Isomorphic Labs Unlocks New Drug Design Frontier Beyond AlphaFold 3
The Isomorphic Labs Drug Design Engine unlocks a new frontier beyond AlphaFold
We are thrilled to introduce IsoDDE, our new unified computational drug-design system that surpasses AlphaFold 3 in predictive accuracy. This engine doubles performance on challenging protein-ligand benchmarks, predicts binding affinities faster than physics-based methods, and identifies novel binding pockets using only amino acid sequences. IsoDDE bridges the gap between structure prediction and real-world drug discovery, enabling the rational design of medicines with unprecedented precision.
IsoDDE can surpass the performance of physics-based methods such as FEP, despite the fact that these require grounding in experimental crystal structures and IsoDDE does not.
- bonsai_spool
This is from February 2026 and notably there’s no way for the public to try out the model, nor is it published in a peer-reviewed journal
- tusimi
"In November 2024, preliminary results of CASP16 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]
In April 2025 Isomorphic Labs raised $600 Million in its first ever external funding round, led by Thrive Capital.[16][17]"
- ashwon13
Would like more details technically on their approach. Is it a neuro-symbolic approach, do they do something beyond just scaling, or some other architecture breakthrough, but alas drug discovery must remain proprietary. Thank gods for capitalism!