Generative Molecular Design Isn't As Easy As People Make It Look
I was taken aback by a recent CNBC article entitled “ Generative AI will be designing new drugs all on its own in the near future ”. I should know better than to pay attention to AI articles in the popular press, but I feel that even scientists working in drug discovery may have a skewed perception of what generative AI can and can’t do. To understand exactly what’s involved, it might be instructive to walk through a typical generative molecular design workflow and point out a few things. First, these programs are far from autonomous. Even when presented with a well-defined problem, generative algorithms produce a tremendous amount of nonsense. Second, domain expertise is essential when sifting through the molecules produced by a generative algorithm. Without a significant medicinal chemistry background, one can’t make sense of the results. Third, while a few nuggets exist in the generative modeling output, a lot of work and good old-fashioned cheminformatics are required to ext