Protein Structure · DeepMind (served as BioNeMo NIM)
The reference MSA-based predictor, with managed MSA search included.
30s–5min
Runs on Managed GPU endpoint
Runs on managed compute. Availability and startup time depend on current capacity.Run this model
About this model
AlphaFold2 remains the accuracy benchmark for monomeric folding when a deep multiple sequence alignment is available. Corollary routes to the managed NIM deployment so you never build an MSA pipeline yourself; expect minutes rather than seconds in exchange for the alignment-derived accuracy.
Reported performance
Standardized I/O contract
Every model in the Hub speaks the same contract, which is what lets the Router and the agent call any of them without special-casing.
Inputs
Protein sequence
Outputs
All-atom coordinates in PDB format, viewable and downloadable.
pLDDT score per residue (0–100). Above 70 is generally reliable.
