AI thinks it can out-code cancer. Leaders in the drug development industry, including @EliLillyandCo's @DaveARicks and @insitro's @DaphneKoller, say not so fast. Read more from @david_wainer in this week’s @WSJ AI & Business newsletter: https://t.co/v5XkgRl3PB
On the difficulty of running a wet lab for AI, from an AI leader who was doing it way before (current) AI.
"The difficulty is the subject of the essay. Building a wet lab is not hard. You buy benches and hire good biologists. A useful analogy is cooking. Most of us can make a good dinner at home. Running a restaurant that serves hundreds of different dishes at the same standard, night after night, is another matter. The best recipes, equipment and crew will still fall short, because the ingredients vary, the ovens drift, and at scale nobody is tasting. In our case the ingredients are also alive."
https://t.co/VzrVUks4vT
What does it truly take to build an AI-native wet lab? In the latest installment of insitro founder and CEO @DaphneKoller's “Drug Discovery Has No Magic Wands” Substack series, we explore the complexities of generating high-quality biological data at massive scale.
In "Getting Data to Grow in a Dish," Daphne and Max Salick, insitro Director of Integrated Technology eXploration, provide a look inside the building of part of our data factory -- POSH (Pooled Optical Screening in Human cells). POSH allows us to profile millions of cells per screen to observe cellular responses to genetic perturbations. Generating robust, AI-ready data demands continuous patience, precision, and ongoing innovation to solve complex challenges as they arise.
Read the full article on Deep Phenotype: https://t.co/YLhKNzRiHr
Catch up on earlier entries in the series here: https://t.co/qded40Qf7i
#DrugDiscovery #AI #Biotech #DrugDiscoveryHasNoMagicWands
What can AI do for drug discovery today, and what can’t it do yet? This week on his podcast, The Long Run, @ldtimmerman asked @DaphneKoller for a reality check, and she gave him one.
Daphne explains why AI companies are building wet labs and how human genetics links experiments in cells to what happens in people. She walks through the programs insitro is advancing in liver disease, ALS and brown fat, and closes with the case for public and philanthropic investment in richer human data.
Luke calls it a conversation worth listening to “for a balanced view from someone in the trenches who is both optimistic and realistic.”
🎧Apple Podcasts: https://t.co/IES6KoWY2t
🎧Spotify: https://t.co/KE1Kd5Uamd
#DrugDiscovery #AI #Biotech
What if the future of medicine isn't about finding better drugs, but understanding disease differently?
At the 10th Anniversary of World Summit AI Amsterdam, we had the privilege of welcoming Daphne Koller, Founder & CEO of insitro, Co-founder of Coursera and former Stanford Professor, for a fascinating conversation on how AI is transforming drug discovery.
Joined by Niall Firth, Executive Editor at MIT Technology Review, Daphne explored From data to targets: Causal AI for better medicines, challenging one of the biggest assumptions in pharmaceutical research.
What if the reason so many drugs fail isn't the chemistry, but our incomplete understanding of what actually causes disease?
From patient-derived cells and machine learning to human genetics and precision AI phenotypes, Daphne shared how insitro is combining biology and AI to identify the mechanisms behind disease and improve the chances of developing successful treatments.
With applications spanning ALS and metabolic health, the conversation offered a compelling glimpse into a future where AI could help us understand human biology at an entirely new level.
This is where AI moves beyond possibility and towards meaningful human impact.
A huge thank you to Daphne Koller and Niall Firth for bringing such an important conversation to our 10th Anniversary stage. 💜
For a decade, World Summit AI has brought together the minds pushing the boundaries of what's possible, while asking how innovation can deliver real-world benefits for humanity.
10 years of defining AI. Shaping what comes next.
#WorldSummitAI #WSAI #AIForHealth #DrugDiscovery #AIForHumanity #HealthcareAI
1/2 Always such a pleasure to listen to @DaphneKoller think, not to mention call BS on AI hyperbole while embracing oppy; @ldtimmerman is a particularly good interviewer - deeply knowledgable, thoughtful, not rushed. Wonderful ep of "The Long Run" - https://t.co/ARzc6ZYhYM
Out now: “Getting Data to Grow in a Dish,” the third issue of Deep Phenotype, insitro’s Substack on scaled biology and deep causality.
Generating biological data at scale is one challenge. Ensuring that data is reliable, reproducible and meaningful enough to power AI-driven drug discovery is another.
In our third installment, insitro founder and CEO @DaphneKoller and insitro director of integrated technology exploration, @ATGmsalickTAG, take readers behind the scenes of building insitro's biological data factory, where automation, AI, and human expertise come together to generate high-quality data and deepen our understanding of disease biology.
