Machine Learning Models

• 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.
• 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.
• 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.
• 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.
• 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).
• Spectra to Structure: Deep Reinforcement Learning for Molecular Inverse Problem
• BiRDS: Binding Residue Detection from Protein Sequences using Deep ResNets
• MolGPT: Molecular Generation Using a Transformer-Decoder Model
• DeepPocket: Ligand Binding Site Detection and Segmentation using 3D Convolutional Neural Networks
• Molegular: Molecule Generation Using Reinforcement Learning with Alternating Rewards
• SCONES: Self Consistent Neural Network for Protein Stability Prediction Upon Mutation
• DART: Deep Learning Enabled Topological Interaction Model for Energy Prediction of Metal Clusters and its Application in Identifying Unique Low Energy Isomers
• IMLE-Net: An Interpretable Multi-level Multi-channel Model for ECG Classification
• MMBERT: Multimodal BERT Pretraining for Improved Medical VQA
• A Model of Graph Transactional Coverage Patterns with Applications to Drug Discovery
• Mining Subgraph Coverage Patterns from Graph transactions
• Linear Prediction Residual for Efficient Diagnosis of Parkinson’s Disease from Gait