TimmermanReport.com - Your Edge In Biotech

11 Jul 2026

David Shaywitz

We rely on models — deliberate simplifications — to navigate, make sense of, and engage productively with an ever-more complicated world.

Patients understand their illnesses through what Dr. Arthur Kleinman called “explanatory models.” Physicians use models such as the pathophysiologic model or the biopsychosocial model to integrate their patients’ symptoms and fashion treatments. Biopharma R&D would be impossible without models as well. Every program rests on a series of them, at every stage of the R&D process.

The catch, as Alfred Korzybski observed nearly a century ago, is that the map is not the territory. Unless we recognize the assumptions built into the models we use, we are liable to be led astray — especially because we tend to reach for models that are cognitively accessible, experimentally tractable, or organizationally useful, whether or not they are especially predictive.

Enter Jack Scannell

In a recent interview with Pablo Lubroth of Decibio, Jack Scannell offers an eloquent and deeply resonant account of the role of models across R&D, highlighting not only their limitations but, more interestingly, why we continue to rely on them. He conveys a deep familiarity with the lived experience of R&D — the critical tacit knowledge that other biopharma veterans will immediately recognize.

Jack Scannell

Scannell, a longtime analyst of drug R&D productivity who now runs the early-stage biotech Etheros, is perhaps best known for coining “Eroom’s Law”: the depressing observation that, from 1950 to roughly 2010, the number of new drugs approved per inflation-adjusted billion dollars of R&D spending fell by about half every nine years. The name is “Moore” spelled backward — a pointed contrast with Moore’s Law, the emblem of exponential progress in computing.

Within R&D, Scannell highlights problems with both the financial and biological models on which the industry relies. I’ll focus mostly on the biological side and simply note that his assertion that “standard drug and biotech valuation models are blind to decision quality,” making companies less sensitive to the value of better decisions, especially early in development.

Reductive Models in Biology

The key biological question Scannell — and really everyone in drug R&D — wrestles with is how to think about something as complex as human biology in a way that allows you to develop a medicine, introduce it into the midst of all this complexity, and have reasonable confidence that it will improve a particular condition without doing harm elsewhere.

It takes a prodigious amount of chutzpah to believe we can do this. The many remarkable medicines that have been developed deserve to be celebrated.

In the words of Dr. Roger Perlmutter, former head of R&D at Merck, “we have no idea what we’re doing.” He continues, “It’s a bloody miracle if you ever make a drug that works.”

To manifest such miracles more reliably, biopharma — following the lead of medical science — has leaned heavily into reductionism: the idea that we can best understand life by breaking complex processes down and studying their individual components.

This has worked especially well for monogenic diseases, conditions that result from a single catastrophic glitch that can be targeted and, ideally, remediated.

It has also encouraged a focus on individual targets, often receptors, and on developing the most potent possible binders. These assays are especially attractive because they are amenable to scale: you can evaluate a huge number of candidates in a high-throughput fashion.

This approach can be effective. But it can also generate premature confidence, since identifying a great ligand is not the same as finding a promising drug candidate. Tight binding to an individual target may be useful to select for, while still failing to predict physiological promise in the organism as a whole.

When Clean Stories Meet Messy Biology

Highly reductionist approaches tend to struggle with complex diseases and psychiatric conditions, Scannell explains, noting “drugs don’t know they’re meant to bind a target,” and often turn out to bind multiple targets at once. Some of the most effective drugs we have, he says, may be more like “magic shotguns” than “magic bullets.”

In psychopharmacology, for instance, clozapine — the only drug approved specifically for treatment-resistant schizophrenia — binds dopamine, serotonin, histamine, muscarinic, and adrenergic receptors. After more than fifty years of research, its mechanism of action remains unclear and debated. Its clinical efficacy may depend on this promiscuity across receptor systems rather than any single interaction.

Clozapine is also a reminder of what highly reductionist approaches can miss. A target-first assay tends to reward exceptional activity against a specified interaction. A phenotypic readout may capture a pattern of modest effects across many interactions — a profile that might look unimpressive receptor by receptor, yet prove meaningful in the organism.

The broader point is not confined to clozapine and psychopharmacology. Some TKIs developed against specific kinase targets turned out to inhibit panels of kinases, and their clinical activity may depend on this broader activity. “In large parts of psychopharmacology,” Scannell explains, “there’s no easy relationship between pattern of binding across receptors and phenotypic impact on people.” He adds that we can confuse “neat stories about targets, creation myths, with how drugs actually work.”

He also points out that a number of drugs approved before the target-centric era — medicines like metformin, the first antipsychotics, and the first antidepressants — have messy or contested mechanisms. Metformin has been attributed to AMPK activation, mitochondrial complex I inhibition, and effects on gut microbiota, with little consensus around a single unifying mechanism. Chlorpromazine and the first antidepressants were discovered empirically, with mechanistic stories built around them later.

Even targeted drugs with seemingly clear mechanisms can become more complicated over time. Anti-VEGF therapy, for example, emerged from Judah Folkman’s elegant insight that tumors depend on angiogenesis. But subsequent work, especially by Rakesh Jain, suggested an additional mechanism: anti-VEGF agents may transiently normalize chaotic tumor vasculature, improving delivery of chemotherapy. The original story was not so much wrong as incomplete — a reminder that even elegant mechanistic stories tend to get more complicated as we learn more.

