Tools · Computational Biology
ESMFold2
Predict protein, DNA, RNA, and ligand complex structures with evolutionary scale modeling
Hardware and price
Price per run
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.
| Hardware | Typical runtime | Basic | Starter | Pro | Enterprise |
|---|---|---|---|---|---|
| Nvidia T4 | 30 min | $1.03 | $0.74 | $0.59 | $0.45 |
| Nvidia L4 | 30 min | $1.40 | $1.01 | $0.79 | $0.59 |
| Nvidia A10Default | 30 min | $1.93 | $1.37 | $1.10 | $0.83 |
| Nvidia L40S | 30 min | $3.42 | $2.45 | $1.94 | $1.46 |
| Nvidia A100, 40 GB | 30 min | $3.67 | $2.63 | $2.11 | $1.58 |
| Nvidia A100, 80 GB | 30 min | $4.37 | $3.13 | $2.50 | $1.87 |
| Nvidia H100 | 30 min | $6.91 | $4.93 | $3.94 | $2.97 |
| Nvidia H200 | 30 min | $7.94 | $5.67 | $4.54 | $3.40 |
| Nvidia B200 | 30 min | $10.94 | $7.81 | $6.25 | $4.70 |
In workflows
Chain it with other steps.
Each input and output has a data kind, so the builder only connects steps that fit.
Inputs
- Protein sequences · optionalFASTA, RAW
Outputs
- ArchiveZIP
- Protein structureCIF
Ready-made workflows that use it
- Dock into a predicted structure without choosing a boxSequence → fold → DiffDockStructure prediction to docking
- Dock against a protein with no solved structureSequence → fold → dockStructure prediction to docking
- Dock into a cleaned predicted structure and see the contactsSequence → fold → prepare → dock → PLIPStructure prediction to docking
- Compare docking against a wild type and its point mutantsPoint mutants vs wild type → fold → dock → compareStructure prediction to docking
References
The method behind it.
- Zeming Lin, Halil Akin, Roshan Rao et al. (2023). Evolutionary-scale prediction of atomic-level protein structure with a language model. Science. doi:10.1126/science.ade2574 (opens in a new tab)
- Salvatore Candido, Thomas Hayes, Alexander Derry et al. (2026). Language Modeling Materializes a World Model of Protein Biology. openRxiv. doi:10.64898/2026.06.03.729735 (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": "esmfold2", "resource": "a10", "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": "esmfold2-1", "job_type": "esmfold2", "resource": "a10", "payload": { ... }}'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
- Evo 2
Genome modeling and design across all domains of life with the Evo 2 DNA language model