The paper develops an interpretable machine learning model to identify allosteric modulators of the AT1R receptor and discovers a negative allosteric modulator.

bioRxiv · Aug 3, 2026 · PreprintMolecular Biology

DRUMBEAT: Temporally resolved interpretable machine learning model for characterizing state transitions in protein dynamics

Babgen Manookian, Elizaveta Mukhaleva, Grigoriy Gogoshin, S. Bhattacharya, Nagarajan Vaidehi, Andréi S. Rodin, Sergio Branciamore

DRUMBEAT is a machine learning model that identifies time-resolved cooperative events in protein dynamics, revealing folding pathways and critical residues.

Communications Biology · Apr 15, 2026Peer-reviewedBiochemistry

Allostery between distant structural regions dictates selectivity in GPCR:G protein coupling.

Elizaveta Mukhaleva, Edgardo J. Sánchez, Sergio Branciamore, Andréi S. Rodin, Sivaraj Sivaramakrishnan, Nagarajan Vaidehi

The paper uses machine learning and simulations to show that distant residue interactions in the G protein core influence GPCR selectivity and can be engineered to change signaling preferences.

Biochemistry · Feb 25, 2026Peer-reviewedBiophysics

Temporally Resolved and Interpretable Machine Learning Model of GPCR Conformational Transition

Babgen Manookian, Elizaveta Mukhaleva, Grigoriy Gogoshin, S. Bhattacharya, Sivaraj Sivaramakrishnan, Nagarajan Vaidehi, Andréi S. Rodin, Sergio Branciamore

This paper develops an interpretable machine learning model to identify residue communities involved in GPCR conformational transitions, with applications to dopamine receptor subtype-specific drug design.

Nature Communications · Dec 6, 2025Peer-reviewedBiochemistry

Protein Frustration Reveals Active Sites in Co-Evolved GPCR:G Protein Complexes and in Engineered Targeted Degrader Complexes

Wenyuan Wei, Roland Del Mundo, Tianyi Yang, Elizaveta Mukhaleva, Indira R. Sivaraj, Veerabahu Shanmugasundaram, Sergio Branciamore, Andréi S. Rodin, Sivaraj Sivaramakrishnan, Ning Ma, Nagarajan Vaidehi

The paper identifies frustrated residues in GPCR:G protein interfaces and engineered degrader complexes, showing higher frustration in engineered interfaces.

bioRxiv · Jun 27, 2025 · PreprintBiophysics

BaNDyT: Bayesian Network modeling of molecular Dynamics Trajectories

Elizaveta Mukhaleva, Babgen Manookian, Hanyu Chen, Indira R. Sivaraj, Ning Ma, Wenyuan Wei, Konstancja Urbaniak, Grigoriy Gogoshin, S. Bhattacharya, Nagarajan Vaidehi, Andréi S. Rodin, Sergio Branciamore

BaNDyT uses Bayesian network modeling to analyze molecular dynamics trajectories, providing data-driven insights into protein function and interactions.

Journal of Chemical Information and Modeling · Jan 23, 2025Peer-reviewedBioinformatics

Insights From Protein Frustration Analysis Of BRD4-Cereblon Degrader Ternary Complexes Show Separation of Strong from Weak Degraders

Tianyi Yang, Elizaveta Mukhaleva, Wenyuan Wei, Dahlia R. Weiss, Ning Ma, Veerabahu Shanmugasundaram, Nagarajan Vaidehi

This study uses protein frustration analysis to identify key residues distinguishing strong from weak BRD4-Cereblon degraders.

RSC Medicinal Chemistry · Jan 1, 2025Peer-reviewedBiophysics

Molecular recognition of an aversive odorant by the murine trace amine-associated receptor TAAR7f

Anastasiia Gusach, Yang Lee, Armin Nikpour Khoshgrudi, Elizaveta Mukhaleva, Ning Ma, Eline J. Koers, Qingchao Chen, Patricia C. Edwards, Fanglu Huang, Jonathan Kim, Filippo Mancia, Dmitry B. Veprintsev, Nagarajan Vaidehi, Simone N. Weyand, Christopher G. Tate

The paper determines the cryo-EM structure of mTAAR7f bound to DMCH, revealing its unique binding site and activation mechanism distinct from ORs.

bioRxiv · Jul 7, 2023 · PreprintMolecular Biology