featuresyrup 0.0.1__tar.gz

featuresyrup-0.0.1/LICENSE

@@ -0,0 +1,22 @@
+
+MIT License
+
+Copyright (c) 2026 Sneha Sil
+
+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.

featuresyrup-0.0.1/MANIFEST.in

@@ -0,0 +1,7 @@
+include README.md
+include LICENSE
+include config_template.yaml
+include environment.yml
+include environment-dev.yml
+
+global-exclude *.py[cod] __pycache__ *.so

featuresyrup-0.0.1/PKG-INFO

@@ -0,0 +1,110 @@
+Metadata-Version: 2.4
+Name: featuresyrup
+Version: 0.0.1
+Summary: A catalyst-specific Python library for featurizing N-heterocyclic carbene organocatalysts, built on graphpancake
+Home-page: https://github.com/sneha-sil/featuresyrup
+Author: Sneha Sil
+Author-email: Sneha Sil <snehasil2029@u.northwestern.edu>
+License-Expression: MIT
+Project-URL: Source, https://github.com/sneha-sil/featuresyrup
+Project-URL: Documentation, https://github.com/sneha-sil/featuresyrup/tree/main/docs
+Project-URL: Issues, https://github.com/sneha-sil/featuresyrup/issues
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: torch
+Requires-Dist: torch-geometric
+Requires-Dist: networkx
+Requires-Dist: plotly
+Requires-Dist: matplotlib
+Requires-Dist: pyyaml
+Requires-Dist: rdkit
+Requires-Dist: morfeus
+Requires-Dist: dscribe
+Requires-Dist: regex
+Requires-Dist: tqdm
+Requires-Dist: psutil
+Requires-Dist: importlib-resources; python_version < "3.10"
+Provides-Extra: test
+Requires-Dist: pytest>=6.1.2; extra == "test"
+Provides-Extra: docs
+Requires-Dist: sphinx>=4.0; extra == "docs"
+Requires-Dist: sphinx-rtd-theme; extra == "docs"
+Requires-Dist: sphinx-autodoc-typehints; extra == "docs"
+Requires-Dist: sphinx-design; extra == "docs"
+Requires-Dist: sphinx-copybutton; extra == "docs"
+Requires-Dist: myst-parser; extra == "docs"
+Requires-Dist: shibuya; extra == "docs"
+Dynamic: license-file
+
+# featuresyrup
+
+featuresyrup is a catalyst-specific modification of graphpancake (Sil 2025) designed for the featurization of N-heterocyclic carbene (NHC) organocatalysts. The additional features on top of graphpancake includes: NMR shieldings, IR intensities, FMO energies, Morfeus descriptors, ACSF, SOAP, and Fukui indices. 
+
+## Installation
+
+### Recommended: conda environment
+
+```bash
+conda env create -f environment.yml
+conda activate featuresyrup-env
+pip install -e .
+```
+
+### Pip installation
+
+```bash
+pip install featuresyrup
+```
+
+## Quick start
+
+```bash
+featuresyrup create-db featuresyrup.db
+
+featuresyrup load-data \
+  --database featuresyrup.db \
+  --mol-id benzaldehyde_nhc \
+  --smiles "C1=CC=C(C=C1)C[NH]C2=CC=CC=C2" \
+  --xyz-file benzaldehyde.xyz \
+  --shermo-output benzaldehyde_shermo.out \
+  --neutral-output benzaldehyde_neutral.out \
+  --cationic-output benzaldehyde_cation.out \
+  --anionic-output benzaldehyde_anion.out \
+  --neutral-nbo benzaldehyde_neutral_nbo.out \
+  --cationic-nbo benzaldehyde_cation_nbo.out \
+  --anionic-nbo benzaldehyde_anion_nbo.out \
+  --nmr-output benzaldehyde_nmr.out \
+  --IR-output benzaldehyde_ir.out \
+  --dipole-polarizability-output benzaldehyde_dipole.out \
+  --homo-lumo-output benzaldehyde_homo_lumo.out
+
+featuresyrup query --database featuresyrup.db
+```
+
+Batch processing uses the same catalyst contract:
+
+```bash
+python -m featuresyrup.batch_processing --config config.yaml
+```
+
+## Documentation
+
+The full user guide and API reference live in the docs folder and are built with Sphinx. The documentation is aligned with the catalyst-only pipeline used by the package.
+
+## Dependencies to cite
+
+- Sil, S., Maskeri, M. A., and Scheidt, K. A. graphpancake: A Python package for representing organic molecules as molecular graphs utilizing electronic structure theory. J. Cheminform. 18, 61 (2026). DOI: 10.5281/zenodo.17553385
+- Jorner, K. morfeus: a Python package for calculating molecular features. Project documentation: https://github.com/digital-chemistry-laboratory/morfeus
+- Himanen, L., Jäger, M. O. J., Vatanen, T., Eriksson, O., and Fellowes, C. DScribe: Library of descriptors for machine learning in materials science. Comput. Phys. Commun. 247, 106949 (2020). DOI: 10.1016/j.cpc.2019.106949
+- Neese, F. et al. The ORCA quantum chemistry program package. J. Chem. Phys. 2020, 152, 224108
+- Nikolaienko et al. JANPA: an open source cross-platform implementation of the Natural Population Analysis on the Java platform, Computational and Theoretical Chemistry 2014, 1050, 15-22, DOI: 10.1016/j.comptc.2014.10.002, http://janpa.sourceforge.net
+- Glendening, E. D., Landis, C. R., Weinhold, F. NBO 7.0: New vistas in localized and delocalized chemical bonding theory. Journal of Computational Chemistry 2019, 40 (25), 2234-2241. https://doi.org/10.1002/jcc.25873
+- Tian, L., Qinxue, C., Shermo: A general code for calculating molecular thermodynamic properties, Comput. Theor. Chem. 2021, 1200, 113249 DOI: 10.1016/j.comptc.2021.113249
+
+## License
+
+MIT License. See [LICENSE](LICENSE) for details.

