Artificial intelligence istaking over drug development, claim some companies and researchers.
AI in drug discoveryis nonsense, warn some industry veterans.
Unlike the success of AI inimage analysis, its effect on drug development remains unclear.
We argue that AI in drug development is not yet a game-changer, nor is it complete nonsense.
AI is not a black box that can turn any idea into gold.
But can AI truly revolutionise drug development and improve success rates?
AI in drug development
Researchers have applied AI and machine learning toevery stageof the drug development process.
Between 2010 and 2022,20 AI-focused startupsdiscovered 158 drug candidates, 15 of which advanced to clinical trials.
This accomplishment demonstrates AIs potential to accelerate drug development.
It is difficult to generate drug-related datasets on cells, animals or humans for millions to billions of compounds.
WhileAlphaFoldis a breakthrough in predicting protein structures,how preciseit can be for drug design remains uncertain.
Meanwhile, many scientists with expertise in drug development lack training in AI and machine learning.
Researchers often overly focus on how to improve a drugs individual properties rather than the root causes of failure.
New AI-guided strategies could help address both of these challenges.
Currently,three interdependent factorsdrive most drug failures: dosage, safety and efficacy.
Some drugs fail because theyre too toxic, or unsafe.
This could help researchers identify optimal drugs while reducing the costs of the current test-and-see approach to clinical trials.
