A5101784501- Machine Learning in Materials Science
- Computational Drug Discovery Methods
- Protein Structure and Dynamics
- Catalysis and Oxidation Reactions
- Molecular spectroscopy and chirality
- Enzyme Structure and Function
- Scientific Computing and Data Management
Stanford University
2023-2024
Carnegie Mellon University
2023
Machine learning plays an important and growing role in molecular simulation. The newest version of the OpenMM dynamics toolkit introduces new features to support use machine potentials. Arbitrary PyTorch models can be added a simulation used compute forces energy. A higher-level interface allows users easily model their molecules interest with general purpose, pretrained potential functions. collection optimized CUDA kernels custom operations greatly improves speed simulations. We...
Rapid determination of molecular structures can greatly accelerate workflows across many chemical disciplines. However, elucidating structure using only one-dimensional (1D) NMR spectra, the most readily accessible data, remains an extremely challenging problem because combinatorial explosion number possible molecules as constituent atoms is increased. Here, we introduce a multitask machine learning framework that predicts (formula and connectivity) unknown compound solely based on its 1D 1H...
Quantum chemistry provides chemists with invaluable information, but the high computational cost limits size and type of systems that can be studied. Machine learning (ML) has emerged as a means to dramatically lower while maintaining accuracy. However, ML models often sacrifice interpretability by using components such artificial neural networks deep function black boxes. These impart flexibility needed learn from large volumes data make it difficult gain insight into physical or chemical...
Two-dimensional electronic spectroscopy (2DES) provides rich information about how the states of molecules, proteins, and solid-state materials interact with each other their surrounding environment. Atomistic molecular dynamics simulations offer an appealing route to uncover nuclear motions mediate energy relaxation manifestation in spectroscopies but are computationally expensive. Here we show that by using equivariant transformer-based machine learning architecture trained only 2500...
Rapid determination of molecular structures can greatly accelerate workflows across many chemical disciplines. However, elucidating structure using only one-dimensional (1D) NMR spectra, the most readily accessible data, remains an extremely challenging problem because combinatorial explosion number possible molecules as constituent atoms is increased. Here, we introduce a multitask machine learning framework that predicts (formula and connectivity) unknown compound solely based on its 1D 1H...
Machine learning plays an important and growing role in molecular simulation. The newest version of the OpenMM dynamics toolkit introduces new features to support use machine potentials. Arbitrary PyTorch models can be added a simulation used compute forces energy. A higher-level interface allows users easily model their molecules interest with general purpose, pretrained potential functions. collection optimized CUDA kernels custom operations greatly improves speed simulations. We...
Quantum chemistry provides chemists with invaluable information, but the high computational cost limits size and type of systems that can be studied. Machine learning (ML) has emerged as a means to dramatically lower while maintaining accuracy. However, ML models often sacrifice interpretability by using components, such artificial neural networks deep learning, function black boxes. These components impart flexibility needed learn from large volumes data make it difficult gain insight into...