A Little More Predictive Validity Goes a Long Way

Scannell has particularly emphasized the importance of improving disease models — increasing the “predictive validity” of the systems in which drug candidates are studied. He notes that while everyone recognizes that good models are better than bad models, the less obvious point is that “marginally better models are much better than marginally worse models.” A model that improves predictive ability even slightly can be more valuable than running ever more compounds through a less predictive system.

By contrast, he warns that “feeding AI with data from poor biological models simply increases the number of wrong answers you can generate per second.” He worries that some AI drug-development companies may industrialize a poor biological model because it is easiest to fit “into an AI-led design-make-test loop” — leading at best, he says, to virtual ligands optimized against a good in silico representation of an irrelevant biological system. Other companies, he encouragingly notes, appear more focused on using AI to develop better biological models.

Why Flawed Models Endure

Given the obvious value of improved models, why are they so hard to come by? Asked differently, what makes existing models so sticky?

The answer, Scannell suggests, comes down largely to incentives.

Academic researchers, he explains, are not rewarded for the slow work of model validation. You “do not get Nature papers by doing long, tedious, gritty work to evaluate whether a particular mouse model of disease X recapitulates the human pathology and then responds the same way to drugs that have been in people,” he says.

Industry researchers, for their part, desperately want better models but are not always incentivized to invest in developing them. A validated model may quickly become useful to everyone, eroding any competitive advantage. Moreover, Scannell explains, while industry scientists may privately acknowledge the limitations of their models, admitting this too directly could threaten the programs built on them.

At the portfolio level, simpler explanations often prevail over more nuanced accounts. Scannell shares a thoroughly relatable story about a colleague preparing to present a project to a portfolio management committee at a mid-sized pharma. The colleague had slides with “really complicated maps and models of biological pathways.” Before the meeting, he was told to come back with something much simpler: “three or four boxes and a couple of arrows,” otherwise “the board would never approve it.”

Context Matters

Perhaps Scannell’s most important observation involves a distinction he borrows from innovation scholar Fred Steward: the difference between “technoscientific” problems and “sociotechnical” problems.

A technoscientific problem, Scannell says, is “like the classic Apollo moonshot” — a problem that can be solved with enough engineers and enough funding.

Sociotechnical problems, by contrast, involve “a complicated mix of economic, regulatory, and process changes happening simultaneously over time.” He cites the building of modern healthcare systems as an example and believes AI in R&D likely falls into this category.

On the process side, he explicitly cites the classic work from Stanford scholar Paul David that I’ve discussed before, on how the arrival of electricity itself did not immediately improve factory productivity. The benefits came later, when electricity allowed factory work to be reorganized. The new technology mattered, but the impact was felt only after the structure of work changed around it.

“I suspect that no one really knows what the reconfigured factory is going to look like when it comes to AI in drug R&D,” Scannell wisely observes — a statement that could apply just as well to the application of contemporary AI across healthcare.

It also speaks to the remarkable opportunity now before us, from biopharma R&D to disease prevention: to use emerging technologies such as AI to reconfigure the work itself, improve the models on which we rely, and turn better models into better decisions — decisions that help us stay healthy longer and, when we become patients, receive treatments more likely to work.

Jun

2026

Precision Cancer Drugs and Combos: Troy Wilson on The Long Run

The Long Run with Luke Timmerman · Ep204: Troy Wilson on Precision Cancer Drugs and Combos

30 Jun 2026

Troy Wilson is today’s guest on The Long Run.

Troy is the co-founder and CEO of San Diego-based Kura Oncology. The company, founded in 2014, has gone all the way through R&D to develop its own novel cancer drug. It’s called ziftomenib (brand name Komzifti). It’s an oral pill that inhibits a target called menin. Ziftomenib was approved by the FDA in November 2025, initially for a small set of patients with acute myeloid leukemia who have specific genetic alterations such as NPM1 mutations or KMT2A rearrangements.

Troy Wilson, CEO, Kura Oncology

This is the start. Kura hopes to demonstrate the drug can help a broader group of patients with AML – a notoriously tough to treat cancer.

Not many biotech startup companies make it all the way through the R&D gauntlet to develop an FDA approved medicine. Kura is also hopeful lightning will hit twice, with another drug called darlifarnib. It’s a farnesyl transferase inhibitor (FTI) inhibitor. Scientists at the company believe this entire class of FTI medicines – once written off as a pharma graveyard – is due for a comeback, especially as it logically ought to complement the new breakthrough RAS inhibitor, daraxonrasib, from Revolution Medicines.

Troy arrives at this auspicious moment in cancer R&D after a long and distinguished career. He co-founded three previous companies that ended up being successfully acquired – Intellikine, a PI3kinase inhibitor company acquired by Takeda; Ambrx, a developer of antibody-drug conjugates acquired by Johnson & Johnson; and Avidity Biosciences, the developer of antibody oligonucleotide conjugates for rare muscular diseases acquired by Novartis.

The Long Run is sponsored by:

AI has advanced from pilot programs into real biopharma workflows. But has it lived up to the hype? Drawing from an expert call with Dr. Paul Agapow, former director of data science at GSK, this report dissects whether AI is on track to make drug development faster, cheaper, and more successful. Learn how AI is reshaping drug development in real time, turning AI execution into a key competitive differentiator.

