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

biopipen/ns/cellranger.py

@@ -0,0 +1,186 @@
+"""Cellranger pipeline module for BioPipen"""
+from ..core.proc import Proc
+from ..core.config import config
+
+
+class CellRangerCount(Proc):
+    """Run cellranger count
+
+    to count gene expression and/or feature barcode reads
+    requires cellranger v7+.
+
+    Input:
+        fastqs: The input fastq files
+            Either a list of fastq files or a directory containing fastq files
+            If a directory is provided, it should be passed as a list with one
+            element.
+        id: The id defining output directory. If not provided, it is inferred
+            from the fastq files.
+            Note that, unlike the `--id` argument of cellranger, this will not select
+            the samples from `in.fastqs`. In stead, it will symlink the fastq files
+            to a temporary directory with this `id` as prefix and pass that to
+            cellranger.
+
+    Output:
+        outdir: The output directory
+
+    Envs:
+        ncores: Number of cores to use
+        cellranger: Path to cellranger
+        ref: Path of folder containing 10x-compatible transcriptome reference
+        tmpdir: Path to temporary directory, used to save the soft-lined fastq files
+            to pass to cellranger
+        outdir_is_mounted (flag): A flag indicating whether the output directory is
+            on a mounted filesystem. As of `cellranger` v9.0.1, `cellranger vdj` will
+            fail when trying to copy/operate files to a mounted filesystem.
+            See <https://github.com/10XGenomics/cellranger/issues/210> and
+            <https://github.com/10XGenomics/cellranger/issues/250> for similar issues.
+            If that is the case, set this flag to `True` to use `envs.tmpdir` as
+            the output directory for `cellranger vdj`, and then move the results
+            to the final output directory after `cellranger vdj` finishes.
+            In this case, make sure that `envs.tmpdir` must have enough space and
+            it must be a local filesystem.
+        copy_outs_only (flag): If `outdir_is_mounted` is `True`, set this flag to `True`
+            to only copy the `outs` folder from the temporary output directory
+            to the final output directory, instead of the whole output directory.
+        include_introns (flag): Set to false to exclude intronic reads in count.
+        create_bam (flag): Enable or disable BAM file generation.
+            This is required by cellrange v8+. When using cellrange v8-, it will be
+            transformed to `--no-bam`.
+        <more>: Other environment variables required by `cellranger count`
+            See `cellranger count --help` for more details or
+            <https://www.10xgenomics.com/support/software/cell-ranger/advanced/cr-command-line-arguments#count>
+    """  # noqa: E501
+    input = "fastqs:files, id"
+    output = """outdir:dir:
+        {%- set fastqs = in.fastqs -%}
+        {%- if len(fastqs) == 1 and isdir(fastqs[0]) -%}
+            {%- set fastqs = fastqs[0] | glob: "*.fastq.gz" -%}
+        {%- endif -%}
+        {%- if in.id -%}
+            {{in.id}}
+        {%- else -%}
+            {%- set id = commonprefix(*fastqs) |
+                regex_replace: "_L\\d+(:?_.*)?$", "" |
+                regex_replace: "_S\\d+$", "" -%}
+            {{- id -}}
+        {%- endif -%}
+    """
+    lang = config.lang.python
+    envs = {
+        "ncores": config.misc.ncores,
+        "cellranger": config.exe.cellranger,
+        "ref": config.ref.ref_cellranger_gex,
+        "tmpdir": config.path.tmpdir,
+        "outdir_is_mounted": False,
+        "copy_outs_only": True,
+        "include_introns": True,
+        "create_bam": False,
+    }
+    script = "file://../scripts/cellranger/CellRangerCount.py"
+    plugin_opts = {
+        "report": "file://../reports/cellranger/CellRangerCount.svelte",
+        "report_paging": 5,
+    }
+
+
+class CellRangerVdj(Proc):
+    """Run cellranger vdj
+
+    to perform sequence assembly and paired clonotype calling.
+    requires cellranger v7+.
+
+    Input:
