bioRxiv · 10.64898/2026.02.17.706409
AlphaFast: High-throughput AlphaFold 3 via GPU-accelerated MSA construction
Abstract
AlphaFold 3 (AF3) enables accurate biomolecular modeling but is limited by slow, CPU-bound multiple sequence alignment (MSA) generation. We introduce AlphaFast, a drop-in framework that integrates GPU-accelerated MMseqs2 sequence search to remove this bottleneck. AlphaFast achieves a 68.5x speedup in MSA construction and a 22.8x reduction in end-to-end runtime on a single GPU, and delivers predictions in 8 seconds per input on four GPUs while maintaining indistinguishable structural accuracy. A serverless deployment enables structure prediction for as little as $0.035 per input. Code is available at https://github.com/RomeroLab/alphafast
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Perry, B. C., Kim, J., Romero, P. A.. 2026-02-18. AlphaFast: High-throughput AlphaFold 3 via GPU-accelerated MSA construction. https://doi.org/10.64898/2026.02.17.706409
Cite the original work for its findings. Save a collection to share your selection of sources.