Now please enjoy this conversation with Troy Wilson on The Long Run.

Jun

2026

The Rise, Fall, and Rise (and Fall…?) of Cell and Gene Therapy

Carl Schoellhammer

29 Jun 2026

Carl Schoellhammer, partner, DeciBio

More than $14 billion in announced acquisition value has flowed into in vivo cell therapy companies over the last 18 months. Lilly acquired Kelonia, AbbVie bought Capstan, BMS acquired Orbital, and AstraZeneca bought EsoBiotec, to name a few.

These acquisitions demonstrate that we’re getting closer to the day when single injections that reprogram cells can fight disease without complex shipping logistics, waiting times and toxic preconditioning regimens of first-generation ex vivo cell therapies.

Over the last decade, the cell therapy field has experienced extraordinary breakthroughs and painful corrections. And yet, just as it has emerged from its first major boom-and-bust cycle with hard-won discipline, in vivo cell therapy is generating the kind of excitement that should, by now, feel familiar.

The first modern wave of cell and gene therapy was built on scientific breakthroughs. CAR-T therapies demonstrated that living medicines could deliver long-lasting remissions for cancer patients who were facing a death sentence. Early AAV therapies showed that a single treatment could meaningfully alter the course of genetic disease. It was heady stuff. Investors responded accordingly.

During the pandemic-era biotech boom, capital flooded the sector in search for the next company like Moderna, with a platform technology with broad potential for multiple diseases, like messenger RNA vaccines. Every company seemed to need a cell and gene therapy strategy.

Looking across DeciBio’s TheraTrack database, there was a period where the average indication being addressed (across oncology, rare disease) attracted more than four gene therapy assets and more than 10 cell therapy assets in development. Multiple companies chased the same diseases with limited differentiation. Capital poured in faster than market realities could justify, and scientific possibility increasingly became confused with commercial inevitability.

The sector delivered effective, generally durable treatments, not the one-and-done “cures” the market was promised. The resulting correction was severe, but necessary.

Today, several approved cell and gene therapy products have reached blockbuster status (Table 1). Sectors written off by some investors as dead in 2022 have steadily continued to attract smaller, but still meaningful investments and generate significant transaction value (Figure 1). The manufacturing challenges that once seemed existential are being converted, steadily, from scientific uncertainties into engineering problems.

The correction hurt. It also forced companies to step up their game.

Table 1: Blockbuster cell and gene therapy products

Figure 1: Investment and financings into AAV-based biotech companies

Which brings us to today’s newest source of excitement: in vivo cell therapy. Rather than extracting cells from a patient, engineering them in a manufacturing facility, and reinfusing them weeks later, why not engineer those cells directly inside the body? In theory, this approach could simplify treatment, reduce costs, shorten timelines, and dramatically expand access.

Many of today’s talking points from companies echo the promises made during the first cell and gene therapy boom. Manufacturing will be simplified, costs will fall, and platform technologies will unlock dozens of indications. Investors and companies have flocked to the sector. But who is left to buy the next wave of companies?

The most logical strategic buyers have largely committed. That leaves a meaningfully thinner pool of potential acquirers for the companies now raising capital, building platforms, and conducting early-stage trials. Exit paths matter, and the number of natural buyers for the next cohort may be more limited than the current pace of investment implies.

Manufacturing Challenges Ahead

One of the most common narratives surrounding in vivo cell therapy is that it eliminates manufacturing complexity. It is more complicated than that. In many cases, we may simply be trading one manufacturing challenge for another.

Consider a targeted LNP-based system. Production involves at least three distinct steps, each requiring purification and each introducing yield losses: synthesis of the mRNA cargo, formulation and encapsulation within the lipid nanoparticle, and conjugation of the targeting ligand to the LNP surface. Losses compound at every stage.

Beyond yield, the chemistry itself is not trivial. Conjugating antibodies or peptides to lipid nanoparticle surfaces introduces questions around conjugation efficiency, batch-to-batch consistency, and analytical characterization that the field is still working through.

Then there is the CDMO problem. Targeted LNP products sit at the intersection of lipid chemistry, biologics manufacturing, nanoparticle formulation, and conjugation science. While each capability exists independently, relatively few organizations have deep expertise across all of them within a single integrated process. As these programs scale, developers will need to navigate manufacturing execution and increasingly complex analytical, comparability, and regulatory expectations.

Longer Term Questions

Clinical reality will also eventually arrive. As programs move into larger patient populations and longer follow-up periods, new questions will emerge around safety, durability, repeat dosing, and immune responses.

Cell and gene therapy has never been a story of failure. It has been a story of overestimation followed, more quietly, by real progress.

The danger today is that we once again mistake early promise for inevitability. If the field applies the lessons learned from AAV and CAR-T, the next decade could be transformative. If not, we may simply be boarding the next rollercoaster before the last one has finished its climb.

Jun

2026

AbbVie Acquires Apogee, FDA Changes Tune on RegenxBio, & Merck Seizes TL1A Lead

25 Jun 2026

Please subscribe and tell your friends why it’s worthwhile. Quality journalism costs money. When you subscribe to Timmerman Report at $199 per year, you reward quality independent biotech reporting, and encourage more.

