biopipen 0.31.4__tar.gz → 0.31.5__tar.gz

{biopipen-0.31.4 → biopipen-0.31.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.31.4
+Version: 0.31.5
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

biopipen-0.31.5/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.31.5"

{biopipen-0.31.4 → biopipen-0.31.5}/biopipen/ns/bam.py

@@ -260,3 +260,44 @@ class BamMerge(Proc):
         "sort_args": [],
     }
     script = "file://../scripts/bam/BamMerge.py"
+
+
+class BamSampling(Proc):
+    """Keeping only a fraction of read pairs from a bam file
+
+    Input:
+        bamfile: The bam file
+
+    Output:
+        outfile: The output bam file
+
+    Envs:
+        ncores: Number of cores to use
+        samtools: Path to samtools executable
+        tool: The tool to use, currently only "samtools" is supported
+        fraction (type=float): The fraction of reads to keep.
+            If `0 < fraction <= 1`, it's the fraction of reads to keep.
+            If `fraction > 1`, it's the number of reads to keep.
+            Note that when fraction > 1, you may not get the exact number
+            of reads specified but a close number.
+        seed: The seed for random number generator
+        index: Whether to index the output bam file
+        sort: Whether to sort the output bam file
+        sort_args: The arguments for sorting bam file using `samtools sort`.
+            These keys are not allowed: `-o`, `-@`,
+            and `--threads`, as they are managed by the script.
+    """
+    input = "bamfile:file"
+    output = "outfile:file:{{in.bamfile | stem}}.sampled{{envs.fraction}}.bam"
+    lang = config.lang.python
+    envs = {
+        "ncores": config.misc.ncores,
+        "samtools": config.exe.samtools,
+        "tool": "samtools",
+        "fraction": None,
+        "seed": 8525,
+        "index": True,
+        "sort": True,
+        "sort_args": [],
+    }
+    script = "file://../scripts/bam/BamSampling.py"

biopipen-0.31.5/biopipen/ns/protein.py

@@ -0,0 +1,84 @@
+"""Protein-related processes."""
+from ..core.proc import Proc
+from ..core.config import config
+
+
+class Prodigy(Proc):
+    """Prediction of binding affinity of protein-protein complexes based on
+    intermolecular contacts using Prodigy.
+
+    See <https://rascar.science.uu.nl/prodigy/> and
+    <https://github.com/haddocking/prodigy>.
+
+    `prodigy-prot` must be installed under the given python of `proc.lang`.
+
+    Input:
+        infile: The structure file in PDB or mmCIF format.
+
+    Output:
+        outfile: The output file generated by Prodigy.
+        outdir: The output directory containing all output files.
+
+    Envs:
+        distance_cutoff (type=float): The distance cutoff to calculate intermolecular
+            contacts.
+        acc_threshold (type=float): The accessibility threshold for BSA analysis.
+        temperature (type=float): The temperature (C) for Kd prediction.
+        contact_list (flag): Whether to generate contact list.
+        pymol_selection (flag): Whether output a script to highlight the interface
+            residues in PyMOL.
+        selection (list): The selection of the chains to analyze.
+            `['A', 'B']` will analyze chains A and B.
+            `['A,B', 'C']` will analyze chain A and C; and B and C.
+            `['A', 'B', 'C']` will analyze all combinations of A, B, and C.
+        outtype (choice): Set the format of the output file (`out.outfile`).
+            All three files will be generated. This option only determines which
+            is assigned to `out.outfile`.
+            - raw: The raw output file from prodigy.
+            - json: The output file in JSON format.
+            - tsv: The output file in CSV format.
+    """
+    input = "infile:file"
+    output = [
+        "outfile:file:{{in.infile | stem}}_prodigy/"
+        "{{in.infile | stem}}.{{envs.outtype if envs.outtype != 'raw' else 'out'}}",
+        "outdir:dir:{{in.infile | stem}}_prodigy",
+    ]
+    lang = config.lang.python
+    envs = {
+        "distance_cutoff": 5.5,
+        "acc_threshold": 0.05,
+        "temperature": 25.0,
+        "contact_list": True,
+        "pymol_selection": True,
+        "selection": None,
+        "outtype": "json",
+    }
+    script = "file://../scripts/protein/Prodigy.py"
+
+
+class ProdigySummary(Proc):
+    """Summary of the output from `Prodigy`.
+
+    Input:
+        infiles: The output json file generated by `Prodigy`.
+
+    Output:
+        outdir: The directory of summary files generated by `ProdigySummary`.
+
+    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 = "infiles:files"
+    input_data = lambda ch: [[f"{odir}/_prodigy.tsv" for odir in ch.outdir]]
+    output = "outdir:dir:prodigy_summary"
+    lang = config.lang.rscript
+    envs = {"group": None}
+    script = "file://../scripts/protein/ProdigySummary.R"
+    plugin_opts = {"report": "file://../reports/protein/ProdigySummary.svelte"}

