All tools

The Ranomics protein-design tool catalog.

Run feasibility scoring, generative binder design, structure prediction, and library planning on the same credit ledger. Every pipeline lands ranked candidates with downloadable PDBs and hands off cleanly into Ranomics' yeast display CRO when a design is worth validating.

Step 1 Score the target Use Epitope Scout to identify candidate epitopes and rate binder-design feasibility before burning GPU-hours.

Step 2 Generate binders Run BindCraft, RFdiffusion, BoltzGen, RFantibody, or PXDesign on a target PDB. Score, clone, tweak, re-run.

Step 3 Validate in silico Refold candidates with AlphaFold2, ColabFold, or ESMFold. Use ProteinMPNN to redesign sequences on a fixed backbone.

Step 4 Validate in the lab Hand the shortlist into a Ranomics yeast display campaign. Same team, same data loop — design and wet-lab share one pipeline.

Scope the target 2 tools

Epitope Scout Free

Score a target's surface for binder-design feasibility before committing GPU time.

Runtime ~30 s

Yeast Display Library Planner Free

Plan yeast display libraries with realistic diversity and screen-size estimates for your scaffold and Kd target.

Runtime <5 s

Design binders 6 tools

BindCraft 20 cr

Structure-based de novo binder design on JAX + AlphaFold2 multimer + ColabDesign. 4-hour max session; results are emailed on completion.

Runtime 45 min Pacesa et al., bioRxiv 2024

BoltzGen 3–10 cr

Boltz-2 binder design. Generates a binder backbone against a target, refolds each candidate, and scores affinity via ipTM and pLDDT.

Runtime 5 min – 15-60 min Wohlwend et al., MIT (2024)

ProteinMPNN Free or 1 cr

Upload a backbone PDB, get N candidate sequences with MPNN scores and per-sequence recovery. ~30 s per run.

Runtime 1 min Dauparas et al., Science 2022

PXDesign 8–15 cr

Binder design with JAX AF2 Initial Guess validation — real ipTM / pLDDT / pAE from the AF2 monomer model run in initial-guess mode against the target. Smoke ~17 min, mini_pilot ~30–40 min, pilot ~30–60 min.

Runtime ~17 min – 30–60 min Bennett, N. R., Coventry, B., Goreshnik, I., et al. "Improving de novo protein binder design with deep learning." Nature Communications 14, 2625 (2023). Ranomics in-house pipeline; scoring stage uses AF2 Initial Guess.

RFantibody 2–15 cr

Structure-based antibody binder design. Generates nanobody (VHH) or scFv candidates against a target epitope, then validates the fold with RoseTTAFold-2.

Runtime 3 min – 15-60 min Bennett et al., bioRxiv 2024

RFdiffusion -- de novo binder design 2–15 cr

Composite binder design: RFdiffusion backbones + ProteinMPNN sequences + AF2 multimer validation. Candidates carry real ipTM / pLDDT / i_pAE scores. Mini_pilot ~7 min warm; pilot ~15-30 min on caller targets.

Runtime ~2 min – 15-30 min Watson, J. L., Juergens, D., Bennett, N. R., et al. "De novo design of protein structure and function with RFdiffusion." Nature 620, 1089-1100 (2023). Composite pipeline: RFdiffusion backbones + ProteinMPNN sequences + AF2 multimer validation.

Predict structures 3 tools

AlphaFold2 Free or 2 cr

Paste a FASTA (monomer or multimer), get a predicted structure with pLDDT, PAE, and pTM/ipTM. ~5-10 min per run.

Runtime 2 min Jumper et al., Nature 2021 (AF2); Mirdita et al., Nature Methods 2022 (ColabFold)

ColabFold Free or 2 cr

Paste a FASTA, get a predicted structure with pLDDT and PAE. No-MSA speed tier — ~1-2 min per run.

Runtime 1-2 min Mirdita et al., Nature Methods 2022

ESMFold Free or 1 cr

Paste a FASTA, get a predicted structure with pLDDT. ESM-2 language-model fold, monomer-only — ~30 s per run.

Runtime 0.5-1 min Lin et al., Science 2023

Check developability 1 tool

Binder Developability Scout Free

Flag developability liabilities in antibody and nanobody sequences before you order them.

