Anton V. Sinitskiy

This paper evaluates five AI frameworks on predicting antibody properties and modeling lipid-RNA interactions, finding they show strengths but fail to match the scope of original studies.

StructureSAFE is a chemical language model that combines protein structure and evolutionary information with molecular representations to improve hit identification and lead optimization, achieving state-of-the-art performance in chemical plausibility and binding affinity prediction.

This paper evaluates agentic AI systems on three scientific tasks, finding that human-led AI-assisted work outperforms autonomous systems, with one AI matching human performance in property prediction.

This paper evaluates five AI frameworks on real scientific tasks, finding they excel in hypothesis generation and reporting but struggle with depth and reliability in real-world research.

This paper evaluates AI frameworks' ability to autonomously conduct scientific research, finding they cannot complete full research cycles but may assist with specific subtasks.

Slogen unifies fragment generation and screening for lead optimization, improving chemical diversity and synthetic tractability while matching state-of-the-art performance.

The paper evaluates if evolutionary proximity correlates with chemical similarity in natural products across multiple taxa using deep learning embeddings.

This paper explores using AI as a co-pilot in biotech research for analyzing functional protein networks in invasive colorectal cancer, finding that AI improves efficiency but requires expert guidance and cannot fully automate complex tasks.

This study presents a computational model of a primitive nervous system in early multicellular organisms, showing how it enhances chemotaxis and survival through optimized movement and energy use.

This paper solves a general optimization problem for the evolutionary cost of a simplified nervous system model, confirming optimal neuronal spikes and response functions.

This paper extends a previous model of a nervous system by analyzing the asymptotic behavior of optimal solutions for motor and sensory responses to predator approach.

The paper uses computer simulations to show that four non-active cryoEM structures of NMDA receptors interconvert rapidly, suggesting they represent the same functional state.