Overview
| Name | MoleculeNet (+OGB) · aliases: MoleculeNet, MolNet, molnet, ogbg-molhiv, ogbg-molpcba |
|---|---|
| Full name | MoleculeNet: a benchmark suite for molecular machine learning (with OGB-derived molecular sets) |
| Ambiguous names (not auto-linked) | OGB |
| Family | Not a family entry. Single dataset suite; OGB molecular sets are derived splits recorded as a version trap, not a family. |
| Domain | Small molecules |
| Inclusion | Original 30 |
| Type | B · Static dataset suite with no official leaderboard |
| Evidence level | L2–L3 · Random split L2; scaffold split (weak OOD) L3 |
| Publisher | Stanford University (academic group), DeepChem open-source project (Academic lab) |
| First release | · paper v1 Basis: arXiv 1703.00564 v1 source |
| Other milestones | |
| Latest update | · paper revision Basis: Last-updated date of v3 in the arXiv API arXiv v3 posted (final paper revision); Chem. Sci. version published 2018; no versioned data snapshot since. Note: DeepChem loaders are still maintained; library upkeep, not a benchmark change source The most recent sourced event, not a claim that nothing changed since. |
| Next expected | The datasets are frozen and no new version has been announced. |
| Status | ○ Frozen · Effectively frozen since 2018; still widely reused for literature alignment |
| Scale | 17 datasets in the paper, from FreeSolv (642) to PCBA (437,929 compounds); QM9 has 133,885 molecules.
|
| Wet-lab refresh | Static data · No new experiments; public databases are reused and QM9 is a computed DFT oracle. |
| Own wet lab needed to evaluate a new model | No, run it as a download |
| Models reported | 2 counted (self 1, modified protocol 1, unconfirmed 1) |
| Unverified fields | † release_milestones.journal_online, ranking.entries[1], ranking.entries[2], models_reported[2] |
| As of | 2026-11-16 |
What it measures
- Task: Small-molecule property prediction across 17 public datasets covering quantum, physical chemistry, biophysics and toxicity endpoints.
- Truth: DFT values for QM sets; others from literature compilations, PubChem screens and Tox21 cell assays.
- Primary metric: ROC-AUC (classification); RMSE/MAE (regression)
- Secondary metrics: PRC-AUC (PCBA, MUV)
- Version traps: Same-name splits differ by implementation; OGB sets use fixed scaffold splits, not comparable; Tox21 here differs from the original challenge.
Current ranking
Not comparable
| Metric | ROC-AUC (classification), MAE/RMSE (regression) |
|---|---|
| Eval set | MoleculeNet 17 datasets; splits (scaffold/random) and seeds differ per paper |
| Snapshot | |
| Board | No official board |
| Retrieved | 2026-11-16 |
Caveat. No official leaderboard; data frozen since 2018 and each paper re-splits, so cross-paper numbers are no ranking; OGB-derived sets are not comparable.
No headline entry: Not comparable: no official board and each paper re-splits, so no headline number.
The entries below use different protocols, so they are listed, not ranked, and the overview table shows no score.
| Rank | Model | Score (verbatim) | Metric · eval set / protocol | Source type · date | Source and note |
|---|---|---|---|---|---|
| — | MoLFormer-XL | Withheld: not-comparable: protocols/subsets differ, so no score is displayed in the ranking row; the per-protocol values live on the entity page. | ROC-AUC (classification), MAE/RMSE (regression) MoleculeNet 17 datasets; splits (scaffold/random) and seeds differ per paper | Self-reported | source Self-reported (Table 1, scaffold splits): authors claim first on 3 of 6 sets and close second on the rest; no board, self-reported positions only. |
| — | Uni-Mol2 | Withheld: not-comparable: protocols/subsets differ, so no score is displayed in the ranking row; the per-protocol values live on the entity page. | ROC-AUC (classification), MAE/RMSE (regression) MoleculeNet 17 datasets; splits (scaffold/random) and seeds differ per paper | Self-reported | source second-hand Reports only 8 QM9 properties with a scaffold rather than the recommended random split; per-property values not re-verified this round. |
| — | Chemprop v2 | Withheld: Incomplete provenance (missing url); the honesty rule forbids displaying a number. | ROC-AUC (classification), MAE/RMSE (regression) MoleculeNet 17 datasets; splits (scaffold/random) and seeds differ per paper | Third-party No sourced date† | no source link No v2-specific MoleculeNet numbers exist; circulating numbers belong to the 2019 D-MPNN original; pairing unverified. |
Models reported
Grouped by relation type; each line shows its source type. Counted relations add up to 2. A pairing whose evidence rests only on this survey's own page is shown as unverified.
Developer report, official protocol (1)
- MoLFormer-XL Self-reported · MoleculeNet scaffold/random splits · evidence: link
Developer report, modified protocol (1)
Unconfirmed (1, not counted)
- Chemprop v2 Unconfirmed source · Page marks it unconfirmed; numbers belong to the 2019 original †disputed · evidence: link
Caveats
- Known data errors are not corrected, and simple fingerprint baselines often match pretrained models; split implementations differ, so numbers are often not comparable.
- Third-party analyses report unparsable SMILES and duplicates in BBBP, stereoisomer activity gaps in BACE, and an ESOL range far beyond industrial assays.
- A 2025 preprint reports that MoleculeNet's Tox21 training and test sets differ from the original challenge.
- A 2025 preprint found that of 25 pretrained molecular embedding models, all but one fail to beat an ECFP baseline.
- No blind or prospective test; no study links its scores to prospective hit rates.
How to use it
Run statically via DeepChem loaders or OGB fixed splits; no wet lab, retrospective evidence only. Use fixed scaffold or cluster splits, report an ECFP plus tree-model baseline, at least 10 seeds with SD, cleaned BBBP/BACE, and deduplicate pretraining data. Pair with TDC, Polaris and FS-Mol.
Pairs well with: TDC (ADMET + DTI) · Polaris / ASAP / OpenADMET · FS-Mol · CASF-2016
Sources
- MoleculeNet paper (arXiv 1703.00564) (preprint)
- MoleculeNet journal version (Chem. Sci. 2018) (journal)
- DeepChem molnet loader source (repository)
- Cheminformatics blog: benchmark data-quality analysis (2023-08) (second-hand) second-hand
- Pretrained molecular embeddings vs ECFP baseline (arXiv 2508.06199) (third-party paper)
- Tox21 reproduction study (arXiv 2511.14744) (third-party paper)
- OGB graph property prediction docs (official site)
- MoLFormer-XL paper (arXiv 2106.09553) (preprint)
- Uni-Mol2 paper (arXiv 2406.14969) (preprint)
Corrections
1 correction
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| ranking.entries[2] (Chemprop v2) | MoleculeNet × Chemprop v2 listed as a pairing with numbers | withheld: incomplete provenance (missing url); numbers belong to the 2019 D-MPNN original | source | 2026-11-16 |
Part of the AI for Bio benchmarks survey · all 44 benchmarks · open in the explorer. Record as of 2026-11-16.