Turning science into medicine. Below, everything that touches this field, including pieces that live mostly in neighboring territory.
Eli Lilly's Chorus unit, established in 2002, emerged as one of the most successful innovations in pharmaceutical R&D productivity, achieving 3-10x productivity improvements over traditional development models…
That’s the title of a great Trends in Biotechnology article led by @the align foundation’s @erika debenedictis. I loved the preprint, I am thrilled to see it published. The Align Foundation is a @schmidt…
I was struck by a statement I read today about a Techbio company that "uses large language models to create billions of druglike molecules". I have nothing against this company and I think they do very…
I am sure many have seen this Y Combinator's Summer 2025 Request for Startups by Jared Friedman. When I founded Icosystem in 2000, I had this exact concept in mind: if we can do analytics and machine learning…
Wow, July 16th, 2025 was Gut Microbiome Day in Nature and Science! I am excited to see this Science paper (Controlled colonization of the human gut with a genetically engineered microbial medicine by Whitaker…
Here is how much increase in P(ts) you get by spending one million US$ in clinical phases and regulatory for 8 therapeutic areas (TAs). This is obviously averaged over many data points (ASPE Drug Development…
As Insilico Medicine has released fascinating R&D benchmarks ( I find it useful to get back to basics to understand the fundamentals. Borrowing from what I consider the gold standard in defining it (2010…
An interesting preprint, Growth vs. Diversity: A Time-Evolution Analysis of the Chemical Space, by a group that has done a lot of work on the concept of chemical space or "chemical multiverse" (a nice review…
Or, evolving on chemical space(s)! The appeal of the concept for me comes from the fact that the topology of a chemical space (the "construction operators") and its boundary conditions are so natural to map to…
There is a lot of excitement in the biotech and pharma world around Eli Lilly and Company's oral, "small" molecule GLP-1R agonist, Orforglipron, licensed in 2018 from Chinese biotech Chugai Pharmaceutical Co.,…
Sergey Kornilov thank you for sharing and for your analysis! Interesting results that point to problem areas and raises some questions... but the results come with enormous caveats. The biggest, I think, are:…
If you are like me and have been following the rise and rise and rise of GLP-1 analogues and other incretin drugs against obesity, diabetes, cardiovascular disease, w̶o̶r̶l̶d̶ ̶c̶o̶n̶f̶l̶i̶c̶t̶ and more, you…
Great post by Ash Jogalekar. Drug discovery is still a prime example of "competence without comprehension" ( we build things that work without always understanding how or why. When a mechanism of action (MOA)…
So there is a lot to unpack in Elliot's latest post. To be clear, I am not trying to unpack Elliot but his post . TL;DR: disruption is here, commoditization is coming and the nexus (or nexi, nexuses?) of value…
That's the title of an insightful blog post ( from Alex Telford. China's pharmaceutical industry has evolved from primarily manufacturing active pharmaceutical ingredients (APIs) to becoming a significant…
Finally found the time to read the excellent BioPharmaTrend.com report "Beyond Legacy Tools: Defining Modern AI Drug Discovery for 2025 and Beyond" (thank you Andrii Buvailo, Ph.D. for the pointer!). The…
I am an avid reader of @stifel’s @tim opler’s reports. His most recent ( is looking at how AI may change medicine, how the roles of physicians and clinicians may be affected, how tech moats compare to…
It looks that way when it comes to preclinical deals in the obesity/diabetes space. Two weeks ago, I noted that Merck's licensing deal with the Chinese biotech Jiangsu Hansoh Pharmaceutical Group Co., Ltd. for…
A company like Formation Bio is reinventing clinical development right where it creates the most value: Phase 2, where you show that not only does your candidate not kill patients, it also meets clinical…
Leveraging AI and a partners network, Formation Bio has really nailed the arbitrage opportunity that is coming out of late discovery (pre-IND or IND-ready) to early development (end of Phase 1). Undeveloped…
In the fourth major deal with a Chinese biotech in just a few months ( Merck (MSD) is paying Hengrui Pharma $200m upfront (and up to $1.77bn on milestones plus royalties on net sales if approved) for a…
