Sompriya Chatterjee
Sompriya Chatterjee has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- Dhiman Ray
University of Oregon
3 shared publications
Latest Publications
- 17 April 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 22 (8) , 4180-4190
Explainable Machine Learning Guided Enhanced Sampling of Protein Conformational Transition in HSP90
Elucidating the thermodynamics, kinetics, and mechanisms of protein conformational transitions remains a longstanding challenge in molecular dynamics simulations. We employ enhanced sampling simulations using explainable machine-learning (ML)-based collective variables (CVs) to efficiently explore the free-energy landscape of the millisecond-time scale ATP-lid conformational transition in heat shock protein 90 (HSP90). Our simulations yielded relative free energies consistent with nuclear magnetic resonance (NMR) experiments at modest computational cost. The interpretability of the surrogate model CV enabled the identification of key residues in the ATP-lid transition, providing mechanistic insight at atomistic resolution. The ML-CV trained on the wild-type system shows transferability to two mutant variants, successfully reproducing experimental population shifts. We could also obtain accurate kinetic rates of the conformational transition using an integrated sampling strategy that combined biased enhanced sampling with an unbiased weighted ensemble algorithm. Our framework provides detailed thermodynamic, kinetic, and mechanistic insights into the complex conformational transitions of the N-terminal domain of HSP90, highlighting the potential of explainable machine-learning-based collective variables for investigating complex conformational landscapes in biomolecular systems and informing future inhibitor design efforts.
- 17 April 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 22 (8) , 4180-4190
Explainable Machine Learning Guided Enhanced Sampling of Protein Conformational Transition in HSP90
Elucidating the thermodynamics, kinetics, and mechanisms of protein conformational transitions remains a longstanding challenge in molecular dynamics simulations. We employ enhanced sampling simulations using explainable machine-learning (ML)-based collective variables (CVs) to efficiently explore the free-energy landscape of the millisecond-time scale ATP-lid conformational transition in heat shock protein 90 (HSP90). Our simulations yielded relative free energies consistent with nuclear magnetic resonance (NMR) experiments at modest computational cost. The interpretability of the surrogate model CV enabled the identification of key residues in the ATP-lid transition, providing mechanistic insight at atomistic resolution. The ML-CV trained on the wild-type system shows transferability to two mutant variants, successfully reproducing experimental population shifts. We could also obtain accurate kinetic rates of the conformational transition using an integrated sampling strategy that combined biased enhanced sampling with an unbiased weighted ensemble algorithm. Our framework provides detailed thermodynamic, kinetic, and mechanistic insights into the complex conformational transitions of the N-terminal domain of HSP90, highlighting the potential of explainable machine-learning-based collective variables for investigating complex conformational landscapes in biomolecular systems and informing future inhibitor design efforts.
- 14 January 2026
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry Letters
- Vol. 17 (4) , 966-975
Characterizing RNA Tetramer Conformational Landscape Using Explainable Machine Learning
The conformational flexibility of RNA molecules enables them to play vital physiological roles, including carrying genetic information, catalyzing reactions, and forming organelles. However, this structural diversity complicates the quantitative sampling of their conformational landscape, even for simple single-stranded RNA tetramers. We show that combining explainable artificial intelligence (XAI) with enhanced sampling algorithms can effectively explore the complex free energy landscapes of RNA tetramers. Our simulations capture key conformational states, such as stacked, intercalated, nucleobase-flipped, and random coil structures, while reproducing unbiased populations with much less computational effort than conventional molecular dynamics. This data-driven approach distinguishes several metastable states that are often indistinguishable in standard analysis. Additionally, our interpretable machine learning framework identifies key torsion angles driving slow transitions and those responsible for unphysical intercalated structures, paving the way for improvements in nucleic acid force fields.
