Алан Нафієв

Leveraging High-Throughput Proteomics and AI-Based Protein Folding to Accelerate VAV1 Molecular Glue Discovery

This paper identifies a novel non-canonical RT-loop degron in VAV1 and demonstrates how conformational restriction and computational modeling enhance molecular glue potency for proteasomal degradation.

Critical Assessment of ML models for ADMET Prediction in TDC leaderboards

The paper evaluates ADMET prediction models on TDC leaderboards, finding most top models lack reproducibility and exhibit data leakage, with only three methods passing rigorous checks.

ArtiDock: accurate Machine Learning approach to protein-ligand docking optimized for high-throughput virtual screening

ArtiDock is a machine learning-based protein-ligand docking method that improves accuracy over classical techniques while maintaining low computational cost for high-throughput virtual screening.

Sampling and ranking of protein conformations using machine learning techniques do not improve quality of rigid protein-protein docking

This study evaluates ML-based conformational sampling in rigid protein-protein docking and finds it does not improve docking accuracy compared to using Apo structures.

Leveraging Large Language Models for Literature-Driven Prioritization of Protein Binding Pockets

This paper combines geometric pocket detection with large language models to prioritize protein binding pockets for drug discovery, using a curated dataset and automated pipeline.

Improving ADMET prediction with descriptor augmentation of Mol2Vec embeddings

This paper improves ADMET prediction by augmenting Mol2Vec embeddings with classical descriptors and feature selection, achieving top results on 10 of 16 TDC benchmarks.

Boosting performance of generative diffusion model for molecular docking by training on artificial binding pockets

This paper introduces a generative diffusion model for molecular docking trained on artificial binding pockets, showing improved performance over existing methods.