nvMolKit

2D structural fingerprint similarity between a reference molecule and candidate molecules

API/CLI tool ID: nvmolkit

Input settings

SettingFormatRequiredDefaultDescription and constraints
inputJsonfileRequired—One reference SMILES and up to 1,000 candidate ID and SMILES pairs. 256 KiB in total at most — Extensions json

Output metrics

ColumnDisplay nameRangeDescription
candidate_idCandidate ID——
tanimotoTanimoto similarity0~1Similarity of fixed Morgan fingerprints. Higher means more similar fingerprints; it is not affinity, potency or binding probability. Stereochemistry is not distinguished

See Reading results for metric definitions and interpretation. A range shows possible values; whether higher or lower is better depends on the metric.

Execution availability

Open an execution plan in your project to see available tool versions and costs. Review and approve the inputs, settings, and terms before running.

License

Code, model weights, and accompanying data have their own terms. The table summarizes terms from official sources; check your execution plan for the configuration you will use. License texts are available in Third-party notices.

ComponentLicenseCommercial useSourceNotes
CodeApache-2.0Allowed, subject to notice requirementsLicense textApache-2.0 text of the main project confirmed. Scope is fingerprint similarity, which uses no model weights

On 2026-11-13 the 33 installed distributions in the pinned execution image (sha256:6723d6f3…) were read. There is no AGPL, non-commercial or research-only restriction. RDKit 2026.3.6 is BSD-3-Clause, the bundled libgomp carries the GCC runtime exception, and the NVIDIA CUDA and cuDNN wheels are under NVIDIA proprietary terms and only run inside the service. Delivering the image or its components to customers (on-premises, export or download) requires meeting their redistribution terms first

Checked on 2026-11-13.

References

On this page