Subscribe Now

Jun

2026

Ollin Advances with $330M to Challenge Roche in DME & Wet AMD

Jun

2026

Kardigan Continues IPO Trend & FDA Reconsiders UniQure and Moderna

Jun

2026

Small Molecules To Correct Disease: Sri Kosuri on The Long Run

The Long Run with Luke Timmerman · Ep203: Sri Kosuri on Small Molecule Correctors of Disease

16 Jun 2026

Sri Kosuri is today’s guest on The Long Run.

Sri is the co-founder and CEO of Emeryville, California-based Octant Bio. The company is developing oral small molecule drugs that are designed to correct protein misfolding and mistrafficking. Quite a few rare diseases, cancers, and metabolic disorders are thought to be amenable to this strategy.

Sri Kosuri, co-founder and CEO, Octant Bio

Octant’s work starts with a platform designed to capture relevant information about these cell processes that go awry. But like any platform company, it needs to demonstrate its value in the form of new drug candidates.

Octant’s lead drug candidate is for rhodopsin-associated autosomal dominant Retinitis Pigmentosa. It’s caused by a gene mutation which causes misfolded proteins to accumulate in the retina. That leads to progressive vision loss over time. The Octant drug candidate, which entered its first clinical trial in March, is intended to help improve low-light vision and halt disease progression.

Sri has a wide range of experiences in academia and in industry. He and his colleagues are seeking to build on recent advances in technology to discover oral small molecules that not only make a big difference for patients, but which ought to be widely accessible to the vast majority of people in need.

The Long Run is sponsored by AlphaSense

Bioanalysis should not rely on which scientists at the CRO you get. These are assays, not consulting. Your results should be the same, regardless of who does the work.

“We love working with our CRO… when we get the right PI” is a red flag, not a compliment. And if the quality of your bioanalysis depends on which principal investigator happens to be assigned to your study, you don’t have a CRO partnership, you have a lottery ticket.

Dash was built around automation and standardized workflows specifically to eliminate that variability. Every study gets the same rigor and the same rapid turnaround, days not weeks, across ELISA/MSD, LC-MS, and PCR. GLP-compliant, transparent pricing, guaranteed outcomes. You shouldn’t have to ask who’s running your study. You should just get great data.

Visit www.dash.bio

Now please enjoy this conversation with Sri Kosuri on The Long Run.

Jun

2026

Parabilis IPO Pops, J&J Buys More Degraders, & GSK’s Precision Oncology Bet

Jun

2026

City Therapeutics Pockets $99.5M, Advances RNAi Candidates to the Clinic

Jun

2026

Wellness Tech: Don’t Use as Directed

06 Jun 2026

David Shaywitz

The Great Technology Plan for Wellness, to simplify only slightly, envisions a path to health that runs through data: collect more (through wearables and blood tests), analyze with AI, and deliver personalized coaching that improves as the data grow and the models sharpen.

It sounds sensible, and one day it may even deliver — I’m long-term optimistic.

But today it seems largely precision health theater; our ability to offer advice that is both meaningfully personalized and scientifically valid is remarkably limited, as Kevin Hall persuasively demonstrated in the case of continuous glucose monitors for non-diabetics (the instruments are unquestionably valuable for those with diabetes).

In fact, if you use tech wellness platforms as directed — intensively pursuing metric maximization — there’s a decent chance you’ll wind up feeling worse. A slew of adverse consequences are starting to be described, from orthosomnia (trouble sleeping because you’re obsessed with sleep metrics) to orthorexia (the obsessive pursuit of “perfect” eating). A New York Times feature introduced us to “Oura paranoia,” a debilitating obsession with the data from your wearables; one user described it as a constant effort to hit metrics in order to “make the ring happy.”

Or consider how Rachel Feinzeig described her time on her exercise bike: “I get on my Peloton and am confronted with a veritable dashboard of my inadequacies: cadence (sluggish), resistance level (embarrassing), output (am I even alive?).”

Do these platforms actually enhance health? So far, the data aren’t compelling. Several comprehensive academic reviews — one in 2022, another in 2025 — found solid evidence of wearables increasing physical activity (slightly), but mixed results on actual health impact.

If there is a benefit, it may come not from data-driven optimization but from the effect of these platforms on mindset — the degree to which they reinforce your sense that you’re the sort of person who cares about their health, and supply dynamic visible evidence of your commitment to it.

Mindset Matters

Mindset, as a mechanism, is surprisingly powerful. A classic 2007 Harvard study examined hotel workers who viewed themselves as doing very little activity. One group was told (accurately) that their daily work already met the criteria for an active lifestyle; the other was told nothing. Four weeks later, the informed group had significantly reduced their body weight, body fat, and blood pressure compared to the control group — apparently driven simply by the shift in mindset, since their actual activity did not change.

The impact of self-belief shows up at the population level too, across a much longer horizon. Examining national samples of over 60,000 adults followed for up to 21 years, researchers found that people who believed they were less active than others their age were far more likely to be dead at follow-up — even after adjusting for a range of risk factors, including actual activity. Believing yourself sedentary independently predicted earlier death, even after accounting for how much you actually moved. To be clear, moving more genuinely is associated with better health; the surprise is that mindset adds to it, independent of the activity itself.

