AlphaFast: High-throughput AlphaFold 3 via GPU-accelerated MSA construction

Avatar
Poster
Voice is AI-generated
Connected to paperThis paper is a preprint and has not been certified by peer review

AlphaFast: High-throughput AlphaFold 3 via GPU-accelerated MSA construction

Authors

Perry, B. C.; Kim, J.; Romero, P. A.

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 .

Follow Us on

0 comments

Add comment