Overview
| Name | GenMol · aliases: GenMol, NV-GenMol, NV-GenMol-89M-v2, GenMol NIM |
|---|---|
| Full name | The paper gives no expanded name |
| Ambiguous names (not auto-linked) | None |
| Family | Not a family entry. v1 and v2 are version axes within one record |
| Organization | NVIDIA |
| Organization type | Big-tech lab |
| Country | United States |
| Model class | Molecule generation (discrete diffusion) |
| Domain | Molecule generation (also: Small molecules) |
| First release | · paper revision Basis: arXiv preprint v1 submitted source |
| Other milestones | |
| Latest update | † partly verified · new version Basis: GenMol NIM 2.0.0 release notes NIM 2.0.0 moves to the NV-GenMol-89M-v2 checkpoint; GitHub has had only maintenance commits since Note: Release notes say 2026-04-24 and the NGC container listing 2026-05-07; v2 weights had appeared in the repository earlier source The most recent sourced event, not a claim that nothing changed since. |
| Status | Active · New version released within 12 months |
| Openness | Code: Open · Apache-2.0 Weights: Open · NVIDIA Open Model License Code Apache-2.0 and weights under the NVIDIA Open Model License; the NIM microservice uses the NVIDIA software licence |
| Benchmarks reported | 1 counted (self 1) |
| Wet-lab validation | None recorded |
| Unverified fields | † latest_update, release_milestones.weights_release |
| As of | 2026-11-17 |
What it does
Writes molecules as SAFE fragment sequences and generates them in parallel by masked discrete diffusion, with fragment remasking to explore chemical space; one pretrained model switches by prompting between de novo, fragment-constrained generation and lead optimisation. Unlike reinforcement-learning frameworks such as REINVENT 4 it needs no retraining per task; it belongs to the NVIDIA BioNeMo / Clara line.
Benchmarks reported
Every row is one pairing from the survey's relation file; a score belongs to the benchmark page's ranking, where it is shown with metric, eval set, source type and date. 1 of 1 pairings are counted.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 19 PMO (Practical Molecular Optimization) | Developer report, official protocol | — | Self-reported | PMO 23 tasks, original protocol · evidence |
Other evaluations (outside the 44)
- De novo and fragment-constrained generation (Own task set) Self-reported: Validity, uniqueness and quality metrics, author-reported; most models are near saturation on these
- Lead optimisation tasks (Own task set) Self-reported: Success on 30 lead-optimisation tasks, author-reported
Developers report: one discrete-diffusion model unifies several molecule-generation tasks, leads prior methods on PMO and ships open weights.
Independent evidence: No independent evidence found. No third-party rerun in a shared environment or wet-lab validation was found
Training data
Group in Figure 7: Public data only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | The SAFE dataset from ZINC and UniChem, about 946 million molecules source |
| b. Private or licensed data | No | source |
| c. Own wet-lab data used for training | No | source |
| d. Wet lab used only for validation | No |
Wet-lab validation
None. The developers report no wet-lab validation.
Background
- Organization: NVIDIA, founded in 1993 and based in Santa Clara, California, is a GPU and accelerated-computing company; Clara and BioNeMo are its open model and tool platforms for biology and drug discovery.
- Funding: A listed company whose drug-discovery work sits in its internal healthcare unit; its venture arm NVentures invests in drug-discovery companies such as Terray and Iambic.
- Products and partnerships: GenMol is offered as a NIM microservice on build.nvidia.com and NGC; KERMT, built with Merck, sits in the same BioNeMo line.
- Related models: REINVENT 4, Saturn, KERMT
Reading notes
- The PMO result is author-reported with baselines copied from other papers, so the margin should be discounted.
- v2 scores below v1 on PMO; cite the version.
- There is no wet lab, so synthesisability and activity of generated molecules are unknown.
- The strength is multitask unification and open weights rather than best-in-class on any one task.
Caveats
- Baselines were not rerun in the same environment.
- Two sources disagree on the latest version date (2026-04-24 vs 2026-05-07).
- No GuacaMol or MOSES results are reported.
Sources
- arXiv preprint (preprint)
- Code repository (repository)
- NIM 2.0.0 release notes (official site)
- NGC v1 resource page (package registry)
- NGC v2 resource page (package registry)
Corrections
2 corrections
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-17.