RNApolis 0.4.3__tar.gz → 0.11.3__tar.gz

rnapolis-0.11.3/MANIFEST.in

@@ -0,0 +1,2 @@
+# Include the entire adapters subpackage (including non-.py assets) in sdists
+graft src/rnapolis/adapters

{rnapolis-0.4.3/src/RNApolis.egg-info → rnapolis-0.11.3}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: RNApolis
-Version: 0.4.3
+Version: 0.11.3
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok
@@ -16,6 +16,7 @@ Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: appdirs
+Requires-Dist: faiss-cpu
 Requires-Dist: graphviz
 Requires-Dist: mmcif
 Requires-Dist: numpy
@@ -24,8 +25,20 @@ Requires-Dist: orjson
 Requires-Dist: pandas
 Requires-Dist: pulp
 Requires-Dist: requests
+Requires-Dist: scikit-learn
 Requires-Dist: scipy
+Requires-Dist: tqdm
 Requires-Dist: viennarna
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: requires-dist
+Dynamic: summary
 
 # RNApolis
 

{rnapolis-0.4.3 → rnapolis-0.11.3}/setup.py

@@ -1,12 +1,12 @@
-from setuptools import setup
+from setuptools import setup, find_packages
 
 with open("README.md") as f:
     long_description = f.read()
 
 setup(
     name="RNApolis",
-    version="0.4.3",
-    packages=["rnapolis"],
+    version="0.11.3",
+    packages=find_packages(where="src", include=["rnapolis", "rnapolis.*"]),
     package_dir={"": "src"},
     author="Tomasz Zok",
     author_email="tomasz.zok@cs.put.poznan.pl",
@@ -27,16 +27,33 @@ setup(
     entry_points={
         "console_scripts": [
             "annotator=rnapolis.annotator:main",
+            "adapter=rnapolis.adapter:main",
+            "aligner=rnapolis.aligner:main",
             "clashfinder=rnapolis.clashfinder:main",
+            "distiller=rnapolis.distiller:main",
             "metareader=rnapolis.metareader:main",
             "molecule-filter=rnapolis.molecule_filter:main",
             "motif-extractor=rnapolis.motif_extractor:main",
             "transformer=rnapolis.transformer:main",
             "rfam-folder=rnapolis.rfam_folder:main",
+            "unifier=rnapolis.unifier:main",
+            "splitter=rnapolis.splitter:main",
         ]
     },
+    include_package_data=True,
+    package_data={
+        "rnapolis": [
+            "component_A.csv",
+            "component_C.csv",
+            "component_G.csv",
+            "component_U.csv",
+            "mmcif_pdbx_v50.dic",
+        ],
+        "rnapolis.adapters": ["*"],
+    },
     install_requires=[
         "appdirs",
+        "faiss-cpu",
         "graphviz",
         "mmcif",
         "numpy",
@@ -45,7 +62,9 @@ setup(
         "pandas",
         "pulp",
         "requests",
+        "scikit-learn",
         "scipy",
+        "tqdm",
         "viennarna",
     ],
 )

{rnapolis-0.4.3 → rnapolis-0.11.3/src/RNApolis.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: RNApolis
-Version: 0.4.3
+Version: 0.11.3
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok
@@ -16,6 +16,7 @@ Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: appdirs
+Requires-Dist: faiss-cpu
 Requires-Dist: graphviz
 Requires-Dist: mmcif
 Requires-Dist: numpy
@@ -24,8 +25,20 @@ Requires-Dist: orjson
 Requires-Dist: pandas
 Requires-Dist: pulp
 Requires-Dist: requests
+Requires-Dist: scikit-learn
 Requires-Dist: scipy
+Requires-Dist: tqdm
 Requires-Dist: viennarna
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: requires-dist
+Dynamic: summary
 
