Boltz Protein Screen

Boltz Protein Screen webserver overview

Boltz Protein Screen scores candidate binder sequences against a protein target and ranks them, returning a predicted complex for each candidate. A job takes up to 500 binders.

ProteinIQ sends the job to the hosted Boltz API pipeline and publishes the finished table, structures and records. To generate binders instead of supplying them, use BoltzProt-1.

Pricing

Each binder is priced by the size of the target plus that binder in tokens. A token is about one residue, so the complex size is the total target length plus the candidate's length. Candidates of different lengths can fall in different bands, and the job total is the sum, rounded once.

Complex size (tokens)	1 binder	10 binders	100 binders	500 binders
Up to 256	51	507	5,064	25,317
257 to 512	102	1,013	10,127	50,633
513 to 1,024	203	2,026	20,254	101,266
1,025 to 2,048	406	4,051	40,507	202,532
More than 2,048	811	8,102	81,013	405,064

For example, a 200-residue target screened against three 60-residue binders is 260 tokens per pair, so the job costs 304 credits. Epitope selection does not change the price.

The exact quote is calculated before submission. If Boltz estimates a noticeably higher cost when the job starts, the run is not started and the credits are refunded.

Inputs

Input	Accepted formats	Limits and behavior
Target protein	FASTA text, .fasta, .fa or .txt file, or a UniProt sequence	Required. Up to 10 chains, files up to 10 MB, one sequence each. Chain IDs are assigned A, B, C in submission order.
Binder sequences	Multi-FASTA text, or a .fasta, .fa or .txt file	Required. One file per job, up to 500 records and 50 MB. One record per candidate, in single-letter amino acid codes.

Each binder is placed on its own chain and scored against the target separately. Repeated FASTA names get a numeric suffix such as _2 so each row stays traceable. Each target input accepts 1 to 10 copies, and each copy becomes its own chain. Job name is an optional label for the saved run.

Settings

Parameter	Type	Default	Description
Epitope residues (epitope_residues)	string	optional	Target residues the binder should contact, as 1-based positions, for example A:10,12-15; B:3. Without a chain prefix the first target chain is used.
Non-binding residues (non_binding_residues)	string	optional	Target residues the binder should avoid, in the same format.

Outputs

Viewer shows the predicted complexes. Results lists the ranked binders. Files holds the downloads.

Download	Contents
boltz_protein_screen_0001_<name>.cif onwards	Predicted complex for each binder, numbered by rank.
boltz_protein_screen_results.csv	The results table.
boltz_protein_screen_results.json	Boltz's run and per-result records.

The predicted complexes can be passed to other structure tools in workflows.

Understanding results

Each row carries a rank, the binder ID, the binder sequence and its chain, Boltz's own metric columns, any warnings Boltz attached and the matching structure file. Ranks follow the order Boltz returns, so rank 1 is its top-scoring candidate. Nested metrics are flattened into columns joined by underscores. The sequence column holds the binder only; the target chains are kept in the structure files.

Scores order candidates within one run. They are model confidence values, not measured binding affinities.