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

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.32.3"
+__version__ = "0.33.1"

biopipen/core/config.toml

@@ -1,9 +1,13 @@
 # Executables or binaries
 [exe]
+# BeEM: https://github.com/kad-ecoli/BeEM
+beem = "BeEM"
 # bedtools to handle bed files
 bedtools = "bedtools"
 # bcftools to handle bcf/vcf files
 bcftools = "bcftools"
+# calculate_rmsd: https://github.com/charnley/rmsd
+calculate_rmsd = "calculate_rmsd"
 # cellranger
 cellranger = "cellranger"
 # Control-FREEC to call cnvs
@@ -27,6 +31,8 @@ cnvnator2vcf = "cnvnator2VCF.pl"
 convert = "convert"
 # fimo from meme
 fimo = "fimo"
+# MAXIT: https://sw-tools.rcsb.org/apps/MAXIT/
+maxit = "maxit"
 # wget
 wget = "wget"
 # aria2c

biopipen/core/filters.py

@@ -1,6 +1,7 @@
 """Additional filters for pipen"""
 from __future__ import annotations
 
+import re
 import shlex
 from pathlib import Path
 from typing import Any, List, Mapping
@@ -9,6 +10,8 @@ from argx import Namespace
 from liquid.filters.manager import FilterManager
 from pipen_report.filters import register_component, render_ui, _tag
 
+# from .defaults import BIOPIPEN_DIR
+
 filtermanager = FilterManager()
 
 
@@ -171,6 +174,8 @@ def r(
             return "FALSE"
         if obj.upper() == "NA" or obj.upper() == "NULL":
             return obj.upper()
+        if re.match(r"^\d+:\d+$", obj):
+            return obj
         if obj.startswith("r:") or obj.startswith("R:"):
             return str(obj)[2:]
         return repr(str(obj))
@@ -222,7 +227,7 @@ def r(
 
 
 @filtermanager.register
-def source_r(path: str | Path) -> str:
+def source_r(path: str | Path, chdir: bool = False) -> str:
     """Source an R script.
 
     In addition to generating `source(path)`, we also include the mtime for the script
@@ -238,7 +243,8 @@ def source_r(path: str | Path) -> str:
     mtime = int(path.stat().st_mtime)
     return (
         f"# Last modified: {mtime}\n"
-        f"source('{path}')"
+        # f"biopipen_dir = {r(BIOPIPEN_DIR)}\n"
+        f"source('{path}', chdir = {r(chdir)})"
     )
 
 
@@ -375,15 +381,15 @@ def _render_enrichr(
     components = []
 
     for db in dbs:
-        enrichr_plot = Path(cont["dir"]).joinpath(f"Enrichr-{db}.png")
-        if enrichr_plot.exists():
+        enrichr_plots = list(Path(cont["dir"]).glob(f"Enrichr-{db}.*.png"))
+        if len(enrichr_plots) == 0:
             components.append(
                 {
                     "title": db,
                     "ui": "tabs",
                     "contents": [
                         {
-                            "title": "Plot",
+                            "title": "Error",
                             "ui": "flat",
                             "contents": [
                                 {
@@ -400,21 +406,8 @@ def _render_enrichr(
                                     )
                                 },
                                 {
-                                    "kind": "image",
-                                    "src": str(enrichr_plot),
-                                    "download": str(enrichr_plot.with_suffix(".pdf")),
-                                }
-                            ],
-                        },
-                        {
-                            "title": "Table",
-                            "ui": "flat",
-                            "contents": [
-                                {
-                                    "kind": "table",
-                                    "src": str(
-                                        Path(cont["dir"]).joinpath(f"Enrichr-{db}.txt")
-                                    ),
+                                    "kind": "error",
+                                    "content": "No enriched terms found.",
                                 }
                             ],
                         },
@@ -422,18 +415,37 @@ def _render_enrichr(
                 }
             )
         else:
+            contents = []
+            for enrichr_plot in enrichr_plots:
+                plot_type = enrichr_plot.stem.split(".")[-1]
+                pdf = enrichr_plot.with_suffix(".pdf")
+                contents.append(
+                    {
+                        "src": str(enrichr_plot),
+                        "title": f"{plot_type.title()} Plot",
+                        "download": str(pdf),
+                    }
+                )
+
             components.append(
                 {
                     "title": db,
                     "ui": "tabs",
                     "contents": [
                         {
-                            "title": "Error",
+                            "title": "Plots",
+                            "ui": "table_of_images",
+                            "contents": contents,
+                        },
+                        {
+                            "title": "Table",
                             "ui": "flat",
                             "contents": [
                                 {
-                                    "kind": "error",
-                                    "content": "No enriched terms found.",
+                                    "kind": "table",
+                                    "src": str(
+                                        Path(cont["dir"]).joinpath(f"Enrichr-{db}.txt")
+                                    ),
                                 }
                             ],
                         },