Runtime <5 s

Side-by-side comparison runtime · cost · paper

Tool	Best for	Typical runtime	Credit cost (smoke / pilot)	Paper / Repo
AlphaFold2 af2	Pick AF2 when you need the gold-standard structure prediction with calibrated pLDDT + PAE. For faster single-sequence folds use ESMFold (D4); for affinity-aware folds use Boltz-2 (D6).	smoke: 2 min pilot: —	smoke: Free pilot: —	Jumper et al., Nature 2021 (AF2); Mirdita et al., Nature Methods 2022 (ColabFold) Source repo
BindCraft bindcraft	Pick BindCraft when you have a target PDB plus known hotspot residues and want de novo 60-150 aa protein binders.	smoke: — pilot: 45 min	smoke: — pilot: 20 credits	Pacesa et al., bioRxiv 2024 Source repo
BoltzGen boltzgen	Pick BoltzGen when your target involves glycans, post-translational modifications, or non-canonical residues. For standard protein-only targets, BindCraft or RFantibody are faster and cheaper.	smoke: 5 min pilot: 15-60 min	smoke: 3 credits pilot: 10 credits	Wohlwend et al., MIT (2024) Source repo
ColabFold colabfold	Pick ColabFold when you need a fast no-MSA fold — 1-2 min per run, no MMseqs2 round-trip. Pair with AF2 standalone (D2) when you want full MSA + templates, or with ESMFold (D4) for single-sequence monomers on an even smaller GPU.	smoke: 1-2 min pilot: —	smoke: Free pilot: —	Mirdita et al., Nature Methods 2022 Source repo
ESMFold esmfold	Pick ESMFold when you need the fastest possible monomer fold - no MSA, no multimer, single-sequence ESM-2 language-model prediction. Pair with ColabFold (D3) for multimers or AF2 standalone (D2) for full MSA-backed accuracy.	smoke: 0.5-1 min pilot: —	smoke: Free pilot: —	Lin et al., Science 2023 Source repo
ProteinMPNN mpnn	Pick ProteinMPNN when you already have a backbone and need candidate sequences. For de novo backbone generation, use RFantibody, BindCraft, or BoltzGen first and feed the output PDB here.	smoke: 1 min pilot: —	smoke: Free pilot: —	Dauparas et al., Science 2022 Source repo
PXDesign pxdesign	Pick PXDesign when AF2 confidence against a defined target matters and you want real ipTM / pLDDT / pAE on every candidate. For hallucination-driven binder design without AF2 filtering use BindCraft, for antibody and nanobody CDRs use RFantibody, and for target structure generation without binder design use BoltzGen.	smoke: ~17 min pilot: 30–60 min	smoke: 8 credits pilot: 15 credits	Bennett, N. R., Coventry, B., Goreshnik, I., et al. "Improving de novo protein binder design with deep learning." Nature Communications 14, 2625 (2023). Ranomics in-house pipeline; scoring stage uses AF2 Initial Guess.
RFantibody rfantibody	Pick RFantibody when you need an antibody scaffold (VHH or scFv) against a target PDB. For de novo non-antibody binders, use BindCraft. For designs involving modified residues or glycans, use BoltzGen.	smoke: 3 min pilot: 15-60 min	smoke: 2 credits pilot: 15 credits	Bennett et al., bioRxiv 2024 Source repo
RFdiffusion -- de novo binder design rfdiffusion	Pick RFdiffusion when you want general de novo binder design scored by AF2 multimer (ipTM / pLDDT / i_pAE). For antibody and nanobody scaffolds use RFantibody, for AF2-IG initial-guess scoring use PXDesign, and for hallucination-driven binders without AF2 filtering use BindCraft.	smoke: ~2 min pilot: 15-30 min	smoke: 2 credits pilot: 15 credits	Watson, J. L., Juergens, D., Bennett, N. R., et al. "De novo design of protein structure and function with RFdiffusion." Nature 620, 1089-1100 (2023). Composite pipeline: RFdiffusion backbones + ProteinMPNN sequences + AF2 multimer validation. Source repo