Skip to main content

LLNL accelerates protein structure prediction on El Capitan

OpenFold3 image

A Lawrence Livermore National Laboratory-led team has harnessed the power of El Capitan to accelerate generation of predicted protein structures. Shown is a predicted structure by OpenFold 3 preview 2 (blue) versus the experimentally determined (gray) structure of a complex of multiple proteins — an antibody (Fab MSC1) binding to an antigen (Human Leukemia Inhibitory Factor).

Credit: Nikoli Dryden/RCSB Protein Data Bank

The ElMerFold project has generated more than 10,700 predicted protein structures per second on the El Capitan exascale supercomputer, reducing the time needed to produce a dataset of 41 million structures from eight days to two and a half hours.

Register for FREE to keep reading

Join 12,000+ scientists, engineers, and IT professionals driving innovation through informatics, HPC, and simulation with:

  • Insights into HPC, AI, lab informatics & data
  • Curated content for life sciences, engineering & academia
  • Access to Breakthroughs: real-world computing success
  • Free reports & panels, including the Lab Informatics Guide
  • White Papers & software updates for smarter research

Sign up now

Already a member? Log in here

Your data is protected under our privacy policy.

Scientific Computing World covers

Media Partners