biopipen/core/testing.py

@@ -96,7 +96,12 @@ def r_test(mem: callable) -> callable:
         )
         rcode = f"{expect}\n\n{rcode}\n\ncat('PASSED')\n"
         if source is not None:
-            rcode = f'suppressWarnings(source("{self.SOURCE_FILE}"))\n\n{rcode}'
+            if not isinstance(source, (list, tuple)):
+                source = [source]
+
+            libs = "\n".join([f"suppressWarnings(source('{s}'))" for s in source])
+            rcode = f'{libs}\n\n{rcode}'
+
         out = _run_rcode(rcode)
         self.assertEqual(
             out,

biopipen/ns/bam.py

@@ -329,3 +329,42 @@ class BamSubsetByBed(Proc):
         "index": True,
     }
     script = "file://../scripts/bam/BamSubsetByBed.py"
+
+
+class BamSort(Proc):
+    """Sort bam file
+
+    Input:
+        bamfile: The bam file
+
+    Output:
+        outfile: The output bam file
+
+    Envs:
+        tool (choice): The tool to use.
+            - samtools: Use `samtools`
+            - sambamba: Use `sambamba`
+        ncores (type=int): Number of cores to use
+        samtools: Path to samtools executable
+        sambamba: Path to sambamba executable
+        tmpdir: The temporary directory to use
+        byname (flag): Whether to sort by read name
+        index (flag): Whether to index the output bam file
+            The index file will be created in the same directory as the output
+            bam file
+        <more>: Other arguments passed to the sorting tool
+            See `samtools sort` or `sambamba sort`
+    """
+    input = "bamfile:file"
+    output = "outfile:file:{{in.bamfile | stem}}.sorted.bam"
+    lang = config.lang.python
+    envs = {
+        "tool": "samtools",
+        "ncores": config.misc.ncores,
+        "samtools": config.exe.samtools,
+        "sambamba": config.exe.sambamba,
+        "tmpdir": config.path.tmpdir,
+        "byname": False,
+        "index": True,
+    }
+    script = "file://../scripts/bam/BamSort.py"

biopipen/ns/cellranger.py

@@ -16,6 +16,10 @@ class CellRangerCount(Proc):
             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
@@ -141,6 +145,7 @@ class CellRangerSummary(Proc):
             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"

biopipen/ns/cellranger_pipeline.py

@@ -28,7 +28,7 @@ class CellRangerCountPipeline(ProcGroup):
 
     def post_init(self):
         """Check if the input is a list of fastq files"""
-        if not is_loading_pipeline() and (
+        if not is_loading_pipeline("-h", "-h+", "--help", "--help+") and (
             not isinstance(self.opts.input, (list, tuple))
             or len(self.opts.input) == 0
         ):
@@ -84,7 +84,7 @@ class CellRangerVdjPipeline(ProcGroup):
 
     def post_init(self):
         """Check if the input is a list of fastq files"""
-        if not is_loading_pipeline() and (
+        if not is_loading_pipeline("-h", "-h+", "--help", "--help+") and (
             not isinstance(self.opts.input, (list, tuple))
             or len(self.opts.input) == 0
         ):

