Graph Inference on MoLEcular Topology. A package for modelling, learning, and inference on molecular topological space written in Python and TensorFlow.

gimlet doesn't depend on any packages except TensorFlow 2.0 , and pandas and pytest, if you must.

https://github.com/choderalab/gimlet/blob/master/lime/scripts/notebooks/190728_yuanqing_gn_with_gru_on_sereina_riniker_dataset.ipynb

• yuanqing wang <[email protected]><[email protected]> (while at Chodera Lab at Memorial Sloan Kettering Cancer Center, Weill Cornell Medicine, and the City College of the City University of New York.)

• gin/ the core (and fun) part of the package.
  • i_o/ reading and writing popular molecule embedding/representing structures.
  • deterministic/ property predictions, conformer and charge generations.
  • probabilistic/ molecular machine learning through graph networks.
• lime/ auxiliary scripts.
  • for_biologists/ ready-to-use modules and scripts.
  • architectures/ off-the-shelf model architectures developed elsewhere.
  • scripts/ fun scripts we used to generate data and hypothesis.
  • trained_models/ Nomen est omen.