Close Menu

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    What's Hot

    CNN Staffers Having Meltdown, Fear Bari Weiss Takeover

    June 30, 2026

    “No deseaba nada menos que eso”

    June 30, 2026

    Trump’s Mount Rushmore fireworks show reignites fire fears

    June 30, 2026
    Facebook X (Twitter) Instagram
    Select Language
    Facebook X (Twitter) Instagram
    NEWS ON CLICK
    Subscribe
    Tuesday, June 30
    • Home
      • United States
      • Canada
      • Spain
      • Mexico
    • Top Countries
      • Canada
      • Mexico
      • Spain
      • United States
    • Politics
    • Business
    • Entertainment
    • Fashion
    • Health
    • Science
    • Sports
    • Travel
    NEWS ON CLICK
    Home»Health & Fitness»US Health & Fitness»The AI Drug Discovery Race Is Heating Up, Not In the Way You Think
    US Health & Fitness

    The AI Drug Discovery Race Is Heating Up, Not In the Way You Think

    News DeskBy News DeskJune 30, 2026No Comments7 Mins Read
    Share Facebook Twitter Pinterest Copy Link LinkedIn Tumblr Email VKontakte Telegram
    The AI Drug Discovery Race Is Heating Up, Not In the Way You Think
    Share
    Facebook Twitter Pinterest Email Copy Link

    Since 2019, roughly $60 billion has gone into using AI to discover drugs. About 175 AI-originated programs have entered human trials. The number approved by the FDA is zero.

    A zero this early is not surprising on its own; it matches traditional drug discovery, but timing makes it worth attention. Over the next two years, a cluster of the most advanced AI-designed drugs will read out of mid- and late-stage trials. We are reaching the final turn of the race. 

    We should ask a more nuanced question than “does AI work in drug discovery.” Rather, we should ask which approaches are about to be proven, and which are about to be exposed, because the field is several bets, and they are not equally sound. 

    Why AlphaFold worked

    Start with the one result everyone agrees on. In 2020, DeepMind’s AlphaFold predicted the three-dimensional shape a protein folds into from its amino acid sequence, solving a problem that had resisted biology for fifty years. It later won a Nobel Prize. It worked for a reason, the same one behind the LLM revolution: the training data encodes the useful thing it was being asked to find.

    A protein is, in a precise sense, written in a language. There is a finite alphabet of twenty amino acids and each protein is a sequence read in one direction, across an enormous corpus, more than 250 million sequences. There is a hidden grammar: when a protein folds, positions along the sequence that end up touching tend to mutate together over evolutionary time, leaving a statistical fingerprint. AlphaFold’s architecture, the same family of model that powers LLMs, was built to read exactly that kind of patterned sequence. The mechanism it was asked to recover was sitting in the data, and it found it.

    Compare that to what most of the rest of the field trained on: cell images, the published literature, patient records. These models are capturing the appearance of a disease with fidelity, but not the mechanism, because it was never in the data.

    The horses in the AI drug discovery race

    Three groups of competitors emerge when you sort them by the training data underneath.

    1. Phenotypic data – The first group trains on data that records how something looks. BenevolentAI is a clear example. Its model is a knowledge graph of scientific literature. In late January 2020 its team successfully used the knowledge graph to identify Eli Lilly’s baricitinib as a Covi-19 treatment, and in 2022 it went public through a significant SPAC merger. Then its lead drug, a topical treatment for eczema, failed a mid-stage trial; the data suggested the molecule worked as designed but the target did not translate to benefit. In March 2025, it delisted from the Euronext Amsterdam exchange. A roughly £1.3B valuation became a company taking itself private in under 3 years.

    Another example is Recursion’s REC-994 for cerebral cavernous malformation. Recursion used AI analysis of perturbed cell images to select a molecule to repurpose. It met its Phase 2 safety endpoint, but was discontinued in May 2025 after long-term extension data failed to show sustained improvement.

