Genesis introduced Pearl, a generative 3D foundation model for protein-ligand structure prediction.
Pearl is trained with physics-based synthetic data to address scarce experimental structures, uses an SO(3)-equivariant diffusion architecture and lets scientists steer predictions. The page reports a 15% improvement over AlphaFold 3 on Runs N' Poses and up to 40% on PoseBusters. It feeds the GEMS platform and uses NVIDIA cuEquivariance kernels.
Genesis Therapeutics (Genesis Molecular AI) is an AI small-molecule discovery company whose GEMS platform and Pearl model support partnerships with Gilead and Incyte.
This sits in the Build stage of the AI use-case lifecycle: Named examples from the foundation-model labs and platforms pharma teams use to actually construct, train and generate the model or application.
Published by Genesis Therapeutics (Genesis Molecular AI) on its own site — read the original case study on genesis.ml ↗
Related use cases
- 01Gilead and Genesis deployed the GEMS platform to find small molecules against targets that lack training data.
- 02Incyte and Genesis expanded their collaboration to at least five new targets, with Incyte data used to train GEMS.
- 03Genesis reported that its Pearl system beat six cofolding models on an OpenBind protease benchmark.
- 04OpenAI's dedicated healthcare vertical page/launch post.
- 05Frontier reasoning model built for biology, drug discovery and translational medicine; named qualified customers include Amgen, Moderna, Allen Institute, and Thermo Fisher Scientific.
- 06follow-up update to the life-sciences model.