AI for Bio · Model

ReaSyn v2

Synthesisability projection model that builds a synthesis route from purchasable building blocks

Small moleculesMixedUnited States, South KoreaMaintained only中文

Overview

NameReaSyn v2 · aliases: ReaSyn v2, NV-ReaSyn-AR-166M-v2, NV-ReaSyn-EB-174M-v2
Full nameA code name plus version, with no expanded form in the paper
Ambiguous names (not auto-linked)ReaSyn
FamilyThis record centres on the second version; the two papers carry different titles and v2 no longer describes the reinforcement-learning step of v1
  • ReaSyn v1 ·
  • ReaSyn v2 (AR-166M) · †
  • ReaSyn v2 (EB-174M) · †
OrganizationNVIDIA, KAIST
Organization typeMixed
CountryUnited States, South Korea
Model classMolecule generation (synthesis route prediction)
DomainSmall molecules (also: Molecule generation)
First release · paper revision
Basis: Preprint v1
Note: The v2 checkpoints went up in January 2026 source
Other milestones
  • First public evidence: · Preprint v1 source
  • Preprint v1: · Preprint v1 source
  • Code release: · README update on the default branch source
  • Weights release: † · Second-version checkpoint files committed source
  • Official announcement: † · Developer platform announcement (not reverified this round) source
Latest update · docs update
Basis: README edit on the default branch
The last substantive change on the default branch is a README update; decoding and index speed-ups exist only on three unmerged pull-request branches, and an October 2026 commit only updates citation details.
Note: The site previously described unmerged branch work as a delivered update source
The most recent sourced event, not a claim that nothing changed since.
StatusMaintained only · Only documentation and citation updates on the main branch; no new weights
OpennessCode: Open · Apache-2.0
Weights: Open · NVIDIA Open Model License
Code under Apache-2.0 with two second-version checkpoints in a public model hub under the developer's own open model licence
Benchmarks reported1 counted (modified protocol 1)
Wet-lab validationNone recorded
Unverified fields† release_milestones.weights_release, release_milestones.official_announcement, training_data.b_private_licensed
As of2026-11-16

What it does

Generates synthesis routes as reasoning chains with an encoder-decoder, finding, for an unsynthesisable molecule, a close analogue assembled from catalogue building blocks and reaction templates; the second version adds bottom-up and top-down tree search plus a discrete-flow model that edits a route by insertion, deletion and substitution. It sits on the same molecule-generation line as GenMol from the same organisation but targets synthesisability rather than general generation.

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
19 PMO (Practical Molecular Optimization)Developer report, modified protocol—Self-reportedUses 15 TDC oracle tasks rather than the full 23 †partly verified · evidence

Other evaluations (outside the 44)

  • Synthesis route reconstruction (Own task set) Self-reported: Route reconstruction on 1,000 molecules from each of three sources, against two synthesis-constrained methods
  • Hit expansion and surrogate optimisation (Own task set) Self-reported: Analogue expansion and optimisation scored by two computational surrogates, with route accessibility checked by a retrosynthesis tool
  • Absent from a third-party comparison (Public benchmark not among the 44) Third-party: A conference paper comparing several models in this area does not list it

Developers report: keeping optimisation on a par with unconstrained methods while enforcing synthesisability, and beating existing synthesis-constrained methods at route reconstruction and hit expansion.

Independent evidence: No independent evidence found. No third-party evaluation was found, and a comparison in the same area does not list it

Training data

Group in Figure 7: Public data only.

ClassValueDetail
a. Public databasesYes211,220 purchasable building blocks from one supplier catalogue and 115 reaction templates, following an existing published setup source
b. Private or licensed dataNot disclosed
c. Own wet-lab data used for trainingNoThe 10.5 million in-house training routes are all computationally generated source
d. Wet lab used only for validationNo

Wet-lab validation

None. The developers report no wet-lab validation.

Background

  • Organization: Produced by a US compute company's research team with a South Korean university, with the lead work done during an internship there; the company's life-science business runs through an open development platform and an open model family.
  • Funding: Internal corporate research with no separate funding.
  • Products and partnerships: Released alongside an RNA model and several chemistry tool libraries; in January 2026 the company and a US pharmaceutical company announced a joint AI lab with up to $1B over five years, with the split undisclosed.
  • Related models: GenMol, Saturn, REINVENT 4

Reading notes

  1. Matching an unconstrained optimiser means the constraint costs nothing, not that it beats other optimisers.
  2. Reconstruction depends heavily on where the molecules come from and looks far better on the set that shares a source with the training blocks.
  3. Synthesisable here means definable by templates and a catalogue, not demonstrably makeable; the paper contains no experimental synthesis.
  4. The latest substantive event is a documentation update, with the speed-up code still sitting on unmerged branches.

Caveats

  1. Its pairing here covers only part of that protocol's task set.
  2. Synthesisability is judged by computational tools with no experimental check.
  3. The training routes are entirely computationally generated.
  4. Model card and repository give checkpoint release dates one day apart.
  5. The platform announcement date was not reverified this round.

Sources

  1. Preprint v1 2025 (preprint)
  2. Preprint v2 full text (preprint)
  3. Code repository (repository)
  4. Second-version checkpoint model card (repository)

Corrections

1 correction
FieldWasNowBasisFound
latest_update2026-07-18 (speed-up commit on an unmerged branch)2026-01-11 (README update on the default branch); event kind changed to documentation updatesource2026-11-16

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