“We trained models on internal data and then predicted on external data… total number of tests … like 13 million across 500 protein targets.”
IQ
Ian Quigley
Latent Space: The AI Engineer Podcast ·
“It was like the total number of tests in the Hermes paper, I think it's like 13 million… across like many, it's like 500 protein targets.”
Ian Quigley · Latent Space: The AI Engineer Podcast · Lab-in-the-Loop at Compute Speed - Ian Quigley, Leash Bio
Play from 57:04
57:04
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
Assembled a benchmark set of ~13 M molecule-protein pairs covering ~500 targets to compare against the state-of-the-art Boltz model
13 M tests, ~500 protein targets
Said nearby on the same subject
“Set up Rate My Clinic where people can get assessments done, find out how they compare on each of those different benchmarks. And importantly, recommendations on how to improve”
♫
Said on The Business of Allied Health
“We assembled the largest possible data set… 34 billion proteins… then you’d just use a hidden Markov model and match… Cas9”
MB
Mammoth Biosciences
The Neuron: AI Explained ·
“Only 1.6% of Torquay 1930 its triples break this rule, and 0.5% of Lama's, against 9% and 13% for the two base models.”
♫
Said on LessWrong (Curated & Popular)
Moments like this, every Monday
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Track a competitor?
Pro watches up to 25 names or phrases and emails you the morning after they are said.
See Pro, $29 a monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.