The Magnificent 7 stocks (Alphabet, Amazon, Apple, Meta, Microsoft, Nvidia, and Tesla) currently make up a disproportionate share of the S&P 500's total market capitalization (around 36% as of late 2025).…
One of the most unexpectedly and delightfully insightful sessions at DOC, the warm and curiously strong gathering curated by Jordan Shlain, MD and John Battelle on the theme of Truth in Medicine, was the one…
The eminently quotable Alex Zhavoronkov, the fearless founder and CEO of Insilico Medicine, presented at hashtaghumanx on the same day Insilico announced $110m in funding ( to propel it to a Hong Kong IPO and…
Biotech unicorn Formation Bio's CEO Benjamine Liu had my favorite quote of the hashtagHumanx week, not because it is provocative but because it aligns with a deep conviction of mine: that the value of AI/genAI…
Ok, this is mysterious. Before drawing conclusions about the speed of exploration there vs. here, I would be grateful if someone could explain Elliot Hershberg's observation. I, too, read the preprint and…
Spurred by a conversation with Reid Hoffman at DOC, I dug out Phase II clinical trial success rates (Pts) since the 10s (I used public data for this as a good first approximation). Here is the trend line over…
This is a post by Nathan Benaich worth reading for anyone interested in hashtagAI and hashtagdrugdiscovery. The important TL;DR is that there is a lot to be excited about in spite of the recent failures of…
You can always count on Derek Lowe for an incisive (meaning, with tooth) analysis of a half-baked paper with a promising title ( While Derek focuses on the paper's poorly defined categories (can a target…
I missed this paper in Nature last week, which reports "the discovery of a natural protein, citrate synthase from the cyanobacterium Synechococcus elongatus, which self-assembles into Sierpiński triangles."…
Fantastic JPM26 Wing Venture Capital event with the inimitable Rajeev Chand touch! No attribution but a few tidbits: - Immigrants get the job done (tongue in cheek, wonder who might have said that ) - Patent…
Another week, another insight-packed report from Tim Opler at Stifel Financial Corp.. One slide that caught my attention compared the relative public markets performances of US and China biotech firms. There…
To all the people who are dismissing @emma Walmsley’s tenure and track record at GSK, with a flat stock price and a big revenue dip in 2020, I’d like to remind them of the terribly long cycle of value in big…
Much has been written about Merck's licensing deal with the Chinese biotech Jiangsu Hansoh Pharmaceutical Group Co., Ltd. for rights to an oral GLP-1 RA asset outside of China, with up to $1. billion in…
In a fascinating short perspective published in 2013 (Does size matter in R&D productivity? If not, what does?, Nature Reviews Drug Discovery December 2013), Michael Ringel (then at BCG, now CEO of Life…
There were 50 new therapeutics approved by the FDA in 2024, which is the third-largest annual number in the past 30 years with 2018 (5) and 2023 (53) having more. Great overview by Asher Mullard in Nature…
I have recently been on a pharma R&D productivity tear, building modern models to analyze leverage points, including value inflection points (Simon Birksø Larsen). Along the way, I found two posts by Ibrahim…
In an interview for the fantastic Longevity.Technology, Nir Barzilai lists the 4 highest-scoring FDA-approved drugs for humans. It is striking that 3 of the 4 drugs were primarily developed as anti-diabetic…
As Eli Lilly and Company's market capitalization shoots over $1trn again (after reporting quarterly revenue approaching $20bn!) and exceeds the value of yesterday's member of the trillion dollar club…
Dr. Amine ZORGANI even if not pursuing microbiome therapeutics, Pharma/Biotech should be interested in interactions between drugs and (mostly gut) microbiome. But it is too complex for an industry that is…
Thank you Kristen Fortney and BioAge Labs for a fantastic gathering of friends, old and new, with a timely topic: "Extending Human Healthspan: Beyond Weight Loss to Metabolic Resilience." Great timing on the…
Intriguing article by a group at Columbia and TU Denmark Lingby: orally delivered E. coli Nissle 117, a workhorse of synthetic biology and the preferred chassis in a number of attempts for human therapeutics,…
