Optifold by ExAnte LabsExplore a folding study.
Structures, confidence, accuracy and compute, in one workspace.
Open an Optifold study bundle to begin. Files stay in this browser.
Your study, ready to explore.
Import the scored matrix and its structures, or start with a protein sequence.
Score a sequence ↗Study file format ↗—median compute saved
—regret rate
—
—proteins that folded
—proteins scored
—folds measured
Optifold's call, beside what actually happened
Source differences
—
—
pLDDT
pLDDT by residue
Very low <50
Low 50–69
Confident 70–90
Very high >90
Confidence along the sequence
Try another protein
Pipeline status
How it works
The experiment behind the results.
- PDBPick a protein whose real structure is already known, so the answer can be checked.
- MSASearch databases for related sequences, then restrict alignment depth.
- GPURun the selected AlphaFold2 settings and record runtime.
- ScoreCompare every structure to the real one, and find the cheapest that was still good.
The 12 settings
Two dials, every combination: MSA depth 32 / 128 / 256 crossed with 0 / 1 / 3 / 8 recycles. Everything else is held fixed — AlphaFold2 v2.3.2, model_3, seed 2026, no templates.
What counts as good
A recorded structure passes the study gate when all five checks pass.
| TM-score | ≥ 0.50 | overall shape match |
| CA-lDDT | ≥ 0.60 | local accuracy |
| CA-RMSD | ≤ 5.0 Å | average atom distance |
| Coverage | ≥ 0.95 | how much of the real structure was compared |
| Identity | ≥ 0.99 | guard: is this even the right protein |
The last two are not accuracy measures. They exist so a good-looking score cannot come from quietly comparing the wrong thing.
Why it matters
Better decisions before compute is committed.
Optifold explores whether sequence features can help prioritize folding experiments for labs with limited compute. Its research asks which sequences pass a defined structural gate, and which tested settings cost less.
Savings and regret
Saving compute is easy if you are allowed to be wrong sometimes. So the saving is always reported with its regret rate — how often the cheap recommendation fails when an expensive one would have worked. Both numbers or neither.
—