Skip to main content
All tools

Tools · Custom Modeling

Thermo Property Models

Correct Joback and Hansen estimates with your own measurements, and predict solubility and mixture properties across solvents and temperatures

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.

Physics-Hybrid Thermo Model Training

Physics-Hybrid Thermo Model Training: reservation per run, USD
HardwareTypical runtimeBasicStarterProEnterprise
CPUDefault20 min$0.17$0.096$0.06$0.036

Mixture Property Model Training

Mixture Property Model Training: reservation per run, USD
HardwareTypical runtimeBasicStarterProEnterprise
CPUDefault1 h$0.50$0.29$0.18$0.11
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

In workflows

Chain it with other steps.

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

Physics-Hybrid Thermo Model Training

Inputs

  • Table (list)CSV, TSV, JSON

Outputs

  • ArchiveZIP
  • TableCSV
  • Trained modelOPAQUE

Mixture Property Model Training

Inputs

  • Table (list)CSV, TSV, JSON

Outputs

  • ArchiveZIP
  • Trained modelOPAQUE

References

The method behind it.

  1. K.G. JOBACK, R.C. REID (1987). ESTIMATION OF PURE-COMPONENT PROPERTIES FROM GROUP-CONTRIBUTIONS. Chemical Engineering Communications. doi:10.1080/00986448708960487 (opens in a new tab)
  2. Emmanuel Stefanis, Costas Panayiotou (2008). Prediction of Hansen Solubility Parameters with a New Group-Contribution Method. International Journal of Thermophysics. doi:10.1007/s10765-008-0415-z (opens in a new tab)
  3. Raghunathan Ramakrishnan, Pavlo O. Dral, Matthias Rupp et al. (2015). Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach. Journal of Chemical Theory and Computation. doi:10.1021/acs.jctc.5b00099 (opens in a new tab)
  4. Esther Heid, Kevin P. Greenman, Yunsie Chung et al. (2023). Chemprop: A Machine Learning Package for Chemical Property Prediction. Journal of Chemical Information and Modeling. doi:10.1021/acs.jcim.3c01250 (opens in a new tab)
  5. Florence H. Vermeire, Yunsie Chung, William H. Green (2022). Predicting Solubility Limits of Organic Solutes for a Wide Range of Solvents and Temperatures. Journal of the American Chemical Society. doi:10.1021/jacs.2c01768 (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": "train-thermo-hybrid", "resource": "cpu", "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": "train-thermo-hybrid-1", "job_type": "train-thermo-hybrid", "resource": "cpu", "payload": { ... }}'
Payload fields and examples in the docs

Custom Modeling

Related tools

  • MPNN Models

    Fast structure-property inference that highlights key molecule substructures

  • QSAR Models

    Compare random forest, LightGBM, Gaussian process and other QSAR models on your data and keep the best

  • Reaction Models

    Predict reaction yield, selectivity and rates from atom-mapped reactions and their conditions

  • Python Script Sandbox

    Short RDKit, pandas, NumPy and SciPy analyses of your results, run in isolation with no network access

All tools