biosim-extractor 0.0.1__tar.gz

biosim_extractor-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025-2026 CCPBioSim
+
+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.

biosim_extractor-0.0.1/PKG-INFO

@@ -0,0 +1,58 @@
+Metadata-Version: 2.4
+Name: biosim_extractor
+Version: 0.0.1
+Summary: Extract simulation metadata from MD output files
+Keywords: molecular dynamics,parser,schema
+Author-email: Jas Kalayan <jas.kalayan@stfc.ac.uk>
+Maintainer-email: Jas Kalayan <jas.kalayan@stfc.ac.uk>
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+Classifier: Development Status :: 3 - Alpha
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Natural Language :: English
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Software Development :: Libraries
+License-File: LICENSE
+Requires-Dist: MDAnalysis==2.10.0
+Requires-Dist: biopython==1.87
+Requires-Dist: rdkit>=2025.9.5
+Requires-Dist: linkml==1.11.1
+Requires-Dist: sphinx>=9,<10 ; extra == "docs"
+Requires-Dist: nbsphinx>=0.9,<1.0 ; extra == "docs"
+Requires-Dist: sphinx_rtd_theme>=3,<3.2 ; extra == "docs"
+Requires-Dist: sphinx_copybutton>=0.5,<1.0 ; extra == "docs"
+Requires-Dist: sphinxcontrib-contentui>=0.2,<1.0 ; extra == "docs"
+Requires-Dist: sphinxcontrib-details-directive>=0.1,<1.0 ; extra == "docs"
+Requires-Dist: furo>=2025.0,<2026.0 ; extra == "docs"
+Requires-Dist: markupsafe>=3.0,<4.0 ; extra == "docs"
+Requires-Dist: ruff>=0.14.8 ; extra == "pre-commit"
+Requires-Dist: pre-commit>=4.5,<5.0 ; extra == "pre-commit"
+Requires-Dist: pylint>=4.0,<5.0 ; extra == "pre-commit"
+Requires-Dist: pytest>=9.0,<10.0 ; extra == "testing"
+Requires-Dist: pytest-cov>=7.0,<8.0 ; extra == "testing"
+Requires-Dist: pytest-sugar>=1.1,<2.0 ; extra == "testing"
+Project-URL: Documentation, https://ccpbiosim-biosim-extractor.github.io/
+Project-URL: Homepage, https://github.com/CCPBioSim/biosim-extractor/
+Project-URL: Repository, https://github.com/CCPBioSim/biosim-extractor.git
+Provides-Extra: docs
+Provides-Extra: pre-commit
+Provides-Extra: testing
+
+biosim-extractor
+================
+A repository for extracting simulation data from output files produced from molecular dynamics (MD) simulations of biomolecules and validating against biosim-schem.
+
+## Project Status
+
+| Category       | Badges |
+|----------------|--------|
+| **Build**      | [![CI](https://github.com/CCPBioSim/biosim-extractor/actions/workflows/biosim_extractor_project-ci.yaml/badge.svg)](https://github.com/CCPBioSim/biosim-extractor/actions/workflows/biosim_extractor_project-ci.yaml) |
+| **Documentation** | [![Docs – Status](https://app.readthedocs.org/projects/biosim-extractor/badge/?version=latest)](https://biosim-extractor.readthedocs.io/en/latest/) |
+| **PyPI**       | [![PyPI - Version](https://img.shields.io/pypi/v/biosim-extractor.svg)](https://pypi.org/project/biosim-extractor/) [![PyPI - Status](https://img.shields.io/pypi/status/biosim-extractor.svg)](https://pypi.org/project/biosim-extractor/) [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/biosim-extractor.svg)](https://pypi.org/project/biosim-extractor/) [![PyPI - Downloads](https://img.shields.io/pypi/dm/biosim-extractor.svg)](https://pypi.org/project/biosim-extractor/) |
+| **Quality**    | [![Coverage Status](https://coveralls.io/repos/github/CCPBioSim/biosim-extractor/badge.svg?branch=main)](https://coveralls.io/github/CCPBioSim/biosim-extractor?branch=main) |
+

