Overview
| Name | PMO (Practical Molecular Optimization) · aliases: PMO, Practical Molecular Optimization, mol_opt, PMO-1K |
|---|---|
| Full name | Practical Molecular Optimization |
| Ambiguous names (not auto-linked) | PMO-Dock |
| Family | Not a family entry. Single benchmark; PMO-1K and PMO-Dock are derivative extensions, not family members. |
| Domain | Small molecules (also: Molecule generation) |
| Inclusion | Original 30 |
| Type | D · Computational-oracle benchmark with a fixed call budget |
| Evidence level | L2 · Computational oracles only, no wet-lab evidence |
| Publisher | Georgia Institute of Technology, Massachusetts Institute of Technology (Academic lab) |
| First release | · paper v1 Basis: arXiv 2206.12411 v1 (v2 2022-10-09) source |
| Other milestones | |
| Latest update | † partly verified · new version Basis: PMO-Dock preprint arXiv 2610.19011 v2, a docking-oracle extension PMO-Dock (ICLR 2026), a docking-oracle extension, arXiv 2610.19011 v2; the mol_opt repository's last commit is 2024-05-23. Note: Task count inconsistent: the ICLR page says 23, a secondary index says 25. source The most recent sourced event, not a claim that nothing changed since. |
| Next expected | No next version or round announced by the organizers. |
| Status | ◐ Low-frequency · Paper final; repository lightly maintained; no official online leaderboard |
| Scale | 23 oracles, a 10,000-call budget, 5 seeds, 25 algorithms compared in the paper.
|
| Wet-lab refresh | Static data · No wet lab; all ground truth comes from computational oracle functions. |
| Own wet lab needed to evaluate a new model | No, run it as a download |
| Models reported | 2 counted (self 1, modified protocol 1, cited only 1) |
| Unverified fields | † latest_update, ranking.entries[4], ranking.snapshot_date, release_milestones.journal_online |
| As of | 2026-11-16 |
What it measures
- Task: Given black-box scalar oracles and a fixed call budget, measure how efficiently an optimizer finds high-scoring molecules.
- Truth: Computational oracle scores: QED, DRD2, GSK3B, JNK3 and 19 objectives taken from GuacaMol, served through TDC.
- Primary metric: AUC top-10, summed over 23 tasks (max 23)
- Secondary metrics: Per-task AUC top-10; Final top-10 mean score
- Version traps: State the budget (10,000 / 1,000 / 100 calls), seed count, whether surrogate training counts as calls, and whether the original suite or PMO-Dock was used.
Current ranking
Self-reported
| Metric | AUC top-10, summed over 23 oracles (max 23), 10,000-call budget |
|---|---|
| Eval set | PMO 23 oracles (QED, DRD2, GSK3B, JNK3 plus 19 GuacaMol-derived), oracle functions via TDC |
| Snapshot | † partly verified |
| Board | No official board |
| Retrieved | 2026-11-16 |
Caveat. No official board; each paper's own table serves as the ranking, with inconsistent budgets (10k/1k/100 calls), no significance tests, and 1-7% gaps at seed-noise level.