A large CVS/Aetna analysis points in the same direction. Members enrolled in a wearable-and-incentive program incurred in the first year roughly $10 less in monthly medical spending than matched non-enrollees — and the savings came almost entirely from fewer non-emergent emergency room visits and reduced specialist and mental-health visits. That looks less like bodies that grew healthier than like people who found themselves in a better headspace and made different decisions about when and where to seek care.

But belief cuts both ways. In a 2023 study, people wearing an Apple Watch received manipulated feedback about their walking: one group saw a step count deflated by 40%, another saw it inflated by 40%, and a control group saw the truth — about 7,000 steps for all of them, well above the US background level of around 4,000. Compared to controls, the deflated group (seeing ~4,200) ate worse, felt worse, and had higher blood pressure and heart rates after four weeks. The inflated group (~9,800) didn’t differ from controls — probably because 7,000 and 9,800 read as much the same, while 4,200 reads as meaningfully low.

What stands out is what didn’t move. The belief reliably changed how people felt, what they ate, and how their bodies registered — heart rate, blood pressure — while the walking itself stayed essentially flat. The mindset shifted; the behavior it was ostensibly about did not follow.

The sports performance literature, by contrast, is replete with cases where inflated feedback shifts mindset and behavior together. Endurance runners given fake EPO ran measurably faster; runners told (falsely) they’d scored above average lifted their VO₂max on retest; cyclists on placebo ergogenics produced measurably more power — gains generally in the 1–5% range. Inflated feedback seems to work when it targets a salient, actionable performance gap, which “7,000 versus 9,800 steps” apparently wasn’t.

Mindset, then, reliably moves how you feel, how you eat, and how your body responds. Whether it moves what you actually do is a separate question — sometimes it does, as the large wearable reviews and the sports studies show, and sometimes, as with those manipulated step counts, it doesn’t. A changed mind doesn’t automatically become a changed life, and belief still has to be translated into durable action.

The initial challenge is how to influence mindset — which is where Dr. Peter Attia, author of Outlive, joins the story. Attia, as best I can tell, has motivated far more people than the many sensible physician- and scientist-authors who urge readers to eat deliberately, move joyfully, and connect with others — exactly the right advice. Attia urges much the same thing, but wraps it in exceptionally specific, detailed protocols, a concrete, actionable-sounding roadmap that gives people something to grip in a way the other authors, very reasonably, do not.

Yet the readers likely to benefit most from Attia aren’t the ones who adhere to his script with religious zeal; it’s those who absorb the spirit and believe they now have a place to start — who take prevention more seriously even if they never get the comprehensive bloodwork he favors, for example. Attia provides a useful scaffold that falters when it’s taken as an inviolable prescription.

Proof, Not Precision

Many wellness tech platforms, I suspect, work the same way. For users engaging with these platforms in the most healthy fashion, quantification isn’t really delivering precision so much as proof. A step count takes an ordinary walk and turns it into evidence — evidence you can see, and show, that you’re the sort of person who moves and pays attention. The hotel workers got that validation in a sentence, but most of us would wave a sentence away; we trust a number on a screen far more than a pep talk – perhaps because a number aligns better with our technology-inflected explanatory model of health.

For many people, the palpability of this receipt is what makes the effort feel real enough to keep making. That is what these platforms can offer — not the optimization they advertise, but the sense of being someone who takes their health seriously, and a place to act on it. (Supplements may work in much the same way, contributing more directly to identity than biology.)

It’s also worth noting that while so much of today’s data-driven personalization looks like theater, the same companies patiently collecting reams of biometric data may be building something genuinely valuable: a longitudinal asset that assesses each individual against their own trajectory rather than against population norms. This is the approach Nathan Price, Professor and Co-Director of the Center for Human Healthspan at the Buck Institute and Chief Scientific Officer of Thorne, has championed for years, and described in his prescient 2023 book with Lee Hood, The Age of Scientific Wellness.

At some point we’ll hit the inflection between theater and real value. Until then, if we’re going to embrace tech wellness platforms, let’s make sure we’re not holding on too tightly — and that the platforms are serving us, rather than the other way around.

Jun

2026

RevMed’s Moment in the Sun, In Vivo CAR-Ts Shine & NewLimit’s Healthspan Haul

Jun

2026

Beyond Language: Why Drug Discovery Needs a Different Kind of AI

Woody Sherman

03 Jun 2026

Woody Sherman, chief innovation officer, PsiThera; Chair of the OpenFold Consortium Executive Committee

In wet labs and dry labs, investor meetings, and medical conferences, it’s impossible to avoid discussions about how AI is transforming the way medicines are discovered.

It is and it isn’t.

This “AI in drug discovery” dogma gets something wrong. It assumes that “AI in drug discovery” is one thing. It is not. It’s true that AI systems help drug discovery teams work faster by organizing information, automating tasks, and, most tantalizingly, generating plausible ideas for future medicines at unprecedented speed.

But there’s still a lot missing. This is language-based AI. Faster, more organized work through large language models is not the same as better prediction of the properties of a physical structure in a live organism. The hardest question in drug discovery remains stubbornly tied to the physical world, not the digital one: which molecules will actually work in biology’s messy, dynamic environment?

