Skip to main content
All tools

Tools · Computational Biology

RFAntibody

Antibody and TCR design with RFdiffusion, ProteinMPNN, and RF2 (stages or full pipeline)

Open in the appRun via API

Hardware and price

Price per run, by step

What a typical run reserves from your wallet: the catalog's expected runtime on each piece of hardware × your plan's per-second rate. Larger inputs reserve more, and you're charged only for the seconds the job actually runs.

RFAntibody Fine-tuning

RFAntibody Fine-tuning: reservation per run, USD
HardwareTypical runtimeBasicStarterProEnterprise
Nvidia T42.3 h$4.79$3.44$2.77$2.10
Nvidia L42.3 h$6.55$4.70$3.70$2.77
Nvidia A102.3 h$8.99$6.38$5.12$3.86
Nvidia L40S2.3 h$15.96$11.42$9.07$6.80
Nvidia A100, 40 GBDefault2.3 h$17.14$12.26$9.83$7.39
Nvidia A100, 80 GB2.3 h$20.41$14.62$11.68$8.74
Nvidia H1002.3 h$32.26$23.02$18.40$13.86
Nvidia H2002.3 h$37.04$26.46$21.17$15.88
Nvidia B2002.3 h$51.07$36.46$29.15$21.92

RFAntibody

RFAntibody: reservation per run, USD
HardwareTypical runtimeBasicStarterProEnterprise
Nvidia T42 h$4.10$2.95$2.38$1.80
Nvidia L42 h$5.62$4.03$3.17$2.38
Nvidia A102 h$7.70$5.47$4.39$3.31
Nvidia L40S2 h$13.68$9.79$7.78$5.83
Nvidia A100, 40 GBDefault2 h$14.69$10.51$8.42$6.34
Nvidia A100, 80 GB2 h$17.50$12.53$10.01$7.49
Nvidia H1002 h$27.65$19.73$15.77$11.88
Nvidia H2002 h$31.75$22.68$18.14$13.61
Nvidia B2002 h$43.78$31.25$24.98$18.79

RFAntibody ProteinMPNN

RFAntibody ProteinMPNN: reservation per run, USD
HardwareTypical runtimeBasicStarterProEnterprise
Nvidia T430 min$1.03$0.74$0.59$0.45
Nvidia L430 min$1.40$1.01$0.79$0.59
Nvidia A10Default30 min$1.93$1.37$1.10$0.83
Nvidia L40S30 min$3.42$2.45$1.94$1.46
Nvidia A100, 40 GB30 min$3.67$2.63$2.11$1.58
Nvidia A100, 80 GB30 min$4.37$3.13$2.50$1.87
Nvidia H10030 min$6.91$4.93$3.94$2.97
Nvidia H20030 min$7.94$5.67$4.54$3.40
Nvidia B20030 min$10.94$7.81$6.25$4.70

RFAntibody RFdiffusion

RFAntibody RFdiffusion: reservation per run, USD
HardwareTypical runtimeBasicStarterProEnterprise
Nvidia T41.5 h$3.08$2.21$1.78$1.35
Nvidia L41.5 h$4.21$3.02$2.38$1.78
Nvidia A101.5 h$5.78$4.10$3.29$2.48
Nvidia L40S1.5 h$10.26$7.34$5.83$4.37
Nvidia A100, 40 GBDefault1.5 h$11.02$7.88$6.32$4.75
Nvidia A100, 80 GB1.5 h$13.12$9.40$7.51$5.62
Nvidia H1001.5 h$20.74$14.80$11.83$8.91
Nvidia H2001.5 h$23.81$17.01$13.61$10.21
Nvidia B2001.5 h$32.83$23.44$18.74$14.09

RFAntibody TCR Predictor

RFAntibody TCR Predictor: reservation per run, USD
HardwareTypical runtimeBasicStarterProEnterprise
Nvidia T41 h$2.05$1.48$1.19$0.90
Nvidia L41 h$2.81$2.02$1.58$1.19
Nvidia A101 h$3.85$2.74$2.20$1.66
Nvidia L40S1 h$6.84$4.90$3.89$2.92
Nvidia A100, 40 GBDefault1 h$7.34$5.26$4.21$3.17
Nvidia A100, 80 GB1 h$8.75$6.26$5.00$3.74
Nvidia H1001 h$13.82$9.86$7.88$5.94
Nvidia H2001 h$15.88$11.34$9.07$6.80
Nvidia B2001 h$21.89$15.62$12.49$9.40

In workflows

Chain it with other steps.

Each input and output has a data kind, so the builder only connects steps that fit.

RFAntibody Fine-tuning

Inputs

None

Outputs

  • ArchiveZIP

RFAntibody

Inputs

  • Protein structurePDB

Outputs

  • ArchiveZIP
  • StructuresPDB

RFAntibody ProteinMPNN

Inputs

  • Protein structurePDB

Outputs

  • ArchiveZIP
  • StructuresPDB

RFAntibody RFdiffusion

Inputs

  • Protein structurePDB

Outputs

  • ArchiveZIP
  • StructuresPDB

RFAntibody TCR Predictor

Inputs

  • Protein structurePDB

Outputs

  • ArchiveZIP
  • StructuresPDB

References

The method behind it.

  1. Nathaniel R. Bennett, Joseph L. Watson, Robert J. Ragotte et al. (2024). Atomically accurate de novo design of antibodies with RFdiffusion. openRxiv. doi:10.1101/2024.03.14.585103 (opens in a new tab)
  2. Joseph L. Watson, David Juergens, Nathaniel R. Bennett et al. (2023). De novo design of protein structure and function with RFdiffusion. Nature. doi:10.1038/s41586-023-06415-8 (opens in a new tab)
  3. J. Dauparas, I. Anishchenko, N. Bennett et al. (2022). Robust deep learning–based protein sequence design using ProteinMPNN. Science. doi:10.1126/science.add2187 (opens in a new tab)

Run via API

Submit it from your own code.

Use an API key from your account. The estimate uses your plan's rates; submitting reserves that amount from your wallet.

# Estimate the reservation for your plan (payload fields: see the API reference)
curl -X POST https://api.cognichem.com/api/v1/jobs/estimate \
  -H "X-Api-Key: $COGNICHEM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"job_type": "rfantibody-finetune", "resource": "a100-40gb", "payload": {}}'

# Submit (retrying with the same Idempotency-Key never submits twice)
curl -X POST https://api.cognichem.com/api/v1/jobs/submit \
  -H "X-Api-Key: $COGNICHEM_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d '{"job_name": "rfantibody-finetune-1", "job_type": "rfantibody-finetune", "resource": "a100-40gb", "payload": { ... }}'
Payload fields and examples in the docs

Computational Biology

Related tools

  • Boltz-2

    Accurate in silico screening for early-stage drug discovery

  • BoltzGen

    Design proteins and peptides to bind biomolecular targets

  • DiffDock

    Protein-ligand docking with diffusion models and confidence-ranked poses

  • DrugFlow

    Generate candidate ligands from a protein target and reference ligand using flow matching

  • Sequence Mutator

    Apply point mutations such as T315I to a protein sequence, checking each wild-type residue

  • ESMFold2

    Predict protein, DNA, RNA, and ligand complex structures with evolutionary scale modeling

All tools