What it is
Isomorphic Labs is DeepMind's drug-discovery spin-off, co-developer of AlphaFold 3. In 2026 it unveiled IsoDDE (the Isomorphic Drug Design Engine), a unified system that more than doubled AF3's accuracy on the hardest protein–ligand generalization benchmark, predicts binding affinity faster than physics methods, and finds novel binding pockets from sequence alone. Backed by a $600M round (2025) and ~$3B in Novartis/Lilly/J&J deals, it plans first-in-human trials of its own oncology candidates by end of 2026.
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 Isomorphic Labs (IsoDDE) 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 pending
0 version records · release year not yet normalized. Model-family identity remains separate from capability and access changes.
Explore version lineage →0 normalized claims
No task, dataset, split and metric claim has been normalized for this record yet.
Open claim intelligence →0 connected frontiers
No frontier-research record currently connects to this model.
Inspect research horizon →Inputs and outputs
Inputs
Disease hypothesis and multimodal evidenceOutputs
Targets, candidates or development programsScientific 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.
Anfinsen’s dogma—the thermodynamic hypothesis
Christian B. AnfinsenProtein structure prediction, inverse folding and generative protein design all assume that sequence strongly constrains structure and function.
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.
Selective toxicity and the ‘magic bullet’
Paul EhrlichTarget selectivity, therapeutic index and mechanism-based screening remain central goals of drug discovery.
Rational antimetabolite drug design
Gertrude B. Elion & George H. HitchingsMechanism-based design, pathway selectivity and iterative medicinal chemistry are direct descendants of this strategy.
Phage display and selection of binding proteins
George P. Smith & Sir Gregory P. WinterDisplay-based selection created an experimental search engine for protein binders and remains a core validation partner for computational antibody design.
Evaluation evidence
BioAtlas has not yet extracted a structured benchmark claim for this record.
Known limitations
- Independent reproducibility is limited by proprietary access.
- A structured benchmark claim has not yet been extracted for this record.
- Outputs require task-specific scientific and experimental validation.
Milestones
IsoDDE more than doubles AF3 accuracy on hardest targets.
Partnerships with Novartis, Eli Lilly and J&J.