Area of research
Artificial Intelligence · Computational Theory and Mathematics
Research interest
Research interests include Computational Drug Discovery Methods, Machine Learning in Materials Science, Topic Modeling, and Machine Learning and Algorithms.
Protein FID: improved evaluation of protein structure generative models
Atom-level enzyme active site scaffolding using RFdiffusion2
AI-driven discovery of synergistic drug combinations against pancreatic cancer
Artificial intelligence for science in quantum, atomistic, and continuum systems
Structural constraint integration in a generative model for the discovery of quantum materials
Scaling Inference Time Compute for Diffusion Models
Diffusion models in protein structure and docking
Virtual node graph neural network for full phonon prediction
Closing the Execution Gap in Generative AI for Chemicals and Materials: Freeways or Safeguards
De novo design of protein structure and function with RFdiffusion
Deep learning-guided discovery of an antibiotic targeting Acinetobacter baumannii
Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back
Generative models for molecular discovery: Recent advances and challenges
Benchmarking AlphaFold‐enabled molecular docking predictions for antibiotic discovery
Deep learning identifies synergistic drug combinations for treating COVID-19
Mol2Image: Improved Conditional Flow Models for Molecule to Image Synthesis
A Deep Learning Approach to Antibiotic Discovery
Current and Future Roles of Artificial Intelligence in Medicinal Chemistry Synthesis
Multi-Objective Molecule Generation using Interpretable Substructures
International Conference on Machine Learning 2020cited by 26position: last
Analyzing Learned Molecular Representations for Property Prediction
Generative models for graph-based protein design
DSpace@MIT (Massachusetts Institute of Technology) 2019cited by 211position: last
Analyzing Learned Molecular Representations for Property Prediction
Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers
DSpace@MIT (Massachusetts Institute of Technology) 2019cited by 36position: last
Correction to Analyzing Learned Molecular Representations for Property Prediction
Are Learned Molecular Representations Ready for Prime Time?
Analyzing Learned Molecular Representations for Property Prediction
A graph-convolutional neural network model for the prediction of chemical reactivity
Approximate Inference in Additive Factorial HMMs with Application to Energy Disaggregation
Junction Tree Variational Autoencoder for Molecular Graph Generation
DSpace@MIT (Massachusetts Institute of Technology) 2018cited by 171position: last
A Graph-Convolutional Neural Network Model for the Prediction of Chemical Reactivity