←
Ron Alfa4,423 posts
Ron Alfa avatar

Ron Alfa

@Ronalfa

CEO & Co-founder @NOETIK_AI Using AI to actually solve cancer.

◷ Joined February 2011▧ 227 Photos and videos
Ron Alfa avatar
Ron Alfa@Ronalfa·Apr 18

1/ Spatial transcriptomics is among the richest view of human biology that we have: 18,963 genes mapped at subcellular resolution. It's also almost never collected outside of research settings. So we trained a foundation model to generate it from a clinical H&E image alone. Meet TARIO-2. 🧵 noetik.blog/p/tario-2-a-whol…

Ron Alfa avatar
Ron Alfa@Ronalfa·1h

Cancer is cooked.

Noetik is expanding the scale and diversity of data behind our cancer biology world models. We’re excited to announce a collaboration with @MSKCancerCenter, providing access to proprietary data from tens of thousands of patients, collected during routine clinical care. By enabling a more diverse and comprehensive view of cancer development, the new data will help us train and advance our models’ ability to predict therapeutic response for patient impact. Read more here: businesswire.com/news/home/2…

Post attachment
Ron Alfa avatar
Ron Alfa@Ronalfa·2h

3/ Our mission is to use frontier intelligence to actually cure cancer by developing models that can predict the right drug for each patient. This collaboration will accelerate both model pretraining and post training as we work to connect tumor biology with therapeutic response for a diversity of new medicines.

Ron Alfa avatar
Ron Alfa@Ronalfa·2h

2/ Frontier intelligence that actually understands human biology requires massive and a diverse pretraining data. @NOETIK_ai has built one of the largest multimodal spatial cancer datasets in existence at our own data foundry. This collaboration with MSK will bring access to tens of thousands of diverse cancer patients into our work, anchored by MSK’s CHORD resource.

Ron Alfa avatar
Ron Alfa@Ronalfa·2h

1/ Today we’re announcing @NOETIK_ai collaboration with @MSKCancerCenter to advance cancer biology world models. This collaboration brings together MSK’s world class oncology expertise and research resources with NOETIK’s frontier AI and data foundry capabilities.

Post attachment
Jean-Paul (JP) Sanday avatar
⟳ Ron Alfa retweeted
Jean-Paul (JP) Sanday@jpsanday·Nov 16

Our latest @MenloVentures healthcare AI report is out: healthcare AI is on fire. We've never seen technology adoption like this. Maybe we can finally start making real progress on access, cost and outcomes!

Healthcare is now AI’s biggest vertical market. Spend grew 2.5x to $3.7B this year, more than double legal ($1.8B) and more than legal and finance combined. It started in paperwork: scribing and billing. Now it’s moving into drug discovery, patient engagement and clinical decision support. Clinical copilots alone grew 5.5x to $550M. Our 2026 State of AI in Healthcare report from @grgyap, @jpsanday, @CroomBeatty, @hu_j, @derekgxiao and @sabrinarlu: mnlo.vc/2026-healthcare-ai-r…

Ron Alfa avatar
Ron Alfa@Ronalfa·Nov 16

Nice piece from @LongmireMD on opportunities for AI to increase clinical trial efficiency. This, and making them fail less, is the unlock for therapeutics abundance.

As we unlock AI drug discovery, we are dire need of innovation that increases clinical trial capacity. Herein, I model the cost and time savings of agentic clinical development and estimate it can double trial capacity. Would love your feedback.

Michelle Longmire avatar
⟳ Ron Alfa retweeted
Michelle Longmire@LongmireMD·Nov 15

Dream bigger. @elonmusk showing most do not push the boundaries of perceived reality hard enough and remain limited by small ambitions perceived as insurmountable barriers.

Listen to this crowd. Elon has achieved Michael Jordan level rizz with...engineering.

0:38
Ron Alfa avatar
Ron Alfa@Ronalfa·Nov 15

We can build intelligent control systems to predict drug response in patients. But for this to approach engineering, we also need to deploy those systems into clinical trials. This requires a full stack build of not just frontier AI + therapeutics, but also diagnostics.

Ron Alfa avatar
Ron Alfa@Ronalfa·Nov 14

Of course, we agree… @NOETIK_ai the most curing-cancer-pilled ai research team in the industry.

Yes, if we were serious about curing cancer, we would have done many things to speed it up. Proof that this is possible without AGI God: China is now ahead of US in cancer therapeutics, while being a backwater just 10 years ago. There is so much left on the table. Out of all applications of AGI, curing cancer is among the ones where the juice is the least juicy compared to the squeeze. That doesn't mean AGI wouldn't help. It's just that we can build good specialised models for biology and also, data and human experimentation remain bottlenecks that we have to solve. Justifying the need for AGI God (as opposed to specialised models) for curing cancer isn't a very good argument.

Ron Alfa avatar
Ron Alfa@Ronalfa·Nov 13

Maybe a hot take: comp bio evals are not biology evals, that’s just coding. We don’t need models to do comp bio.

Ron Alfa avatar
Ron Alfa@Ronalfa·Nov 11

fwiw frontier ai is exponentially accelerating our work building frontier ai to actually solve cancer

Ron Alfa avatar
Ron Alfa@Ronalfa·Nov 9

"Drug development isn’t rocket science, its actually much harder." 🔥

Convincingly negative result here. IL6 looks almost the same. Not often 2 of the most anticipated targets in CV go down at once. There will be lots of Monday morning quarterbacking these bets but it’s why we do the studies and they were reasoned bets, uncertain outcomes despite genetics and biomarkers with asymmetric value if positive. Drug development isn’t rocket science, its actually much harder. In the near term, beyond LDL optimization (looks like real benefit), Incretin therapy in obesity now the one big idea left on the board to reduce CVD death and disability at scale. Surmount MMO is coming! clinicaltrials.gov/study/NCT… Pelacarsen and Cardiovascular Outcomes in Patients with High Lipoprotein(a) | New England Journal of Medicine nejm.org/doi/full/10.1056/NE…

Ron Alfa avatar
Ron Alfa@Ronalfa·Nov 9

While we see very clear scaling laws with our models getting better with more human data and compute - we already have strong results predicting drug response on a diversity of patient cohorts, tumors and mechanisms. This is the beginning of an inflection for making better medicines.