AI for Bio · Model

MiniMol

Ten-million-parameter molecular foundation model densely pretrained on thousands of supervised tasks

Small moleculesAI-native biotechUnited StatesMaintained onlySite entity page (Chinese site)中文

Overview

NameMiniMol · aliases: MiniMol, minimol
Full nameThe paper uses the model name only; no expanded name
Ambiguous names (not auto-linked)None
FamilyNot a family entry. A single model; the group's earlier MolE has its own record
OrganizationValence Labs (Recursion Pharmaceuticals)
Organization typeAI-native biotech
CountryUnited States
Model classProperty prediction (molecular foundation model, graph model)
DomainSmall molecules
First release · paper revision
Basis: arXiv 2404.14986 v1 submission date (also accepted at a machine-learning conference workshop) source
Other milestones
  • First public evidence: · Preprint v1 source
  • Preprint v1: · Preprint v1 (no later version) source
  • Code release: · Package registry 1.3.5 (1.3.4 on 2024-08-05) source
Latest update · code release
Basis: Public package release 1.3.5 on the registry
Public package releases 1.3.4 (2024-08-05) and 1.3.5 (2024-08-22); the matching repository exists with no releases or tags and a last commit of 2025-05-29 for storage-path maintenance. This is the latest sourced event
Note: Corrects the site's "no update since release" wording: these package versions post-date the first release source
The most recent sourced event, not a claim that nothing changed since.
StatusMaintained only · Maintenance commits only, the last on 2025-05-29
OpennessCode: Open
Weights: Unclear
The authors call it open source and a public package is installable; this round the official repository and weights were not found under the expected organisation path (the old path is dead), so licence and weight status are unverified
Benchmarks reported1 counted (board 1)
Wet-lab validationNone recorded
Unverified fields† open_status.code, open_status.weights, open_status.code_license, open_status.weights_license, training_data.b_private_licensed
As of2026-11-16

What it does

Takes the small-model, many-supervised-tasks route: about ten million parameters pretrained on millions of molecules, hundreds of millions of labels and roughly three thousand sparsely defined graph- and node-level tasks spanning quantum chemistry and biology, then applied to downstream property prediction. Against the group's earlier MolE it uses a smaller molecule set with denser labels, and against Uni-Mol2 it is more than two orders of magnitude smaller, emphasising parameter efficiency.

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.

BenchmarkRelationEval set / protocolSource typeNote and evidence
04 TDC (ADMET + DTI)Official leaderboard or results—BoardSelf paper plus official board entries · evidence

Other evaluations (outside the 44)

  • Parameter-efficiency comparison (Comparison against baselines only) Self-reported: Uses a far smaller parameter count than peer foundation models as its selling point and comparison; a self-reported framing, not an independent evaluation

Developers report: dense multitask supervised pretraining lets a ten-million-parameter model significantly beat the previous best molecular foundation model on most ADMET tasks.

Independent evidence: The public per-task ADMET board carries its entries so they can be read alongside other submissions, though the organisers did not re-run the model independently.

Training data

Group in Figure 7: Public data only.

ClassValueDetail
a. Public databasesYesAbout 6 million molecules, 500 million labels and 3,300 graph- and node-level tasks; the abstract lists no database names source
b. Private or licensed dataNot disclosed
c. Own wet-lab data used for trainingNo
d. Wet lab used only for validationNo

Wet-lab validation

None. The developers report no wet-lab validation.

Background

  • Organization: The developer is the AI research arm of a listed AI-pharma company, announced in 2023 at a machine-learning conference and formed by merging the parent's machine-learning team with an acquired molecular-design company; the parent was founded 2013-11-05 and is based in Salt Lake City, Utah.
  • Funding: Not disclosed
  • Products and partnerships: The research arm co-developed the co-folding and affinity model Boltz-2 with a US university team; its earlier in-house model is MolE.
  • Related models: MolE, Boltz-2, Uni-Mol2, KERMT

Reading notes

  1. "Better on 17 tasks" is a comparison with the previous best foundation model, not with all methods: on the official per-task board several fingerprint and gradient-boosting models rank higher.
  2. It is a workshop paper with no journal version and only a v1 preprint.
  3. The benchmark's datasets are small with high variance, so rank gaps are close to noise.
  4. The official repository and weights were not located this round, so openness is treated as unverified.

Caveats

  1. Open-source and weight status unverified (the expected repository path is dead).
  2. The abstract does not name the foundation model it is compared against.
  3. Workshop paper only, no journal version.
  4. The site's "no update since release" wording is corrected to the public package releases.

Sources

  1. Preprint arXiv 2404.14986 (preprint)
  2. Conference workshop entry (official site)
  3. Package registry page (package registry)
  4. Code repository (no releases or tags) (repository)
  5. Public ADMET per-task board (sample task) (leaderboard)

Corrections

2 corrections
FieldWasNowBasisFound
latest_update2024-04-23, no update since release2024-08-22, public package 1.3.5 (overturns "no later event")source2026-11-16
latest_update.event_kindnone-since-releasecode-releasesource2026-11-16

Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.