biosim_extractor-0.0.1/README.md

@@ -0,0 +1,12 @@
+biosim-extractor
+================
+A repository for extracting simulation data from output files produced from molecular dynamics (MD) simulations of biomolecules and validating against biosim-schem.
+
+## Project Status
+
+| Category       | Badges |
+|----------------|--------|
+| **Build**      | [![CI](https://github.com/CCPBioSim/biosim-extractor/actions/workflows/biosim_extractor_project-ci.yaml/badge.svg)](https://github.com/CCPBioSim/biosim-extractor/actions/workflows/biosim_extractor_project-ci.yaml) |
+| **Documentation** | [![Docs – Status](https://app.readthedocs.org/projects/biosim-extractor/badge/?version=latest)](https://biosim-extractor.readthedocs.io/en/latest/) |
+| **PyPI**       | [![PyPI - Version](https://img.shields.io/pypi/v/biosim-extractor.svg)](https://pypi.org/project/biosim-extractor/) [![PyPI - Status](https://img.shields.io/pypi/status/biosim-extractor.svg)](https://pypi.org/project/biosim-extractor/) [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/biosim-extractor.svg)](https://pypi.org/project/biosim-extractor/) [![PyPI - Downloads](https://img.shields.io/pypi/dm/biosim-extractor.svg)](https://pypi.org/project/biosim-extractor/) |
+| **Quality**    | [![Coverage Status](https://coveralls.io/repos/github/CCPBioSim/biosim-extractor/badge.svg?branch=main)](https://coveralls.io/github/CCPBioSim/biosim-extractor?branch=main) |

biosim_extractor-0.0.1/biosim_extractor/__init__.py

@@ -0,0 +1,8 @@
+"""
+example_package
+
+A short description of your package.
+"""
+
+__all__ = []  # Populate with public exports when needed
+__version__ = "0.0.1"

