Andrey V. Kajava

LLPSight predicts LLPS-driving proteins using machine learning and protein language models, achieving an F1 score of 0.885 and identifying promising targets in the human proteome.

The paper analyzes frameshifts in tandem repeats across proteomes, showing they significantly alter protein physicochemical properties and function.

This paper evaluates the cross-reactivity of a recombinant Plasmodium vivax protein with sera from Plasmodium falciparum-exposed individuals and demonstrates its transmission-blocking activity against P. falciparum.

The paper develops a biophysical model to explain the energy mechanisms behind iRBC membrane curling during malaria parasite egress, showing that lateral lipid diffusion, not viscosity, drives the process.

The paper develops machine learning predictors for amyloid formation using a new database of naturally occurring cross-beta amyloids, showing improved performance over existing methods.

The paper identifies and analyzes Exposed Aggregation-prone Regions (EARs) in proteomes across three kingdoms of life using a bioinformatics pipeline.

The paper evaluates 43 methods for predicting intrinsically disordered regions and binding regions in proteins, finding that deep learning methods outperform older physicochemical approaches but binding prediction remains challenging.