Source Details

{
    "source_type": "extension",
    "content_hash": "fb706edb59c3684b4a8ad801537f8358840e1ef525509d91108d6b13bd70c507",
    "submitted_via": "chrome_extension",
    "extension_version": "1.0.18",
    "original_url": "https:\/\/www.nytimes.com\/2026\/09\/17\/well\/ai-drug-discovery-stanford.html?emc=edit_nn_20260918&nl=the-morning&segment_id=226681",
    "parsed_content": "AdvertisementSKIP ADVERTISEMENTSupported bySKIP ADVERTISEMENTA.I. Agents as \u2018Co-Scientists\u2019? This Lab Says They Could Speed Drug Research.A.I. is already a powerful tool for scientific discovery. Now, some biomedical researchers are teaching it to do even more.Listen \u00b7 6:40 min Share full articleJames Zou and his colleagues at Stanford have developed teams of A.I. \u201cco-scientists.\u201dCredit...Ian C. Bates for The New York TimesBy Teddy RosenbluthSept. 17, 2026When John Pak and his collaborators tasked a team of A.I. bots with redesigning part of a Covid-19 vaccine in 2024, he doubted that they would develop something successful or even coherent. At least they\u2019d learn something about the deficiencies of these models, he thought.The lab of A.I. agents had hundreds of conversations to brainstorm, unburdened by the distractions that typically bog human researchers down, like eating or sleeping. They often duplicated themselves and discussed the same topic in five different conversations simultaneously, each of which lasted only a few seconds.As he watched the A.I. agents debate with one another, Dr. Pak, a human scientist who specializes in the kind of research the bots were doing, fought the urge to give them pointers. \u201cTake a step back,\u201d his research partner, James Zou, told him. \u201cSee what they can do.\u201dWithin a few days, the results were in: dozens of novel proteins that would theoretically bind to new Covid variants. Testing showed two of them actually worked \u2014 created at a fraction of the time and cost it would take a lab of humans.AdvertisementSKIP ADVERTISEMENT\u201cIt was shocking,\u201d Dr. Pak said.In recent years, artificial intelligence has emerged as a powerful new tool in drug development, allowing scientists to predict the structure of proteins and how molecules will interact with them. But Dr. Zou\u2019s team at Stanford University is working to develop a future where the technology is doing more than just carry out a researcher\u2019s bidding. He envisions fleets of A.I. agents that work as \u201cco-scientists,\u201d rapidly accelerating the drug discovery process by independently generating hypotheses and running experiments on the computer with the oversight of a human researcher.In a new paper published Thursday in the journal Science, the lab reported on its latest progress: Tens of thousands of A.I. agents predicted which approach to attacking a protein involved in lung cancer would be most effective at treating the disease in clinical trials. Weeks after the experiment started, a large pharmaceutical company announced promising results from a drug that used the same approach \u2014 a coincidence which Dr. Zou said was \u201ca very nice, independent corroboration\u201d of the agents\u2019 work.As fears over A.I.\u2019s potential to create bioweapons or hack into critical infrastructure have ratcheted up, the scientists see this early research as a reason for optimism about some of the technology\u2019s advancements.\u201cIt really does feel like a new era where one person plus a bunch of GPT or Claude models can really make significant, fast progress in drug discovery,\u201d said Kyle Swanson, a former graduate student in Dr. Zou\u2019s lab who was involved in the Covid vaccine research.ImageVirtual labs contain teams of A.I. agents with various specialties, like immunology or computational biology. Credit...Ian C. Bates for The New York TimesDr. Zou first devised the idea of the \u201cvirtual lab\u201d as a way to deal with the mountain of ideas he had \u2014 more than his team could ever possibly tackle.AdvertisementSKIP ADVERTISEMENTIt was led by a \u201cprofessor A.I.,\u201d who compiled a team of other agents with various specialties, depending on the task. In the case of the vaccine problem, it picked immunology, computational biology and machine learning. After a few \u201cmeetings\u201d together, the bots identified a research direction and gave Dr. Zou a list of required research tools.\u201cI\u2019m very jealous that it doesn\u2019t get tired,\u201d Dr. Zou said. \u201cIt just goes 24\/7, and its meetings are so much more efficient than mine.\u201dDr. Zou and his colleagues are still tinkering with the system. For example, the team realized early on that the A.I. agents were too polite to one another during scientific debates, which Dr. Zou said was preventing them from \u201cgetting to the truth directly.