So How Is AI Drug Discovery Doing, Really?

Summary

An important article by field experts points out that despite widespread AI application in drug discovery, evidence of clinically relevant impact remains 'disappointingly limited'. They conclude we are at a stage of 'absence of evidence', not necessarily 'evidence of absence'. Desired outcomes like better decision-making in selecting disease areas, targets, lead molecules, and trial designs are among areas current AI is least equipped to assist. However, there is no fundamental obstacle, but improvements will be slower and costlier than press releases suggest. Even without AI, obtaining good data on these effects is difficult due to natural attribution biases.