AlphaFold2
Paste a sequence — one chain or several — and get a predicted 3D structure back with per-residue and per-residue-pair confidence scores. About 5 to 10 min per run.
What it is for
You have a sequence and want the most trusted 3D prediction of it, with per-residue confidence you can act on. It searches for related natural sequences first, which is where the accuracy comes from and where the time goes. For a faster answer use ColabFold or ESMFold; to score a binder against its target use Boltz-2.
Predicts the 3D structure of a protein from its sequence — one chain, or several chains folded together as a complex. It searches public databases for related natural sequences first, which is where most of its accuracy comes from and most of its runtime goes, then returns a structure with per-residue confidence (pLDDT) and an estimate of the error between any two residues (PAE). Both are calibrated, meaning the numbers mean what they say. AlphaFold2, Jumper et al., Nature 2021, packaged via ColabFold (Mirdita et al., Nature Methods 2022).
When it fits:
- You have a sequence and want the most trusted structure prediction available, with confidence numbers you can act on.
- Your target is a single chain, or a small complex of two to four chains.
- You can wait 5 to 10 minutes per run for the homolog search and three refinement passes.
Inputs
You will need:
- Single-letter FASTA sequence(s). Multimers separated by
:or pasted as multi-record FASTA. - A stable target topology. AF2 underperforms on intrinsically disordered or flexible regions.
Each run uses a preset that sets the scale and scope:
- Standalone with your FASTA
- Paste or upload FASTA (single chain or multimer). ColabFold MMseqs2 MSA plus AF2. Up to 1500 AA total across chains. ~5 to 10 min on A100-80GB.
- Batch for many fold targets
- Fold many independent targets in one job (up to 50 records). Each record can be a monomer or a multimer (use ``:`` to separate chains inside a record). Per-design results stream into the job page as folds complete. Slowest of the structure-prediction tools. Expect ~5 to 10 min per fold.
Parameters you set on the form:
- Sequence
- Paste FASTA. Use
:as a chain separator for multimers (e.g.SEQ_A:SEQ_B). - Recycles
- Number of model recycles. 3 is the AF2 default; lower is faster but trades a small amount of accuracy.
Typical runtime:
- standalone
- 5 to 10 min
How to read the results
Predicted PDB with per-residue pLDDT, pairwise PAE, and pTM or ipTM (for multimers). Download PDB or PAE matrix for downstream filtering and analysis.
Where a tool reports them, the scores mean:
- ipTM
- Predicted confidence in the contact between two chains, on a 0 to 1 scale. Higher is better: > 0.75 strong; > 0.65 acceptable. Individual tools set their own pass bar a little either side of that — this guide's own results summary above states this tool's. On a multi-chain target the number may cover the target's own chain–chain interface as well as the binder's, so read the per-tool note on the results table before comparing designs on it.
- pLDDT
- Per-residue confidence in the predicted fold. Higher means the model is more sure of that part of the structure.
- i_pAE and pAE
- Predicted alignment error, at the interface (i_pAE) or across the whole structure (pAE). Lower is better.
References
Jumper et al., Nature 2021 (AF2); Mirdita et al., Nature Methods 2022 (ColabFold)