{biopipen-0.31.4 → biopipen-0.31.5}/biopipen/ns/vcf.py

@@ -463,7 +463,7 @@ class BcftoolsAnnotate(Proc):
         columns (auto): Comma-separated or list of columns or tags to carry over from
             the annotation file. Overrides `-c, --columns`
         remove (auto): Remove the specified columns from the input file
-        header (type=list): Headers to be added
+        header (list): Headers to be added
         gz (flag): Whether to gzip the output file
         index (flag): Whether to index the output file (tbi) (`envs.gz` forced to True)
         <more>: Other arguments for `bcftools annotate`

biopipen-0.31.5/biopipen/reports/protein/ProdigySummary.svelte

@@ -0,0 +1,16 @@
+{% from "utils/misc.liq" import report_jobs -%}
+
+<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.out.outdir | stem | escape}}</h1>
+{%- endmacro -%}
+
+{{ report_jobs(jobs, head_job, report_job) }}

{biopipen-0.31.4 → biopipen-0.31.5}/biopipen/scripts/bam/BamMerge.py

@@ -1,7 +1,7 @@
 from pathlib import Path
-from biopipen.utils.misc import run_command
+from biopipen.utils.misc import run_command, logger
 
-bamfiles = {{in.bamfiles | repr}}  # pyright: ignore
+bamfiles = {{in.bamfiles | repr}}  # pyright: ignore # noqa
 outfile = Path({{out.outfile | repr}})  # pyright: ignore
 ncores = {{envs.ncores | int}}  # pyright: ignore
 tool = {{envs.tool | quote}}  # pyright: ignore
@@ -18,7 +18,7 @@ if should_index and not should_sort:
 
 def use_samtools():
     """Use samtools to merge bam files"""
-    print("Using samtools")
+    logger.info("Using samtools ...")
     ofile = (
         outfile
         if not should_sort
@@ -43,11 +43,11 @@ def use_samtools():
         *merge_args,
         *bamfiles,
     ]
-    print("- Merging")
+    logger.info("- Merging the bam files ...")
     run_command(cmd)
 
     if should_sort:
-        print("- Sorting")
+        logger.info("- Sorting the merged bam file ...")
         for key in ["-o", "-@", "--threads"]:
             if key in sort_args:
                 raise ValueError(
@@ -67,16 +67,14 @@ def use_samtools():
         run_command(cmd)
 
     if should_index:
-        print("- Indexing")
+        logger.info("- Indexing the output bam file ...")
         cmd = [samtools, "index", "-@", ncores, outfile]
         run_command(cmd)
 
-    print("Done")
-
 
 def use_sambamba():
     """Use sambamba to merge bam files"""
-    print("Using sambamba")
+    logger.info("Using sambamba ...")
     ofile = (
         outfile
         if not should_sort
@@ -90,11 +88,11 @@ def use_sambamba():
             )
 
     cmd = [sambamba, "merge", "-t", ncores, *merge_args, ofile, *bamfiles]
-    print("- Merging")
+    logger.info("- Merging the bam files ...")
     run_command(cmd)
 
     if should_sort:
-        print("- Sorting")
+        logger.info("- Sorting the merged bam file ...")
         for key in ["-t", "--nthreads", "-o", "--out"]:
             if key in sort_args:
                 raise ValueError(
@@ -115,12 +113,10 @@ def use_sambamba():
         run_command(cmd)
 
     if should_index:
-        print("- Indexing")
+        logger.info("- Indexing the output bam file ...")
         cmd = [sambamba, "index", "-t", ncores, outfile]
         run_command(cmd)
 
-    print("Done")
-
 
 if __name__ == "__main__":
     if tool == "samtools":