Shown in the overview table: Self-reported
| Rank | Model | Score (verbatim) | Metric · eval set / protocol | Source type · date | Source and note |
|---|---|---|---|---|---|
| 1 | GenMol | Sum 18.362 (Table 3, 'Goal-directed hit generation results', 23 PMO tasks, AUC top-10) | AUC top-10, summed over 23 oracles (max 23), 10,000-call budget PMO 23 oracles (QED, DRD2, GSK3B, JNK3 plus 19 GuacaMol-derived), oracle functions via TDC | Self-reported | source Re-verified from the primary table (23 tasks, mean of 3 runs). Same table: f-RAG 16.928, Genetic GFN 16.213, REINVENT 14.196. The repository README lists a V2 score of 17.943 (site note, not re-verified). Self-reported. |
| 2 | f-RAG | Sum 16.928 | AUC top-10, summed over 23 oracles (max 23), 10,000-call budget PMO 23 oracles (QED, DRD2, GSK3B, JNK3 plus 19 GuacaMol-derived), oracle functions via TDC | Third-party | source Not a site model; re-verified as a baseline row. |
| 3 | Genetic GFN | Sum 16.213 | AUC top-10, summed over 23 oracles (max 23), 10,000-call budget PMO 23 oracles (QED, DRD2, GSK3B, JNK3 plus 19 GuacaMol-derived), oracle functions via TDC | Third-party | source Not a site model; 16.213 is self-reported in its own paper and re-tabulated here. |
| 5 | REINVENT (prior generation; the site page covers REINVENT 4) | Sum 14.196 (top of the original PMO paper's 25-method comparison; Graph GA 13.751, SELFIES-REINVENT 13.471, GP BO 13.156, lowest MolDQN 5.620) | AUC top-10, summed over 23 oracles (max 23), 10,000-call budget PMO 23 oracles (QED, DRD2, GSK3B, JNK3 plus 19 GuacaMol-derived), oracle functions via TDC | Third-party | source The 14.196 value is re-verified in GenMol's Table 3; the other totals from the PMO paper come from the site note and are not re-verified. REINVENT 4 itself reports no PMO score, so the pairing points at the prior-generation REINVENT. |
| — | ReaSyn v2 | Withheld: Incomplete provenance (no url, no date), so the honesty rule forbids showing a number. | AUC top-10, summed over 23 oracles (max 23), 10,000-call budget PMO 23 oracles (QED, DRD2, GSK3B, JNK3 plus 19 GuacaMol-derived), oracle functions via TDC | Self-reported No sourced date† | no source link No 23-task total was located this round, so the score is null. |
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)
Developer report, modified protocol (1)
- ReaSyn v2 Self-reported · Uses 15 TDC oracle tasks rather than the full 23 †partly verified · evidence: link
Cited as comparison only (1, not counted)
- REINVENT 4 Third-party · The PMO paper used the prior-generation REINVENT as a baseline; REINVENT 4 itself reports no PMO score. †partly verified · evidence: link
Caveats
- All oracles are cheap computational functions and most come from GuacaMol, so the two are not independent evidence; no docking, no assays.
- Self-reported gains of 1-7% sit at the noise level of 5 seeds, and most papers run no significance test.
- Summing 23 tasks is an arbitrary weighting; task difficulty varies and a single task can dominate the total.
- Budgets are mixed (10,000 / 1,000 / 100 calls), so numbers across papers are often not comparable.
- No evidence links PMO scores to measured hit rates; rediscovery tasks can be solved from pretraining memory.
How to use it
Clone mol_opt, build per-method environments, pull oracles through TDC and run 5 seeds for AUC top-10; no wet lab needed. Report the budget, the seed count and whether surrogate training counts as calls, and re-run baselines instead of copying other papers' tables; claims about real value need synthetic-accessibility, QED and diversity filters plus a docking or free-energy oracle.
Pairs well with: GuacaMol (+MOSES) · CACHE · TDC (ADMET + DTI) · CrossDocked2020
Sources
- PMO paper, arXiv 2206.12411 (preprint) ·
- mol_opt repository (repository)
- GenMol paper with the 23-task PMO table (preprint) ·
- PMO-Dock preprint (preprint) · †
- PMO-Dock page at ICLR 2026 (official site)
- Third-party analysis of docking-oracle exploitation (third-party paper)
Corrections
3 corrections
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| latest_update | 2026 | 2026-11-09 (PMO-Dock preprint arXiv 2610.19011 v2; v1 2026-10-13) | source | 2026-11-16 |
| ranking.entries | ReaSyn v2 shown with a PMO score | score withheld: no url and no date for the figure | source | 2026-11-16 |
| models_reported | REINVENT 4 counted as reporting PMO | cited-as-comparison-only: only the prior-generation REINVENT appears, as a baseline in the PMO paper | 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.