Overview
| Name | DiffDock · aliases: DiffDock, DiffDock-L |
|---|---|
| Full name | Official materials use DiffDock only; no expanded name |
| Ambiguous names (not auto-linked) | None |
| Family | Not a family entry. The record covers DiffDock and its in-repo successor DiffDock-L without separate family members |
| Organization | MIT CSAIL |
| Organization type | Academic lab |
| Country | United States |
| Model class | Blind docking (diffusion plus confidence ranking) |
| Domain | Structure & co-folding (also: Small molecules) |
| First release | · preprint Basis: arXiv v1 (conference version the following year) source |
| Other milestones | |
| Latest update | · new version Basis: GitHub v1.1: DiffDock-L release DiffDock-L was trained with larger augmented data and confidence bootstrapping and appeared at that year's conference; v1.1.1-v1.1.3 (to 2024-09-04) are fixes and the last commit is 2025-05-02 source The most recent sourced event, not a claim that nothing changed since. |
| Status | Maintained only · No newer generation; later activity is maintenance |
| Openness | Code: Open Weights: Open Code and weights are public on GitHub, with DiffDock-L as the repository default |
| Benchmarks reported | 2 counted (retrospective 2, cited only 1) |
| Wet-lab validation | None recorded |
| Unverified fields | None |
| As of | 2026-11-16 |
What it does
Treats docking as generation: it diffuses over ligand translation, rotation and torsion, then ranks candidate poses with a confidence model, and DiffDock-L is the larger-data successor. In the co-folding era it serves as the deep-learning docking baseline against the physics-scoring line of Vina and against AlphaFold3 and NeuralPLexer3.
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 3 pairings are counted.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 12 DUD-E / LIT-PCBA | Retrospective dataset use | LIT-PCBA virtual-screening study by a third party | Third-party | Third-party LIT-PCBA study (arXiv 2605.01681) †partly verified · evidence |
| 33 PoseX | Retrospective dataset use | PoseX, rerun by the benchmark authors | Third-party | Evaluated by the benchmark paper. †partly verified · evidence |
| 05 PoseBusters | Cited as comparison only (not counted) | PoseBusters V2 comparison table in a third-party paper | Third-party | Quoted from the comparison table of another model's paper †partly verified · evidence |
Other evaluations (outside the 44)
- Self-reported blind-docking sets (self report) Self-reported: The DiffDock-L paper self-reports top-1 results on two blind-docking sets under a fixed sampling budget, a different protocol from physical-validity checks (no figures)
- Second-hand reviews (second hand) Third-party: The claim that it beats other blind-docking methods partly reaches readers through reviews rather than independent reruns (second-hand)
- Baseline role (third party evaluation) Third-party: Several co-folding and docking papers rerun it as the deep-learning baseline, with conclusions that vary by task
Developers report: Developers report that DiffDock-L, trained with larger augmented data and confidence bootstrapping, beats other blind-docking methods (self-reported, partly relayed by reviews).
Independent evidence: Third-party papers and benchmark authors have rerun it; the conclusion is a baseline role, with no edge in physical validity or screening (no figures).
Training data
Group in Figure 7: Public data only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | PDBBind, with DiffDock-L adding other PDB complexes and synthetic augmentation that cuts ligands from real structures source |
| b. Private or licensed data | No | |
| 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: An academic group with no company: teams at MIT CSAIL and an affiliated clinic, whose authors were then mostly doctoral students and faculty at the institute.
- Funding: Academic project; funding amounts undisclosed
- Products and partnerships: The successor DiffDock-L is the repository default; it shares an academic lineage with Boltz-2 but no institutional link is evident.
- Related models: Vina, Boltz-2, NeuralPLexer3, AlphaFold 3
Reading notes
- Most of its benchmark figures come from other papers under mixed protocols and should be read as a baseline only.
- Its self-reported blind-docking protocol differs from physical-validity checks; do not swap them.
- It has no edge in virtual screening; strong pose generation does not imply strong screening.
- Classical docking scores higher when the pocket is known, but the settings differ.
Caveats
- The developers self-report on none of the site's benchmarks; all three relations come from third parties.
- The PoseBusters line is cited as comparison only and does not count as an established relation.
- The last substantive update was 2024-02, followed only by fixes and maintenance.
Sources
- DiffDock paper (preprint) ·
- DiffDock-L paper (preprint)
- DiffDock GitHub releases (repository)
- Third-party comparison table in a co-folding paper (third-party paper)
- Third-party virtual-screening study (third-party paper)
- Evaluation paper by the benchmark authors (third-party paper)
Corrections
None recorded.
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.