biopipen-0.31.5/biopipen/scripts/bam/BamSampling.py

@@ -0,0 +1,90 @@
+from pathlib import Path
+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
+ncores = {{ envs.ncores | int }} # pyright: ignore
+samtools = {{ envs.samtools | repr }} # pyright: ignore
+tool = {{ envs.tool | repr }} # pyright: ignore
+fraction = {{ 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
+sort_args = {{ envs.sort_args | repr }} # pyright: ignore
+
+if should_index and not should_sort:
+    raise ValueError("Indexing requires sorting")
+
+if fraction is None:
+    raise ValueError("'envs.fraction' must be provided.")
+
+if tool != "samtools":
+    raise ValueError(
+        f"Tool {tool} is not supported. "
+        "Currently only samtools is supported."
+    )
+
+if fraction > 1:
+    # calculate the fraction based on the number of reads
+    logger.info("Converting fraction > 1 to a fraction of reads.")
+    cmd = [
+        samtools,
+        "view",
+        "--threads",
+        ncores,
+        "-c",
+        bamfile
+    ]
+    nreads = run_command(cmd, stdout="return").strip()
+    fraction = fraction / float(int(nreads))
+
+ofile = (
+    outfile
+    if not should_sort
+    else outfile.with_stem(f"{outfile.stem}.unsorted")
+)
+
+cmd = [
+    samtools,
+    "view",
+    "--subsample",
+    fraction,
+    "--subsample-seed",
+    seed,
+    "--threads",
+    ncores,
+    "-b",
+    "-o",
+    ofile,
+    bamfile
+]
+run_command(cmd, fg=True)
+
+if should_sort:
+    logger.info("Sorting the output bam file.")
+    for key in ["-o", "-@", "--threads"]:
+        if key in sort_args:
+            raise ValueError(
+                f"envs.sort_args cannot contain {key}, "
+                "which is managed by the script"
+            )
+
+    cmd = [
+        samtools,
+        "sort",
+        "-@",
+        ncores,
+        *sort_args,
+        "-o",
+        outfile,
+        ofile
+    ]
+    run_command(cmd, fg=True)
+
+if should_index:
+    logger.info("Indexing the output bam file.")
+    cmd = [samtools, "index", "-@", ncores, outfile]
+    run_command(cmd, fg=True)

biopipen-0.31.5/biopipen/scripts/protein/Prodigy.py

@@ -0,0 +1,119 @@
+import json
+import logging
+import sys
+from pathlib import Path
+from prodigy_prot.predict_IC import (
+    Prodigy,
+    check_path,
+    parse_structure,
+)
+
+infile = {{in.infile | repr}}  # pyright: ignore # noqa
+outfile = {{out.outfile | repr}}  # pyright: ignore
+outdir = {{out.outdir | repr}}  # pyright: ignore
+distance_cutoff = {{envs.distance_cutoff | float}}  # pyright: ignore
+acc_threshold = {{envs.acc_threshold | float}}  # pyright: ignore
+temperature = {{envs.temperature | float}}  # pyright: ignore
+contact_list = {{envs.contact_list | repr}}  # pyright: ignore
+pymol_selection = {{envs.pymol_selection | repr}}  # pyright: ignore
+selection = {{envs.selection | repr}}  # pyright: ignore
+outtype = {{envs.outtype | repr}}  # pyright: ignore
+
+raw_outfile = Path(outdir) / "_prodigy_raw.txt"
+json_outfile = Path(outdir) / "_prodigy.json"
+tsv_outfile = Path(outdir) / "_prodigy.tsv"
+
+# log to the raw_outfile
+logging.basicConfig(level=logging.INFO, stream=sys.stdout, format="%(message)s")
+logger = logging.getLogger("Prodigy")
+
+if isinstance(selection, str):
+    selection = [selection]
+
+struct_path = check_path(infile)
+
+# parse structure
