Overview
| Name | DPLM-2 · aliases: DPLM-2 |
|---|---|
| Full name | The paper uses the model name only, with no expanded form |
| Ambiguous names (not auto-linked) | DPLM, DPLM-2.1 |
| Family | Not a family entry. The sequence-only predecessor and DPLM-2.1 are separate items; this record covers DPLM-2 only |
| Organization | ByteDance Research, Nanjing University |
| Organization type | Mixed · A joint project of an internet company's research arm and a university computer-science department, with no separate corporate entity |
| Country | China |
| Model class | Design (joint sequence-structure diffusion) |
| Domain | Proteins (also: Molecule generation, Structure & co-folding) |
| First release | · preprint Basis: Preprint v1 submission source |
| Other milestones | |
| Latest update | † partly verified · maintenance only Basis: The final commit before the repository was archived The final commit tweaked a sampling default, after which the repository became read-only (the archive date itself is unsourced); the successor DPLM-2.1 paper is listed separately and is not an update to this model Note: No source found for the archive date (unverified) source The most recent sourced event, not a claim that nothing changed since. |
| Status | Archived · Repository archived read-only; development moved to the successor |
| Openness | Code: Open · Apache-2.0 (per a mirror site, unverified) Weights: Open Code and weights are public and the repository is archived read-only; the licence label comes from a mirror site (unverified) |
| Benchmarks reported | 1 counted (retrospective 1) |
| Wet-lab validation | None recorded |
| Unverified fields | † latest_update, open_status.code_license, release_milestones.code_release, release_milestones.official_announcement, benchmarks_reported[0] |
| As of | 2026-11-16 |
What it does
Turns 3D coordinates into discrete structure tokens with lookup-free quantization and runs discrete diffusion over the joint sequence-structure distribution, generating matched sequence and structure in one pass while supporting folding, inverse folding and motif scaffolding; it is warm-started from the sequence-only predecessor. ESM3 is the comparable joint sequence-structure model on this site.
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.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 15 CAMEO | Retrospective dataset use | frozen 2022 target set, folding and inverse folding | Third-party | Uses a frozen 2022 target set; no live submission, no service ranking. · evidence |
Other evaluations (outside the 44)
- Structure prediction (folding) (Public benchmark not among the 44) Self-reported: Sequence-to-structure on a frozen target set and a date-split structure database, against several folding and multimodal models
- Inverse folding (Public benchmark not among the 44) Self-reported: Amino-acid recovery and self-consistency on the same frozen target set and date split
- Unconditional co-generation (Comparison against baselines only) Self-reported: One hundred samples at each of five lengths, comparing designability and diversity against several generative models
- Motif scaffolding (Public benchmark not among the 44) Self-reported: Twenty-four motif problems taken from prior work with 100 scaffolds each, against several generative models
- Representation-learning tasks (Public benchmark not among the 44) Self-reported: Localization, thermostability, protein interaction and metal-ion binding against the predecessor and others, not winning on all of them
Developers report: Developers report that one multimodal sequence-structure diffusion model handles folding, inverse folding and motif scaffolding competitively, with diverse and structurally plausible co-generated samples, and that structure-aware representations also help predictive tasks.
Independent evidence: No independent evidence found. No third-party evaluation or independent replication found
Training data
Group in Figure 7: Public data only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | Public sequence and experimental-structure databases, an annotated protein database and synthetic structures source |
| b. Private or licensed data | No | No private or licensed data reported |
| c. Own wet-lab data used for training | No | |
| d. Wet lab used only for validation | No |
Wet-lab validation
None. The developers report no wet-lab validation.
Background
- Organization: A big-tech lab and university joint project with no separate corporate entity. The research arm used one name on the 2024 paper and a different in-group research brand on the 2025 successor paper (same team); the partner is a university computer-science department.
- Funding: Funded from the company's internal R&D budget; no external grants itemised
- Products and partnerships: The predecessor is the sequence-only discrete-diffusion protein language model; the successor DPLM-2.1 (preprint v1 2025-04, v3 2025-06) explores the multimodal design space and is recorded separately from this model's repository events.
- Related models: ESM3, La-Proteina, RFdiffusion2 / RFdiffusion3
Reading notes
- Its only site pairing is retrospective dataset use on a frozen target set: not participation, and with no service-assigned ranking.
- All evaluation is computational, with no wet-lab validation.
- The value is methodological: it shows discrete diffusion can unify sequence and structure generation.
- Synthetic structures enter training, so generation quality is capped by the model that produced them.
Caveats
- The repository is archived read-only, so expect no further fixes; the successor has its own entry.
- The archive date is unsourced (unverified), so the latest update is the final commit before archiving.
- Under this round's rules it leaves the zero-pairing list, but that pairing is retrospective reuse and must not be written as participation.
- The licence label comes from a mirror site (unverified).
Sources
- DPLM-2 preprint (preprint)
- Preprint v1 full text with the evaluation setup (preprint)
- Official repository (archived) (repository)
- Project page (official site)
- Successor DPLM-2.1 preprint (preprint)
Corrections
3 corrections
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| latest_update.date | 2025-04-15, the date of the successor paper DPLM-2.1 v1 | 2025-07-25, the final commit before this model's repository was archived, with the successor paper recorded separately | source | 2026-11-16 |
| latest_update.event_kind | Recorded as a successor model | Changed to code maintenance only: the event is a repository commit, not a new model | source | 2026-11-16 |
| benchmarks_reported | The site said it reported no site benchmark and listed it as zero-pairing | Under this round's rules it has a retrospective-dataset-use relation with one evaluation service and therefore leaves the zero-pairing list | source | 2026-11-16 |
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.