organization
Isomorphic Labs
Also known as Isomorphic, IsoDDE, Isomorphic Labs Drug Design Engine
Isomorphic Labs is a London-based AI drug-discovery company founded in 2021 and led by Demis Hassabis, who shared the 2024 Nobel Prize in Chemistry for AlphaFold.[1][2][3] It raised $2.1 billion in May 2026 and says it expects its first clinical trials by the end of 2026, a year later than first planned.[4][5]
Key facts
Isomorphic Labs aims to turn AlphaFold-style AI into medicines. Founded in 2021 and headquartered in London, it is led by chief executive Demis Hassabis and president Max Jaderberg.[1][2]
Funding
On 12 May 2026 the company announced a $2.1 billion round led by Thrive Capital. Existing investors Alphabet and GV took part, along with new investors MGX, Temasek, CapitalG and the UK Sovereign AI Fund.[4] The company said the money would fund its AI drug design engine, IsoDDE, and expand its internal and partnered programmes.[6]
Technology
Isomorphic describes IsoDDE as a set of proprietary models forming a unified engine that works across multiple therapeutic areas and drug modalities.[6] The company says it released AlphaFold 3 together with Google DeepMind in 2024.[7] Its chief executive shared the Nobel Prize for alphafold, whose third version, published in 2024, predicts how proteins bind small molecules and reported far greater accuracy on protein–ligand interactions than standard docking tools.[3][8][9]
In February 2026 the company published a technical report on IsoDDE. It says the engine more than doubles AlphaFold 3’s accuracy on a challenging protein–ligand generalisation benchmark and predicts binding affinities more accurately than gold-standard physics-based methods.[10] These are the company’s own benchmark results; open academic models such as Boltz-2 make related claims about fast affinity prediction.[10][11] Isomorphic says it is building the system to scale from small molecules to antibodies, peptides and other types of medicine.[12]
Partners
Isomorphic lists strategic partnerships with Novartis, Eli Lilly and Johnson & Johnson.[13] The Johnson & Johnson deal, announced on 20 January 2026, is a cross-modality, multi-target research collaboration.[14] In October 2026 Isomorphic also became a founding member of the Virtual Biology Initiative, a Biohub-convened effort to generate open, AI-ready biological data.[15]
Clinical timeline
At the World Economic Forum in January 2026, the company said it expected its first clinical trials by the end of 2026, a year later than its earlier target of the end of 2025.[5] On 29 September 2026 its president wrote that the company’s preclinical data was helping it “gear up for clinical developments”; the post did not announce a trial.[16]
Why it matters
The field’s central question is whether AI-designed molecules succeed more often in patients. A 2024 analysis found AI-discovered molecules had 80–90% phase I success but about 40% in phase II, similar to industry averages, on a small sample.[17][18] Isomorphic’s first trials, when they start, will add to that evidence.[5]
The bar it has to clear
Few AI-discovered or AI-designed drugs have reached human trials at all, according to the authors of the 2025 rentosertib trial.[19] Takeda’s zasocitinib, a computationally designed drug nearing an FDA decision, came from physics-based simulation combined with machine learning rather than a single AI engine, with that decision due in the first quarter of 2027.[20][21] Insilico’s AI-generated rentosertib went further still, starting a 320-patient phase III trial in China in July 2026.[22] Isomorphic’s results will be compared with all of these. The debate is covered in this course’s analysis of AI-designed drugs.
Questions readers ask
Who has invested in Isomorphic Labs?
Alphabet and GV are existing investors; its May 2026 round added Thrive Capital, MGX, Temasek, CapitalG and the UK Sovereign AI Fund.[4]
Does Isomorphic Labs have drugs in clinical trials?
Not as of late September 2026. In January 2026 it said it expected its first clinical trials by the end of 2026, after earlier targeting the end of 2025; on 29 September its president wrote that preclinical data was helping it "gear up for clinical developments".[5][16]
How good is IsoDDE?
Isomorphic reported in February 2026 that IsoDDE more than doubles AlphaFold 3's accuracy on a hard protein–ligand benchmark. These are company-reported benchmarks, not clinical results.[10]
Which drug companies work with Isomorphic Labs?
It lists strategic partnerships with Novartis, Eli Lilly and Johnson & Johnson.[13]
Sources
Each numbered claim is a statement we checked against the sources listed with it. Status shows how well established it is.