To materially improve drug discovery, we need to distinguish between systems that organize information with language and systems that predict physical reality. Until the field makes the distinction between orchestrating and predicting, capital and scientific effort will continue to flow toward the wrong problems, and patients will wait longer than they should for new medicines.

Language-Based AI Is a Powerful Start. Drug Discovery Needs More.

The most visible AI systems today — including ChatGPT, Claude, and Gemini — are built to recognize patterns in symbolic information such as alphabets, sequences, and other structured data. They are already proving useful in drug discovery, from helping teams search information, summarizing knowledge to generating hypotheses and working more efficiently.

What makes drug discovery hard is that every promising molecule must pass through a gauntlet of physical tests rooted in chemistry, biology, and pharmacology. What matters is the physical properties of these molecules in the real world, not just in how language can describe them. Language- based AI can help summarize and classify what we already know. What it cannot do, at least not on its own, is reliably predict the physical properties that determine whether a molecule will actually work in a cell assay, animal model, or human patient. That is the gap Physical AI is meant to close.

Why Physical AI Matters

An AI system trained on airplane blueprints might generate plausible aircraft designs, but engineers would never skip aerodynamics, simulation, wind tunnels, stress tests, and flight testing. Drug discovery is similar. A plausible molecule is only a starting point. The real challenge is predicting whether it will survive the experimental and physical tests imposed by biology along the path of discovery, pre-clinical studies, and human trials.

Physical AI operates on a similar logic. It is built to predict how real systems behave under chemical, biological, and time constraints. In drug discovery, that means predicting molecular behavior: binding, motion, solubility, permeability, metabolism, toxicity, exposure, pharmacology, and more.

This matters because drug discovery is fundamentally about how molecules behave inside and outside the cell. A molecule does not become a medicine because it is an interesting idea, or even because it looks plausible in a model. It becomes a medicine only if it behaves correctly in the crowded, complex, dynamic environment of cells that give rise to life. Predicting that behavior is the central challenge.

Different problems will require different forms of prediction: synthesis, binding, solubility, permeability, metabolism, toxicity, exposure, and pharmacology, each of which imposes different physical constraints and require different data. To succeed, physical AI will not use one predictive model. It will be a system of task-specific models, simulations, experimental feedback loops, and decision tools.

Molecular representation matters, too. Many current AI systems still treat molecules as strings or flat diagrams. But in drug discovery, molecules are 3-dimensional entities that change shape and properties within the crowded and changing biological environment. Small changes can have enormous consequences. Move one atom, change one bond, or alter one geometric arrangement, and a molecule can bind differently, distribute in the body differently, cause toxic effects, or fail entirely. Molecules are not static sketches. They are dynamic physical objects defined by electron clouds, geometry, motion, and quantum-mechanical interactions with their surroundings. Better prediction requires models that treat molecules much closer to that reality.

The practical lesson is simple: molecule generation is not molecule optimization. The real value in drug discovery comes not from proposing more molecules, but from learning faster which ones are actually worth making, and why. This is not just a scientific distinction. It is a practical framework for deciding where to invest capital, talent, and attention. The relevant question is no longer whether a company uses AI. It is which decisions its AI improves, how much those decisions improve, and whether those decisions ultimately lead to better medicines.

In other words, the key distinction is not between companies that use AI and companies that do not. It is between AI that helps scientists navigate existing information and AI that helps them predict behavior of novel molecules. Both matter. The first can be helpful is speeding up existing processes. But only the second can improve the odds that a molecule will become a medicine.

The Real Test: Scientific Leverage, Not Workflow Efficiency

Real progress in AI for drug discovery should not be judged only by whether it makes teams move faster. It should be judged by whether it creates scientific leverage: better decisions about what to make, what to test, what to stop, and why.

A useful rule of thumb: be skeptical when a system is easy to demo but hard to validate. In drug discovery, the most valuable models are often not the ones that produce the flashiest outputs, but the ones that quietly help teams avoid bad bets and make better molecules.

Language-based AI will absolutely be part of the future of drug discovery. It will help search the literature, map the competitive landscape, write code, coordinate teams, and increasingly orchestrate closed-loop laboratories that connect prediction, experiment, and decision-making. It will make discovery organizations more nimble, better informed, and better coordinated.

Better prediction will also require better infrastructure. Progress in drug discovery depends not just on clever models, but on rigorous benchmarks, blind challenges, and the ability to scale. It also depends on infrastructure that is open, extensible, and designed for others to build on, much like shared platforms in the technology world have accelerated innovation far beyond what any one company could do alone. Not everything needs to be open, but not everything can be built from scratch within a single organization.

One especially promising area is co-folding, where the field has made striking progress in predicting biomolecular structure — progress significant enough to be recognized with the 2024 Nobel Prize in Chemistry. But structure alone is not enough. The next step is to connect those models to molecular recognition, energetics, mechanism, and design — the things that determine whether a structure is merely interesting or actually useful for making medicines.

This is the premise behind work done with my academic collaborators, colleagues at PsiThera, and the OpenFold community on “Grand Challenges for Predictive Modeling in Small Molecule Drug Discovery.” The impact of AI will ultimately depend on whether it helps teams predict which molecules to make next, which risks to prioritize, and which compounds have a realistic path to becoming drugs.

