Olivier Mailhot

Large scale prospective evaluation of co-folding across hundreds of Mac1-ligand complexes and three virtual screens

On 489 evaluable new Mac1 complexes, AlphaFold3, Chai-1 and Boltz-2 placed over half of ligands within 2 Å, but on docking hit-lists AF3 and Boltz-2 added little over docking.

Toward a Random Background for Ligand Optimization

This study systematically evaluates the effectiveness of random small perturbations in ligand optimization, finding 11.2% of analogs improved potency by ≥10-fold but often had worse pharmacokinetics.

A database for large-scale docking and experimental results

The paper develops a database of docking results and experimental data to improve benchmarking and chemical space exploration.

NRGRank: Coarse-grained structurally-informed ultra-massive virtual screening

NRGRank is a fast, accurate virtual screening tool that outperforms docking methods on some targets and complements them on others, enabling efficient large-scale screening.

The impact of Library Size and Scale of Testing on Virtual Screening

This paper tests the impact of library size and testing scale on virtual screening by comparing results from 1.7 billion vs. 99 million molecule libraries against AmpC β-lactamase, finding improved hit rates and potency with larger libraries.

The Elastic Network Contact Model applied to RNA: enhanced accuracy for conformational space prediction

The paper adapts the Elastic Network Contact Model (ENCoM) for RNA dynamics, showing improved accuracy in predicting conformational changes and structural variance compared to existing methods.