Protein Hunter

Overview

Exploratory binder-design campaigns.
Iterating sequence/design/prediction loops around a target and desired interface.
Producing candidate sets for manual review and follow-up assays.

Modes

Mode	Input shape	When to use it
`protein_target_binder` Protein Target Binder Default	No uploaded input is required by the mode itself.	Design protein binders against one or more target protein sequences.
`nucleic_acid_binder` Nucleic Acid Binder	No uploaded input is required by the mode itself.	Design protein binders against a DNA or RNA target sequence.
`small_molecule_binder` Small-Molecule Binder	No uploaded input is required by the mode itself.	Design protein binders against a CCD or SMILES small molecule.
`target_free_design` Target-Free Design	No uploaded input is required by the mode itself.	Generate target-free protein designs.

Canonical Job Configuration

These are the fields exposed by the default job configuration for protein-hunter. They are also returned by GET /api/v1/program/params?program=protein-hunter and submitted as the params JSON object to POST /api/v1/job/submit.

Parameter	Type	Modes	What it does
`target_protein_sequences` Target Protein Sequence	Sequence	Protein Target Binder	Paste the target protein sequence. For multiple target chains, use FASTA records or separate bare sequences with colons. Required
`nucleic_type` Nucleic Acid Type	Text	Nucleic Acid Binder	Default: DNA; Options: DNA, RNA
`nucleic_sequence` Nucleic Acid Sequence	Sequence	Nucleic Acid Binder	ACGTACGTACGT Required
`ligand_type` Ligand Type	Text	Small-Molecule Binder	Describe the small molecule by Chemical Component Dictionary code or SMILES. Default: CCD Code; Options: CCD Code, SMILES
`ligand_ccd` CCD Code	Text	Small-Molecule Binder	SAM Required; Shown when ligand_type is CCD Code
`ligand_smiles` SMILES	Ligand text	Small-Molecule Binder	CC(=O)NCCNC(C)=O Required; Shown when ligand_type is SMILES
`protein_binder_length` Binder Length	Length or range	Protein Target Binder, Nucleic Acid Binder	90-140 Default: 90-140; Range: 1-2000
`small_molecule_binder_length` Binder Length	Length or range	Small-Molecule Binder	120-160 Default: 120-160; Range: 1-2000
`target_free_length` Protein Length	Length or range	Target-Free Design	100-150 Default: 100-150; Range: 1-2000
`num_designs` Generated Designs	Integer	All modes	Default: 3; Range: 1-1000
`num_cycles` Design Cycles	Integer	All modes	Default: 5; Range: 1-50
`percent_x` Masked Residues %	Integer	All modes	Percent of designed residues initially treated as unknown X during the iterative search. Default: 80; Range: 0-100
`high_iptm_threshold` High iPTM Threshold	Number	All modes	Designs above this iPTM threshold are copied into high-confidence output folders. Default: 0.7; Range: 0-1
`cyclic` Cyclic Design	Yes/no	All modes	Request cyclic designed proteins. Default: false
`contact_residues` Contact Residues	Residue selection	Protein Target Binder, Nucleic Acid Binder	Optional target residues for contact filtering.

Advanced configuration fields

Parameter	Type	Modes	What it does
`template_structure` Template Structure	Structure file	All modes	Optional PDB or mmCIF template selected from an upload, dataset, or previous job output. Files: .pdb, .cif, .mmcif
`template_chain_id` Template Chain ID	Text	All modes	Optional template chain ID passed to Protein Hunter when a template structure is selected.
`design_name` Output Prefix	Text	All modes	subseq_protein_hunter
`omit_amino_acids` Omit Amino Acids	Text	All modes	One-letter amino-acid codes to avoid in designed sequences.
`exclude_proline` Exclude Proline	Yes/no	All modes	Default: false
`no_contact_filter` Disable Contact Filter	Yes/no	All modes	Default: false
`contact_cutoff` Contact Cutoff	Number	All modes	Range: 0.1-100
`max_contact_filter_retries` Contact Filter Retries	Integer	All modes	Range: 0-50
`temperature` Sampling Temperature	Number	All modes	Range: 0.001-5
`diffuse_steps` Diffuse Steps	Integer	All modes	Range: 1-500
`recycling_steps` Recycling Steps	Integer	All modes	Range: 1-24
`high_plddt_threshold` High pLDDT Threshold	Number	All modes	Range: 0-1

Outputs And Metrics

Candidate structures, sequences, score tables, and design metadata depending on mode.
Ranked result bundles intended for downstream inspection and filtering.
Use confidence, interface, and ranking metrics as prioritization signals, not validation.

Common Examples

Target-focused campaign with a PDB target, chain selection, hotspot residues, and a modest final candidate count.
Rerun promising candidates with stricter final selection after manual inspection.

Example API params

{
  "mode": "binder_design",
  "target_structure": "target.pdb",
  "target_chains": "A",
  "hotspots": "A45,A52,A76"
}

Caveats

This is an experimental high-level design workflow; inspect every candidate before acting on it.
Residue numbering, target preparation, and biological context strongly affect outcomes.

Advanced Submit

Advanced submit is still available for direct program arguments through POST /api/v1/job/submit-advanced. Prefer canonical configuration unless you need exact low-level arguments or are reproducing a known command line.

Advanced submit is for direct workflow configuration and reproducing previous command-line campaigns.
Canonical configuration is preferred for routine target and candidate-count settings.

curl -X POST https://subseq.bio/api/v1/job/submit \
  -H "Authorization: Bearer <api_key>" \
  -F program=protein-hunter \
  -F 'params={"mode":"binder_design","target_structure":"target.pdb","target_chains":"A","hotspots":"A45,A52,A76"}'