Metadata-Version: 2.4
Name: molgrid
Version: 0.5.5
Summary: Grid-based molecular modeling library
Home-page: https://github.com/gnina/libmolgrid
Author: David Ryan Koes and Jocelyn Sunseri
Author-email: dkoes@pitt.edu
Project-URL: Documentation, http://gnina.github.io/libmolgrid
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Chemistry
Classifier: License :: OSI Approved :: Apache Software License
Classifier: License :: OSI Approved :: GNU General Public License v2 (GPLv2)
Classifier: Programming Language :: C++
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3
Requires-Dist: numpy>=1.16.2
Requires-Dist: pyquaternion
Requires-Dist: importlib-metadata>=1.0; python_version < "3.8"
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: home-page
Dynamic: project-url
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

molgrid can be used to generate several types of tensors from input molecules, most uniquely three-dimensional voxel grids. Input can be specified fairly flexibly, with native support for numpy arrays and torch tensors as well as major molecular file formats via OpenBabel. Output generation has several options that facilitate obtaining good performance from machine learning algorithms, including features like data augmentation and resampling.
