Following are the codes corresponding to the Machine Learning frameworks and tutorials developed in the lab

1.     CIGIN , Chemically Interpretable Graph Interaction Network for Prediction of Pharmacokinetic Properties of Drug-like Molecules. This method allows prediction of solvation free energies of drug like molecules in any organic solvent and to obtain interaction maps.

2.    delNetFF Machine Learning for Accurate Force Calculations in Molecular Dynamics Simulation. delNetFF method supplements the forces calculated using classical force field for running DFT level simulations at low computational cost.

3.     BAND-NN , A deep learning architecture for prediction of atomization energy and for geometry optimization. The deep neural network allows prediction of DFT level molecular energies of small organic molecules. This can also be used to perform geometry optimization.

4.    DING , Deep learning enabled for INorganic material Generator. This method is developed based on conditional variation auto encoder(CVAE) generates novel inorganic molecules with certain desired properties.

5.    rex_md_kinetic , A probabilistic framework for visualizing "most reactive pathways" in molecular trajectories. This method allows calculation of qualitative kinetic properties without using temporal information (for eg: replica change molecular trajectories).

6.    ml4science_tut , two simple machine learning tasks that may be useful for beginners in Machine Learning applications in fundamental sciences.

Made with Mobirise css templates