The company draws upon DeepMind'sAlphaFold technology, which can be used to predict protein structures in the human body with high accuracy, allowing its researchers to find new target pathways fordrug delivery.[7][8]
In May 2024,Google DeepMind and Isomorphic Labs announced the release ofAlphaFold 3, an artificial intelligence and foundation model platform. Available for free on the AlphaFold server for non-commercial research, the platform was developed by training it with nearly 100,000 known proteins.[11] AlphaFold 3 can predict how proteins fold and the interactions with molecules typically found in drugs such asligands orantibodies, which is expected to significantly accelerate drug discovery.[12]
In November 2024, preliminary results ofCASP16 showed AlphaFold 3-based models did not significantly outperform older methods for predicting protein-ligand interactions. The top performing models in the CASP16 Pose Prediction for Pharma Targets section were ClusPro[13] and CoDock[14] utilizing AlphaFold 2 based predictions, human visual inspection, and manual adjustments.[15]