- [1]
Isomorphic Labs was founded in 2021, is headquartered in London and has offices in Cambridge, Massachusetts and Lausanne, Switzerland. confirmedas of 2026-05-12
- Isomorphic Labs secures $2.1 billion funding to scale its AI drug design engine · Isomorphic Labs (via PR Newswire) · 2026-05-12 · About Isomorphic Labs (retrieved 2026-10-10)
- [2]
Demis Hassabis is chief executive of Isomorphic Labs and Max Jaderberg is its president, according to the company's May 2026 funding announcement. confirmedas of 2026-05-12
- Isomorphic Labs secures $2.1 billion funding to scale its AI drug design engine · Isomorphic Labs (via PR Newswire) · 2026-05-12 (retrieved 2026-10-10)
- [3]
The 2024 Nobel Prize in Chemistry went half to David Baker for computational protein design and half jointly to Demis Hassabis and John Jumper for protein structure prediction. confirmedas of 2024-10-09
- Press release: The Nobel Prize in Chemistry 2024 · The Royal Swedish Academy of Sciences (Nobel Prize) · 2024-10-09 (retrieved 2026-10-10)
- [4]
On 12 May 2026 Isomorphic Labs announced a $2.1 billion funding round led by Thrive Capital, with Alphabet and GV among existing investors and MGX, Temasek, CapitalG and the UK Sovereign AI Fund as new investors. confirmedas of 2026-05-12
- Isomorphic Labs secures $2.1 billion funding to scale its AI drug design engine · Isomorphic Labs (via PR Newswire) · 2026-05-12 (retrieved 2026-10-10)
- Isomorphic Labs Raises $2.1 Billion to Expand AI-Driven Drug Discovery Platform · BioPharm International · 2026-05-13 (retrieved 2026-10-10)
- [5]
In January 2026 Isomorphic Labs said it expected its first clinical trials by the end of 2026, a year later than its earlier target of the end of 2025. reportedas of 2026-01-20
- Google-backed Isomorphic Labs delays clinical trial timeline · Reuters (via Yahoo Finance) · 2026-01-20 (retrieved 2026-10-10)
- [6]
Isomorphic Labs says its funding will develop its AI drug design engine, IsoDDE, which it describes as working across multiple therapeutic areas and drug modalities. confirmedas of 2026-05-12
- Isomorphic Labs secures $2.1 billion funding to scale its AI drug design engine · Isomorphic Labs (via PR Newswire) · 2026-05-12 (retrieved 2026-10-10)
- Isomorphic Labs Raises $2.1 Billion to Expand AI-Driven Drug Discovery Platform · BioPharm International · 2026-05-13 (retrieved 2026-10-10)
- [7]
Isomorphic Labs says it released AlphaFold 3 in 2024 together with Google DeepMind. confirmedas of 2026-02-10
- The Isomorphic Labs Drug Design Engine unlocks a new frontier beyond AlphaFold · Isomorphic Labs · 2026-02-10 (retrieved 2026-10-10)
- [8]
AlphaFold 3, published in Nature in May 2024, uses a diffusion-based architecture to predict joint structures of complexes containing proteins, nucleic acids, small molecules, ions and modified residues. confirmedas of 2024-05-08
- Accurate structure prediction of biomolecular interactions with AlphaFold 3 · Nature · 2024-05-08 (retrieved 2026-10-10)
- [9]
The AlphaFold 3 paper reported far greater accuracy for protein–ligand interactions than state-of-the-art docking tools and higher antibody–antigen accuracy than AlphaFold-Multimer. confirmedas of 2024-05-08
- Accurate structure prediction of biomolecular interactions with AlphaFold 3 · Nature · 2024-05-08 (retrieved 2026-10-10)
- [10]
In February 2026 Isomorphic Labs reported that its drug design engine, IsoDDE, more than doubles AlphaFold 3's accuracy on a challenging protein–ligand generalisation benchmark and predicts binding affinities more accurately than gold-standard physics-based methods; these are company-reported benchmark results. reportedas of 2026-02-10
- The Isomorphic Labs Drug Design Engine unlocks a new frontier beyond AlphaFold · Isomorphic Labs · 2026-02-10 (retrieved 2026-10-10)
- [11]
Boltz-2, described in a June 2025 preprint by MIT and Recursion researchers, predicts both complex structures and small molecule–protein binding affinity, and its authors say it is the first AI model to approach free-energy perturbation accuracy while being at least 1,000 times more computationally efficient. confirmedas of 2025-06-18
- Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction · bioRxiv (MIT CSAIL, MIT Jameel Clinic and Recursion authors) · 2025-06-18 (retrieved 2026-10-10)
- [12]
Isomorphic Labs says it is building its approach to scale across disease areas and types of medicine, from small molecules to antibodies and peptides. confirmedas of 2026-09-29
- Building a new path to make medicines with AI · Isomorphic Labs · 2026-09-29 (retrieved 2026-10-10)
- [13]
Isomorphic Labs has strategic partnerships with Novartis, Eli Lilly and Johnson & Johnson. confirmedas of 2026-05-12
- Isomorphic Labs secures $2.1 billion funding to scale its AI drug design engine · Isomorphic Labs (via PR Newswire) · 2026-05-12 (retrieved 2026-10-10)
- [14]
On 20 January 2026 Isomorphic Labs announced a cross-modality, multi-target research collaboration with Johnson & Johnson. confirmedas of 2026-01-20
