Conversation

The problem with antibiotic drug discovery is that it is unprofitable. There have been many, many exciting molecules developed at the laboratory/pre-clinical stage over the past 30 years. They are not brought to market because it is unprofitable to do so.
2
6
Hmm, OK, that's sort of a different level of analysis than I was asking for… what I was curious about was, does this actually represent an interesting/important new way to find antibiotics? Let alone if there is some other bottleneck in the whole process
2
3
Even if the ML use case is weak in the restricted context of new *antibiotic* discovery, could computational drug discovery _in general_ not benefit from ML approaches? 'In drug discovery, generative AI models’ ability to create new data samples based on..
1
Several metrics missing here. In general, short-term AI may be "just as likely to get things wrong as right" unless carefully specialized. But once optimized, the dev acceleration might be significant, especially when simulations have been vetted. Those costs are hard to factor.