This is pretty clear proof that top-tier ML engineers can outperform pharma teams at problems relevant to drug discovery.https://twitter.com/AndrewCutler13/status/1194706278074871809 …
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
A meta point: The practical question to ask of any ML algorithm is “what expensive manual process can this replace”? In biotech, that will usually mean “predict the result of an experiment so well you don’t have to run it” or “classify sample data so a human doesn’t have to”
Initial binding-affinity experiments are automated and scalable enough today that any computational chemistry algorithm would have to pass a *really* high bar for it to usefully replace these experiments.
Sarah, while the Google team's results were impressive, I think their better numbers came from not actually trying to solve the same problem. Think about it: instead of predicting binding based on sequences, they're predicting distances between sequence pairs.
And the model is trained on a large set of known protein structures&sequences. Now, why would a pair of sequences want to be at a specific long distance from each other? They don't; that correlation is a result of evolutionary similarity!
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.