featuresyrup-0.0.1/README.md

@@ -0,0 +1,68 @@
+# featuresyrup
+
+featuresyrup is a catalyst-specific modification of graphpancake (Sil 2025) designed for the featurization of N-heterocyclic carbene (NHC) organocatalysts. The additional features on top of graphpancake includes: NMR shieldings, IR intensities, FMO energies, Morfeus descriptors, ACSF, SOAP, and Fukui indices. 
+
+## Installation
+
+### Recommended: conda environment
+
+```bash
+conda env create -f environment.yml
+conda activate featuresyrup-env
+pip install -e .
+```
+
+### Pip installation
+
+```bash
+pip install featuresyrup
+```
+
+## Quick start
+
+```bash
+featuresyrup create-db featuresyrup.db
+
+featuresyrup load-data \
+  --database featuresyrup.db \
+  --mol-id benzaldehyde_nhc \
+  --smiles "C1=CC=C(C=C1)C[NH]C2=CC=CC=C2" \
+  --xyz-file benzaldehyde.xyz \
+  --shermo-output benzaldehyde_shermo.out \
+  --neutral-output benzaldehyde_neutral.out \
+  --cationic-output benzaldehyde_cation.out \
+  --anionic-output benzaldehyde_anion.out \
+  --neutral-nbo benzaldehyde_neutral_nbo.out \
+  --cationic-nbo benzaldehyde_cation_nbo.out \
+  --anionic-nbo benzaldehyde_anion_nbo.out \
+  --nmr-output benzaldehyde_nmr.out \
+  --IR-output benzaldehyde_ir.out \
+  --dipole-polarizability-output benzaldehyde_dipole.out \
+  --homo-lumo-output benzaldehyde_homo_lumo.out
+
+featuresyrup query --database featuresyrup.db
+```
+
+Batch processing uses the same catalyst contract:
+
+```bash
+python -m featuresyrup.batch_processing --config config.yaml
+```
+
+## Documentation
+
+The full user guide and API reference live in the docs folder and are built with Sphinx. The documentation is aligned with the catalyst-only pipeline used by the package.
+
+## Dependencies to cite
+
+- Sil, S., Maskeri, M. A., and Scheidt, K. A. graphpancake: A Python package for representing organic molecules as molecular graphs utilizing electronic structure theory. J. Cheminform. 18, 61 (2026). DOI: 10.5281/zenodo.17553385
+- Jorner, K. morfeus: a Python package for calculating molecular features. Project documentation: https://github.com/digital-chemistry-laboratory/morfeus
+- Himanen, L., Jäger, M. O. J., Vatanen, T., Eriksson, O., and Fellowes, C. DScribe: Library of descriptors for machine learning in materials science. Comput. Phys. Commun. 247, 106949 (2020). DOI: 10.1016/j.cpc.2019.106949
+- Neese, F. et al. The ORCA quantum chemistry program package. J. Chem. Phys. 2020, 152, 224108
+- Nikolaienko et al. JANPA: an open source cross-platform implementation of the Natural Population Analysis on the Java platform, Computational and Theoretical Chemistry 2014, 1050, 15-22, DOI: 10.1016/j.comptc.2014.10.002, http://janpa.sourceforge.net
+- Glendening, E. D., Landis, C. R., Weinhold, F. NBO 7.0: New vistas in localized and delocalized chemical bonding theory. Journal of Computational Chemistry 2019, 40 (25), 2234-2241. https://doi.org/10.1002/jcc.25873
+- Tian, L., Qinxue, C., Shermo: A general code for calculating molecular thermodynamic properties, Comput. Theor. Chem. 2021, 1200, 113249 DOI: 10.1016/j.comptc.2021.113249
+
+## License
+
+MIT License. See [LICENSE](LICENSE) for details.