- 14 January 2026
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry Letters
- Vol. 17 (4) , 966-975
Characterizing RNA Tetramer Conformational Landscape Using Explainable Machine Learning
The conformational flexibility of RNA molecules enables them to play vital physiological roles, including carrying genetic information, catalyzing reactions, and forming organelles. However, this structural diversity complicates the quantitative sampling of their conformational landscape, even for simple single-stranded RNA tetramers. We show that combining explainable artificial intelligence (XAI) with enhanced sampling algorithms can effectively explore the complex free energy landscapes of RNA tetramers. Our simulations capture key conformational states, such as stacked, intercalated, nucleobase-flipped, and random coil structures, while reproducing unbiased populations with much less computational effort than conventional molecular dynamics. This data-driven approach distinguishes several metastable states that are often indistinguishable in standard analysis. Additionally, our interpretable machine learning framework identifies key torsion angles driving slow transitions and those responsible for unphysical intercalated structures, paving the way for improvements in nucleic acid force fields.
- 4 February 2025
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 21 (4) , 1561-1571
Acceleration with Interpretability: A Surrogate Model-Based Collective Variable for Enhanced Sampling
Most enhanced sampling methods facilitate the exploration of molecular free energy landscapes by applying a bias potential along a reduced dimensional collective variable (CV) space. The success of these methods depends on the ability of the CVs to follow the relevant slow modes of the system. Intuitive CVs, such as distances or contacts, often prove inadequate, particularly in biological systems involving many coupled degrees of freedom. Machine learning algorithms, especially neural networks (NN), can automate the process of CV discovery by combining a large number of molecular descriptors and often outperform intuitive CVs in sampling efficiency. However, their lack of interpretability and high cost of evaluation during trajectory propagation make NN-CVs difficult to apply to large biomolecular processes. Here, we introduce a surrogate model approach using lasso regression to express the output of a neural network as a linear combination of an automatically chosen subset of the input descriptors. We demonstrate successful applications of our surrogate model CVs in the enhanced sampling simulation of the conformational landscape of alanine dipeptide and chignolin mini-protein. In addition to providing mechanistic insights due to their explainable nature, the surrogate model CVs showed a negligible loss in efficiency and accuracy, compared to the NN-CVs, in reconstructing the underlying free energy surface. Moreover, due to their simplified functional forms, these CVs are better at extrapolating to unseen regions of the conformational space, e.g., saddle points. Surrogate model CVs are also less expensive to evaluate compared to their NN counterparts, making them suitable for enhanced sampling simulation of large and complex biomolecular processes.
- 4 February 2025
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 21 (4) , 1561-1571
Acceleration with Interpretability: A Surrogate Model-Based Collective Variable for Enhanced Sampling
Most enhanced sampling methods facilitate the exploration of molecular free energy landscapes by applying a bias potential along a reduced dimensional collective variable (CV) space. The success of these methods depends on the ability of the CVs to follow the relevant slow modes of the system. Intuitive CVs, such as distances or contacts, often prove inadequate, particularly in biological systems involving many coupled degrees of freedom. Machine learning algorithms, especially neural networks (NN), can automate the process of CV discovery by combining a large number of molecular descriptors and often outperform intuitive CVs in sampling efficiency. However, their lack of interpretability and high cost of evaluation during trajectory propagation make NN-CVs difficult to apply to large biomolecular processes. Here, we introduce a surrogate model approach using lasso regression to express the output of a neural network as a linear combination of an automatically chosen subset of the input descriptors. We demonstrate successful applications of our surrogate model CVs in the enhanced sampling simulation of the conformational landscape of alanine dipeptide and chignolin mini-protein. In addition to providing mechanistic insights due to their explainable nature, the surrogate model CVs showed a negligible loss in efficiency and accuracy, compared to the NN-CVs, in reconstructing the underlying free energy surface. Moreover, due to their simplified functional forms, these CVs are better at extrapolating to unseen regions of the conformational space, e.g., saddle points. Surrogate model CVs are also less expensive to evaluate compared to their NN counterparts, making them suitable for enhanced sampling simulation of large and complex biomolecular processes.