 ncores = {{ envs.ncores | int }} # pyright: ignore
 samtools = {{ envs.samtools | repr }} # pyright: ignore
 tool = {{ envs.tool | repr }} # pyright: ignore
-fraction = {{ envs.fraction | repr }} # pyright: ignore
+fraction: float = {{ envs.fraction | repr }} # pyright: ignore
 seed = {{ envs.seed | int }} # pyright: ignore
 should_index = {{ envs.index | repr }} # pyright: ignore
 should_sort = {{ envs.sort | repr }} # pyright: ignore
@@ -38,7 +38,7 @@ if fraction > 1:
         "-c",
         bamfile
     ]
-    nreads = run_command(cmd, stdout="return").strip()
+    nreads = run_command(cmd, stdout="return").strip()  # type: ignore
     fraction = fraction / float(int(nreads))
 
 ofile = (

biopipen/scripts/bam/BamSort.py

@@ -0,0 +1,141 @@
+from hashlib import md5
+from pathlib import Path
+from biopipen.utils.misc import run_command, dict_to_cli_args
+
+infile: str = {{ in.bamfile | quote }} # pyright: ignore # noqa
+outfile = Path({{ out.outfile | quote }}) # pyright: ignore
+args: dict = {{ envs | dict | repr }} # pyright: ignore
+ncores = args.pop("ncores")
+tool = args.pop("tool")
+samtools = args.pop("samtools")
+sambamba = args.pop("sambamba")
+tmpdir = args.pop("tmpdir")
+byname = args.pop("byname")
+should_index = args.pop("index")
+sig = md5(infile.encode()).hexdigest()
+tmpdir = Path(tmpdir).joinpath(
+    f"biopipen_BamSort_{{job.index}}_{sig}_{Path(infile).name}"
+)
+tmpdir.mkdir(parents=True, exist_ok=True)
+tmpdir = str(tmpdir)
+
+
+def use_samtools():
+    """Use samtools to sort/index bam file.
+
+    Usage: samtools sort [options...] [in.bam]
+    Options:
+    -l INT     Set compression level, from 0 (uncompressed) to 9 (best)
+    -u         Output uncompressed data (equivalent to -l 0)
+    -m INT     Set maximum memory per thread; suffix K/M/G recognized [768M]
+    -M         Use minimiser for clustering unaligned/unplaced reads
+    -K INT     Kmer size to use for minimiser [20]
+    -n         Sort by read name (not compatible with samtools index command)
+    -t TAG     Sort by value of TAG. Uses position as secondary index (or read name if -n is set)
+    -o FILE    Write final output to FILE rather than standard output
+    -T PREFIX  Write temporary files to PREFIX.nnnn.bam
+        --no-PG
+                Do not add a PG line
+        --template-coordinate
+                Sort by template-coordinate
+        --input-fmt-option OPT[=VAL]
+                Specify a single input file format option in the form
+                of OPTION or OPTION=VALUE
+    -O, --output-fmt FORMAT[,OPT[=VAL]]...
+                Specify output format (SAM, BAM, CRAM)
+        --output-fmt-option OPT[=VAL]
+                Specify a single output file format option in the form
+                of OPTION or OPTION=VALUE
+        --reference FILE
+                Reference sequence FASTA FILE [null]
+    -@, --threads INT
+                Number of additional threads to use [0]
+        --write-index
+                Automatically index the output files [off]
+        --verbosity INT
+                Set level of verbosity
+    """  # noqa
+    sargs = args.copy()
+    sargs["n"] = byname
+    sargs["T"] = f"{tmpdir}/tmp"
+    sargs["threads"] = ncores
+
+    if should_index:
+        sargs["write-index"] = True
+        # https://github.com/samtools/samtools/issues/1196
+        sargs["o"] = f"{outfile}##idx##{outfile}.bai"
+    else:
+        sargs["o"] = outfile
+
+    n_outfmt = sum(["O" in sargs, "output-fmt" in sargs])
+    if n_outfmt > 1:
+        raise ValueError(
+            "envs.args cannot contain both 'O' and 'output-fmt'"
+        )
+    if n_outfmt == 0:
+        sargs["O"] = "BAM"
+
+    cmd = [
+        samtools,
+        "sort",
+        *dict_to_cli_args(sargs),
+        infile,
+    ]
+    run_command(cmd)
+
+
+def use_sambamba():
+    """Use sambamba to sort/index bam file.
+
+    sambamba 0.8.2
+    by Artem Tarasov and Pjotr Prins (C) 2012-2021
+        LDC 1.28.1 / DMD v2.098.1 / LLVM12.0.0 / bootstrap LDC - the LLVM D compiler (1.28.1)
+
+    Usage: sambamba-sort [options] <input.bam>
+
+    Options: -m, --memory-limit=LIMIT
+                approximate total memory limit for all threads (by default 2GB)
+            --tmpdir=TMPDIR
+                directory for storing intermediate files; default is system directory for temporary files
+            -o, --out=OUTPUTFILE
+                output file name; if not provided, the result is written to a file with .sorted.bam extension
+            -n, --sort-by-name
+                sort by read name instead of coordinate (lexicographical order)
+            --sort-picard
+                sort by query name like in picard
+            -N, --natural-sort
+                sort by read name instead of coordinate (so-called 'natural' sort as in samtools)
+            -M, --match-mates
+                pull mates of the same alignment together when sorting by read name
+            -l, --compression-level=COMPRESSION_LEVEL
+                level of compression for sorted BAM, from 0 to 9
+            -u, --uncompressed-chunks
+                write sorted chunks as uncompressed BAM (default is writing with compression level 1), that might be faster in some cases but uses more disk space
+            -p, --show-progress
+                show progressbar in STDERR
+            -t, --nthreads=NTHREADS
+                use specified number of threads
+            -F, --filter=FILTER
+                keep only reads that satisfy FILTER
+    """  # noqa
+    sargs = args.copy()
+    sargs["nthreads"] = ncores
+    sargs["n"] = byname
+    sargs["tmpdir"] = tmpdir
+    sargs["o"] = outfile
+    cmd = [
+        sambamba,
+        "sort",
+        *dict_to_cli_args(sargs, sep="="),
+        infile,
+    ]
+    run_command(cmd)
+
+
+if __name__ == "__main__":
+    if tool == "samtools":
+        use_samtools()
+    elif tool == "sambamba":
+        use_sambamba()
+    else:
+        raise ValueError(f"Unknown tool: {tool}")

