Control strategy for large scale bio datasets serving as substrate for AI is its own science (and one I’d suggest we played a very meaningful role in pioneering).
Can’t agree more with Ron. If you see controls in a row, column or on the edge of your plate, rather than randomized across a plate, you know your dataset is not built with ML/AI in mind.
People are still generating “ML datasets” with all kinds of confounds. If the controls are all next to each other on the edge of the plate, no randomization, ngmi.
A lot of wisdom from a person and team @_DimensionCap that has been at the bleeding edge of Tech x Bio longer than almost anyone. The @CoefficientBio x @AnthropicAI is just the beginning from this team.
@drrichjlaw@LinkedIn I mean I think it is going to make GPs redundant for most people within a handful of years, and that would be much more efficient for healthcare spend and outcomes (I suspect). But the system will resist it…
News! @airstreet has raised $232,323,232 for Fund III to back AI-first companies from the earliest stages in the US and Europe.
Now the largest solo GP venture firm in Europe.
Our third epoch begins today. Join us!
Freed from the shackles of daily operation, and with a few weeks of decent sleep under my belt, I found the time to sit down and write a thing about TechBio. Take a read and then tell me if you are an 'AI maximalist' or an 'AI minimalist'... (yes, that's a leading question). https://t.co/ASWmSJiQj6 via @LinkedIn
Joining the @PacBio board.
In the AI era, data quality is the moat. Doesn’t matter how good your model is if your training data is noise.
I believe PacBio makes the best sequencing data on the planet. Time to help them turn that into a category-defining advantage. 🧬
https://t.co/pPAh84UW8r