AI for Bio · Model

PoET-2

182M-parameter multimodal retrieval-augmented protein foundation model using family context

ProteinsPlatform companySingaporeActive中文

Overview

NamePoET-2 · aliases: PoET-2
Full nameThe paper uses the model name only, with no expanded form
Ambiguous names (not auto-linked)PoET
FamilyNot a family entry. The earlier PoET is a separate model; this record covers PoET-2 only
OrganizationOpenProtein.AI
Organization typePlatform company
CountrySingapore
Model classProtein language model (in-context learning)
DomainProteins (also: Structure & co-folding)
First release · preprint
Basis: Preprint v1 submission source
Other milestones
  • First public evidence: · Preprint v1 source
  • Preprint v1: · Preprint v1 source
  • Official announcement: † · The company publications page carries the work from the same period source
Latest update · paper revision
Basis: Preprint v2 revision
Paper revised to v2 (v1 was 2025-08-05); no new weights or product tier found source
The most recent sourced event, not a claim that nothing changed since.
StatusActive · Paper revised within 12 months and the platform is still sold
OpennessCode: Partly open
Weights: Unclear
The abstract says weights are public in a repository, but neither repository nor terms were verified this round; it is also sold as a commercial platform (unverified)
Benchmarks reported1 counted (self 1)
Wet-lab validationNone recorded
Unverified fields† open_status.code, open_status.weights, open_status.weights_license, open_status.code_license, background.funding, other_evaluations[0]
As of2026-11-16

What it does

Adds multimodal inputs such as structure on top of its predecessor and uses a set of homologous sequences as context to score or generate new sequences, pitched as a small model needing little data. It shares the retrieval-augmented route with Profluent-E1, which uses its predecessor as a comparison, and resembles VenusREM but is built around a platform product.

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
02 ProteinGymDeveloper report, official protocolzero-shot (substitutions, indels, higher-order, clinical) plus supervised settingsSelf-reportedPaper table claims the official protocol; not found on the official table · evidence

Other evaluations (outside the 44)

  • Vendor low-data claim (Comparison against baselines only) Self-reported: Marketing material claims about 30x less experimental data with no public protocol, a vendor figure (unverified)
  • Ensemble with another model (Own task set) Self-reported: The paper also reports an ensemble setting with a retrieval-augmented model, a developer-built control

Developers report: Developers report that multimodal retrieval augmentation and family in-context learning let a 182M model lead zero-shot tasks, especially indels and higher-order mutants, and claim about 30x less experimental data (a vendor figure, not an independent evaluation).

Independent evidence: No independent evidence found. Self-reported results are not confirmed on the official board or by third parties

Training data

Group in Figure 7: Public data only.

ClassValueDetail
a. Public databasesYes62 million homolog sets from a public sequence database, with public predicted structures for structure conditioning rather than experimental ones source
b. Private or licensed dataNoNo private or licensed training data reported
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: A platform company headquartered in a Singapore biomedical park and listed in a commercial database as founded in 2021. It offers a no-code protein design platform, free for universities and licensed to pharma, with no public headcount.
  • Funding: A commercial database lists two funds as investors with an early venture round logged in 2024-01 and no amount disclosed (second-hand); the company was also selected for a government research program on next-generation protein foundation models.
  • Products and partnerships: The earlier PoET was a 2023 conference paper and PoET-2 followed in 2025. A large pharma company has used the platform since 2025 and announced an expansion into antibody discovery on 2026-03-31, with terms undisclosed. Competitors include Profluent-E1.
  • Related models: Profluent-E1, VenusREM, ProSST

Reading notes

  1. The self-reported results are not separately confirmed on the official board and there is no public submission record.
  2. Scores on the same benchmark are not directly comparable between retrieval-augmented and sequence-only models.
  3. Reaching the top tier at 182M parameters shows parameters are not the only factor, but that is not a cross-family conclusion.
  4. The vendor's "30x less data" is marketing, not an independent evaluation.

Caveats

  1. Openness unverified: the abstract claims public weights, but neither repository nor licence terms were checked this round.
  2. No wet-lab validation; all evaluation is computational.
  3. A commercial platform and open weights are claimed side by side and must be cited separately.

Sources

  1. PoET-2 preprint (preprint)
  2. Preprint v1 full text with the self-reported table (preprint)
  3. Company publications page (official site)
  4. University news story on the platform (press)
  5. Commercial database funding entry (second-hand) (second-hand) second-hand
  6. Company announcement: selected for a government program (company blog)
  7. ProteinGym official repository (leaderboard)

Corrections

2 corrections
FieldWasNowBasisFound
latest_update.event_kindRecorded as a new versionChanged to a paper revision: 2026-02-26 is preprint v2 and the description itself says there are no new weightssource2026-11-16
latest_update.descriptionSaid only "v2 revision, no new weights or product tier" without tying the dates togetherAdds the v1 and v2 dates alongside the unchanged "no new weights" statementsource2026-11-16

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