biosim_extractor-0.0.1/biosim_extractor/amber/amberlog.py

@@ -0,0 +1,310 @@
+#!/usr/bin/env python
+"""
+Extract AMBER log file metadata into a structured dictionary.
+
+This script parses AMBER log files and outputs structured metadata as JSON.
+It can be used as a standalone CLI tool or imported as a module.
+"""
+
+import argparse
+import json
+import re
+
+from biosim_extractor.helpers.log_utils import add_value, normalize_name, parse_value
+
+
+# -------------------------
+# PARSER
+# -------------------------
+class AmberLogParser:
+    """
+    Parser for AMBER log files.
+    """
+
+    def __init__(self, filepath):
+        """
+        Args:
+            filepath (str): Path to the AMBER log file.
+        """
+        self.filepath = filepath
+        self.lines = []
+        self.data = {
+            # "Header": {},
+            "SimulationSettings": {},
+            "Results": {
+                "TimeSeries": [],
+                "Averages": {},
+                "RMSFluctuations": {},
+                "Timings": {},
+            },
+        }
+
+    # -------------------------
+    # PUBLIC API
+    # -------------------------
+    def parse(self):
+        """
+        Parse the AMBER log file.
+
+        Returns:
+            dict: Parsed metadata.
+        """
+        with open(self.filepath) as f:
+            self.lines = f.readlines()
+
+        # self._parse_header()
+        self._parse_simulation_settings()
+        self._parse_results()
+        # print(json.dumps(self.data, indent=2))
+        return self.data
+
+    # # -------------------------
+    # # HEADER
+    # # -------------------------
+    # def _parse_header(self):
+    #     for line in self.lines[:200]:
+    #         if "=" in line:
+    #             parts = line.split(",")[0].split("=")
+    #             if len(parts) == 2:
+    #                 key, val = parts
+    #                 add_value(self.data["Header"], key.strip(), parse_value(val))
+
+    # -------------------------
+    # SIMULATION SETTINGS
+    # -------------------------
+    def _parse_simulation_settings(self):
+        """
+        Parse simulation settings from the log file.
+        """
+        settings = self.data["SimulationSettings"]
+        current_section = None
+        capture_cntrl = False
+
+        for line in self.lines:
+            stripped = line.strip()
+
+            # Stop at time series
+            if "NSTEP" in line and "TIME" in line:
+                break
+
+            # -------------------------
+            # &cntrl block
+            # -------------------------
+            if "&cntrl" in stripped:
+                capture_cntrl = True
+                current_section = "cntrl"
+                settings[current_section] = {}
+                continue
+
+            if capture_cntrl:
+                if "/" in stripped:
+                    capture_cntrl = False
+                    current_section = None
+                    continue
+
+                for part in stripped.split(","):
+                    if "=" in part:
+                        k, v = part.split("=")
+                        add_value(settings["cntrl"], k.strip(), parse_value(v))
+                continue
+
+            # -------------------------
+            # Colon sections
+            # -------------------------
+            if stripped.endswith(":") and "=" not in stripped:
+                section_name = normalize_name(stripped[:-1])
+                current_section = section_name
+                settings[current_section] = {}
+                continue
+
+            # -------------------------
+            # Key-value pairs
+            # -------------------------
+            if "=" in line:
+                matches = re.findall(r"([A-Za-z0-9_\-\s]+?)\s*=\s*([-\d\.E+]+)", line)
+
+                for k, v in matches:
+                    key = normalize_name(k)
+                    val = parse_value(v)
+
+                    if current_section:
+                        add_value(settings[current_section], key, val)
+                    else:
+                        add_value(settings, key, val)
+
+            # Reset section on blank line
+            if not stripped:
+                current_section = None
+
+        self._parse_file_assignments(settings)
+
+    # -------------------------
+    # SETTINGS: FILE ASSIGNMENTS
+    # -------------------------
+    def _parse_file_assignments(self, settings):
+        """
+        Parse file assignments from the log file.
+
+        Args:
+            settings (dict): Simulation settings dictionary to update.
+        """
+        capture = False
+        files = {}
+
+        pattern = r"\|\s*([A-Z0-9_]+):\s*(.+)"
+
+        for line in self.lines:
+            stripped = line.strip()
+
+            # Start block
+            if "File Assignments:" in line:
+                capture = True
+                continue
+
+            if capture:
+                # Stop if block ends
+                if not stripped or not stripped.startswith("|"):
+                    break
+
+                match = re.search(pattern, line)
+                if match:
+                    key = match.group(1).strip()
+                    val = match.group(2).strip()
+
+                    files[key] = val
+
+        if files:
+            settings["File_Assignments"] = files
+
+    # -------------------------
+    # RESULTS (ALL OUTPUT DATA)
+    # -------------------------
+    def _parse_results(self):
+        """
+        Parse results blocks from the log file.
+        """
+        # self._parse_time_series()
+        self._parse_block(
+            "A V E R A G E S", "R M S  F L U C T U A T I O N S", "Averages"
+        )
+        # self._parse_block("R M S  F L U C T U A T I O N S", "TIMINGS", "RMSFluctuations")
+        self._parse_timings()
+
+    # -------------------------
+    # TIME SERIES
+    # -------------------------
+    def _parse_time_series(self):
+        """
+        Parse time series data from the log file.
+        """
+        steps = []
+        current = {}
+        in_series = False
+
+        for line in self.lines:
+            if "NSTEP" in line and "TIME" in line:
+                in_series = True
+                if current:
+                    steps.append(current)
+                    current = {}
+
+                matches = re.findall(r"([A-Za-z\(\)\-]+)\s*=\s*([-\d\.E+]+)", line)
+                for k, v in matches:
+                    current[k] = parse_value(v)
+                continue
+
+            if in_series and "=" in line:
+                matches = re.findall(r"([A-Za-z\(\)\-]+)\s*=\s*([-\d\.E+]+)", line)
+                for k, v in matches:
+                    current[k] = parse_value(v)
+
+            if "A V E R A G E S" in line:
+                break
+
+        if current:
+            steps.append(current)
+
+        self.data["Results"]["TimeSeries"] = steps
+
+    # -------------------------
+    # GENERIC BLOCK PARSER
+    # -------------------------
+    def _parse_block(self, start_marker, end_marker, target_key):
+        """
+        Parse a generic results block.
+
+        Args:
+            start_marker (str): Line indicating the start of the block.
+            end_marker (str): Line indicating the end of the block.
+            target_key (str): Key in the results dictionary to populate.
+        """
+        capture = False
+        target = self.data["Results"][target_key]
+
+        for line in self.lines:
+            if start_marker in line:
+                capture = True
+                continue
+
+            if capture and "=" in line:
+                matches = re.findall(r"([A-Za-z\(\)\-]+)\s*=\s*([-\d\.E+]+)", line)
+                for k, v in matches:
+                    add_value(target, k, parse_value(v))
+
+            if end_marker in line:
+                break
+
+    # -------------------------
+    # TIMINGS
+    # -------------------------
+    def _parse_timings(self):
+        """
+        Parse timing information from the log file.
+        """
+        timings = self.data["Results"]["Timings"]
+        pattern = r"\|\s*(.*?)\s*:\s*([-\d\.E+]+)\s*seconds"
+
+        for line in self.lines:
+            if "CPU time" in line or "wall time" in line:
+                match = re.search(pattern, line)
+                if match:
+                    key = normalize_name(match.group(1))
+                    val = parse_value(match.group(2))
+                    add_value(timings, key, val)
+
+
+# =========================
+# ENTRY POINT
+# =========================
+
+
+def parse_args():
+    """Parse command-line arguments.
+
+    Returns:
+        Parsed ``argparse.Namespace`` object.
+    """
+    parser = argparse.ArgumentParser(
+        description="Extract Amber log file metadata to JSON"
+    )
+    parser.add_argument("logfile", help="Path to Amber log file")
+    parser.add_argument("--output", "-o", help="Output file path (default: stdout)")
+    return parser.parse_args()
+
+
+def main():
+    """Entry point: parse args, run extraction, and write output."""
+    args = parse_args()
+
+    parser = AmberLogParser(args.logfile)
+    result = parser.parse()
+
+    if args.output:
+        with open(args.output, "w") as f:
+            json.dump(result, f, indent=2)
+    else:
+        print(json.dumps(result, indent=2))
+
+
+if __name__ == "__main__":
+    main()