Publications

Selected Work

Publications and talks at the intersection of simulation and machine learning

These papers reflect a recurring theme in my work: using statistical learning and molecular physics together to make difficult biomolecular and medicinal chemistry problems more tractable.

5 publications and preprints Communications Biology JCIM and ACS Combinatorial Science AI-driven computational chemistry

Selected Work

Publications

  1. 2022 Gupta, Aayush, Dey, Souvik, Hicks, Alan, and Zhou, Huan-Xiang. Artificial intelligence guided conformational mining of intrinsically disordered proteins. Communications Biology, 5, 610. PDF
  2. 2021 Gupta, Aayush and Zhou, Huan-Xiang. A machine learning-enabled pipeline for large-scale virtual drug screening. Journal of Chemical Information and Modeling, 61(9), 4236-4244. PDF
  3. 2020 Gupta, Aayush and Zhou, Huan-Xiang. Profiling SARS-CoV-2 main protease binding to repurposed drugs using molecular dynamics simulations in classical and neural network-trained force fields. ACS Combinatorial Science, 22(12), 826-832. PDF
  4. 2020 Gupta, Aayush. Profiling molecular simulations of SARS-CoV-2 main protease binding to repurposed drugs using neural network force fields. ChemRxiv
  5. 2017 Gupta, Aayush and Arora, Jyotsna S. DFT evidence of unforeseen bending in linearly fused polycyclic rings of hexasilabenzenoids. Computational and Theoretical Chemistry, 1099, 87-91. PDF

Talks

Presentations

  • Oral presentation at the ACS Meeting in San Francisco, April 2017.
  • Poster presentation at the Annual Midwest Theoretical Conference in East Lansing, June 2017.

Research Direction

Recurring themes

  • Machine learning guided conformational exploration for difficult biomolecular systems.
  • Virtual screening and ranking pipelines grounded in both statistics and physical chemistry.
  • Hybrid workflows that connect molecular simulation, representation learning, and experimental decision making.