featuresyrup-0.0.1/config_template.yaml

@@ -0,0 +1,81 @@
+# featuresyrup configuration template for batch processing
+# 
+# Copy this file and customize the paths for your data structure.
+# Save as config.yaml and use with: python -m featuresyrup.batch_processing --config config.yaml
+
+data_paths:
+  # Option 1: Individual directories (set archive_file to null if using this)
+  base_dir: null # "/path/to/your/molecular/data"
+  xyz_dir: null # "/path/to/your/molecular/data/xyz_files"
+  shermo_dir: null # "/path/to/your/molecular/data/shermo_outputs"
+  janpa_dir: null # "/path/to/your/molecular/data/janpa_outputs"
+  nbo_dir: null # "/path/to/your/molecular/data/nbo_outputs"
+  neutral_output_dir: null # "/path/to/your/molecular/data/neutral_orca_outputs"
+  cationic_output_dir: null # "/path/to/your/molecular/data/cationic_orca_outputs"
+  anionic_output_dir: null # "/path/to/your/molecular/data/anionic_orca_outputs"
+  neutral_nbo_dir: null # "/path/to/your/molecular/data/neutral_nbo_outputs"
+  cationic_nbo_dir: null # "/path/to/your/molecular/data/cationic_nbo_outputs"
+  anionic_nbo_dir: null # "/path/to/your/molecular/data/anionic_nbo_outputs"
+  nmr_dir: null # "/path/to/your/molecular/data/nmr_outputs"
+  IR_dir: null # "/path/to/your/molecular/data/ir_outputs"
+  dipole_polarizability_dir: null # "/path/to/your/molecular/data/dipole_polarizability_outputs"
+  homo_lumo_dir: null # "/path/to/your/molecular/data/homo_lumo_outputs"
+
+  # Option 2: Compressed archive containing all data (set directories to null if using this)
+  archive_file: /home/uvx4187/featuresyrup_data/SS-07-07_data.tar.gz # "/path/to/your/data.tar.gz"
+
+file_patterns:
+  # IMPORTANT: featuresyrup expects the full catalyst input set.
+  # Matching files to your molecular identifier, customize each pattern as necessary.
+  # Use {mol_id} as placeholder for the molecule identifier
+  xyz_pattern: "{mol_id}_geom.xyz"                    # e.g., mol_001_geom.xyz
+  shermo_pattern: "{mol_id}_shermo.out"          # e.g., mol_001_shermo.out
+  janpa_pattern: "{mol_id}_wft.JANPA"            # e.g., mol_001_wft.JANPA
+  nbo_pattern: "{mol_id}_nbo.out"                # e.g., mol_001_nbo.out
+  neutral_output_pattern: "{mol_id}_neutral.out"   # e.g., mol_001_neutral.out
+  cationic_output_pattern: "{mol_id}_cation.out"   # e.g., mol_001_cation.out
+  anionic_output_pattern: "{mol_id}_anion.out"     # e.g., mol_001_anion.out
+  neutral_nbo_pattern: "{mol_id}_neutral_nbo.out"  # e.g., mol_001_neutral_nbo.out
+  cationic_nbo_pattern: "{mol_id}_cation_nbo.out"   # e.g., mol_001_cation_nbo.out
+  anionic_nbo_pattern: "{mol_id}_anion_nbo.out"     # e.g., mol_001_anion_nbo.out
+  nmr_pattern: "{mol_id}_nmr.out"                  # e.g., mol_001_nmr.out
+  IR_pattern: "{mol_id}_ir.out"                    # e.g., mol_001_ir.out
+  dipole_polarizability_pattern: "{mol_id}_dipole.out" # e.g., mol_001_dipole.out
+  homo_lumo_pattern: "{mol_id}_homo_lumo.out"      # e.g., mol_001_homo_lumo.out
+
+# CSV file containing molecular identifiers, SMILES strings, and miscellaneous properties
+data_file: "/home/uvx4187/featuresyrup_data/SS-07-07_data.csv"
+
+labels_file: "/home/uvx4187/featuresyrup_data/SS-07-07_labels.csv"  # CSV file with labels corresponding to rows in the data csv file (can be the same as the data_file)
+
+labels_config:
+  # Column names in your labels CSV file
+  id_column: "mol_id"        # Column containing unique molecule identifiers, taken from data csv
+  smiles_column: "SMILES"    # Column containing SMILES strings, taken from data csv
+  labels_column: "logP"     # Column containing target property for regression/classification, taken from labels csv
+
+settings:
+  max_workers: 16            # Number of parallel workers (setting this too high will lock the database!)
+  batch_size: 1000           # Molecules processed per batch  
+
+memory:
+  clear_cache_frequency: 1000        # Clear file cache every N molecules
+  max_memory_usage_gb: 16.0          # Approximate memory limit (GB)
+
+cleanup:
+  remove_temp_files: true            # Remove temporary extraction directory after processing
+  
+output:
+  database_name: "SS-07-07_QM"              # Whether to overwrite existing database
+  export_ml_features: true                # Export a csv file of ML features
+  ml_export_dir: "/home/uvx4187/featuresyrup_data"                # Directory for ML feature exports
+
+error_handling:
+  continue_on_error: true           # Continue processing if some molecules fail
+  save_error_log: true              # Save failed molecules to JSON file
+  max_errors: 1000                  # Stop processing after this many errors
+  
+logging:
+  level: "INFO"                     # DEBUG, INFO, WARNING, ERROR
+  save_to_file: true                # Save logs to file
+  log_file: "SS-07-07_batch_processing.log"  # Log file name

