Computational Biologist Joins MIT to Advance Protein Modeling

Sergei Kotelnikov aims to develop new machine learning methods to study the building blocks of life.

Apr. 1, 2026 at 7:58am

Got story updates? Submit your updates here. ›

Sergei Kotelnikov, a computational biologist, has joined MIT's School of Science as part of the Dean's Postdoctoral Fellowship. Kotelnikov's goal is to develop new machine learning methods to model protein structure, function, and interactions, with potential applications in fields like medicine and agriculture. He previously worked at Stony Brook University, where he made advancements in predicting the structures of protein complexes.

Why it matters

Understanding the structure and behavior of proteins, the fundamental building blocks of life, is crucial for advancing fields like drug discovery and crop protection. Kotelnikov's work in computational biology, combining physics and machine learning, has the potential to significantly improve protein modeling and lead to important real-world applications.

The details

At MIT, Kotelnikov will work with Professor Amy Keating, a leader in the field of protein structure and function research. He also plans to collaborate with professors in the Department of Electrical Engineering and Computer Science to explore geometric deep learning, which can integrate physical and geometric knowledge about biomolecules into neural network architectures. Kotelnikov's state-of-the-art protein modeling methods have been instrumental in his team's top performance in international competitions like the Critical Assessment of protein Structure Prediction (CASP).

  • Kotelnikov began his PhD at Stony Brook University in New York in 2018.
  • He has now joined MIT's School of Science as part of the Dean's Postdoctoral Fellowship.

The players

Sergei Kotelnikov

A computational biologist who has joined MIT's School of Science as part of the Dean's Postdoctoral Fellowship. His goal is to develop new machine learning methods to model protein structure, function, and interactions.

Amy Keating

The Jay A. Stein (1968) Professor of Biology, biology department head, and professor of biological engineering at MIT. Keating employs both computational and experimental methods to study proteins, their interactions, and how this can impact disease.

Dima Kozakov

A recognized leader in the field of predicting protein interactions and complex structures, who Kotelnikov worked with during his PhD at Stony Brook University.

Got photos? Submit your photos here. ›

What they’re saying

“Life is, to some degree, magical. You can write formulas on how a molecule behaves, but yet somehow, a few orders of magnitude above, on a bigger scale, it gives rise to such a mystery.”

— Sergei Kotelnikov, Computational Biologist

“Kotelnikov stands to gain a lot from working closely with wet lab researchers who are doing the experiments that will complement and test his predictions, and my lab will benefit from his experience developing and applying advanced computational analyses.”

— Amy Keating, Jay A. Stein (1968) Professor of Biology, Biology Department Head, and Professor of Biological Engineering, MIT

What’s next

Kotelnikov plans to work with professors Tommi Jaakkola and Tess Smidt in MIT's Department of Electrical Engineering and Computer Science to explore geometric deep learning, which can integrate physical and geometric knowledge about biomolecules into neural network architectures.

The takeaway

Kotelnikov's work in computational biology, combining physics and machine learning, has the potential to significantly improve protein modeling and lead to important real-world applications in fields like medicine and agriculture. His collaboration with experimental researchers at MIT will help bridge the gap between computational predictions and real-world validation.