With the right data, the same foundation model can discover new drugs, patient subsets, and predict clinical response. This accelerates therapeutics, but ultimately changes medicine.

Big news for pediatric cancer patients today.

“I’ve seen a lot of companies over 37 years,” Nelsen said. “You can tell when they’re going to be really cool, because the smartest people start self-selecting into them.”

endpts.com/archs-bob-nels…

One of my biggest takeaways from the Llama3 announcement - data gravity is king. And access to high quality, annotated, LLM ready data will drive which companies truly utilize AI vs those who don't

As the number of accessible, highly performant models continues to grow (both…

Day 2 of our NOETIK onsite with some incredible talks from Eng team about our data infrastructure.

Can’t believe the world class infra for multimodal data and ML the team has built so quickly.

“If you were teleported to a disease free society in the Year 3024 what do they have that we don’t?”

ML platform discussion this morning. 🔥

Training agent models to discover biology from world models. 🤯

Very good thread on ADCs. Personally thinking a lot about novel approaches with non-cytotoxic payloads.

The patients can’t wait, nor can the planet. This is our why at Boom Capital. We will do whatever it takes to accelerate the missions of the founders and Collectives we work with.

Have always been a huge fan of Ginkgo Bioworks, love how they’ve nailed the bio foundry model.

'Its not the number of T-cells, but their spatial configuration that matters for tumor removal. Spatial context is my favorite thing and The SchietiLab is demonstrating so beautifully in her talk #AACR24 and she is taking brilliant her ideas all the way to the clinic!

Introducing BELKA, the biggest public molecule-protein interaction dataset on earth, generated by us at Leash Biosciences in the basement of my house.
leashbio.substack.com/p/introducing-…
kaggle.com/competitions/l…

Working on ML for Drug Discovery I have been frustrated with the size and/or quality of publicly available datasets to train and benchmark models with, so when my co-founder and I started our company we swore we would open-source some data as quickly as possible.

Enjoyed this interview w Celine Halioua. Some really great points on how to move more quickly in bio.

'Underdog' founders are absolutely crushing it.

• 70% of unicorns have “underdog founders” (immigrants, women, people of color).

• Unicorns used to have only male founders, but this is changing, with 17% having a female founder in 2023.

• 53% have degrees from the top 10…

Big news today: Incredibly thrilled to welcome Shafique Virani, MD to NOETIK as CBO!

Shaf is a world-class leader with decades of experience at innovative large organizations such as Roche, and trailblazing biotechs such as Recursion (RXRX) & BridgeBio Pharma (BBIO).…