- Isomorphic Labs Enters into a Research Collaboration with Johnson & Johnson · Isomorphic Labs · 2026-01-20 (retrieved 2026-10-10)
- [15]
On 7 October 2026 Isomorphic Labs said it is a founding member of the Virtual Biology Initiative, a Biohub-convened effort to generate open, AI-ready biological data. confirmedas of 2026-10-07
- Isomorphic Labs joins the Virtual Biology Initiative · Isomorphic Labs · 2026-10-07 (retrieved 2026-10-10)
- [16]
On 29 September 2026 Isomorphic Labs' president wrote that the company's preclinical data was helping it "gear up for clinical developments"; the post did not announce a clinical trial. confirmedas of 2026-09-29
- Building a new path to make medicines with AI · Isomorphic Labs · 2026-09-29 (retrieved 2026-10-10)
- [17]
A 2024 analysis of AI-native biotech pipelines in Drug Discovery Today found an 80–90% phase I success rate for AI-discovered molecules, higher than historic industry averages. confirmedas of 2024-06-01
- How successful are AI-discovered drugs in clinical trials? A first analysis and emerging lessons · Drug Discovery Today · 2024-06-01 · Abstract (publisher site blocks automated fetches; abstract text checked via Europe PMC) (retrieved 2026-10-10)
- [18]
The same 2024 analysis found a phase II success rate of about 40% for AI-discovered molecules, on a limited sample, comparable to historic industry averages. confirmedas of 2024-06-01
- How successful are AI-discovered drugs in clinical trials? A first analysis and emerging lessons · Drug Discovery Today · 2024-06-01 · Abstract (publisher site blocks automated fetches; abstract text checked via Europe PMC) (retrieved 2026-10-10)
- [19]
The rentosertib paper notes that few novel AI-discovered or AI-designed drugs have reached human clinical trials. confirmedas of 2025-06-03
- A generative AI-discovered TNIK inhibitor for idiopathic pulmonary fibrosis: a randomized phase 2a trial · Nature Medicine · 2025-06-03 (retrieved 2026-10-10)
- [20]
Zasocitinib came from a Nimbus Therapeutics TYK2 programme that, with Schrödinger from 2016, used machine learning and physics-based free energy perturbation to assess more than 13,000 compounds computationally. confirmedas of 2026-09-25
- Nimbus used AI to help develop Takeda's $4B psoriasis bet. Here's where it's taking the tech next · PharmaVoice (via Yahoo Finance) · 2026-09-25 (retrieved 2026-10-10)
- Case study: Design of a highly selective, allosteric, picomolar TYK2 inhibitor using novel FEP+ strategies · Schrödinger · 2024-07-01 (retrieved 2026-10-10)
- [21]
On 14 September 2026 Takeda said the FDA had accepted its new drug application for zasocitinib (TAK-279), an oral TYK2 inhibitor for moderate-to-severe plaque psoriasis, under priority review with a target action date in the first quarter of 2027. confirmedas of 2026-09-14
- U.S. FDA Accepts New Drug Application Under Priority Review for Takeda's Zasocitinib in Moderate-to-Severe Plaque Psoriasis · Takeda · 2026-09-14 (retrieved 2026-10-10)
- [22]
On 7 July 2026 Insilico Medicine announced the start of a phase III trial of rentosertib, a randomised, double-blind, placebo-controlled study expected to enrol 320 patients with idiopathic pulmonary fibrosis in China over 52 weeks. confirmedas of 2026-07-07
- Insilico Initiates Phase III Clinical Trial for Rentosertib, Its AI-Empowered TNIK Inhibitor for Idiopathic Pulmonary Fibrosis · Insilico Medicine · 2026-07-07 (retrieved 2026-10-10)
- Insilico Medicine begins Phase III trial of AI-designed IPF drug Rentosertib · Drug Target Review (retrieved 2026-10-10)
Revision history (2)
Created Oct 10, 2026. Last reviewed by an editor on Oct 10, 2026. Next scheduled review: Jan 10, 2027.
Cite this page
"Isomorphic Labs." ContentLora, updated Oct 10, 2026. https://contentlora.com/wiki/isomorphic-labs
Spotted an error? Suggest a correction or emailcorrections@contentlora.com.
Keep exploring
- AnalysisDo AI-designed drugs work? What the clinical evidence showsAI-designed drug candidates are reaching patients. What trial data show so far, what they don't, and why "AI-designed" is a contested label.
- WikiAlphaFoldAlphaFold is Google DeepMind's AI system for predicting protein and biomolecular structures. Versions, accuracy, database and limits.
- WikiGoogle DeepMindGoogle DeepMind is Alphabet's AI research lab, maker of Gemini and AlphaFold. Its origins, leadership, models and 2026 news.
- WikiEli Lilly and CompanyEli Lilly makes tirzepatide (Mounjaro, Zepbound) and the GLP-1 pill Foundayo, and is developing retatrutide. Its 2026 results, pipeline and pricing.
- WikiRFdiffusionRFdiffusion is an open-source generative AI model from the Institute for Protein Design that designs new proteins and binders.
- DevelopingAI for science tracker: milestones and what to watchLive tracker of AI for science: protein AI, AI weather models, materials, autonomous labs and AI drug discovery, with dated milestones.