Isomorphic Labs IsoDDE
DeepMind's AI Drug Design Engine that doubles AlphaFold 3 accuracy in protein-ligand prediction
Overview
Isomorphic Labs IsoDDE (Isomorphic Drug Design Engine) is a unified AI computational platform for end-to-end drug discovery, announced in February 2026 as the most capable publicly benchmarked system for protein-ligand structure prediction. Built on foundations pioneered by AlphaFold, IsoDDE integrates four major capabilities: protein-ligand structure prediction, antibody-antigen interface modelling, binding affinity estimation, and ligandable pocket identification — achieving a 50% success rate on the hardest out-of-distribution benchmark category, more than doubling AlphaFold 3's 23.3% on the same test. It also surpasses gold-standard physics-based methods like FEP+ on binding affinity prediction at lower computational cost.\n\nAccess to IsoDDE is exclusively through strategic pharmaceutical partnerships — not public APIs or software licensing. Isomorphic Labs operates as a drug design and development business, co-developing therapeutics with partners including Novartis, Eli Lilly, and Johnson & Johnson under milestone-based agreements worth up to approximately $3 billion combined. The company raised $600 million in its Series A (April 2025, led by Thrive Capital) and $2.1 billion in its Series B (May 2026, with Thrive, Alphabet, GV, MGX, Temasek, CapitalG, and the UK Sovereign AI Fund), targeting clinical trials for its first fully AI-designed drugs by end of 2026.
Pricing
Pricing shown for reference only. These figures reflect RECATOOLS research as of 11 Jul 2026 and may be out of date or incomplete. This is not financial or purchasing advice — always confirm the current price on the provider’s official website before making any decision.
- Upfront cash + milestone structure
- Multi-target drug-design collaboration
- Partners include Lilly, Novartis, J&J
- Cross-modality, multi-target scope
- Milestone commitments exceed $3B across current partners
Use cases
What you can produce with Isomorphic Labs IsoDDE
- Protein-ligand complex structure predictions at 2x+ AlphaFold 3 accuracy on novel systems
- Antibody-antigen interface models with 39% high-fidelity rate (vs 17% for AlphaFold 3)
- Binding affinity rankings with Pearson correlation of 0.85 on FEP+ benchmark — exceeding the physics-based method itself
- Novel ligandable binding pocket maps generated from amino acid sequence alone (AUPRC 0.75 vs 0.51 for P2Rank)
- Cryptic and allosteric pocket identification without prior ligand knowledge
- Integrated drug design workflow from target identification to candidate molecule optimisation
- Pipeline of fully AI-designed small-molecule drug candidates targeting clinical trials by end of 2026
ASEAN Perspective
Isomorphic Labs IsoDDE in Southeast Asia
ASEAN's pharmaceutical and biotech sectors — including Singapore's Biopolis cluster, Malaysia's NIH, and Indonesia's emerging drug innovation programs — have no direct access pathway to IsoDDE, which is reserved for top-tier global pharma partners. Notably, Temasek (Singapore's sovereign wealth fund) participated in the May 2026 Series B round, signalling regional institutional confidence in Isomorphic Labs' long-term value even without local access. The indirect benefit for ASEAN may come through any licensed drugs eventually commercialised by Novartis, Eli Lilly, or J&J using IsoDDE-designed compounds. ASEAN researchers seeking comparable open tools should look to AlphaFold 3 (free for non-commercial use) or Boltz-2 (MIT licence) as accessible alternatives.
Isomorphic Labs IsoDDE represents a genuine scientific leap in AI-driven drug design — its 50% accuracy on the hardest protein-ligand prediction benchmark, outperformance of physics-based gold standards in binding affinity, and integration of pocket identification into a single system place it at the frontier of computational drug discovery. The Nobel Prize-winning AlphaFold lineage and $2.7B+ in total funding from Alphabet, Thrive Capital, Temasek, and MGX underline the credibility of its technical claims. For the pharmaceutical companies fortunate enough to partner with it, IsoDDE likely compresses years of early-stage drug design work.\n\nThe critical caveat is access: IsoDDE is entirely proprietary, available only via bilateral billion-dollar partnership agreements with major pharma. There is no public API, no open weights, no software license, and the technical paper provides limited methodological detail, making independent verification difficult. Academic institutions, biotech startups, and ASEAN researchers cannot access it at any price. For the vast majority of the drug discovery community, IsoDDE is a benchmark to aspire to — not a tool to deploy.
What people say
You can't buy this. That's the first thing to know about IsoDDE — Isomorphic Labs' unified drug-design engine, released February 10, 2026, is available only through nine- and ten-figure partnership deals with Novartis, Eli Lilly, and Johnson & Johnson, not as a product or API anyone else can touch.
The benchmark numbers are legitimate, not marketing spin: on the hardest out-of-distribution protein-ligand cases (under 20% sequence similarity to training data), IsoDDE hits roughly 50% accuracy versus AlphaFold 3's 23.3% on the same test, and it beats physics-based methods like FEP+ on binding affinity at a fraction of the compute cost. The 27-page technical report backing these claims is thinner on methodology than an academic paper would be, which makes independent verification harder than the headline stats suggest.
Money follows the results: a $2.1 billion Series B closed May 12, 2026, led by Thrive Capital with Alphabet, GV, MGX, Temasek, CapitalG, and the UK Sovereign AI Fund, on top of a $600 million round from March 2025 — $2.7 billion total. Combined milestone value across the three pharma partnerships now tops $3 billion. Isomorphic is targeting first-in-human trials for an internally designed candidate by the end of 2026.
None of this reaches academic labs, biotech startups, or ASEAN research institutions, who have zero access at any price. Judge IsoDDE as a benchmark to watch, not a tool anyone outside a handful of pharma giants will ever run.
Summary of public user & expert reviews, compiled by RECATOOLS.
Notable facts
- Demis Hassabis won the 2024 Nobel Prize in Chemistry for AlphaFold 2 — the same foundational work that underpins IsoDDE.
- IsoDDE achieves 39% high-fidelity antibody-antigen prediction accuracy versus only 2% for the open-source Boltz-2 model.
- Singapore's Temasek joined the $2.1B Series B — making it one of the few ASEAN institutions with a financial stake in the platform.
- Isomorphic Labs' pharma partnerships with Novartis and Eli Lilly alone carry potential milestone payments of up to ~$3 billion combined.
Frequently asked questions
About this listing
This entry was compiled from publicly available data including Isomorphic Labs IsoDDE's official website, press releases, documentation, and reputable third-party publications. RECATOOLS is not affiliated with Isomorphic Labs IsoDDE unless explicitly stated.
Third-party AI tools update their pricing, features, availability, and policies frequently. Information here may be outdated by the time you read this — we make reasonable efforts to keep listings current, but cannot guarantee absolute accuracy.
For the latest details, please refer to Isomorphic Labs IsoDDE directly →
Spotted something out of date? Suggest an update →
More in Research & Data
