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

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.28.1"
+__version__ = "0.29.0"

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/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/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/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/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/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/ns/gene.py

@@ -9,46 +9,91 @@ class GeneNameConversion(Proc):
 
     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:
-        inopts: Options to read `in.infile` for `pandas.read_csv()`
-            See https://pandas.pydata.org/docs/reference/api/pandas.read_csv.html
-        outopts: Options to write `out.outfile` for `pandas.to_csv()`
-            See https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.to_csv.html
-        notfound: 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
-            error: Report error
-        genecol: The index (0-based) or name of the column where
-            genes are present
-        output: How to output
-            keep: Keep the original name column and add new converted columns
-            drop: Drop the original name column, and add the converted names
-            replace: Drop the original name column, and insert
-                the converted names at the original position
-            only: Only keep the query and the converted name columns
+        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
+        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.python
+    lang = config.lang.rscript
     envs = {
-        "inopts": {"sep": "\t", "index_col": False},
-        "outopts": {"sep": "\t", "index": False},
         "notfound": "error",
-        "genecol": 0,
-        "output": "keep",
+        "genecol": 1,
+        "dup": "first",
+        "output": "append",
         "infmt": ["symbol", "alias"],
         "outfmt": "symbol",
         "species": "human",
     }
-    script = "file://../scripts/gene/GeneNameConversion.py"
+    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/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"

