AI and the Hard Stuff

Derek Lowe · 25 May 2023 · web.archive.org ↗

2 korrents from this piece

Derek Lowe did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

Our reading
No AI system today reduces either of the two risks that sink most drugs in the clinic: picking the wrong target, and human toxicity.

Their wordsThere are no existing AI/ML systems that mitigate clinical failure risks due to target choice or toxicology.

Interesting
Our reading
We have neither the data nor the insight to use machine learning to pick drug targets that succeed in the clinic more often.

Their wordsBut we do not have enough data and we do not have enough insight to use AI/ML to pick better targets that have a higher chance of succeeding in the clinic.

Interesting