Through the evolution of our Pooled Optical Screening in Human cells (POSH) platform, Daphne explores the extensive scientific and engineering advances required to turn complex cellular experiments into scalable, reproducible workflows.
Along the way, the share of cells we could match to their genetic perturbation more than doubled, from 34% to above 71%, and developing a new cell-segmentation model went from six to twelve months to about a month.
“The most important thing we have built is not any single platform. It is the ability to build the next one.”
╰┈➤ Read the latest installment of Deep Phenotype: https://t.co/3DJXfm0Hlr
#DrugDiscovery #AI #Biology #CausalBiology
The Moment in AI Drug Discovery. @DaphneKoller of @insitro is the latest guest on The Long Run. Sponsors: @AlphaSenseInc and Dash Bio. https://t.co/QcGWcVpbLz
At insitro, we proved again we don't spook easy at our annual Halloween costume contest last week. Every team that participated shared the same stretch goal: win.
Protein Sciences modeled the central dogma of molecular biology with paper bases and arrows. Read the costumes from left to right, and you could follow the path from DNA to RNA to protein. MASH rounded up the classic monsters, Op Ex and EH&S suited up as the OSHA-Busters, and our distributed LIMS team grew a field of broccoli one video tile at a time.
The fiercest rivalry was between the Legal and People teams. Legal’s take on “The Wizard of Oz” and “Wicked” featured an AI-generated Tin Man inspired by pooled optical screening and cellular perturbation. The People team deployed Ted Lasso and AFC Richmond, setting off a wave of spirited banter and tactical maneuvering. Then came the twist. As “Ted Lasso” writer and actor Brett Goldstein has explained, the show is a retelling of “The Wizard of Oz,” with Ted as Dorothy and Roy Kent as the Tin Man.
The competition was intense, but when the yellow brick road met the pitch, camaraderie was the real winner.
#Halloween #Halloween2026 #costume #sciencepuns #insitro
Pattern recognition tells you what’s associated with disease, not what drives it. At #AIDDD2026, insitro CSO Philip Tagari presents “Generative AI for Target Hypothesis Design: Moving Beyond Pattern Recognition,” plus Workshop 5 on building techbio at scale, Oct 27.
Today, @insitro announces our new collaboration with @AstraZeneca worth up to $1.5 billion.
The partnership pairs insitro's AI and causal human biology platform with AstraZeneca's drug development expertise to pursue new medicines for cardiometabolic diseases.
This is what applying AI to the life sciences is all about: the opportunity to understand what drives a disease and turn those insights into medicines that make a difference for patients.
Congrats to @DaphneKoller, @im_dlight, @mmrozenman, Sharon Barr, Aradhana Sarin, and the entire insitro and AstraZeneca teams.
AstraZeneca bets $40M on AI to crack liver and heart diseases it's struggled to crack alone: AstraZeneca is partnering with AI startup insitro — handing over $40 million upfront and up to $1.5 billion in milestones — to hunt for drug targets in… dlvr.it/TVwbT9 #AstraZeneca#AI
Today, insitro announced a strategic collaboration with @AstraZeneca for the AI-enabled discovery of novel therapeutics for metabolic dysfunction-associated steatohepatitis (MASH) and cardiomyopathies.
insitro will receive $40 million upfront and is eligible for up to approximately $1.46 billion in potential, discovery, development and commercial milestones, plus tiered royalties.
Both diseases are defined by the problem the collaboration is built to address. In each case, a single diagnostic label spans patients whose underlying biology differs. The heterogeneity across these diseases has made them difficult to treat, and the condition under which insitro’s machine learning capabilities on human data is most useful.
Under the agreement, insitro will identify causal disease biology in both indications and advance AstraZeneca-nominated targets from discovery through to development candidate; AstraZeneca will lead clinical development, regulatory work, and commercialization.
“Partnering with AstraZeneca allows us to pair our deep biological precision with their deep pharmaceutical expertise and scale with potential for accelerated advancement of novel programs through development and to patients.” — @DaphneKoller, founder and CEO of insitro
Sharon Barr, Executive Vice President and Head of BioPharmaceuticals R&D, AstraZeneca: "Partnering with insitro, we are using AI to identify the biological drivers of disease to support the rapid discovery of high-quality novel molecules, advancing our ambition to deliver the next generation of medicines to patients faster.”
Read the announcement: https://t.co/J7OxlXbj2e
More on our approach to causal biology: https://t.co/ggUTg35rCF
#AIDrugDiscovery #MASH #Cardiomyopathies