 # RNApolis
 

rnapolis-0.11.3/src/RNApolis.egg-info/SOURCES.txt

@@ -0,0 +1,63 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+setup.py
+src/RNApolis.egg-info/PKG-INFO
+src/RNApolis.egg-info/SOURCES.txt
+src/RNApolis.egg-info/dependency_links.txt
+src/RNApolis.egg-info/entry_points.txt
+src/RNApolis.egg-info/requires.txt
+src/RNApolis.egg-info/top_level.txt
+src/rnapolis/adapter.py
+src/rnapolis/aligner.py
+src/rnapolis/annotator.py
+src/rnapolis/clashfinder.py
+src/rnapolis/common.py
+src/rnapolis/component_A.csv
+src/rnapolis/component_C.csv
+src/rnapolis/component_G.csv
+src/rnapolis/component_U.csv
+src/rnapolis/distiller.py
+src/rnapolis/metareader.py
+src/rnapolis/mmcif_pdbx_v50.dic
+src/rnapolis/molecule_filter.py
+src/rnapolis/motif_extractor.py
+src/rnapolis/parser.py
+src/rnapolis/parser_v2.py
+src/rnapolis/py.typed
+src/rnapolis/rfam_folder.py
+src/rnapolis/splitter.py
+src/rnapolis/tertiary.py
+src/rnapolis/tertiary_v2.py
+src/rnapolis/transformer.py
+src/rnapolis/unifier.py
+src/rnapolis/util.py
+src/rnapolis/adapters/__init__.py
+src/rnapolis/adapters/barnaba.py
+src/rnapolis/adapters/bpnet.py
+src/rnapolis/adapters/dssr.py
+src/rnapolis/adapters/fr3d.py
+src/rnapolis/adapters/maxit.py
+src/rnapolis/adapters/mc_annotate.py
+src/rnapolis/adapters/rnaview.py
+src/rnapolis/adapters/__pycache__/__init__.cpython-313.pyc
+src/rnapolis/adapters/__pycache__/barnaba.cpython-313.pyc
+src/rnapolis/adapters/__pycache__/bpnet.cpython-313.pyc
+src/rnapolis/adapters/__pycache__/dssr.cpython-313.pyc
+src/rnapolis/adapters/__pycache__/fr3d.cpython-313.pyc
+src/rnapolis/adapters/__pycache__/maxit.cpython-313.pyc
+src/rnapolis/adapters/__pycache__/mc_annotate.cpython-313.pyc
+src/rnapolis/adapters/__pycache__/rnaview.cpython-313.pyc
+tests/test_adapter.py
+tests/test_annotator.py
+tests/test_bugfixes.py
+tests/test_common.py
+tests/test_metareader.py
+tests/test_molecule_filter.py
+tests/test_parser.py
+tests/test_quadruplexes.py
+tests/test_rfam_folder.py
+tests/test_tertiary.py
+tests/test_transformer.py
+tests/test_v2.py

{rnapolis-0.4.3 → rnapolis-0.11.3}/src/RNApolis.egg-info/entry_points.txt

@@ -1,8 +1,13 @@
 [console_scripts]
+adapter = rnapolis.adapter:main
+aligner = rnapolis.aligner:main
 annotator = rnapolis.annotator:main
 clashfinder = rnapolis.clashfinder:main
+distiller = rnapolis.distiller:main
 metareader = rnapolis.metareader:main
 molecule-filter = rnapolis.molecule_filter:main
 motif-extractor = rnapolis.motif_extractor:main
 rfam-folder = rnapolis.rfam_folder:main
+splitter = rnapolis.splitter:main
 transformer = rnapolis.transformer:main
+unifier = rnapolis.unifier:main