For investors and managers, that distinction matters. It separates operational efficiency from scientific leverage. The most important question is not whether a company can generate plausible outputs, but whether its technology improves real molecular decisions in ways that change asset quality, cycle time, capital efficiency, and ultimately probability of success.

That is the standard the field should reward: prospective validation over retrospective storytelling; physically grounded prediction over pattern matching alone; and open, extensible infrastructure over black-box claims that are difficult to test. If drug discovery makes that shift, AI will not merely accelerate existing processes. It will change how new medicines are found.

Woody Sherman, Ph.D., is the chief innovation officer of PsiThera and Chair of the OpenFold Consortium Executive Committee

Jun

2026

Reimagining Science for the AI Era: Becky Pferdehirt on The Long Run

The Long Run with Luke Timmerman · Ep202: Becky Pferdehirt on Reimagining Science for the AI Era

02 Jun 2026

Becky Pferdehirt is today’s guest on The Long Run.

Becky Pferdehirt, CEO, Radial

Becky is the CEO of Radial, the Emeryville, CA-based life sciences division of the Astera Institute. The nonprofit made news in March when it committed $500 million to Radial with a mission to reimagine data generation, sharing, infrastructure and tools necessary to create the best conditions for AI to help solve biological problems. Becky called it “unglamorous, unsexy infrastructure and tools” in an interview with STAT.

Becky comes to this work with a wide range of experiences in science. She started in academia, moved to industry labs, and eventually migrated to the business side of the biotech industry. She was most recently on the investing team at Andreesen Horowitz’s Bio & Health Fund.

This episode is about a fundamental question that a lot of people are wrestling with – how to lay down the ideal conditions for biology to thrive in the age of AI.

The Long Run is sponsored by:

AI has advanced from pilot programs into real biopharma workflows. But has it lived up to the hype? Drawing from an expert call with Dr. Paul Agapow, former director of data science at GSK, AlphaSense has a new report that dissects whether AI is on track to make drug development faster, cheaper, and more successful. Learn how AI is reshaping drug development in real time, turning AI execution into a key competitive differentiator.

Download the Report

Bioanalysis should not rely on which scientists at the CRO you get. These are assays, not consulting. Your results should be the same, regardless of who does the work.

Dash was built around automation and standardized workflows specifically to eliminate that variability. Every study gets the same rigor and the same rapid turnaround, days not weeks, across ELISA/MSD, LC-MS, and PCR. GLP-compliant, transparent pricing, guaranteed outcomes. You shouldn’t have to ask who’s running your study. You should just get great data.

Visit www.dash.bio

Now please enjoy this conversation with Becky Pferdehirt on The Long Run.

May

2026

Vaccines Get a Boost, Apogee Hunts Down Dupixent, GSK Raises the Bar in HepB

May

2026

Summer Content Recommendations

24 May 2026

David Shaywitz

Back by popular demand – my highly curated list of summer content recommendations for TR readers.

Books

Inside the Box – David Epstein

By now, you’ve read, or should have read Range, David Epstein’s previous book and his paean to generalists (my reflections here). Now, he introduces us to an intriguing paradox – the unexpected power of constraints to inspire greater creativity and productivity. It’s his most Gladwellian, for better (an intriguing read) and worse (conspicuously tidy at times), but it will absolutely keep you thinking long after you’ve finished. Bonus feature: the audiobook is read by the author, which I always prefer and applaud.

AI for Good – Josh Tyrangiel

I reviewed this book for the WSJ, and discussed in a recent TR, but it’s worth flagging again here because of its savvy focus on implementation challenges, and the many human-related barriers aspiring AI champions need to overcome.

A Giant Leap – Robert Wachter

Same story: I also reviewed this for the WSJ, and cited in passing in several TR columns (eg here). The book deserves highlighting because of the unusually good job Dr. Wachter does in contextualizing not only AI but technology more generally within the complex process of healthcare delivery.

The Future of Seeing – Daniel Sodickson

Dr. Daniel Sodickson, the author of this wonderful account of the history of imaging, is (disclosure) a med school classmate and friend, and his deep knowledge, visceral enthusiasm, and wry humor practically leap from every page. He delivers a fascinating look at the past, present, and possible future of extraordinary imaging technologies – as well as a warm introduction to the people responsible.

The Way of Excellence – Brad Stulberg

Brad Stulberg, a prominent executive coach and popular writer and podcast host (“Excellence, Actually”) has written an appealing guide to performance excellence, one that eschews quick fixes in favor of sustained engagement. While shading a bit aphoristic and “coachy” for my taste, the underlying substance is remarkably solid and informed by evidence; there’s a real “there” there.

Outlive – Peter Attia

This book, by Dr. Peter Attia (whose reputation was tarnished this year after his association with Jeffrey Epstein was revealed) is on the list more than a year after we discussed the book in TR. Why? Because while many physician-authors have written knowledgably about healthy living, Attia’s book seems to have motivated – truly lit a fire under — far more people (including more physicians) than most other similar books I’ve read, including many that (in my view) are scientifically on target with their shared lifestyle message of eat thoughtfully, move joyfully, and connect with friends and community. Somehow, in Attia’s hands, the message seems more compelling. I clearly don’t share his obsession with relentless optimization, but his book, together with some lessons from (David!) Epstein on constraints, make me wonder if there’s some real value in offering at least a modicum of gratuitous specificity.

