Overview
| Name | Pearl · aliases: Pearl, Pearl-2026.1.dev, Pearl system, DeCAF-Pearl |
|---|---|
| Full name | No expanded name; official materials use Pearl |
| Ambiguous names (not auto-linked) | Pearl |
| Family | Not a family entry. Single model line; Pearl system and DeCAF-Pearl are its inference system and distilled variant |
| Organization | Genesis Molecular AI |
| Organization type | AI-native biotech |
| Country | United States |
| Model class | Co-folding (protein-ligand, SO(3)-equivariant diffusion) |
| Domain | Structure & co-folding (also: Small molecules) |
| First release | · preprint Basis: arXiv v1, with the Genesis release post the same day source |
| Other milestones | |
| Latest update | · product update Basis: Genesis blog post: DeCAF-Pearl distillation Announced DeCAF-Pearl (flow-map distillation on the Pearl-2026.1.dev checkpoint), after the 06-03 Pearl system with inference-time scaling and pose ranking Note: Blog page dates taken from search results; the model remains proprietary, with no weights or API found source The most recent sourced event, not a claim that nothing changed since. |
| Status | Active · Official product updates within 12 months; the model itself is closed |
| Openness | Code: Closed Weights: Closed Neither the paper nor the release page offers weights or inference code; no API found |
| Benchmarks reported | 2 counted (self 1, modified protocol 1) |
| Wet-lab validation | 1 recorded campaign |
| Unverified fields | None |
| As of | 2026-11-16 |
What it does
Predicts protein-ligand complex structures, with pocket conditioning and templates at inference. The paper says performance scales with synthetic data, and concedes out-of-distribution accuracy drops and confidence-based pose selection is unreliable. Unlike Boltz-2 it targets pose accuracy, not affinity; unlike AlphaFold 3 it relies on synthetic data.
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. 2 of 2 pairings are counted.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 30 PLINDER / PINDER / Runs N' Poses | Developer report, official protocol | Runs N' Poses, best@5 with PB-valid filter | Self-reported | Runs N' Poses best@5; baselines rerun by the Pearl authors †partly verified · evidence |
| 05 PoseBusters | Developer report, modified protocol | PoseBusters V2, best@5 with PB-valid filter | Self-reported | Mixes its own best@5 with another model's top-confidence result; one model excluded for its cutoff †partly verified · evidence |
Other evaluations (outside the 44)
- InternalXtals internal crystal set (Own task set) Self-reported: 111 internal crystal structures, unconditioned and pocket-conditioned; private and not reproducible
- OpenBind zero-shot evaluation (Pearl system) (Public benchmark not among the 44) Self-reported: Company blog says Pearl system beats all co-folding models zero-shot; company account only
Developers report: it beats AlphaFold 3 and open models on PoseBusters and Runs N' Poses (best@5 with PB-valid), with performance scaling with synthetic data.
Independent evidence: No independent evidence found. No third-party replication; weights unreleased
Training data
Group in Figure 7: Public data + wet lab for validation only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | PDB (to 2021-09-30) plus OpenFold / AFDB monomer distillation, and physics-generated synthetic structures source |
| b. Private or licensed data | No | The paper says no proprietary experimental data was used source |
| c. Own wet-lab data used for training | No | Synthetic structures are physics-generated (582,065 in the scaling experiment), not wet lab; flagship set size undisclosed source |
| d. Wet lab used only for validation | Yes | 111 existing internal crystal structures used for evaluation only, not new wet lab source |
Wet-lab validation
Every rate carries its numerator and denominator. Claims that could not be verified are shown as unverified, without numbers; different paper versions are separate entries.
Denominator basis: 111 internal crystal structures used for evaluation only; training strictly on public data
Developer-reported; the set is private and cannot be reproduced externally, not an independent replication; the synthetic set is not wet lab
Background
- Organization: Genesis Molecular AI (formerly Genesis Therapeutics), founded in 2019, is based in Burlingame, California, with its own lab in San Diego and an office in New York; an AI-native small-molecule drug discovery company, it renamed itself and released Pearl on 2025-10-28.
- Funding: $52M Series A (2020-12); $200M Series B (2023-08, a16z co-led, NVentures among participants); further NVentures equity investment in 2024-11. A cumulative figure above $280M is second-hand only.
- Products and partnerships: Pearl is the structure engine of the GEMS platform; NVIDIA engineering work speeds training and inference (company figures); pharma partners include Gilead and Incyte, whose 2026-05-20 expansion brings $120M upfront and proprietary experimental data to train Genesis's next models.
- Related models: AlphaFold 3, Boltz-2, Boltz-1 / Boltz-1x, Chai-1, Protenix
Reading notes
- Both headline results are author-reported under best@5 with PB-valid; with single predictions or without PB-valid, both numbers and ranking change.
- The comparison takes AlphaFold 3 at its official max-confidence protocol, below other papers' re-runs, which inflates the margin.
- The synthetic-data route is notable, but the paper admits out-of-distribution decline, matching the Runs N' Poses pattern of lower similarity, worse results.
- Gains on the internal crystal set cannot be reproduced externally and are company claims only.
Caveats
- Other models' results in the paper were re-run or cited by the Pearl team; this page does not reproduce them.
- Neither weights nor inference code are public, so third parties cannot check the results.
- Pearl is a common word; searches and auto-linking can hit unrelated projects of the same name.
Sources
- Pearl paper (arXiv 2510.24670) (preprint)
- Pearl paper v2 full text (preprint)
- Genesis: Introducing Pearl (company blog)
- Pearl technical report PDF (official site)
- Genesis: DeCAF-Pearl model distillation (company blog)
- Genesis: Pearl system zero-shot on OpenBind (company blog)
- Genesis Molecular AI Pearl launch press release (2025-10-28) (press)
- Genesis Series B announcement (press)
- TechCrunch: Genesis Series A (press)
- Genesis NVIDIA investment and collaboration announcement (press)
- Incyte and Genesis collaboration expansion press release (press)
Corrections
None recorded.
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.