Searching...
13 results for “undruggable targets”
“AI models have no defense against hidden crypto wallet stealing commands”
certain tokens as trusted and and certain, tokens as untrusted. And that means, when those tokens end up in the model, you could have someone that puts, like, a blog post online. It looks like a, you
31:32 / 32:06
market insight31:32 – 32:06
“Why the first AI-generated drug won't exist for another decade”
...them undruggable targets we've not been able to drug ourselves, we think are are interesting. They're working on drugging them using AlphaFold three,
33:18 / 33:47
prediction33:18 – 33:47
...them undruggable targets we've not been able to drug ourselves, we think are are interesting. They're working on drugging them using AlphaFold three, where Bolt's also being a similar kind of technology that could be used for that. You have others th
32:51 / 34:00
from transcript32:51 – 34:00
...like two fifty three that so many companies try to target and no one really managed to get to molecules that really works or, like, it worked, but the target product profile wasn't desirable. Yeah. I think until we clear out that list, there's defini
29:57 / 31:01
from transcript29:57 – 31:01
...targets. And so that sort of, like, gave to the paper a lot of, you know, validation to the model, a lot of validation that was kind of, wide. And so those would be therapeutics for those animals, or are they relevant to humans as well? They're relev
56:59 / 58:08
from transcript56:59 – 58:08
Sometimes they become apoptotic. Sometimes they become cell cycle rested. They become stressed. They're metabolically starved. They're hungry in some way. And so if you have this, sort of this representation of universal sort of cell space, right, ca
11:51 / 13:04
from transcript11:51 – 13:04
...nine targets from the PDB filtering to things where there is no known interaction, in, in the PDB. So basically the model has never seen kind of this particular protein bound or similar protein bound to another protein. So there is no way that the mo
1:00:44 / 1:01:46
from transcript1:00:44 – 1:01:46
...and having higher confidence in, the predicting the efficacy of the drug. There are some exciting directions. And then especially when it comes to expressing ideas in molecules, I think that a lot of these platforms and capabilities to take new inter
26:55 / 28:02
from transcript26:55 – 28:02
...two targets just to make sure there's not, like, a huge bug and, you know, make sure not everything fails. But, you know, even if everything fails in one or two, you know, the hit rate's fifty percent. You could've just gone unlucky. So that's one of
10:25 / 12:46
from transcript10:25 – 12:46
Kind of in silico libraries, you have, like, tens of millions of compounds and biologics, you know, infinite biologics if you really put your mind to it. But most of these have never existed and will never exist because there's no use for them. So a
38:15 / 39:28
from transcript38:15 – 39:28
difficulty hierarchy we should have in our minds, or is it just, like, unexplored space in terms of enzymes and peptides, small molecules, other domains? Yeah. It's actually a lot more than just success rates. There's lots of properties that need to
27:01 / 28:10
from transcript27:01 – 28:10
...targets, in a tissue or cell type specific way. Right? And so, you know, I think, you know, part of why biology is slow is because there's just this Russian nesting doll of complexity,
23:54 / 25:01
from transcript23:54 – 25:01
Ninety percent of drugs fail in clinical trials. So, you know, we're pretty bad at making drugs. Right? And I think that implies two things. The first is maybe our drug matter is not very good in the sense that its potency, its ability to bind the ta
39:05 / 40:10
from transcript39:05 – 40:10
Have a podcast?
Run your podcast through Clypt
Get ranked clips, hooks, and ready-to-post copy from your own episodes. Free to try.