Loading…
A nonprofit AI research institute in Moscow pursuing fundamental and applied machine learning, including AI for biology, chemistry, and medicine.
Ab initio gene annotation model that predicts gene boundaries and exon-intron structure from raw DNA, generalizing zero-shot to unseen species.
Molecular docking model that predicts protein-ligand binding poses with multi-stage Riemannian flow matching, yielding physically valid geometry.
Family of transformer-based DNA language models using BPE tokenization and BigBird sparse attention to reach context lengths up to 36,000 base pairs.