biopipen/scripts/bam/BamSplitChroms.py

@@ -2,12 +2,12 @@ from pathlib import Path
 from biopipen.utils.misc import run_command
 from biopipen.utils.reference import bam_index
 
-bamfile = {{in.bamfile | quote}}  # pyright: ignore
-outdir = {{out.outdir | quote}}  # pyright: ignore
-tool = {{envs.tool | quote}}  # pyright: ignore
-samtools = {{envs.samtools | quote}}  # pyright: ignore
-sambamba = {{envs.sambamba | quote}}  # pyright: ignore
-ncores = {{envs.ncores | repr}}  # pyright: ignore
+bamfile: str = {{in.bamfile | quote}}  # pyright: ignore  # noqa
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
+tool: str = {{envs.tool | quote}}  # pyright: ignore
+samtools: str = {{envs.samtools | quote}}  # pyright: ignore
+sambamba: str = {{envs.sambamba | quote}}  # pyright: ignore
+ncores: int = {{envs.ncores | repr}}  # pyright: ignore
 keep_other_sq = {{envs.keep_other_sq | repr}}  # pyright: ignore
 chroms_to_keep = {{envs.chroms | repr}}  # pyright: ignore
 should_index = {{envs.index | bool}}  # pyright: ignore
@@ -17,13 +17,13 @@ def _remove_other_sq(infile, chrom, outfile):
     exe = samtools if tool == "samtools" else sambamba
     print("\nRemoving other chromosomes in @SQ in header")
     header_cmd = [exe, "view", "-H", infile]
-    header_p = run_command(
+    header_p = run_command(  # type: ignore
         header_cmd,
         stdout=True,
         wait=False,
         print_command=True,
     )
-    header = header_p.stdout.read().decode().strip().splitlines()
+    header = header_p.stdout.read().decode().strip().splitlines()  # type: ignore
     new_header = []
     for line in header:
         if line.startswith("@SQ"):
@@ -63,7 +63,7 @@ def use_samtools():
             "| grep '^@SQ' | cut -f 2 | cut -d ':' -f 2"
         )
         p = run_command(cmd, stdout=True, wait=False)
-        chroms = p.stdout.read().decode().strip().splitlines()
+        chroms = p.stdout.read().decode().strip().splitlines()  # type: ignore
     else:
         print("\nUsing provided chromosomes")
         chroms = chroms_to_keep
@@ -121,7 +121,7 @@ def use_sambamba():
             "| grep '^@SQ' | cut -f 2 | cut -d ':' -f 2"
         )
         p = run_command(cmd, stdout=True, wait=False)
-        chroms = p.stdout.read().decode().splitlines()
+        chroms = p.stdout.read().decode().splitlines()  # type: ignore
     else:
         print("\nUsing provided chromosomes")
         chroms = chroms_to_keep

