What we need to do to see the promise of AI in drug discovery
Despite the years of hype of AI in drug discovery, there are few companies that have made it to the clinic. There are some gaps in our focus on number of molecules screened rather than underlying models, for example. Other difficulties include lack of feedback from clinical trials. If we address these two problems, we can finally see the renaissance of AI in drug discovery.
This was discussed in last week’s Decoding TechBio where they presented an article which displayed the similarities of Exscientia’s AI designed candidates to a drug, Haloperidol, which was approved by the FDA in 1967. Similarly, a paper in February of this year analyzed the chemical space of drugs created by AI-native companies, showing that adjacent, not new, chemical space was inhabited by the molecules (their figure below). To some degree this makes sense because the models were likely trained on successful drugs for the corresponding targets. However, the molecules inhabiting the same chemical space are clearly not living up to the expectations we had regarding AI in drug discovery - where ideally we would be finding more effective treatments by the models finding molecules outside the known chemical space. The ‘novel chemical space’ issue is part of the reason why I’m so bullish on metabolomic mining companies, such as Enveda and Brightseed. Other companies are mining genomes such as Erebagen and Hexagon Bio to discover new molecules are also promising. A recent article by the Eroom’s Law inventor, Jack Scannell et al., compares high-throughput methods for screening in low predictive disease models and low-throughput methods for screening in high disease predictive models. His analysis on the positive predictive value against the number of candidates selected shows the comparatively small effect of orders of magnitude more molecules compared to the predictive validity of the assay being used. Another nuance to drug discovery is that cost savings matter the most in the clinic - especially in Phase II clinical trials. Brender and Cortés-Ciriano modeled in a recent article that cost, quality, and speed savings are most salient in the clinic, especially in Phase II clinical trials (figure below). Both of these views are somewhat at odds with the current state of the field where companies focusing on target discovery and target binding abound.
Moreover, the Scannell et al. 2022, and Brender and Cortés-Ciriano articles highlight the field’s emphasis on throughput (Scannell et al., 2022) or cost and speed (Brender and Cortés-Ciriano) as opposed to quality. Thankfully, improved quality can come in many forms. Although imperfect, below are some cited modes of drug discovery improvement gains:
All AI in drug discovery companies.
