[AI Seminar Series] Seminar by Prof. Dhiman Ray, Friday June 6, 12-1pm, MRB Seminar Room

[Vassilis Tsotras]

Colleagues,
the next AI Seminar will be on Friday June 6, 12:00-1:00pm at the MRB
Seminar Room (1st floor). This seminar is in collaboration with the
Bioengineering Department.

**** Pizza and refreshments will be provided ****

To keep track of the number of attendees, please *register* at:
https://www.eventbrite.com/e/ai-seminar-series-tickets-1391174533479

The talk will be given by Prof. Dhiman Ray, Department of Chemistry and
Biochemistry, University of Oregon

TITLE:
"Interpretable and Data-Efficient Machine Learning for Biomolecular
Simulations"


ABSTRACT:
Molecular dynamics (MD) simulations are widely used to study the mechanisms
of biological processes at an atomistic resolution. Most physiological
events, e.g., drug-target binding and protein folding, occur at timescales
beyond milliseconds. But, we can simulate only up to a few microseconds at
an affordable computational cost. Enhanced sampling algorithms can
accelerate conformational sampling by applying an external biasing
potential. The accuracy and efficiency of these algorithms are sensitive to
the choice of collective variable (CV), a low-dimensional space along which
the bias is applied. Deep neural networks can be used to construct CVs
using a generic and system-agnostic feature space to compute an accurate
free energy surface for complex molecular processes. However, their lack of
interpretability and high cost of evaluation during trajectory propagation
make NN-CVs difficult to apply to biomolecular processes. In addition, it
often requires a large amount of training data to build NN-CVs that align
well with the slow modes of the system, thereby increasing the overall
computational cost. In this talk, I will describe a surrogate model
approach to express the output of a neural network as a linear combination
of a subset of the input descriptors. In addition to providing mechanistic
insights due to their explainable nature, the surrogate model CVs exhibit
negligible losses in efficiency and accuracy compared to the NN-CVs in
reconstructing the underlying free energy surface. Surrogate model CVs are
less expensive to evaluate compared to their neural network (NN)
counterparts, making them suitable for enhanced sampling simulations of
large and complex biomolecular processes. I will also describe a
variational Koopman algorithm for data-efficient training of deep learning
CVs using short metadynamics trajectories, sampling only forward
transitions. I will show some preliminary applications of enhanced sampling
methods on RNA conformational dynamics and ligand binding


Bio:
Dhiman grew up in Kolkata, India, and graduated from Indian Institute of
Science Education and Research (IISER) Kolkata with an integrated BS-MS
dual degree in Chemistry in 2018. He completed his PhD in Chemistry in 2022
from the University of California Irvine working with Prof. Ioan
Andricioaei. Subsequently, he held a postdoctoral position in the group of
Prof. Michele Parrinello at the Italian Institute of Technology, Genoa,
Italy. Since the fall of 2024 he is an assistant professor at the
Department of Chemistry and Biochemistry, at the University of Oregon, USA.

------------------------------------
Sponsored by the RAISE at UCR Institute, the AI Seminar Series presents
speakers working on cutting edge Foundational AI or apply AI in their
research. The goal of these seminars is to inform the UCR community about
current trends in AI research and promote collaborations between faculty in
this emerging field. These seminars are open to interested faculty and
graduate students. Please forward this email to other colleagues or
graduate students in your lab that may be interested. After the seminar a
discussion will follow for questions, open problems, ideas for possible
collaborations etc.

Sincerely,
Vassilis Tsotras
Professor, CSE Department
co-Director, RAISE at UCR Institute

Amit Roy-Chowdhury
Professor, ECE Department
co-Director, RAISE at UCR Institute
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.ucr.edu/pipermail/raise-seminar/attachments/20250601/b7052255/attachment.htm>