biopipen/ns/plot.py

@@ -150,3 +150,149 @@ class ROC(Proc):
         "show_auc": True,
     }
     script = "file://../scripts/plot/ROC.R"
+
+
+class Manhattan(Proc):
+    """Plot Manhattan plot.
+
+    Using the [`ggmanh`](https://bioconductor.org/packages/devel/bioc/vignettes/ggmanh/inst/doc/ggmanh.html) package.
+    Requires `ggmanh` v1.9.6 or later.
+
+    Input:
+        infile: The input file for data
+            It should contain at least three columns, the chromosome, the position
+            and the p-value of the SNPs.
+            Header is required.
+
+    Output:
+        outfile: The output figure file
+
+    Envs:
+        chrom_col: The column for chromosome
+            An integer (1-based) or a string indicating the column name.
+        pos_col: The column for position
+            An integer (1-based) or a string indicating the column name.
+        pval_col: The column for p-value
+            An integer (1-based) or a string indicating the column name.
+        label_col: The column for label.
+            Once specified, the significant SNPs will be labeled on the plot.
+        devpars (ns): The parameters for `png()`
+            - res (type=int): The resolution
+            - width (type=int): The width
+            - height (type=int): The height
+        title: The title of the plot
+        ylabel: The y-axis label
+        rescale (flag): Whether to rescale the p-values
+        rescale_ratio_threshold (type=float): Threshold of that triggers the rescale
+        signif (auto): A single value or a list of values to indicate the significance levels
+            Multiple values should be also separated by comma (`,`).
+            The minimum value will be used as the cutoff to determine if the SNPs are significant.
+        hicolors (auto): The colors for significant and non-significant SNPs
+            If a single color is given, the non-significant SNPs will be in grey.
+            Set it to None to disable the highlighting.
+        thin_n (type=int): Number of max points per horizontal partitions of the plot.
+            `0` or `None` to disable thinning.
+        thin_bins (type=int): Number of bins to partition the data.
+        zoom (auto): Chromosomes to zoom in
+            Each chromosome should be separated by comma (`,`) or in a list. Single chromosome is also accepted.
+            Ranges are also accepted, see `envs.chroms`.
+            Each chromosome will be saved in a separate file.
+        zoom_devpars (ns): The parameters for the zoomed plot
+            - width (type=int): The width
+            - height (type=int): The height, inherited from `devpars` by default
+            - res (type=int): The resolution, inherited from `devpars` by default
+        chroms (auto): The chromosomes and order to plot
+            A hyphen (`-`) can be used to indicate a range.
+            For example `chr1-22,chrX,chrY,chrM` will plot all autosomes, X, Y and M.
+            if `auto`, only the chromosomes in the data will be plotted in the order
+            they appear in the data.
+        args (ns): Additional arguments for `manhattan_plot()`.
+            See <https://rdrr.io/github/leejs-abv/ggmanh/man/manhattan_plot.html>.
+            Note that `-` will be replaced by `.` in the argument names.
+            - <more>: Additional arguments for `manhattan_plot()`
+    """  # noqa: E501
+    input = "infile:file"
+    output = "outfile:file:{{in.infile | stem0}}.manhattan.png"
+    lang = config.lang.rscript
+    envs = {
+        "chrom_col": 1,
+        "pos_col": 2,
+        "pval_col": 3,
+        "label_col": None,
+        "devpars": {"res": 100, "width": 1000, "height": 500},
+        "zoom_devpars": {"width": 500, "height": None, "res": None},
+        "title": "Manhattan Plot",
+        "ylabel": "-log10(p-value)",
+        "rescale": True,
+        "rescale_ratio_threshold": 5,
+        "signif": [5e-8, 1e-5],
+        "hicolors": None,
+        "thin_n": None,
+        "thin_bins": 200,
+        "zoom": None,
+        "chroms": "auto",
+        "args": {},
+    }
+    script = "file://../scripts/plot/Manhattan.R"
+
+
+class QQPlot(Proc):
+    """Generate QQ-plot or PP-plot using qqplotr.
+
+    See <https://cran.r-project.org/web/packages/qqplotr/vignettes/introduction.html>.
+
+    Input:
+        infile: The input file for data
+            It should contain at least one column of p-values or the values to be
+            plotted. Header is required.
+
+    Output:
+        outfile: The output figure file
+
+    Envs:
+        val_col: The column for values to be plotted
+            An integer (1-based) or a string indicating the column name.
+        devpars (ns): The parameters for `png()`
+            - res (type=int): The resolution
+            - width (type=int): The width
+            - height (type=int): The height
+        xlabel: The x-axis label
+        ylabel: The y-axis label
+        title: The title of the plot
+        trans: The transformation of the values
+            You can use `-log10` to transform the values to `-log10(values)`.
+            Otherwise you can a direct R function or a custom R function.
+            For example `function(x) -log10(x)`.
+        kind (choice): The kind of the plot, `qq` or `pp`
+            - qq: QQ-plot
+            - pp: PP-plot
+        band (ns): The arguments for `stat_qq_band()` or `stat_pp_band()`
+            See <https://rdrr.io/cran/qqplotr/man/stat_qq_band.html> and
+            <https://rdrr.io/cran/qqplotr/man/stat_pp_band.html>.
+            - <more>: Additional arguments for `stat_qq_band()` or `stat_pp_band()`
+        line (ns): The arguments for `stat_qq_line()` or `stat_pp_line()`
+            See <https://rdrr.io/cran/qqplot/man/stat_qq_line.html> and
+            <https://rdrr.io/cran/qqplot/man/stat_pp_line.html>.
+            - <more>: Additional arguments for `stat_qq_line()` or `stat_pp_line()`
+        point (ns): The arguments for `geom_qq_point()` or `geom_pp_point()`
+            See <https://rdrr.io/cran/qqplot/man/stat_qq_point.html> and
+            <https://rdrr.io/cran/qqplot/man/stat_pp_point.html>.
+        ggs (list): Additional ggplot expression to adjust the plot.
+    """
+    input = "infile:file"
+    output = "outfile:file:{{in.infile | stem}}.{{envs.kind}}.png"
+    lang = config.lang.rscript
+    envs = {
+        "val_col": 1,
+        "devpars": {"res": 100, "width": 1000, "height": 1000},
+        "xlabel": "Theoretical Quantiles",
+        "ylabel": "Observed Quantiles",
+        "title": "QQ-plot",
+        "trans": None,
+        "kind": "qq",
+        "band": {},
+        "line": {},
+        "point": {},
+        "ggs": None,
+    }
+    script = "file://../scripts/plot/QQPlot.R"