Gennady M. Verkhivker

The paper evaluates multimodal protein foundation models for allosteric binding site detection, finding that dataset properties, not model complexity, primarily determine performance.

This paper shows that deep learning models' performance in predicting protein-ligand binding poses depends on the energy landscape's frustration quenching and network topology, not algorithmic flaws.

This study introduces DynGeo-Pheno, a geometric deep learning framework that predicts disease-associated phosphosites and missense mutations by integrating protein dynamics and structural information.

This study uses computational methods to analyze class 3 and class 4 antibodies' mechanisms of neutralizing SARS-CoV-2, revealing distinct strategies for binding, dynamics, and immune escape.

This paper analyzes the molecular mechanisms of broadly neutralizing SARS-CoV-2 antibodies by combining computational methods to reveal how conserved epitopes resist immune escape.

This study uses explainable AI to analyze the energy landscape of protein kinases, revealing that allosteric sites are in neutrally frustrated regions, explaining their detection challenges.

This study identifies a universal failure in AI models to predict allosteric ligand binding, linking it to biophysical constraints in energy landscapes.

This paper introduces a generative framework for designing SRC kinase inhibitors, showing that inhibitors organize into a low-dimensional manifold and highlighting representation gaps in SMILES-based generation.

This paper compares sequence-based and structure-based methods for predicting allosteric binding sites in protein kinases, finding that sequence-based models perform poorly on allosteric sites despite good performance on orthosteric ones.

This study identifies how ultrapotent antibodies neutralize SARS-CoV-2 by distributing binding energy across rigid interfaces, enabling tolerance to mutations and informing therapeutic design.

This study uses computational methods to analyze how class 4 antibodies neutralize SARS-CoV-2 by targeting cryptic epitopes, revealing mechanisms involving allostery, binding energetics, and immune escape.

This study investigates how Class 4 and Class 5 antibodies modulate the conformational dynamics and immune escape of SARS-CoV-2 spike protein through allosteric effects and mutational scanning.

This study analyzes how different antibodies interact with SARS-CoV-2 spike protein using computational methods to identify binding hotspots and resistance mechanisms against variants.

This study identifies conserved allosteric hotspots in KRAS that mediate effector mimicry and allosteric modulation through molecular simulations and mutational analysis.

This study uses computational modeling to analyze binding mechanisms of four antibodies against SARS-CoV-2 Omicron variants, revealing distinct dynamic and evolutionary adaptations that influence immune escape.

This study identifies conserved allosteric hotspots in KRAS through computational analysis of interactions with monobodies and affimers, revealing structural and functional networks that govern binding and allostery.

This study identifies immune escape hotspots and binding determinants for broadly neutralizing antibodies against Omicron variants using molecular dynamics and deep mutational scanning.

This study integrates molecular dynamics, mutational scanning, and network modeling to characterize KRAS-RAF1 binding hotspots, allostery, and conformational dynamics, revealing how oncogenic mutations alter binding affinity and signaling.

This study uses interpretable machine learning and structural dynamics to analyze PTEN mutations linked to cancer and autism, revealing shared molecular mechanisms.

protPheMut predicts cancer and neurodevelopmental disorder phenotypes from missense variants using interpretable machine learning, achieving high accuracy in PI3K and PTEN mutation analysis.

This study evaluates AlphaFold2's ability to predict apo and holo protein conformations using randomized alanine masking and subsampling, finding it effective for minor changes but less so for large domain movements.

This study adapts AlphaFold2 to predict conformational ensembles of allosteric ABL kinase mutants, showing that sequence masking and subsampling improve prediction of structural state shifts caused by mutations.

This study uses AlphaFold2 and molecular dynamics to predict conformational ensembles and binding mechanisms of SARS-CoV-2 Omicron variants, showing agreement with experimental data.

This study uses molecular dynamics simulations and Markov state models to analyze mutation-induced allostery in AsLOV2, identifying key β-sheet interactions critical for signal transmission during photoactivation.

This study uses AlphaFold2 and molecular dynamics to analyze the structure, dynamics, and binding of SARS-CoV-2 Omicron BA.2.86 spike protein with ACE2 and antibodies, revealing key mutations that enhance immune evasion and ACE2 binding.

This study adapts AlphaFold2 to predict conformational ensembles and allosteric states of ABL kinase using sequence scanning and frustration profiling, revealing limitations in detecting low-populated inactive states.

This study uses AlphaFold2 and molecular simulations to analyze how mutations in SARS-CoV-2 Spike protein variants balance ACE2 binding and antibody resistance through epistatic interactions.

This study uses simulations and analysis of SARS-CoV-2 Omicron variants to examine conformational dynamics, protein stability, and evolution of cryptic binding pockets in the spike complex with ACE2.

The paper investigates how emerging mutations affect the dynamic properties of SARS-CoV-2 main protease using molecular dynamics simulations and identifies potential allosteric targets.