I am also interested in the impact of a potential elimination of self-affirmed GRAS, as Kennedy and the FDA have been alluding to. ZBiotics has expertly navigated a tight space both with GRAS self-affirmation…
That's my (slightly clickbaity) summary of this article, which I am sure will reverberate in the haging and healthspan scientific community. To be clear, the inclusion criteria for this (BMI ≥ 25 and ≤ 47…
A great resource just published in Cell by Cell Press by a stellar group of authors, Guido KROEMER, Andrea B. Maier, Ana Maria Cuervo (Albert Einstein College of Medicine), Vadim Gladyshev, Luigi Ferrucci,…
That's my favorite quote from Derek Lowe's Science opinion, "The End of Disease". And Derek was kind enough to collect links to all his AI-based drug discovery opinions from the past few years, a treasure…
Before Insilico Medicine, Recursion, Atomwise and many others, CoalesiX, launched in 2006, used another form of AI, Evolutionary Computation (EC), to turbocharge the ability of medicinal chemists to explore a…
Always stimulated by Derek Lowe's writings (in spite of an average 50% agreement rate), I tried (a condensed version of) his OpenAI Deep Research prompt on the toxic effects of thalidomide with Perplexity Deep…
Antibiotics have been much maligned for promoting resistant strains of pathogenic bacteria and wiping out good bacteria in the gut. While caution is definitely warranted, it turns out that a number of other…
This timely report (in press) of the American College of Cardiology summarizes evidence and recommendations around Cardiovascular (CV) disease and (chronic, systemic, low-grade) inflammation (CLGI). The…
That’s the title of blog post by @jesse johnson, Scaling Biotech. I believe, with characteristic humility, that the question is ill-posed, even though the framework the author proposes can be useful in…
This graph is from an article in The Economist on 7/14/2025 (AI is killing the web. Can anything save it?). The first-order interpretation is that traditional search is imploding: people are increasingly…
Zealand Pharma's decision to "pause" development of its dual GLP-1/GLP-2 receptor agonist dapiglutide due to a lack of clinical differentiation in a crowded obesity marketplace is notable and viewed largely in…
My colleague Germán Plata pointed me to a super interesting "chatGPT" for biology, bioloGPT ( developed by Conner Lambden. It may sound boring -you know, yet another chatbot, or why not use Perplexity. But…
Such a transformation in public perception cannot be attributed to a single factor and I would point to at least a couple: (1) A messaging shift in the community from longevity to healthspan: while the former…
A great Quanta Magazine article by Gabriel Popkin focuses on how "crowded" and active cells are: "the packing of molecules into tiny spaces is emerging as a fundamental way that cells have evolved to harness…
In a thought-provoking blog post a little more than 2 years ago ($200 Billion in Revenue: How an Aging Drug Will Conquer Pharma, age1's Alex Kesin, Maggie Li and Alex Colville wondered who will pay for an…
The placebo effect (and its evil twin, the hashtagnocebo effect) has always been a fascinating topic to me, a miracle to some and a plague to the pharmaceutical industry, especially in therapeutic areas that…
In the first week of January 2026, I have finally caught up with Andrej Karpathy: I am overwhelmed. I have crossed a threshold that I don't know how to uncross: I am spending more than 5 hours daily trying to…
Oh me . . . The protagonist student (who today would be called a user) knows that +4 is not 3. Therein lies a lesson that applies to LLMs and other blackboxy contraptions: you better have knowledge of the…
Around age 45, I felt like my body was suddenly becoming more fragile. According to an article in Nature Aging on August 14th, 2024 by the prolific Michael Snyder and his team at Stanford University (Nonlinear…
Very cool! Mapping 2,600 previously uncharacterized human proteolytic peptide fragments cleaved by prohormone convertases 1/3 (PCSK1/3) using a computational prediction model, a team led by Stanford University…
The conviction that hashtagserendipity can be, if not systematized, at least harnessed for augmented scientific discovery, has fueled my (obviously nonlinear) professional trajectory. As we saw with Fleming's…
One irregular dispatch when a new piece lands: notes on AI, evolution, complexity, and the biology of discovery. No noise.
Delivered with Buttondown · unsubscribe anytime