darkprofiler 0.1.0__tar.gz

darkprofiler-0.1.0/LICENSE.txt

@@ -0,0 +1,17 @@
+MIT License
+Copyright (c) 2025 Hanjun Lee, Stephen J. Elledge
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

darkprofiler-0.1.0/PKG-INFO

@@ -0,0 +1,124 @@
+Metadata-Version: 2.1
+Name: darkprofiler
+Version: 0.1.0
+Summary: DarkProfiler: Alignment and Classification of Peptides from Reference-Independent De Novo Peptide Sequencing Experiments.
+Author-email: Hanjun Lee <hanjun@alum.mit.edu>
+License: MIT
+Keywords: proteomics,immunopeptidomics,neoantigen,bioinformatics
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+Requires-Dist: biopython>=1.78
+Requires-Dist: matplotlib>=3.3
+
+# DarkProfiler
+
+**DarkProfiler: Alignment and Classification of Peptides from Reference-Independent De Novo Peptide Sequencing Experiments**
+
+DarkProfiler takes peptide sequences (e.g. from de novo sequencing) and classifies them into:
+
+- **Canonical proteome**
+- **Alternative splicing**
+- **Neoantigens (SNV-derived mutanome)**
+- **Alternative reading frame peptides**
+- **Amino acid misincorporations**
+- **Unknown / unaligned**
+
+It supports human and mouse references: `hg19`, `hg38`, `mm10`, `mm39`.
+
+---
+
+## Installation
+
+### Install with pip (PyPI)
+
+```bash
+pip install darkprofiler
+```
+
+### Install with conda (bioconda)
+
+```bash
+conda install bioconda::darkprofiler
+```
+
+---
+
+## Reference genome
+
+DarkProfiler supports human and mouse reference genomes.
+
+Supported genome assemblies are:
+
+```
+hg19 (GENCODE release 19)
+hg38 (GENCODE release 37)
+mm10 (GENCODE release M19)
+mm39 (GENCODE release M37)
+```
+
+---
+
+## Command-line usage
+
+### Download reference data
+
+```bash
+darkprofiler download hg38
+```
+
+### Run classification
+
+```bash
+darkprofiler run hg38 peptides.fa output_dir
+```
+
+Optional flags:
+
+```
+--vcf-path FILE
+--database-path DIR
+--num-threads N
+```
+
+---
+
+## Python API
+
+```python
+from darkprofiler.run import classify_peptides
+
+classify_peptides(
+    reference="hg38",
+    peptide_fasta="peptides.fa",
+    output_dir="output",
+    vcf_path=None,
+    database_path=None,
+    num_threads=4
+)
+```
+
+---
+
+## Outputs
+
+- canonicalProteome.fa  
+- alternativeSplicing.fa  
+- neoantigen.fa  
+- alternativeReadingFrame.fa  
+- aminoAcidMisincorporation.fa  
+- unknown.fa  
+- pieChart.tsv  
+- pieChart.pdf  
+
+---
+
+## License
+
+MIT License  
+Copyright (c) 2025  

darkprofiler-0.1.0/README.md

@@ -0,0 +1,106 @@
+# DarkProfiler
+
+**DarkProfiler: Alignment and Classification of Peptides from Reference-Independent De Novo Peptide Sequencing Experiments**
+
+DarkProfiler takes peptide sequences (e.g. from de novo sequencing) and classifies them into:
+
+- **Canonical proteome**
+- **Alternative splicing**
+- **Neoantigens (SNV-derived mutanome)**
+- **Alternative reading frame peptides**
+- **Amino acid misincorporations**
+- **Unknown / unaligned**
+
+It supports human and mouse references: `hg19`, `hg38`, `mm10`, `mm39`.
+
+---
+
+## Installation
+
+### Install with pip (PyPI)
+
+```bash
+pip install darkprofiler
+```
+
+### Install with conda (bioconda)
+
+```bash
+conda install bioconda::darkprofiler
+```
+
+---
+
+## Reference genome
+
+DarkProfiler supports human and mouse reference genomes.
+
+Supported genome assemblies are:
+
+```
+hg19 (GENCODE release 19)
+hg38 (GENCODE release 37)
+mm10 (GENCODE release M19)
+mm39 (GENCODE release M37)
+```
+
+---
+
+## Command-line usage
+
+### Download reference data
+
+```bash
+darkprofiler download hg38
+```
+
+### Run classification
+
+```bash
+darkprofiler run hg38 peptides.fa output_dir
+```
+
+Optional flags:
+
+```
+--vcf-path FILE
+--database-path DIR
+--num-threads N
+```
+
+---
+
+## Python API
+
+```python
+from darkprofiler.run import classify_peptides
+
+classify_peptides(
+    reference="hg38",
+    peptide_fasta="peptides.fa",
+    output_dir="output",
+    vcf_path=None,
+    database_path=None,
+    num_threads=4
+)
+```
+
+---
+
+## Outputs
+
+- canonicalProteome.fa  
+- alternativeSplicing.fa  
+- neoantigen.fa  
+- alternativeReadingFrame.fa  
+- aminoAcidMisincorporation.fa  
+- unknown.fa  
+- pieChart.tsv  
+- pieChart.pdf  
+
+---
+
+## License
+
+MIT License  
+Copyright (c) 2025  