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):

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.
@@ -76,30 +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.
-            - subset: An R expression to subset the data.
-                If you want to keep the distinct records, you can use
-                `!duplicated(<col>)`.
-            - 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`.
@@ -112,15 +120,13 @@ 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": {},
     }

biopipen/ns/protein.py

@@ -82,3 +82,102 @@ class ProdigySummary(Proc):
     envs = {"group": None}
     script = "file://../scripts/protein/ProdigySummary.R"
     plugin_opts = {"report": "file://../reports/protein/ProdigySummary.svelte"}
+
+
+class MMCIF2PDB(Proc):
+    """Convert mmCIF or PDBx file to PDB file.
+
+    Using [BeEM](https://github.com/kad-ecoli/BeEM)
+
+    Input:
+        infile: The input mmCIF or PDBx file.
+
+    Output:
+        outfile: The output PDB file.
+            The "outfmt" set to 3 to always output a single PDB file.
+
+    Envs:
+        tool (choice): The tool to use for conversion.
+            - maxit: Use MAXIT.
+            - beem: Use BeEM.
+        maxit: The path to the MAXIT executable.
+        beem: The path to the BeEM executable.
+        <more>: Other options for MAXIT/BeEM.
+            For BeEM, "outfmt" will not be used as it is set to 3.
+    """
+    input = "infile:file"
+    output = "outfile:file:{{in.infile | stem}}.pdb"
+    lang = config.lang.python
+    envs = {
+        "tool": "maxit",
+        "maxit": config.exe.maxit,
+        "beem": config.exe.beem,
+    }
+    script = "file://../scripts/protein/MMCIF2PDB.py"
+
+
+class RMSD(Proc):
+    """Calculate the RMSD between two structures.
+
+    See also https://github.com/charnley/rmsd.
+
+    If the input is in mmCIF format, convert it to PDB first.
+
+    Input:
+        infile1: The first structure file.
+        infile2: The second structure file.
+
+    Output:
+        outfile: The output file containing the RMSD value.
+
+    Envs:
+        beem: The path to the BeEM executable.
+        calculate_rmsd: The path to the calculate_rmsd executable.
+        conv_tool (choice): The tool to use for conversion.
+            - maxit: Use MAXIT.
+            - beem: Use BeEM.
+        ca_only (flag): Whether to calculate RMSD using only C-alpha atoms.
+        duel (choice): How to handle the duel atoms. Default is "keep".
+            - keep: Keep both atoms.
+            - keep_first: Keep the first atom.
+            - keep_last: Keep the last atom.
+            - average: Average the coordinates.
+        reorder (flag): Whether to reorder the atoms in the structures.
+        <more>: Other options for calculate_rmsd.
+    """
+    input = "infile1:file, infile2:file"
+    output = "outfile:file:{{in.infile1 | stem}}-{{in.infile2 | stem}}.rmsd.txt"
+    lang = config.lang.python
+    envs = {
+        "maxit": config.exe.maxit,
+        "beem": config.exe.beem,
+        "calculate_rmsd": config.exe.calculate_rmsd,
+        "conv_tool": "maxit",
+        "ca_only": False,
+        "duel": "keep",
+        "reorder": True,
+    }
+    script = "file://../scripts/protein/RMSD.py"
+
+
+class PDB2Fasta(Proc):
+    """Convert PDB file to FASTA file.
+
+    Input:
+        infile: The input PDB file.
+
+    Output:
+        outfile: The output FASTA file.
+
+    Envs:
+        chains (auto): The chains to extract. A list of chain IDs or separated by
+            commas.
+            If None, extract all chains.
+        wrap (type=int): The number of residues per line in the output FASTA
+            file. Set to 0 to disable wrapping.
+    """
+    input = "infile:file"
+    output = "outfile:file:{{in.infile | stem}}.fasta"
+    lang = config.lang.python
+    envs = {"chains": None, "wrap": 80}
+    script = "file://../scripts/protein/PDB2Fasta.py"