What it is
DiffDock treats docking as generative diffusion over the space of ligand poses rather than an optimization search, giving faster, more accurate blind docking. It became a template for generative approaches to protein–ligand interaction and ships inside NVIDIA BioNeMo.
Evidence trail
BioAtlas keeps the path from source to decision visible. A connection records provenance; it does not imply that evidence is sufficient for every context.
Model passport
How DiffDock represents biology
Category is navigation. These fields describe the model-specific computational transformation and deliberately override broad category defaults.
Biological scale
Modalities & tasks
Registry, claims and frontier intelligence
Version history not yet curated
1 version record · release year not yet normalized. Model-family identity remains separate from capability and access changes.
Explore version lineage →1 normalized claim
Protein–ligand pose prediction · PDBBind
Open claim intelligence →3 connected frontiers
Structure + affinity · Recent preprint
Inspect research horizon →Connected research frontiers
These records describe active research directions, not guaranteed capabilities of this model. Evidence stages and unresolved questions are preserved separately.
Joint structure and binding-affinity reasoning
Isomorphic Labs · MIT · Open community · 2026-03-06Can one model predict both the bound geometry and the energetic ranking needed to prioritize compounds?
Evidence boundary and unresolved questions
Recent independent evaluations report that strong global correlations may not preserve ranking among top compounds, where lead-selection decisions occur.
- Can models rank close analogues within a chemical series?
- How well do they extrapolate across assays, protonation states and target families?
- Can uncertainty identify when physics or experiment should take over?
binding affinity · ranking · virtual screening · free energy · uncertaintyOpen frontier record →Finding cryptic pockets from sequence
Isomorphic Labs · 2026-02-10Can a model reveal ligandable pockets that are hidden in the unbound protein and only open after a ligand or allosteric change?
Evidence boundary and unresolved questions
The public evidence is currently a company technical report and benchmark narrative. Prospective medicinal-chemistry validation and independent replication remain essential.
- How often are predicted pockets experimentally ligandable rather than geometrically plausible?
- How robust is pocket discovery across membrane proteins, intrinsically disordered regions and low-data target families?
- Can calibrated confidence distinguish genuine induced pockets from model hallucinations?
cryptic pockets · allostery · induced fit · ligandability · dockingOpen frontier record →Fast, uncertainty-aware affinity screening
Terray Therapeutics research team · 2026-02-08Can virtual screening retain useful structural and affinity accuracy without expensive all-atom diffusion for every compound?
Evidence boundary and unresolved questions
The results are preprint claims; proprietary assay details and cross-lab prospective replication remain limited.
- Does coarse representation preserve water, ion, metal and covalent chemistry?
- How well does uncertainty calibrate under target and chemistry shift?
- Can active learning improve real design-make-test cycles?
virtual screening · uncertainty · active learning · coarse representationOpen frontier record →Inputs and outputs
Inputs
Molecular structures or discovery objectivesOutputs
MoleculesScores or posesScientific and technical profile
Scientific principles
Technology
Scientific lineage
These are transparent concept matches—not claims that one scientist alone caused this model. Each connection is based on the model’s recorded domain, scientific principles, technical terms or an explicit lineage link.
Denoising diffusion generative models
Jascha Sohl-Dickstein, Jonathan Ho and collaboratorsModern protein-backbone, molecular-pose and biomolecular-complex generators use diffusion to sample valid three-dimensional structures and designs.
Atomic structures of biologically important molecules by X-ray crystallography
Dorothy Crowfoot HodgkinStructure-based drug design depends on the experimental structural tradition she helped establish.
Lock-and-key molecular recognition
Emil FischerThe metaphor seeded structure-based ligand design, pharmacophore thinking and the search for complementary binding pockets.
Quantitative structure–activity relationships
Corwin HanschClassical QSAR established the central premise that molecular features can predict potency and guide optimization—the conceptual ancestor of modern molecular machine learning.
Levinthal’s paradox and efficient folding pathways
Cyrus LevinthalModern folding algorithms, energy landscapes, learned priors and diffusion models solve a constrained search problem rather than brute-force conformational enumeration.
Intermolecular forces and excluded volume
Johannes D. van der WaalsModern force fields, docking scores, molecular dynamics and ligand–protein packing depend on these non-covalent interactions.
Evaluation evidence
Task-specific evidence only; not comparable as a universal leaderboard score.
PDBBind
Version history not yet curated · PDBBind held-out complexesPeer-reviewed top-ranked docking-pose evaluation.
Claim caveats
- Random and temporal splits can produce materially different estimates.
- Pose accuracy is not binding-affinity accuracy.
Known limitations
- Performance depends on the evaluation dataset and operating conditions.
- Task-specific benchmark results should not be compared across unlike domains.
- Outputs require task-specific scientific and experimental validation.
Milestones
Open-sourced and integrated into BioNeMo.
Shifted docking from search to generation.