+        fastqs: The input fastq files
+            Either a list of fastq files or a directory containing fastq files
+            If a directory is provided, it should be passed as a list with one
+            element.
+        id: The id determining the output directory. If not provided, it is inferred
+            from the fastq files.
+
+    Output:
+        outdir: The output directory
+
+    Envs:
+        ncores: Number of cores to use
+        cellranger: Path to cellranger
+        ref: Path of folder containing 10x-compatible transcriptome reference
+        tmpdir: Path to temporary directory, used to save the soft-lined fastq files
+            to pass to cellranger.
+        outdir_is_mounted (flag): A flag indicating whether the output directory is
+            on a mounted filesystem. As of `cellranger` v9.0.1, `cellranger vdj` will
+            fail when trying to copy the VDJ reference files to a mounted filesystem.
+            See <https://github.com/10XGenomics/cellranger/issues/210> and
+            <https://github.com/10XGenomics/cellranger/issues/250> for similar issues.
+            If that is the case, set this flag to `True` to use `envs.tmpdir` as
+            the output directory for `cellranger vdj`, and then move the results
+            to the final output directory after `cellranger vdj` finishes.
+            In this case, make sure that `envs.tmpdir` must have enough space and
+            it must be a local filesystem.
+        copy_outs_only (flag): If `outdir_is_mounted` is `True`, set this flag to `True`
+            to only copy the `outs` folder from the temporary output directory
+            to the final output directory, instead of the whole output directory.
+        <more>: Other environment variables required by `cellranger vdj`
+            See `cellranger vdj --help` for more details or
+            <https://www.10xgenomics.com/support/software/cell-ranger/advanced/cr-command-line-arguments#vdj>
+    """  # noqa: E501
+    input = "fastqs:files, id"
+    output = """outdir:dir:
+        {%- set fastqs = in.fastqs -%}
+        {%- if len(fastqs) == 1 and isdir(fastqs[0]) -%}
+            {%- set fastqs = fastqs[0] | glob: "*.fastq.gz" -%}
+        {%- endif -%}
+        {%- if in.id -%}
+            {{in.id}}
+        {%- else -%}
+            {%- set id = commonprefix(*fastqs) |
+                regex_replace: "_L\\d+(:?_.*)?$", "" |
+                regex_replace: "_S\\d+$", "" -%}
+            {{- id -}}
+        {%- endif -%}
+    """
+    lang = config.lang.python
+    envs = {
+        "ncores": config.misc.ncores,
+        "cellranger": config.exe.cellranger,
+        "ref": config.ref.ref_cellranger_vdj,
+        "outdir_is_mounted": False,
+        "copy_outs_only": True,
+        "tmpdir": config.path.tmpdir,
+    }
+    script = "file://../scripts/cellranger/CellRangerVdj.py"
+    plugin_opts = {
+        "report": "file://../reports/cellranger/CellRangerVdj.svelte",
+        "report_paging": 5,
+    }
+
+
+class CellRangerSummary(Proc):
+    """Summarize cellranger metrics
+
+    Input:
+        indirs: The directories containing cellranger results
+            from `CellRangerCount`/`CellRangerVdj`.
+
+    Output:
+        outdir: The output directory
+
+    Envs:
+        group (type=auto): The group of the samples for boxplots.
+            If `None`, don't do boxplots.
+            It can be a dict of group names and sample names, e.g.
+            `{"group1": ["sample1", "sample2"], "group2": ["sample3"]}`
+            or a file containing the group information, with the first column
+            being the sample names and the second column being the group names.
+            The file should be tab-delimited with no header.
+    """
+    input = "indirs:dirs"
+    input_data = lambda ch: [list(ch.iloc[:, 0])]
+    output = "outdir:dir:{{in.indirs | first | stem | append: '-etc.summary'}}"
+    lang = config.lang.rscript
+    script = "file://../scripts/cellranger/CellRangerSummary.R"
+    envs = {"group": None}
+    plugin_opts = {
+        "report": "file://../reports/cellranger/CellRangerSummary.svelte",
+        "report_paging": 8,
+    }

