AI for Bio · Model

La-Proteina

All-atom protein generation with flow matching in a partially latent space, co-designable up to 800 residues

ProteinsBig-tech labUnited StatesActive中文

Overview

NameLa-Proteina · aliases: La-Proteina
Full nameNo separate expanded name
Ambiguous names (not auto-linked)Proteina
FamilyNot a family entry. Single-model entry, not a family
OrganizationNVIDIA
Organization typeBig-tech lab
CountryUnited States
Model classAll-atom protein generation
DomainProteins (also: Molecule generation)
First release · preprint
Basis: arXiv 2507.09466 v1 source
Other milestones
  • Preprint v1: · arXiv v1 source
  • Code release: · Code added on GitHub source
Latest update · new version
Basis: arXiv v2 posted
arXiv v2 posted; the last code push is a small fix on 2025-09-23 source
The most recent sourced event, not a claim that nothing changed since.
StatusActive · New paper version within 12 months
OpennessCode: Open · Apache-2.0
Weights: Open · NVIDIA Open Model License
Code Apache-2.0; weights under the NVIDIA Open Model License
Benchmarks reported1 counted (board 1)
Wet-lab validationNone recorded
Unverified fieldsNone
As of2026-11-16

What it does

Generates all-atom proteins with flow matching in a partially latent space: an explicit backbone plus per-residue latents carrying sequence and side-chain detail; co-designable proteins reach 800 residues.

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
40 MotifBenchOfficial leaderboard or results—BoardThe board lists this model (29.75, 2026-07); the Chinese model page says there is no score, which is wrong. · evidence

Other evaluations (outside the 44)

None recorded.

Developers report: Source states no developer claim

Independent evidence: No independent evidence found. No independent evidence found

Training data

Group in Figure 7: Public data only.

ClassValueDetail
a. Public databasesYesTwo public structure-database subsets (~344.5k and ~46.94M structures); PDB not used
b. Private or licensed dataNo
c. Own wet-lab data used for trainingNo
d. Wet lab used only for validationNoNo wet lab in the paper; a downstream model did validation

Wet-lab validation

None. The developers report no wet-lab validation.

Background

Reading notes

  1. Its only pairing is an official board entry; the site model page previously said none, a published error
  2. The paper has no wet lab; wet-lab evidence comes from a downstream model

Caveats

  1. Training uses predicted-structure subsets only, not the experimental structure database
  2. Its metrics are computational self-consistency, not wet-lab feasibility

Sources

  1. Official page export.arxiv.org (company blog)
  2. GitHub repository NVIDIA-BioNeMo/la-proteina (repository)
  3. arXiv preprint 2507.09466 (preprint)

Corrections

1 correction
FieldWasNowBasisFound
benchmarks_reportedThe Chinese model page said no MotifBench entry was foundThe official board lists it; relation is official participationsource2026-11-16

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