Agree with Abhishaike Mahajan “While computation alone may have delivered the first fundamental advance in ML in biology, I believe it will not be alone sufficient for the next. The next breakthrough needed for better ML in biology will not be better ML. Rather, it will be better wet-lab methods.” https://lnkd.in/dP7wRDbF
Key assays that can inform disease relavent PK/PD is more relavent. Generating more date on “wet lab” assay that don’t inform on biology is not that useful data. Most drug discovery programs fall apart due to disconnect between in vitro assay and PK/PD. Having predictive information in that area is quite useful
Technology to bridge the gap between in silico bits and the atomic world of medicine is exactly what we are focused on via our partnership with the BioML Society and Dell Medical School at the University of Texas at Austin in a just announced hackathon! —> https://www.biomlsociety.org/challenge And https://www.linkedin.com/posts/wesley-wierson_hackathon-biomlchallenge-leahlabs-activity-7219014364597501952-mhSU?utm_source=share&utm_medium=member_desktop
And not just “wet-lab methods” but robust, reliable & integrated data generation & qualification.
I agree with Abhishaike as well. Generalising his main point, can we not say that AI in general is going to need to move beyond abstract bits and engage the physical world as it really is to move on? Whether it is wet labs, real world motion or maybe something as mundane as the current temperature of some component of somebody’s mobile phone? Time to get some hands dirty!
Great to hear Nathan Benaich. One of the most prolific AI investors acknowledging the need for better wet-lab data that sends an important signal to fellow investors and companies that are building technology platforms anchored in both dry and wet lab like we do at iuvantium.
And wet lab methods informed by / in the loop with computational methods.
Cofounder, CEO of Leash
1moAgree so hard I wrote about it already https://leashbio.substack.com/p/we-need-more-and-it-needs-to-be-better