    In 2025, several independent benchmarking studies tested the largest cell-based foundation models on the task the whole grouping depends on: predicting how a cell would respond to a perturbation it had not seen in training. The cleanest, published in Nature Methods, found that none of the models beat a trivial baseline that amounted to averaging the responses already in the training data. A model with a hundred million parameters did no better than arithmetic.

    2. Surrogate data – The second group trains on data that carries the design task itself: structure-to-property relationships are real and learnable, and a closed test-learn loop generates its own labels. Exscientia is a good example. One famous proof point was DSP-1181 designed on its platform for Sumitomo in about 12 months versus roughly five years. The Phase 1 data was announced in Jan 2020 and it was discontinued in 2021 when it did not meet expected criteria. Its training data encodes “will this molecule bind and behave against the target we chose.” It says nothing about whether that target is the right one for the disease. The company was later absorbed into Recursion, expanding its approach to training data.

    Insilico Medicine is arguably in both the surrogate and phenotypic data group. They use two bodies of training data: phenotypic data (for targeting) and surrogate data (for molecule design). The result, rentosertib, showed very strong safety data in Phase 2a trial and an encouraging but small early signal from a trial not designed to prove efficacy. The molecule is safe and behaves as designed. The efficacy verdict will depend on whether the AI picked the right target and that came from the weaker data. Note, Insilico’s success was achieved alongside traditional medicinal chemistry.

    3. Mechanistic data – The third group of candidates trains on data that encodes the relevant mechanism as AlphaFold did. The families that followed, including ESM, RFdiffusion, and ProteinMPNN, extend the same logic from predicting existing proteins to designing new ones. Antibody design sits on the most language-like data in biology, with effectively unlimited training material from natural and engineered repertoires and a binding mechanism that is sequence-encoded.

    The clinical evidence here is earlier but arriving. Generate Biomedicines has two AI-designed antibodies in the clinic, including GB-0895, an anti-TSLP antibody entering in Phase 3 for severe asthma, and GB-0669, a COVID-neutralizing antibody that reached a previously undruggable target with positive Phase 1 data. Isomorphic Labs, built directly on AlphaFold, has pushed its first-in-human trials to the end of 2026 and is not yet dosing patients, but is the cleanest test of the original mechanism in a drug-design setting.

    None are yet at the point where the companies named earlier sit. The comparison is only structural so far. The companies above placed drugs into trials using training data that did not carry the mechanism the models needed to learn. Ultimately, the training data must encode whether the drug works in the human body, in the context of disease. This dataset is elusive.

    For this group, a designed antibody still has to behave as a drug in a human, and the next two years will test that, but the structural question is already answered correctly. That is a different starting position.

    The final stretch

    None of this means AI failed in drug discovery. Most of these stories are not over, and AlphaFold shows how high the ceiling goes. The field placed several bets, and so far the one that paid was where the training data carried the mechanism.

    When evaluating the AI race, the instinct is to evaluate the model, its size, benchmark, and demo. The first question should be whether the data underneath the model encodes the thing you are asking the model to predict. If you want a tool to predict which patients respond to a therapy, ask whether the training data holds the causal link between treatment and response, or only records who got what.

    The AI drugs that have made it to trials fare better than the industry standard in Phase 1, a safety gate, but no better in the later stages where efficacy is tested, though the sample is still small. Their training data did not encode that success. This phase-gate discrepancy is the difference between reversing Eroom’s Law and accelerating it. If AI simply generates candidates faster, it only speeds up the rate at which companies reach expensive mid-stage failures. To actually reverse Eroom’s Law, AI must increase the probability of success, not just the velocity of discovery.

    As the horses race to the finish over the next two years, it will be read as a verdict on AI in medicine. It is better read as a verdict on data. Where the training data carried the mechanism, the results will hold. Where it carried only the appearance, no model will recover what was never there.

    Photo: metamorworks, Getty Images


    Andrew Ryscavage is the founder of Brinton Bio. He spent two decades inside life sciences organizations, with earlier work at the NIH and Monitor Deloitte. He writes about where artificial intelligence is and is not changing how medicines get made. He is based in Tampa, FL and in Bethesda, MD.