featuresyrup-0.0.1/environment.yml

@@ -0,0 +1,40 @@
+name: featuresyrup-env
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  # Base Python environment
+  - python>=3.8
+  - pip
+  
+  # Core dependencies (conda-forge when possible for better compatibility)
+  - pandas
+  - numpy
+  - rdkit
+  - networkx
+  - matplotlib
+  - pyyaml
+  - tqdm
+  - psutil
+  - regex
+  - plotly
+  - morfeus
+  - dscribe
+  
+  # PyTorch ecosystem (conda-forge)
+  - pytorch
+  - pyg  # PyTorch Geometric
+  
+  # Database and file handling
+  - sqlite  # For database operations (sqlite3 module uses this)
+  
+  # Python version specific
+  - importlib-resources  # Only needed for Python <3.10
+  
+  # Development and build tools
+  - setuptools
+  - wheel
+  
+  # Install featuresyrup from the local checkout via pip
+  - pip:
+    - -e .

featuresyrup-0.0.1/pyproject.toml

@@ -0,0 +1,112 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+# Self-descriptive entries which should always be present
+# https://packaging.python.org/en/latest/specifications/declaring-project-metadata/
+[project]
+name = "featuresyrup"
+description = "A catalyst-specific Python library for featurizing N-heterocyclic carbene organocatalysts, built on graphpancake"
+version = "0.0.1"
+readme = "README.md"
+authors = [
+    { name = "Sneha Sil", email = "snehasil2029@u.northwestern.edu" }
+]
+license = "MIT"
+license-files = ["LICENSE"]
+# See https://pypi.org/classifiers/
+classifiers = [
+    "Programming Language :: Python :: 3",
+]
+requires-python = ">=3.8"
+dependencies = [
+    "pandas",
+    "numpy",
+    "torch",
+    "torch-geometric",
+    "networkx",
+    "plotly",
+    "matplotlib",
+    "pyyaml",
+    "rdkit",
+    "morfeus",
+    "dscribe",
+    "regex",
+    "tqdm",
+    "psutil",
+    "importlib-resources; python_version<'3.10'",
+]
+
+[project.urls]
+Source = "https://github.com/sneha-sil/featuresyrup"
+Documentation = "https://github.com/sneha-sil/featuresyrup/tree/main/docs"
+Issues = "https://github.com/sneha-sil/featuresyrup/issues"
+
+[project.scripts]
+featuresyrup = "featuresyrup.cli:main"
+graphpancake = "featuresyrup.cli:main"
+
+[project.optional-dependencies]
+test = [
+  "pytest>=6.1.2",
+]
+docs = [
+  "sphinx>=4.0",
+  "sphinx-rtd-theme",
+  "sphinx-autodoc-typehints",
+  "sphinx-design",
+  "sphinx-copybutton",
+  "myst-parser",
+  "shibuya",
+]
+
+[tool.setuptools]
+# This subkey is a beta stage development and keys may change in the future, see https://setuptools.pypa.io/en/latest/userguide/pyproject_config.html for more details
+#
+# As of version 0.971, mypy does not support type checking of installed zipped
+# packages (because it does not actually import the Python packages).
+# We declare the package not-zip-safe so that our type hints are also available
+# when checking client code that uses our (installed) package.
+# Ref:
+# https://mypy.readthedocs.io/en/stable/installed_packages.html?highlight=zip#using-installed-packages-with-mypy-pep-561
