AI in drug discovery is overhyped: examples from AstraZeneca, Harvard, Stanford

Re:AI in drug discovery is overhyped: examples from AstraZen... by msamwald on Friday January 05, 2018 @03:25PM (#16081365)

Well, as far as I know the state-of-the-art results on current drug toxicity prediction benchmarks (e.g., Tox21) are held by deep neural networks; it seems like recent AI advances HAVE proven useful in that regard.

[ Parent | on HN ]

Re:AI in drug discovery is overhyped: examples from AstraZen... by digitalzombie on Saturday January 06, 2018 @03:19PM (#16087220)

Do you have a source for that? I'm super interested into reading more.

I had to do Tox21 I was using Bayesian Network for drug toxicity at the FDA we used the DILI database.

[ Parent | on HN ]

Re:AI in drug discovery is overhyped: examples from AstraZen... by _untom_ on Monday January 08, 2018 @02:15PM (#16099225)

This is the paper from the winners of the Tox21 Challenge: https://www.frontiersin.org/articles/10.3389/fenvs.2015.0008.... (fun fact: one of the authors is the inventor of the LSTM)

[ Parent | on HN ]