Request Early Access

Cofolding models like AlphaFold3, OpenFold3, Boltz-2, and Chai-1 can generate protein–ligand complexes that look convincing but often break basic chemical rules. In this post, we describe how post-processing steps such as restoring bond types, hydrogens, and realistic geometry can make these AI-predicted poses chemically interpretable and ready for downstream modeling.

deepmirror™ enabled Tes Pharma to screen 1 billion molecules in just a few hours, unlocking novel chemotypes against one of the toughest target classes in drug discovery.

Researchers from around the world collaborate with MMV and deepmirror to adapt machine-learning platform to accelerate drug discovery.

Partnership between Collaborative Drug Discovery and deepmirror announced.

Evaluating Boltz-2 on Real Drug Targets: Does it work?

Using Boltz-2 for fast co-folding and affinity prediction

New collaboration with the Sanders Tri-Institutional Therapeutics Discovery Institute

The Drug Design for Global Health platform aims to accelerate global health security by supporting scientists in LMICs

deepmirror, in collaboration with Google Cloud, enabled Curie.Bio to run advanced protein structure models to tackle challenging, undrugged targets.