darkprofiler-0.1.0/pyproject.toml

@@ -0,0 +1,37 @@
+[build-system]
+requires = ["setuptools>=61", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "darkprofiler"
+version = "0.1.0"
+description = "DarkProfiler: Alignment and Classification of Peptides from Reference-Independent De Novo Peptide Sequencing Experiments."
+readme = "README.md"
+requires-python = ">=3.7"
+license = { text = "MIT" }  # or whatever license you want
+authors = [
+  { name = "Hanjun Lee", email = "hanjun@alum.mit.edu" }
+]
+keywords = ["proteomics", "immunopeptidomics", "neoantigen", "bioinformatics"]
+classifiers = [
+  "Programming Language :: Python :: 3",
+  "License :: OSI Approved :: MIT License",
+  "Operating System :: OS Independent",
+  "Intended Audience :: Science/Research",
+  "Topic :: Scientific/Engineering :: Bio-Informatics"
+]
+
+dependencies = [
+  "biopython>=1.78",
+  "matplotlib>=3.3"
+]
+
+[project.scripts]
+darkprofiler = "darkprofiler.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+darkprofiler = ["genome/*/*"] 
+

darkprofiler-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

darkprofiler-0.1.0/src/darkprofiler/__init__.py

@@ -0,0 +1,6 @@
+from .run import classify_peptides
+
+__all__ = ["classify_peptides"]
+
+__version__ = "0.1.0"
+

darkprofiler-0.1.0/src/darkprofiler/cli.py

@@ -0,0 +1,142 @@
+import argparse
+import os
+import sys
+import zipfile
+from pathlib import Path
+from urllib.request import urlopen
+
+from .run import classify_peptides
+
+SUPPORTED_REFERENCES = ("hg19", "hg38", "mm10", "mm39")
+
+# Reference Zip Files from Elledge Lab
+URL_PREFIX = "https://elledge.hms.harvard.edu/wp-content/uploads/2025/12/"
+
+
+def _get_package_root() -> Path:
+    # Directory where this file lives (src/darkprofiler)
+    return Path(__file__).resolve().parent
+
+def _download_reference(reference: str) -> None:
+    reference = reference.lower()
+    if reference not in SUPPORTED_REFERENCES:
+        raise SystemExit(
+            f"Unsupported reference '{reference}'. Must be one of: "
+            f"{', '.join(SUPPORTED_REFERENCES)}"
+        )
+
+    url_prefix = URL_PREFIX
+
+    pkg_root = _get_package_root()
+    genome_dir = pkg_root / "genome"
+    genome_dir.mkdir(exist_ok=True)
+
+    # URL like: {url_prefix}/darkprofiler_hg38.zip
+    url = f"{url_prefix.rstrip('/')}/darkprofiler_{reference}.zip"
+    zip_path = genome_dir / f"{reference}.zip"
+
+    print(f"[darkprofiler] Downloading {url} ...", file=sys.stderr)
+    try:
+        with urlopen(url) as resp, open(zip_path, "wb") as out_fh:
+            # Stream copy to disk
+            chunk = resp.read(8192)
+            while chunk:
+                out_fh.write(chunk)
+                chunk = resp.read(8192)
+    except Exception as e:
+        if zip_path.exists():
+            zip_path.unlink()
+        raise SystemExit(f"Failed to download {url}: {e}")
+
+    print(f"[darkprofiler] Extracting to {pkg_root} ...", file=sys.stderr)
+    try:
+        with zipfile.ZipFile(zip_path, "r") as zf:
+            zf.extractall(path=pkg_root)
+    except Exception as e:
+        raise SystemExit(f"Failed to extract {zip_path}: {e}")
+
+    print(
+        f"[darkprofiler] Finished. Reference '{reference}' is now available.",
+        file=sys.stderr,
+    )
+
+def cmd_download(args: argparse.Namespace) -> None:
+    _download_reference(args.reference)
+
+
+def cmd_run(args: argparse.Namespace) -> None:
+    classify_peptides(
+        reference=args.reference,
+        peptide_fasta=args.peptide_fasta,
+        output_dir=args.output_dir,
+        vcf_path=args.vcf_path,
+        database_path=args.database_path,
+        num_threads=args.num_threads,
+    )
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        prog="darkprofiler",
+        description=(
+            "DarkProfiler: classify peptides into canonical, alternative, "
+            "mutant, and dark proteome categories."
+        ),
+    )
+    subparsers = parser.add_subparsers(dest="command", required=True)
+
+    # ---------------- download ----------------
+    p_download = subparsers.add_parser(
+        "download",
+        help="Download a reference genome bundle (hg19/hg38/mm10/mm39).",
+    )
+    p_download.add_argument(
+        "reference",
+        choices=SUPPORTED_REFERENCES,
+        help="Reference assembly version to download.",
+    )
+    p_download.set_defaults(func=cmd_download)
+
+    # ---------------- run ----------------
+    p_run = subparsers.add_parser(
+        "run",
+        help="Run DarkProfiler classification pipeline.",
+    )
+    p_run.add_argument(
+        "reference",
+        choices=SUPPORTED_REFERENCES,
+        help="Reference assembly version to use (must be downloaded first).",
+    )
+    p_run.add_argument("peptide_fasta", help="Path to peptide FASTA file.")
+    p_run.add_argument("output_dir", help="Output directory.")
+    p_run.add_argument(
+        "--vcf-path",
+        default=None,
+        help="Optional path to VCF or VCF.GZ file with SNVs.",
+    )
+    p_run.add_argument(
+        "--database-path",
+        default=None,
+        help=(
+            "Optional path to existing database directory containing "
+            "canonicalProteome.fa, alternativeSplicing.fa, mutanome.fa, "
+            "mutatedCanonicalTranscriptome.fa, mutatedAlternativeTranslatome.fa, "
+            "mutatedAlternativeORFeome.fa."
+        ),
+    )
+    p_run.add_argument(
+        "--num-threads",
+        type=int,
+        default=1,
+        help="Threads for amino acid misincorporation search.",
+    )
+    p_run.set_defaults(func=cmd_run)
+
+    return parser
+
+
+def main(argv=None) -> None:
+    parser = build_parser()
+    args = parser.parse_args(argv)
+    args.func(args)
+