biopipen/ns/cellranger_pipeline.py

@@ -0,0 +1,126 @@
+"""The cellranger pipelines
+
+Primarily cellranger process plus summary for summarizing the metrics for
+multiple samples.
+"""
+from __future__ import annotations
+from typing import TYPE_CHECKING
+
+from diot import Diot
+from pipen.utils import is_loading_pipeline
+from pipen_args.procgroup import ProcGroup
+
+if TYPE_CHECKING:
+    from pipen import Proc
+
+
+class CellRangerCountPipeline(ProcGroup):
+    """The cellranger count pipeline
+
+    Run cellranger count for multiple samples and summarize the metrics.
+
+    Args:
+        input (list): The list of lists of fastq files.
+            or the list of comma-separated string of fastq files.
+        ids (list): The list of ids for the samples.
+    """
+    DEFAULTS = Diot(input=None, ids=None)
+
+    def post_init(self):
+        """Check if the input is a list of fastq files"""
+        if not is_loading_pipeline("-h", "-h+", "--help", "--help+") and (
+            not isinstance(self.opts.input, (list, tuple))
+            or len(self.opts.input) == 0
+        ):
+            raise TypeError(
+                "The input of `CellRangerCountPipeline` should be a list of lists of "
+                "fastq files."
+            )
+
+        if isinstance(self.opts.input, (list, tuple)):
+            self.opts.input = [
+                [y.strip() for y in x.split(",")]
+                if isinstance(x, str)
+                else x
+                for x in self.opts.input
+            ]
+
+    @ProcGroup.add_proc
+    def p_cellranger_count(self) -> Proc:
+        """Build CellRangerCount process"""
+        from .cellranger import CellRangerCount as _CellRangerCount
+
+        class CellRangerCount(_CellRangerCount):
+            if self.opts.ids:
+                input_data = list(zip(self.opts.input, self.opts.ids))
+            else:
+                input_data = self.opts.input
+
+        return CellRangerCount
+
+    @ProcGroup.add_proc
+    def p_cellranger_count_summary(self) -> Proc:
+        """Build CellRangerCountSummary process"""
+        from .cellranger import CellRangerSummary
+
+        class CellRangerCountSummary(CellRangerSummary):
+            requires = self.p_cellranger_count
+            input_data = lambda ch: [list(ch.iloc[:, 0])]
+
+        return CellRangerCountSummary
+
+
+class CellRangerVdjPipeline(ProcGroup):
+    """The cellranger vdj pipeline
+
+    Run cellranger vdj for multiple samples and summarize the metrics.
+
+    Args:
+        input (list): The list of lists of fastq files.
+            or the list of comma-separated string of fastq files.
+        ids (list): The list of ids for the samples.
+    """
+    DEFAULTS = Diot(input=None, ids=None)
+
+    def post_init(self):
+        """Check if the input is a list of fastq files"""
+        if not is_loading_pipeline("-h", "-h+", "--help", "--help+") and (
+            not isinstance(self.opts.input, (list, tuple))
+            or len(self.opts.input) == 0
+        ):
+            raise TypeError(
+                "The input of `CellRangerVdjPipeline` should be a list of lists of "
+                "fastq files."
+            )
+
+        if isinstance(self.opts.input, (list, tuple)):
+            self.opts.input = [
+                [y.strip() for y in x.split(",")]
+                if isinstance(x, str)
+                else x
+                for x in self.opts.input
+            ]
+
+    @ProcGroup.add_proc
+    def p_cellranger_vdj(self) -> Proc:
+        """Build CellRangerVdj process"""
+        from .cellranger import CellRangerVdj as _CellRangerVdj
+
+        class CellRangerVdj(_CellRangerVdj):
+            if self.opts.ids:
+                input_data = list(zip(self.opts.input, self.opts.ids))
+            else:
+                input_data = self.opts.input
+
+        return CellRangerVdj
+
+    @ProcGroup.add_proc
+    def p_cellranger_vdj_summary(self) -> Proc:
+        """Build CellRangerVdjSummary process"""
+        from .cellranger import CellRangerSummary
+
+        class CellRangerVdjSummary(CellRangerSummary):
+            requires = self.p_cellranger_vdj
+            input_data = lambda ch: [list(ch.iloc[:, 0])]
+
+        return CellRangerVdjSummary

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
@@ -134,7 +150,7 @@ class TMADScore(Proc):
         excl_chroms (list): The chromosomes to be excluded
     """
     input = "segfile:file"
-    output = "outfile:file:{{in.segfile | stem0}}.tmad.txt"
+    output = "outfile:file:{{in.segfile | stem}}.tmad.txt"
     lang = config.lang.rscript
     envs = {
         "chrom_col": "chrom",

biopipen/ns/cnvkit.py

@@ -482,7 +482,7 @@ class CNVkitDiagram(Proc):
     }
     script = "file://../scripts/cnvkit/CNVkitDiagram.py"
     plugin_opts = {
-        "report": "file://../reports/cnvkit/CNVkitScatter.svelte",
+        "report": "file://../reports/cnvkit/CNVkitDiagram.svelte",
         "report_paging": 10,
     }
 

biopipen/ns/cnvkit_pipeline.py

@@ -276,7 +276,10 @@ class CNVkitPipeline(ProcGroup):
         """Build CNVkitGuessBaits process"""
         from .cnvkit import CNVkitGuessBaits
 
-        if not self.opts.guessbaits and not is_loading_pipeline():
+        if (
+            not self.opts.guessbaits and
+            not is_loading_pipeline("-h", "-h+", "--help", "--help+")
+        ):
             return None
 
         def _guess_baits_bams(ch):
@@ -487,7 +490,8 @@ 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 +778,15 @@ 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 +829,15 @@ 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/delim.py

@@ -51,6 +51,10 @@ class SampleInfo(Proc):
     Output:
         outfile: The output file with sample information, with mutated columns
             if `envs.save_mutated` is True.
+            The basename of the output file will be the same as the input file.
+            The file name of each plot will be slugified from the case name.
+            Each plot has 3 formats: pdf, png and code.zip, which contains the
+            data and R code to reproduce the plot.
 