Blogs

Two recommendations here, both available without charge: the always rigorous Ground Truths, from Dr. Eric Topol, and the recently-launched Substance Over Noise, from Dr. Michael Albert.

Podcasts

Ground Truths: Eric Topol spends quality time with science newsmakers; he’s apparently become a mandatory stop for authors who’ve just launched a book. The happy result: consistently interesting and timely discussions.

Recommended recent episode: Topol’s chat with Sebastian Mallaby author of The Infinity Machine.

The Future of Everything: Stanford’s Russ Altman speaks with leading scholars (generally from Stanford) at the cutting edge of a range of fields, making for especially thoughtful discussions.

Recommended recent episode: Altman’s conversation with communications professor Angèle Christin on influencers.

Business History: I’ve highlighted this show before, and it’s remained one of my favorites – tight, engaging stories about (yes), the history of a particular business.

Recommended recent episode: history of Veuve Clicquot champagne.

Acquired: Also previously recommended, and also still good – very deep dives into specific businesses.

Recommended recent episode: John Bogle and Vanguard – “the most effective vehicle ever created for participating in the fruits of American capitalism.”

Approved: This is a highly recommended, relatively new podcast hosted by Alex Kesin and Matthew Pech. Essentially “Acquired” but for FDA-approved drugs, the show features deep dives into the history of how the medicine came to be.

Recommended recent episode: history of Keytruda – a captivating story I’ve discussed in detail here (also referenced by the show).

The Happiness Lab: A return appearance by a perennial favorite. Hosted by Yale professor Laurie Santos, the show features thoughtful, accessible interviews with experts around topics in positive psychology.

Recommended recent episode: interview with Shawn Achor, author (most recently) of The Power of Beliefs.

NEJM-AI Grand Rounds: A podcast hosted by Raj Manrai and Andrew Beam, featuring discussions with leaders at the intersection of AI and medicine. I’ve highlighted the show before, and it remains excellent.

Recommended recent episode: fascinating discussion w Travis Zack, the CMO of Open Evidence (my TR on Open Evidence here).

Of course, TR readers will continue to enjoy and appreciate Luke’s always captivating interviews with biotech leaders on The Long Run.

Finally: have a great summer! Savor the opportunity to move outside, connect with family and friends, enjoy late dinners in the delightfully warm air. Find a few minutes to reflect on what’s most important to you, and pursue meaningful engagement – with people, ideas, interests, communities.

Be kind and be well.

– David

May

2026

Lilly’s Triple-G Delivers, Parabilis Eyes IPO, & Regeneron’s LAG-3 Whiff

May

2026

Biotech in the Balance: Saving a Strategic Industry. Jeremy Levin on The Long Run

The Long Run with Luke Timmerman · Ep201: Jeremy Levin on Biotech in the Balance

19 May 2026

Jeremy Levin is today’s guest on The Long Run.

He is the executive chairman and founder of New York-based Ovid Therapeutics. He’s also a board member of the Biotechnology Innovation Organization, and a past chairman of the BIO board of directors.

Jeremy Levin, executive chair, Ovid Therapeutics

Jeremy has a new book out today, called “Biotech in the Balance: Saving a Strategic Industry in an Age of Distrust.” It’s for biotech executives, policymakers, or any curious citizen interested in how we better harness biotechnology for the betterment of the maximum number of people around the world.

This book is not just a laundry list of what’s wrong with the industry or the public. It contains 10 commitments. These are practical suggestions of things companies can do to make for a healthier industry, and to help create a more stable, thriving industry that earns more public support.

I hope you enjoy this conversation, and that it might help serve as a conversation starter in your circles.

The Long Run is sponsored by:

AlphaSense is an AI-powered market intelligence platform designed to help investors and operators find critical insights faster. Think of it as a search engine for the entire financial and life sciences landscape, aggregating over 500 million documents across company filings, clinical trial registries, FDA documents, earnings calls, expert transcripts, broker research, and industry publications into one unified, searchable platform.

For those researching biotech, medtech, and the broader life sciences landscape, it is a game-changer, purpose-built to surface the clinical, regulatory, and commercial insights that matter most. You can use Smart Summaries to instantly synthesize thousands of pages of trial data, regulatory filings, and KOL commentary, while Channel Checks and expert insights help you understand how therapies are actually being adopted in the real world across physicians, payers, and hospital systems, not just how they are modeled on paper.

Instead of spending hours digging through 10-Ks, AlphaSense surfaces the ‘Alpha’—the specific insights that move the needle—in seconds. To experience it firsthand, you can start a free trial at alpha-sense.com/thelongrun.

Bioanalysis should not rely on which scientists at the CRO you get. These are assays, not consulting. Your results should be the same, regardless of who does the work.

Dash was built around automation and standardized workflows specifically to eliminate that variability. Every study gets the same rigor and the same rapid turnaround, days not weeks, across ELISA/MSD, LC-MS, and PCR. GLP-compliant, transparent pricing, guaranteed outcomes. You shouldn’t have to ask who’s running your study. You should just get great data.

Visit www.dash.bio

Now please enjoy this conversation with Jeremy Levin on The Long Run.

May

2026

Can AI-Powered Consumer Health Break Medicine’s Destructive Spiral?