Metadata-Version: 2.1
Name: molcomplib
Version: 1.1.2
Summary: A library for the projection of chemical compounds onto 2D space, mostly for visualization purposes.
Home-page: https://github.com/sergsb/molcompview
Author: Sergey Sosnin
Author-email: sergey.sosnin@univie.ac.at
License: MIT
Keywords: chemistry,cheminformatics,t-SNE,visualization,chemical space
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.6
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Development Status :: 5 - Production/Stable
Classifier: Topic :: Scientific/Engineering :: Chemistry
Classifier: Intended Audience :: Science/Research
Requires-Python: >=3.6
License-File: LICENSE
Requires-Dist: rdkit
Requires-Dist: numpy

Molcomplib is a key component of the MolCompass project. It is a python library, that provides the pretrained parametric t-SNE model for molecular visualization. This model was trained on ChEMBL data (about 1 Million of molecules). This library generates X and Y coordinates for compounds so that similar compounds group together forming well-recognisible clusters. The library is lightweight, and requires only rdkit and numpy (optionally, pandas)