biopipen/scripts/bam/BamSubsetByBed.py

@@ -4,9 +4,9 @@ from biopipen.utils.misc import run_command, logger
 # using:
 # samtools view --subsample 0.1 --subsample-seed 1234 --threads 4 -b -o out.bam in.bam
 
-bamfile = {{ in.bamfile | repr }} # pyright: ignore # noqa
-bedfile = {{ in.bedfile | repr }} # pyright: ignore # noqa
-outfile = Path({{ out.outfile | repr }}) # pyright: ignore
+bamfile = {{ in.bamfile | quote }} # pyright: ignore # noqa
+bedfile = {{ in.bedfile | quote }} # pyright: ignore # noqa
+outfile = Path({{ out.outfile | quote }}) # pyright: ignore
 ncores = {{ envs.ncores | int }} # pyright: ignore
 samtools = {{ envs.samtools | repr }} # pyright: ignore
 tool = {{ envs.tool | repr }} # pyright: ignore

biopipen/scripts/bam/CNVpytor.py

@@ -6,17 +6,17 @@ from datetime import datetime
 from biopipen.utils.reference import bam_index
 from biopipen.utils.misc import run_command, dict_to_cli_args, logger
 
-bamfile = {{in.bamfile | quote}}  # pyright: ignore # noqa
-snpfile = {{in.snpfile | repr}}  # pyright: ignore
+bamfile: str = {{in.bamfile | quote}}  # pyright: ignore # noqa
+snpfile: str = {{in.snpfile | quote}}  # pyright: ignore
 outdir = Path({{out.outdir | quote}})  # pyright: ignore
-cnvpytor = {{envs.cnvpytor | quote}}  # pyright: ignore
-samtools = {{envs.samtools | quote}}  # pyright: ignore
-ncores = {{envs.ncores | int}}  # pyright: ignore
+cnvpytor: str = {{envs.cnvpytor | quote}}  # pyright: ignore
+samtools: str = {{envs.samtools | quote}}  # pyright: ignore
+ncores: int = {{envs.ncores | int}}  # pyright: ignore
 refdir = {{envs.refdir | quote}}  # pyright: ignore
 genome = {{envs.genome | quote}}  # pyright: ignore
-chrsize = {{envs.chrsize | quote}}  # pyright: ignore
-filters = {{envs.filters | repr}}  # pyright: ignore
-args = {{envs | repr}}  # pyright: ignore
+chrsize: str = {{envs.chrsize | quote}}  # pyright: ignore
+filters: dict = {{envs.filters | repr}}  # pyright: ignore
+args: dict = {{envs | dict}}  # pyright: ignore
 
 del args['cnvpytor']
 del args['ncores']
@@ -27,7 +27,7 @@ del args['chrsize']
 del args['filters']
 
 
-bamfile = bam_index(bamfile, outdir, samtools, ncores)
+bamfile: Path = bam_index(bamfile, str(outdir), samtools, ncores=ncores)
 
 NOSNP_COLS = [
     "CNVtype",
@@ -293,7 +293,7 @@ def cnvpytor2vcf(infile, snp):
         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")
+        fout.write(f"#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t{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()