+zip-safe = false
+# Let setuptools discover the package in the current directory,
+# but be explicit about non-Python files.
+# See also:
+#   https://setuptools.pypa.io/en/latest/userguide/pyproject_config.html#setuptools-specific-configuration
+# Note that behavior is currently evolving with respect to how to interpret the
+# "data" and "tests" subdirectories. As of setuptools 63, both are automatically
+# included if namespaces is true (default), even if the package is named explicitly
+# (instead of using 'find'). With 'find', the 'tests' subpackage is discovered
+# recursively because of its __init__.py file, but the data subdirectory is excluded
+# with include-package-data = false and namespaces = false.
+
+include-package-data = false
+[tool.setuptools.packages.find]
+namespaces = false
+where = ["src"]
+
+# Ref https://setuptools.pypa.io/en/latest/userguide/datafiles.html#package-data
+[tool.setuptools.package-data]
+
+featuresyrup = [
+    "py.typed"
+]
+
+[tool.versioningit]
+default-version = "1+unknown"
+
+[tool.versioningit.format]
+distance = "{base_version}+{distance}.{vcs}{rev}"
+dirty = "{base_version}+{distance}.{vcs}{rev}.dirty"
+distance-dirty = "{base_version}+{distance}.{vcs}{rev}.dirty"
+
+[tool.versioningit.vcs]
+# The method key:
+method = "git"  # <- The method name
+# Parameters to pass to the method:
+match = ["*"]
+default-tag = "1.0.0"
+
+[tool.versioningit.write]
+file = "src/featuresyrup/_version.py"

featuresyrup-0.0.1/setup.cfg

@@ -0,0 +1,52 @@
+[metadata]
+name = featuresyrup
+version = 0.0.1
+description = A catalyst-specific Python library for featurizing N-heterocyclic carbene organocatalysts, built on graphpancake.
+author = Sneha Sil
+author_email = snehasil2029@u.northwestern.edu
+license = MIT
+long_description = file: README.md
+long_description_content_type = text/markdown
+url = https://github.com/sneha-sil/featuresyrup
+
+[options]
+packages = find:
+package_dir = 
+	= src
+python_requires = >=3.8
+install_requires = 
+	pandas
+	numpy
+	torch
+	torch-geometric
+	networkx
+	plotly
+	matplotlib
+	morfeus
+	dscribe
+	qmllib
+	importlib-resources; python_version<'3.10'
+
+[options.package_data]
+featuresyrup = data/*.dat
+
+[coverage:run]
+omit = 
+	*/tests/*
+	src/featuresyrup/_version.py
+
+[yapf]
+COLUMN_LIMIT = 119
+INDENT_WIDTH = 4
+USE_TABS = False
+
+[flake8]
+max-line-length = 119
+
+[aliases]
+test = pytest
+
+[egg_info]
+tag_build = 
+tag_date = 0
+

featuresyrup-0.0.1/src/featuresyrup/__init__.py

@@ -0,0 +1,6 @@
+"""FeatureSyrup: catalyst-focused molecular feature extraction and graph export."""
+
+from ._version import __version__
+from .classes import DictData, Edge, GraphInfo, Node, Targets
+from .functions import *
+from .graph import Graph, GraphDatabase, MolecularGraph

featuresyrup-0.0.1/src/featuresyrup/_version.py

@@ -0,0 +1 @@
+__version__ = "1.0.0+18.g9938c35.dirty"