How Recursion and MIT Built Boltz-2 to Cut Drug Discovery Wet Lab Work 40% with NVIDIA
Recursion and MIT’s Jameel Clinic partnered to develop Boltz-2, an open-source biomolecular foundation model trained on NVIDIA’s BioHive-2 supercomputer that simultaneously predicts protein complex structures and binding affinities. The model ranked first on CASP16 affinity data, delivers results in ~20 GPU-seconds per ligand-protein pair, and achieves up to 3x inference speedup via NVIDIA NIM — enabling drug discovery teams to get 80% of experimental value with 40% less wet lab work.
Impact
40%
Wet lab work reduction for equivalent value
2x–3x
Inference speedup with NVIDIA NIM
up to 5x
Triangle operation acceleration with cuEquivariance
~20 GPU-seconds
Processing time per ligand-protein pair
1st
CASP16 affinity benchmark ranking
Challenge
Protein-ligand structure prediction and binding affinity estimation required separate computational pipelines, with physics-based affinity methods taking weeks per large compound library — creating a fundamental throughput bottleneck that forced drug discovery teams to rely heavily on expensive wet lab experiments for candidate filtering.
Solution
Recursion and MIT’s Jameel Clinic trained Boltz-2 on NVIDIA’s BioHive-2 supercomputer, creating an open-source foundation model that unifies co-folding and binding affinity prediction with cuEquivariance-accelerated geometry operations and NVIDIA NIM deployment, processing ligand-protein pairs in ~20 GPU-seconds with up to 3x inference speedup.
Tools & Technologies
What Leaders Say
“With AI in the loop today, we can get 80% of the value with 40% of the wet lab work.”
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.
Full Story
Recursion is a US-based biotechnology company applying computational and AI methods to drug discovery, operating at the intersection of machine learning and experimental biology. MIT’s Jameel Clinic and Computer Science and AI Laboratory (CSAIL) are research partners focused on applying AI to medicine. Their collaboration targeted one of the central bottlenecks in structure-guided drug discovery: the fact that predicting protein-ligand binding structures and estimating binding affinities has historically required separate computational pipelines, each consuming significant GPU time and wet lab validation resources.
Physics-based methods for binding affinity estimation traditionally took weeks to process large compound libraries. The computational cost of running these predictions at the scale required for modern drug screening programs created a fundamental throughput constraint: teams could only evaluate a fraction of candidate compounds in the time available, forcing heavy reliance on expensive, time-consuming wet lab experiments to validate predictions that should have been pre-filtered computationally.
Working on NVIDIA’s BioHive-2 supercomputer — a 63-node DGX H100 system — MIT and Recursion trained Boltz-2, an open-source foundation model that unified protein complex co-folding and binding affinity prediction into a single architecture. NVIDIA cuEquivariance kernels accelerated the custom equivariant operations required for accurate molecular geometry modeling, delivering up to 5x speedup on triangle operations versus standard implementations. NVIDIA NIM packaging enables production deployment of Boltz-2 as an enterprise microservice with 2x–3x inference speedup, and the model is available as Boltz-2 NIM for teams deploying at scale.
The results validated the approach across multiple benchmarks. Boltz-2 ranked first on CASP16 affinity prediction data. It achieves 0.62–0.66 Pearson correlation on affinity predictions and processes individual ligand-protein pairs in approximately 20 GPU-seconds on an A100. At the application level, the operational transformation is significant: as Recursion CTO Ben Mabey described it, “With AI in the loop today, we can get 80% of the value with 40% of the wet lab work.” That ratio — maintained prediction quality while substantially reducing experimental burden — is the metric that matters for drug discovery pipelines operating under time and cost pressure.
Boltz-2 is open-source and available for broad adoption across the drug discovery community. Its combination of structure prediction and affinity estimation in a single model, trained on a purpose-built supercomputing cluster and packaged for enterprise deployment via NVIDIA NIM, establishes a new baseline for what computational drug discovery infrastructure can deliver before wet lab experiments begin.
Amazon SageMaker