{rnapolis-0.4.3 → rnapolis-0.11.3}/src/RNApolis.egg-info/requires.txt

@@ -1,4 +1,5 @@
 appdirs
+faiss-cpu
 graphviz
 mmcif
 numpy
@@ -7,5 +8,7 @@ orjson
 pandas
 pulp
 requests
+scikit-learn
 scipy
+tqdm
 viennarna

rnapolis-0.11.3/src/RNApolis.egg-info/top_level.txt

@@ -0,0 +1 @@
+

rnapolis-0.11.3/src/rnapolis/adapter.py

@@ -0,0 +1,204 @@
+#! /usr/bin/env python
+import argparse
+import logging
+import os
+from enum import Enum
+from typing import List, Tuple
+
+from rnapolis.adapters.barnaba import parse_barnaba_output
+from rnapolis.adapters.bpnet import parse_bpnet_output
+from rnapolis.adapters.dssr import parse_dssr_output
+from rnapolis.adapters.fr3d import parse_fr3d_output
+from rnapolis.adapters.maxit import parse_maxit_output
+from rnapolis.adapters.mc_annotate import parse_mcannotate_output
+from rnapolis.adapters.rnaview import parse_rnaview_output
+from rnapolis.annotator import (
+    add_common_output_arguments,
+    handle_output_arguments,
+)
+from rnapolis.common import BaseInteractions, Structure2D
+from rnapolis.parser import read_3d_structure
+from rnapolis.tertiary import (
+    Mapping2D3D,
+    Structure3D,
+)
+from rnapolis.util import handle_input_file
+
+
+class ExternalTool(Enum):
+    FR3D = "fr3d"
+    DSSR = "dssr"
+    RNAVIEW = "rnaview"
+    BPNET = "bpnet"
+    MAXIT = "maxit"
+    BARNABA = "barnaba"
+    MCANNOTATE = "mc-annotate"
+
+
+logging.basicConfig(level=os.getenv("LOGLEVEL", "INFO").upper())
+
+
+def auto_detect_tool(external_files: List[str]) -> ExternalTool:
+    """
+    Auto-detect the external tool based on file patterns.
+
+    Args:
+        external_files: List of external tool output file paths
+
+    Returns:
+        ExternalTool enum value based on detected patterns
+    """
+    if not external_files:
+        return ExternalTool.MAXIT
+
+    for file_path in external_files:
+        basename = os.path.basename(file_path)
+
+        # Check for FR3D pattern
+        if basename.endswith("basepair_detail.txt"):
+            return ExternalTool.FR3D
+
+        # Check for RNAView pattern
+        if basename.endswith(".out"):
+            return ExternalTool.RNAVIEW
+
+        # Check for BPNet pattern
+        if basename.endswith("basepair.json"):
+            return ExternalTool.BPNET
+
+        # Check for MC-Annotate pattern
+        if basename.endswith("stdout.txt"):
+            return ExternalTool.MCANNOTATE
+
+        # Check for Barnaba pattern
+        if "pairing" in basename or "stacking" in basename:
+            return ExternalTool.BARNABA
+
+        # Check for JSON files (DSSR)
+        if basename.endswith(".json"):
+            return ExternalTool.DSSR
+
+    # Default to MAXIT if no patterns match
+    return ExternalTool.MAXIT
+
+
+def parse_external_output(
+    file_paths: List[str], tool: ExternalTool, structure3d: Structure3D
+) -> BaseInteractions:
+    """
+    Parse the output from an external tool (FR3D, DSSR, etc.) and convert it to BaseInteractions.
+
+    Args:
+        file_paths: List of paths to external tool output files
+        tool: The external tool that generated the output
+        structure3d: The 3D structure parsed from PDB/mmCIF
+
+    Returns:
+        BaseInteractions object containing the interactions found by the external tool
+    """
+    if tool == ExternalTool.FR3D:
+        return parse_fr3d_output(file_paths, structure3d)
+    elif tool == ExternalTool.DSSR:
+        return parse_dssr_output(file_paths, structure3d)
+    elif tool == ExternalTool.MAXIT:
+        return parse_maxit_output(file_paths, structure3d)
+    elif tool == ExternalTool.BPNET:
+        return parse_bpnet_output(file_paths, structure3d)
+    elif tool == ExternalTool.RNAVIEW:
+        return parse_rnaview_output(file_paths, structure3d)
+    elif tool == ExternalTool.BARNABA:
+        return parse_barnaba_output(file_paths, structure3d)
