Small Molecules
topic on 4 shows · 8 statements across 6 episodes
Latent Space 
WTF is with Nikhil Kamath 
the a16z Podcast 
TBPN
8 statements about Small Molecules, every show
Edunov: Small molecules can be modeled with physics to generate training data
“In small molecular space, you can actually model your small molecules with physics. You can model their behavior, and that allows you to create more data that you can train model on. Something which is not necessarily possible in protein to protein.”
Feinberg: Small molecules make up 65% of FDA-approved drugs
“Small molecules are still 65% of FDA approved drugs, so we're talking about the biggest part of the pie.”
Prasad: Global drug development pipeline is shifting from small molecules to biologics
“Pipeline used to be largely small molecules. It's now shifting to large molecules in biologics and peptides, and also another class of compounds called oligonucleotides.”
Prasad: Novel biologics require lower capital intensity to develop than small molecules
“You can also generate novel biologics at a relatively lower intensity of cost than small molecules. It's easier to develop.”
Shkreli: Pharma avoids peptides as the worst of both worlds
“And in fact, in pharma, you try to avoid peptides because of their inherent weaknesses. You go for small molecules or Really large molecules like antibodies. Peptides are sort of the worst of both worlds.”
Alternating Atomic and Token-Level Modeling Enabled AlphaFold 3 Small Molecules
“The other part, I think that's enough for three is sort of this moving away from modeling just at the amino acid level to actually sort of having the model sort of alternate between you know, sort of atomic resolution modeling and then more like it's got token…”
Bowen Liu: Small Molecules Currently Lack Self-Supervised Learning Frameworks
“Because like with protein sequences and biological sequences, like you can actually do self-supervised learning, right? Because there is this like complicated generative process with like evolutionary pressure that you can learn from. There's no equivalent for…”
Fortney: Small molecule longevity drugs will likely emerge first
“I guess I'm expecting small molecules to come first because that's what pharma is used to. You know, that's what the, we have all the models to make that work. And the space of chemicals has been so unexplored. So I think there are going to be other repomycins…”