+structure, n_chains, n_res = parse_structure(struct_path)
+logger.info(
+    "[+] Parsed structure file {0} ({1} chains, {2} residues)".format(
+        structure.id, n_chains, n_res
+    )
+)
+prodigy = Prodigy(structure, selection, temperature)
+prodigy.predict(distance_cutoff=distance_cutoff, acc_threshold=acc_threshold)
+prodigy.print_prediction(outfile=raw_outfile, quiet=False)
+
+# Print out interaction network
+if contact_list:
+    prodigy.print_contacts(f"{outdir}/prodigy.ic")
+
+# Print out interaction network
+if pymol_selection:
+    prodigy.print_pymol_script(f"{outdir}/prodigy.pml")
+
+# [+] Reading structure file: <path/to/structure.cif>
+# [+] Parsed structure file <structure> (4 chains, 411 residues)
+# [+] No. of intermolecular contacts: 191
+# [+] No. of charged-charged contacts: 17
+# [+] No. of charged-polar contacts: 18
+# [+] No. of charged-apolar contacts: 60
+# [+] No. of polar-polar contacts: 5
+# [+] No. of apolar-polar contacts: 41
+# [+] No. of apolar-apolar contacts: 50
+# [+] Percentage of apolar NIS residues: 33.90
+# [+] Percentage of charged NIS residues: 30.48
+# [++] Predicted binding affinity (kcal.mol-1):    -21.3
+# [++] Predicted dissociation constant (M) at 25.0˚C:  2.3e-16
+
+output = {}
+with open(raw_outfile, "r") as f:
+    for line in f:
+        if line.startswith("[+"):
+            line = line.lstrip("[").lstrip("+").lstrip("]").lstrip()
+            if line.startswith("Reading structure file"):
+                continue
+            if line.startswith("Parsed structure file"):
+                continue
+
+            key, value = line.split(":", 1)
+            key = key.strip()
+            value = value.strip()
+            if key == "No. of intermolecular contacts":
+                output["nIC"] = int(value)
+            elif key == "No. of charged-charged contacts":
+                output["nCCC"] = int(value)
+            elif key == "No. of charged-polar contacts":
+                output["nCPC"] = int(value)
+            elif key == "No. of charged-apolar contacts":
+                output["nCAPC"] = int(value)
+            elif key == "No. of polar-polar contacts":
+                output["nPPC"] = int(value)
+            elif key == "No. of apolar-polar contacts":
+                output["nAPPC"] = int(value)
+            elif key == "No. of apolar-apolar contacts":
+                output["nAPAPC"] = int(value)
+            elif key.startswith("Percentage of apolar NIS residues"):
+                output["pANISR"] = float(value)
+            elif key.startswith("Percentage of charged NIS residues"):
+                output["pCNISR"] = float(value)
+            elif key.startswith("Predicted binding affinity"):
+                output["BindingAffinity"] = float(value)
+            elif key.startswith("Predicted dissociation constant"):
+                output["DissociationConstant"] = float(value)
+
+with open(json_outfile, "w") as f:
+    json.dump(output, f, indent=2)
+
+with open(tsv_outfile, "w") as f:
+    f.write("\t".join(output.keys()) + "\n")
+    f.write("\t".join(map(str, output.values())) + "\n")
+
+if outtype == "json":
+    json_outfile.rename(outfile)
+    json_outfile.symlink_to(outfile)
+elif outtype == "tsv":
+    tsv_outfile.rename(outfile)
+    tsv_outfile.symlink_to(outfile)
+else:
+    raw_outfile.rename(outfile)
+    raw_outfile.symlink_to(outfile)

