BoltzProt-1
boltzprot-1Protein, peptide, nanobody and antibody binder design.
BoltzProt-1 designs protein binders for a target sequence. The binder can be a mini-protein, a peptide, or a nanobody or antibody built on Boltz's curated scaffolds. A job returns each design's sequence, Boltz's scores and a predicted complex with the target.
ProteinIQ sends the job to the hosted Boltz API pipeline and publishes the finished sequences, structures and records. To score binder sequences you already have, use Boltz Protein Screen. To change chosen residues on an existing structure, use Boltz Sequence Redesign.
BoltzProt-1 is billed per design, and each design is priced by the size of the target plus binder complex in tokens. A token is about one residue, so the complex size is the total target length plus the binder length. A mini-protein or peptide counts as its maximum length, a nanobody as 130 and an antibody as 250.
| Complex size (tokens) | 10 designs | 20 designs | 100 designs | 500 designs |
|---|---|---|---|---|
| Up to 256 | 500 | 1,000 | 5,000 | 25,000 |
| 257 to 512 | 1,000 | 2,000 | 10,000 | 50,000 |
| 513 to 1,024 | 2,000 | 4,000 | 20,000 | 100,000 |
| 1,025 to 2,048 | 4,000 | 8,000 | 40,000 | 200,000 |
| More than 2,048 | 8,000 | 16,000 | 80,000 | 400,000 |
For example, a 150-residue target with the default 100-residue maximum binder length is 250 tokens, so the default 10 designs cost 500 credits. The same target with a nanobody binder is 280 tokens and costs 1,000 credits. The total is rounded once for the whole job. Epitope selection and the sequence filters do 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.
| 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. |
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.
Residue modifications set on a target chain, given as 1-based positions and CCD codes such as SEP for phosphoserine, are sent to Boltz and appear in the predicted complexes. They are part of the target, not a design objective: the designs are not steered toward the modified atoms, even when the modified residue is selected as an epitope residue.
| Parameter | Type | Default | Description |
|---|---|---|---|
Binder type (binder_type) | enum | custom_protein | custom_protein (mini-protein), peptide, nanobody or antibody. Nanobody and antibody designs use Boltz's curated scaffolds. |
Minimum binder length (binder_min_length) | integer | 60 | Shortest designed binder in residues, from 4 to 400. Shown for mini-protein and peptide binders. |
Maximum binder length (binder_max_length) | integer | 100 | Longest designed binder in residues, from 4 to 400, and never below the minimum. Shown for mini-protein and peptide binders. |
Designs (num_designs) | integer | 10 | Designs to return, from 10 to 500. Each one is billed. |
| Parameter | Type | Default | Description |
|---|---|---|---|
Epitope residues (epitope_residues) | string | optional | Target residues the binder is encouraged to 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 is encouraged to avoid, in the same format. A position cannot appear in both lists. |
Both selections are guidance for the design model, not guarantees. Some designs can bind elsewhere on the target, so check the contacts in each predicted complex. A single residue is a small target, especially on a short peptide or for a modified residue. Selecting a few neighboring residues as well, for example A:4-8 around position 6, gives the designs a wider region to contact, and a larger number of designs gives more chances to see the contact you want.
| Parameter | Type | Default | Description |
|---|---|---|---|
Excluded amino acids (excluded_amino_acids) | string | C | Amino acids never placed in designed positions, as single-letter codes separated by commas. |
Maximum hydrophobic fraction (max_hydrophobic_fraction) | number | 1 | Largest fraction of hydrophobic residues in a design, from 0 to 1. 1 turns the filter off. |
Excluded sequence motifs (excluded_motifs) | string | optional | Motifs designs must not contain, one per line or comma-separated. |
Viewer shows the predicted complexes. Results lists the designs. Files holds the downloads.
| Download | Contents |
|---|---|
boltzprot_0001_<name>.cif onwards | Predicted complex for each design, numbered by rank. |
boltzprot_sequences.fasta | Designed binder sequences, with the chain IDs in each header. |
boltzprot_results.csv | The results table. |
boltzprot_results.json | Boltz's run and per-result records. |
boltzprot_0001_<name>_archive.tar.gz onwards | Boltz's result archive for each design. |
The FASTA sequences and the predicted complexes can be passed to other tools in workflows, for example to score the designs with Boltz Protein Screen.
Each row carries a rank, the design ID, the designed sequence and chains, 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 design. Nested metrics are flattened into columns joined by underscores. The table and the FASTA file hold the designed binder only, not the target chains.
Scores order designs within one run. They are model confidence values, not measured binding, so designs still need experimental validation.
Design antibody sequences from structure with AI-powered inverse folding
Design protein, peptide, and nanobody binders against protein or small-molecule targets.
Design minibinders and antibody scFvs against a protein target.
Humanize antibodies with optimal V-gene matching.
Design VHH nanobody binders using structure-guided modeling.
Design antibody CDRs with Proteo-R1 reasoning, diffusion, and optional framework inpainting.
Design de novo binders, TCR binders and CDR or VHH redesigns with ESMFold2.
Design antibody and nanobody binders with an end-to-end RosettaCommons pipeline
Design antibody CDR loops from antibody-antigen complex structures using inverse folding.
Protein design by backpropagation through AlphaFold