+    elif tool == ExternalTool.MCANNOTATE:
+        return parse_mcannotate_output(file_paths, structure3d)
+    else:
+        raise ValueError(f"Unsupported external tool: {tool}")
+
+
+def process_external_tool_output(
+    structure3d: Structure3D,
+    external_file_paths: List[str],
+    tool: ExternalTool,
+    input_file_path: str,
+    find_gaps: bool = False,
+) -> Tuple[Structure2D, Mapping2D3D]:  # Added Mapping2D3D to return tuple
+    """
+    Process external tool output and create a secondary structure representation.
+
+    This function can be used from other code to process external tool outputs
+    and get a Structure2D object with the secondary structure information.
+
+    Args:
+        structure3d: The 3D structure parsed from PDB/mmCIF
+        external_file_paths: List of paths to external tool output files (empty for MAXIT)
+        tool: The external tool that generated the output (FR3D, DSSR, etc.)
+        input_file_path: Path to the input file (used when external_file_paths is empty)
+        find_gaps: Whether to detect gaps in the structure
+
+    Returns:
+        A tuple containing the Structure2D object and the Mapping2D3D object.
+    """
+    # Parse external tool output
+    if not external_file_paths:
+        # For MAXIT or when no external files are provided, use the input file
+        file_paths_to_process = [input_file_path]
+    elif tool == ExternalTool.MCANNOTATE or tool == ExternalTool.RNAVIEW:
+        # MC-Annotate and RNAView requires both the stdout and the PDB file
+        file_paths_to_process = external_file_paths + [input_file_path]
+    else:
+        # Process all external files
+        file_paths_to_process = external_file_paths
+
+    base_interactions = parse_external_output(file_paths_to_process, tool, structure3d)
+
+    # Extract secondary structure using the external tool's interactions
+    return structure3d.extract_secondary_structure(base_interactions, find_gaps)
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("input", help="Path to PDB or mmCIF file")
+    parser.add_argument(
+        "external_files",
+        nargs="*",
+        help="Path(s) to external tool output file(s) (FR3D, DSSR, etc.)",
+    )
+    parser.add_argument(
+        "--tool",
+        choices=[t.value for t in ExternalTool],
+        help="External tool that generated the output file (auto-detected if not specified)",
+    )
+    parser.add_argument(
+        "-f",
+        "--find-gaps",
+        action="store_true",
+        help="(optional) if set, the program will detect gaps and break the PDB chain into two or more strands",
+    )
+    add_common_output_arguments(parser)
+    # The --inter-stem-csv and --stems-csv arguments are now added by add_common_output_arguments
+    args = parser.parse_args()
+
+    file = handle_input_file(args.input)
+    structure3d = read_3d_structure(file, None)
+
+    # Auto-detect tool if not specified
+    if args.tool is not None:
+        tool = ExternalTool(args.tool)
+    else:
+        tool = auto_detect_tool(args.external_files)
+        logging.info(f"Auto-detected tool: {tool.value}")
+
+    # Process external tool output files and get secondary structure
+    # Always call process_external_tool_output, even for MAXIT (empty external files)
+    structure2d, mapping = process_external_tool_output(
+        structure3d,
+        args.external_files,
+        tool,
+        args.input,
+        args.find_gaps,
+    )
+
+    handle_output_arguments(args, structure2d, mapping, args.input)
+
+
+if __name__ == "__main__":
+    main()

rnapolis-0.11.3/src/rnapolis/adapters/__init__.py

@@ -0,0 +1,7 @@
+"""Adapters subpackage.
+
+This module marks 'rnapolis.adapters' as a regular Python package so it is
+discovered by setuptools and included in distributions.
+"""
+
+__all__: list[str] = []