biopipen-0.31.5/biopipen/scripts/protein/ProdigySummary.R

@@ -0,0 +1,133 @@
+{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
+
+library(rlang)
+library(dplyr)
+library(ggplot2)
+library(ggprism)
+
+theme_set(theme_prism())
+
+infiles <- {{in.infiles | r}}
+outdir <- {{out.outdir | r}}
+joboutdir <- {{job.outdir | r}}
+group <- {{envs.group | r}}
+
+if (is.character(group)) {
+    group <- read.csv(group, header = FALSE, row.names = NULL)
+    colnames(group) <- c("Sample", "Group")
+} else if (is.list(group)) {
+    group <- do_call(
+        rbind,
+        lapply(names(group), function(n) data.frame(Sample = group[[n]], Group = n))
+    )
+} else if (!is.null(group)) {
+    stop(paste0("Invalid group: ", paste0(group, collapse = ", ")))
+}
+
+log_info("Reading and merging metrics for each sample ...")
+metrics <- NULL
+
+for (infile in infiles) {
+    sample <- sub("_prodigy$", "", basename(dirname(infile)))
+    log_debug("- Reading metrics from {sample}")
+    metric <- read.table(
+        infile,
+        header = TRUE,
+        sep = "\t",
+        stringsAsFactors = FALSE,
+        check.names = FALSE,
+        row.names = NULL)
+    metric$Sample <- sample
+    metric <- metric %>% select(Sample, everything())
+    if (is.null(metrics)) {
+        metrics <- metric
+    } else {
+        metrics <- rbind(metrics, metric)
+    }
+}
+
+# Save metrics
+write.table(
+    metrics,
+    file.path(outdir, "metrics.txt"),
+    sep = "\t",
+    quote = FALSE,
+    row.names = FALSE
+)
+
+add_report(
+    list(kind = "descr", content = "Metrics for all samples"),
+    list(kind = "table", src = file.path(outdir, "metrics.txt")),
+    h1 = "Metrics of all samples"
+)
+
+METRIC_DESCR = list(
+    nIC = "No. of intermolecular contacts",
+    nCCC = "No. of charged-charged contacts",
+    nCPC = "No. of charged-polar contacts",
+    nCAPC = "No. of charged-apolar contacts",
+    nPPC = "No. of polar-polar contacts",
+    nAPPC = "No. of apolar-polar contacts",
+    nAPAPC = "No. of apolar-apolar contacts",
+    pANISR = "Percentage of apolar NIS residues",
+    pCNISR = "Percentage of charged NIS residues",
+    BindingAffinity = "Predicted binding affinity (kcal.mol^-1)",
+    DissociationConstant = "Predicted dissociation constant (M)"
+)
+
+if (!is.null(group)) {
+    log_info("Merging group information ...")
+    metrics <- group %>%
+        left_join(metrics, by = "Sample") %>%
+        mutate(Group = factor(Group, levels = unique(Group)))
+}
+
+log_info("Plotting Prodigy metrics ...")
+for (metric in names(METRIC_DESCR)) {
+    log_info("- {metric}: {METRIC_DESCR[[metric]]}")
+
+    add_report(
+        list(
+            kind = "descr",
+            content = METRIC_DESCR[[metric]] %||% paste0("Metric: ", metric)
+        ),
+        h1 = metric
+    )
+
+    # barplot
+    p <- ggplot(metrics, aes(x = Sample, y = !!sym(metric))) +
+        geom_bar(stat = "identity", fill = "steelblue") +
+        labs(x = "Sample", y = metric) +
+        theme(axis.text.x = element_text(angle = 90, hjust = 1))
+
+    figfile <- file.path(outdir, paste0(slugify(metric), ".barplot.png"))
+    png(figfile, height = 600, res = 100, width = nrow(metrics) * 30 + 200)
+    print(p)
+    dev.off()
+
+    add_report(
+        list(src = figfile, name = "By Sample"),
+        ui = "table_of_images",
+        h1 = metric
+    )
+
+    if (is.null(group)) { next }
+    # group: Sample, Group
+    p <- ggplot(metrics, aes(x = Group, y = !!sym(metric))) +
+        geom_boxplot(fill = "steelblue") +
+        labs(x = "Group", y = metric) +
+        theme(axis.text.x = element_text(angle = 90, hjust = 1))
+
+    figfile <- file.path(outdir, paste0(slugify(metric), ".boxplot.png"))
+    png(figfile, height = 600, res = 100, width = length(unique(metrics$Group)) * 30 + 200)
+    print(p)
+    dev.off()
+
+    add_report(
+        list(src = figfile, name = "By Group"),
+        ui = "table_of_images",
+        h1 = metric
+    )
+}
+
+save_report(joboutdir)

{biopipen-0.31.4 → biopipen-0.31.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "biopipen"
-version = "0.31.4"
+version = "0.31.5"
 description = "Bioinformatics processes/pipelines that can be run from `pipen run`"
 authors = ["pwwang <pwwang@pwwang.com>"]
 license = "MIT"
@@ -38,6 +38,7 @@ gene = "biopipen.ns.gene"
 gsea = "biopipen.ns.gsea"
 misc = "biopipen.ns.misc"
 plot = "biopipen.ns.plot"
+protein = "biopipen.ns.protein"
 regulatory = "biopipen.ns.regulatory"
 rnaseq = "biopipen.ns.rnaseq"
 scrna = "biopipen.ns.scrna"

{biopipen-0.31.4 → biopipen-0.31.5}/setup.py

@@ -10,6 +10,7 @@ packages = \
  'biopipen.scripts.cellranger',
  'biopipen.scripts.cnvkit',
  'biopipen.scripts.misc',
+ 'biopipen.scripts.protein',
  'biopipen.scripts.regulatory',
  'biopipen.scripts.scrna',
  'biopipen.scripts.snp',
@@ -29,6 +30,7 @@ package_data = \
               'reports/cnvkit/*',
               'reports/delim/*',
               'reports/gsea/*',
+              'reports/protein/*',
               'reports/scrna/*',
               'reports/scrna_metabolic_landscape/*',
               'reports/snp/*',
@@ -68,6 +70,7 @@ entry_points = \
                    'gsea = biopipen.ns.gsea',
                    'misc = biopipen.ns.misc',
                    'plot = biopipen.ns.plot',
+                   'protein = biopipen.ns.protein',
                    'regulatory = biopipen.ns.regulatory',
                    'rnaseq = biopipen.ns.rnaseq',
                    'scrna = biopipen.ns.scrna',
@@ -82,7 +85,7 @@ entry_points = \
 
 setup_kwargs = {
     'name': 'biopipen',
-    'version': '0.31.4',
+    'version': '0.31.5',
     'description': 'Bioinformatics processes/pipelines that can be run from `pipen run`',
     'long_description': 'None',
     'author': 'pwwang',

biopipen-0.31.4/biopipen/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.31.4"