     Envs:
         sep: The separator of the input file.
@@ -76,37 +80,34 @@ class SampleInfo(Proc):
                 If `FALSE`, you can mutate the meta data frame with the
                 returned ids. Non-paired ids will be `NA`.
         save_mutated (flag): Whether to save the mutated columns.
-        exclude_cols: The columns to exclude in the table in the report.
+        exclude_cols (auto): The columns to exclude in the table in the report.
             Could be a list or a string separated by comma.
         defaults (ns): The default parameters for `envs.stats`.
-            - on: The column name in the data for the stats.
-                Default is `Sample`. The column could be either continuous or not.
-            - distinct: The column name in the data for the distinct records.
-                For example, you may have multiple `Sample`s for each patient.
-                In this case, you can set `distinct` to `Patient` to get the
-                stats for each patient, instead of each sample with duplicated
-                values. Default is `None`, which means all records are distinct.
-                Note that when `distinct` is provided, your `group` and `each` should
-                be the same for each distinct record. For example, it doesn't make
-                sense if you are doing statistics for each patient (`on = "Sample"`),
-                but your `group` is `SampleSource`, defining the source of each
-                sample.
-            - group: The column name in the data for the group ids.
-                If not provided, all records will be regarded as one group.
-            - na_group (flag): Whether to include `NA`s in the group.
-            - each: The column in the data to split the analysis in different
-                plots.
-            - ncol (type=int): The number of columns in the plot when `each`
-                is not `NULL`. Default is 2.
-            - na_each (flag): Whether to include `NA`s in the `each` column.
-            - plot: Type of plot. If `on` is continuous, it could be
-                `boxplot` (default), `violin`, `violin+boxplot` or `histogram`.
-                If `on` is not continuous, it could be `barplot` or
-                `pie` (default).
+            - plot_type: The type of the plot.
+                See the supported plot types here:
+                <https://pwwang.github.io/plotthis/reference/index.html>
+                The plot_type should be lower case and the plot function used in
+                `plotthis` should be used. The mapping from plot_type to the
+                plot function is like `bar -> BarPlot`, `box -> BoxPlot`, etc.
+            - more_formats (list): The additional formats to save the plot.
+                By default, the plot will be saved in png, which is also used to
+                display in the report. You can add more formats to save the plot.
+                For example, `more_formats = ["pdf", "svg"]`.
+            - save_code (flag): Whether to save the R code to reproduce the plot.
+                The data used to plot will also be saved.
+            - subset: An expression to subset the data frame before plotting.
+                The expression should be a string of R expression that will be passed
+                to `dplyr::filter`. For example, `subset = "Sample == 'A'"`.
+            - section: The section name in the report.
+                In case you want to group the plots in the report.
             - devpars (ns): The device parameters for the plot.
                 - width (type=int): The width of the plot.
                 - height (type=int): The height of the plot.
                 - res (type=int): The resolution of the plot.
+            - descr: The description of the plot, shown in the report.
+            - <more>: You can add more parameters to the defaults.
+                These parameters will be expanded to the `envs.stats` for each case,
+                and passed to individual plot functions.
         stats (type=json): The statistics to perform.
             The keys are the case names and the values are the parameters
             inheirted from `envs.defaults`.
@@ -119,18 +120,16 @@ class SampleInfo(Proc):
         "save_mutated": False,
         "exclude_cols": None,
         "defaults": {
-            "on": "Sample",
-            "distinct": None,
-            "group": None,
-            "na_group": False,
-            "each": None,
-            "ncol": 2,
-            "na_each": False,
-            "plot": None,
-            "devpars": {"width": 800, "height": 600, "res": 100},
+            "plot_type": "bar",
+            "more_formats": [],
+            "save_code": False,
+            "subset": None,
+            "section": None,
+            "descr": None,
+            "devpars": {"width": None, "height": None, "res": 100},
         },
         "stats": {},
     }
     lang = config.lang.rscript
     script = "file://../scripts/delim/SampleInfo.R"
-    plugin_opts = {"report": "file://../reports/delim/SampleInfo.svelte"}
+    plugin_opts = {"report": "file://../reports/common.svelte"}

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"