Foundation model builders and drug discovery veterans
Our team combines pioneers in AI-driven drug discovery with proven leaders in therapeutic development and company building. From developing widely used models such as Chemprop, RFDiffusion 3, and ADMET-AI to advancing medicines from discovery to approval, our experience spans the full journey from scientific innovation to patient impact.
Landmark papers from the team
Publications
- 01 A cryptic pocket in CB1 drives peripheral and functional selectivity Nature · 2025
- 02 Structural basis of efficacy-driven ligand selectivity at GPCRs Nature Chemical Biology · 2023
- 03 Xanomeline displays concomitant orthosteric and allosteric binding modes at the M4 mAChR Nature Communications · 2023
- 04 Geometric deep learning for structure-based ligand design ACS Central Science · 2023
- 05 Structural basis for modulation of a G-protein-coupled receptor by allosteric drugs Nature · 2013
- 06 Pathway and mechanism of drug binding to G-protein-coupled receptors PNAS · 2011
- 07 Molecular dynamics simulation for all Neuron · 2018
- 08 De novo design of all-atom biomolecular interactions with RFdiffusion3 bioRxiv · 2025
- 09 Geometric deep learning of protein–DNA binding specificity (DeepPBS) Nature Methods · 2024
- 10 A deep learning approach to antibiotic discovery Cell · 2020
- 11 Analyzing learned molecular representations for property prediction (Chemprop) Journal of Chemical Information and Modeling · 2019
- 12 Generative AI for designing and validating easily synthesizable and structurally novel antibiotics (SyntheMol) Nature Machine Intelligence · 2024
- 13 ADMET-AI: a machine learning ADMET platform for evaluation of large-scale chemical libraries Bioinformatics · 2024