    This post appears through the MedCity Influencers program. Anyone can publish their perspective on business and innovation in healthcare on MedCity News through MedCity Influencers. Click here to find out how.

    AI drug discovery biopharma nl pharmaceuticals
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Telegram Copy Link
    News Desk
    • Website

    News Desk is the dedicated editorial force behind News On Click. Comprised of experienced journalists, writers, and editors, our team is united by a shared passion for delivering high-quality, credible news to a global audience.

    Related Posts

    US Health & Fitness

    MedCity Pivot Podcast: The Evolution of At-Home Care

    June 30, 2026
    US Health & Fitness

    Hospitals Have Always Had Eyes — AI is Giving Them a Brain

    June 30, 2026
    US Health & Fitness

    From Management to Personalized Prevention: The Phase Shift in Chronic Disease

    June 30, 2026
    US Health & Fitness

    Headache Disorders Have Been Part of the American Story for 250 Years

    June 30, 2026
    US Health & Fitness

    How Payers Can Use AI to Improve the Healthcare Financial Experience

    June 30, 2026
    US Health & Fitness

    Healthcare Moves: A Monthly Summary of Hires, Exits and Layoffs

    June 29, 2026
    Add A Comment
    Leave A Reply Cancel Reply

    Don't Miss

    CNN Staffers Having Meltdown, Fear Bari Weiss Takeover

    News DeskJune 30, 20260

    CNN staffers are allegedly in full meltdown mode as they fear Bari Weiss may soon…

    “No deseaba nada menos que eso”

    June 30, 2026

    Trump’s Mount Rushmore fireworks show reignites fire fears

    June 30, 2026

    New Trump book, ‘Regime Change,’ has sold 300,000 copies, with more being printed, publisher says

    June 30, 2026
    Tech news by Newsonclick.com
    Top Posts

    Twitch Creators Will Soon Be Able To Stream In Horizontal And Vertical Formats Simultaneously

    May 31, 2026

    Cardinals Designate Matt Pushard, Recall Hunter Dobbins

    May 31, 2026

    ‘Today’ Hoda Kotb Returns For Special Celebration

    May 31, 2026

    Bruce Willis’ Wife Gives Rare Update On Actor’s Dementia Battle

    May 31, 2026
    Stay In Touch
    • Facebook
    • Twitter
    • Pinterest
    • Instagram
    • YouTube
    • Vimeo

    Subscribe to Updates

    Get the latest creative news from SmartMag about art & design.

    Editors Picks

    CNN Staffers Having Meltdown, Fear Bari Weiss Takeover

    June 30, 2026

    “No deseaba nada menos que eso”

    June 30, 2026

    Trump’s Mount Rushmore fireworks show reignites fire fears

    June 30, 2026

    New Trump book, ‘Regime Change,’ has sold 300,000 copies, with more being printed, publisher says

    June 30, 2026
    About Us

    NewsOnClick.com is your reliable source for timely and accurate news. We are committed to delivering unbiased reporting across politics, sports, entertainment, technology, and more. Our mission is to keep you informed with credible, fact-checked content you can trust.

    We're social. Connect with us:

    Facebook X (Twitter) Instagram Pinterest YouTube
    Latest Posts

    CNN Staffers Having Meltdown, Fear Bari Weiss Takeover

    June 30, 2026

    “No deseaba nada menos que eso”

    June 30, 2026

    Trump’s Mount Rushmore fireworks show reignites fire fears

    June 30, 2026

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    Facebook X (Twitter) Instagram Pinterest
    • About Us
    • Editorial Policy
    • Privacy Policy
    • Terms and Conditions
    • Disclaimer
    • Advertise
    • Contact Us
    © 2026 Newsonclick.com || Designed & Powered by ❤️ Trustmomentum.com.

    Type above and press Enter to search. Press Esc to cancel.