\u201dThey made the personas more critical and installed \u201cprofessional devil\u2019s advocate\u201d bots whose task was to poke holes in the other agents\u2019 ideas, and make sure they were not dangerous. Dr. Zou added that a human expert always reviews the agents\u2019 work before any proteins are synthesized in real life, to minimize the risk of developing something harmful to humans.AdvertisementSKIP ADVERTISEMENTDr. Zou and his team are also experimenting with ways to incentivize the bots . (They don\u2019t respond to mortal perks, like raises or promotions.) They created a leaderboard for the agents; top performers were rewarded with more computational resources.The human scientists also have had to periodically jump in to ensure the bots stayed in budget.\u201cThey were sometimes trying to plan out like a multiyear, multimillion-dollar set of experiments,\u201d Dr. Swanson said. \u201cThat would be cool. But I was trying to finish my Ph.D.\u201dOver time, Dr. Zou added thousands more agents to the team and organized them into different departments of a virtual biotechnology company. It was that \u201ccompany\u201d that tackled the lung cancer research.After extensively analyzing scientific studies on a protein called B7-H3 \u2014 a well-known and promising lung cancer drug target \u2014 the agents conducted their own analyses to study how the protein worked in cancer at a cellular level and then recommended the approach most likely to be successful in targeting it.Dr. Zou said the A.I. agents could not have known about the successful trial results from the drug using a similar approach, which was developed by Merck. The bots were not connected to the internet, and the underlying language model had a knowledge cutoff of January 2025. (Merck did not respond to a request for comment.)AdvertisementSKIP ADVERTISEMENTDr. Charles Rudin, who studies this class of drugs at Memorial Sloan Kettering Cancer Center, noted that we wouldn\u2019t necessarily know whether the approach the agents selected was the best, since no other drugs going after this target have been tested in a clinical trial.The research is simply a proof of concept, and there are many parts of the drug discovery process the A.I. bots still can\u2019t do like run experiments with cells in a lab. There\u2019s also an open question of whether the technology can be as successful with another target that hasn\u2019t been as well studied by humans.Still, Dr. Rudin said he thought the study was a \u201cnice example\u201d of how it can accelerate drug development.All in all, the work took the team of agents less than a day and about $46 in computing power.AdvertisementSKIP ADVERTISEMENT",
    "published_at": "2026-09-17T18:00:08+00:00",
    "author_name": "Teddy Rosenbluth",
    "site_name": "The New York Times",
    "section": "Well",
    "publisher": "The New York Times Company",
    "ai_headline": "A.I. Agents as \u2018Co-Scientists\u2019? This Lab Says They Could Speed Drug Research.",
    "ai_simplified_title": "Stanford Lab Uses AI Co-Scientists to Accelerate Drug Research",
    "ai_excerpt": "Researchers at Stanford University are developing A.I. \"co-scientists\" to rapidly accelerate drug discovery by independently generating hypotheses and running computer-based experiments. This approach has already shown promising results in Covid-19 vaccine redesign and lung cancer drug target identification.",
    "ai_subject_tags": [
        "Artificial Intelligence",
        "Drug Discovery",
        "Biomedical Research",
        "Stanford University",
        "COVID-19",
        "Cancer Research",
        "Machine Learning"
    ],
    "ai_context_type": "News",
    "ai_context_details": {
        "tone": "informative",
        "perspective": "neutral",
        "audience": "general",
        "credibility_indicators": [
            "expert_quotes",
            "research_cited",
            "institutional_affiliation"
        ]
    },
    "ai_source_vector": null,
    "ai_confidence_score": 0.9999999999999999,
    "ai_extraction_metadata": {
        "extracted_at": "2026-09-18T19:08:35.679827Z",
        "ai_model": "gemini-2.5-flash",
        "extraction_method": "automated",
        "content_length": 6975,
        "metadata_prompt_body_chars": 6975,
        "metadata_prompt_truncated": false,
        "url": "https:\/\/nytimes.com\/2026\/09\/17\/well\/ai-drug-discovery-stanford.html",
        "existing_metadata": {
            "author_name": null,
            "published_at": null,
            "domain_name": "nytimes.com",
            "site_name": null,
            "section": null,
            "publisher": null
        },
        "openai_refusal_gemini_fallback": false
    }
}

{
    "extracted_at": "2026-09-18T19:08:35.679827Z",
    "ai_model": "gemini-2.5-flash",
    "extraction_method": "automated",
    "content_length": 6975,
    "metadata_prompt_body_chars": 6975,
    "metadata_prompt_truncated": false,
    "url": "https:\/\/nytimes.com\/2026\/09\/17\/well\/ai-drug-discovery-stanford.html",
    "existing_metadata": {
        "author_name": null,
        "published_at": null,
        "domain_name": "nytimes.com",
        "site_name": null,
        "section": null,
        "publisher": null
    },
    "openai_refusal_gemini_fallback": false
}