AI Finds New Drugs Faster

Hello, and thanks for reading One AI Thing. Get smarter about artificial intelligence, one thing at a time.

👀 Today’s Thing: AI Finds New Drugs Faster.

🤖 When it comes to AI saving the world, nothing hits home quite like humans living longer and with fewer ailments. Doctors and drugmakers alike have been leveraging artificial intelligence for several years now, for everything from medical imaging to smart prosthetics. But perhaps no area of health care has been impacted by AI like drug discovery.

🎧 Want to go deeper? Check out my podcasts with two researchers working to deomcratize drug discovery and the Co-Founder of immunotherapy company Immun.ai.

📖 Backstory

☞ Developing a new drug takes, on average, ten years and billions of dollars.

☞ DSP-1181, a treatment for Obsessive Compulsive Disorder (OCD) became the first AI-designed drug to enter clinical trials in early 2020. Oxford startup Exscientia reached the clinical trial stage with DSP-1181 in less than twelve months.

☞ The integration of AI into the drug discovery and development pipeline has increased almost 40% annually.

🔑 Keys to Understanding

🥇 Drug makers are leveraging machine learning (a form of AI) to identify potential new drugs, predict effectiveness and safety, and optimize their design, all on computers. AI both accelerates this process and cuts down on the amount of more expensive and painstaking lab work required during the rest of the drug development process.

🥈 AI isn’t a stand-in for hands-on lab work with tissue, or clinical trials. It excels at coming up with potential molecules and predicting how well they’ll work in the human body. This lets researchers narrow down millions of candidates to, say, a few hundred compounds promising enough to actually make and test in the lab.

🥉 “The AI can learn faster than conventional approaches, so we had to make and test only 350 compounds, a fifth of the normal number of compound candidates, which is record-breaking productivity,” said Andrew Hopkins, chief executive of [Exscientia] and a molecular biophysicist. “The algorithms . . . can be applied to any drug targets, against a huge range of diseases in oncology, cardiovascular and rare diseases.”

- Madhumita Murgia, Ft.com, Jan 2020

🕵️ Need More?

Searching for a certain kind of AI thing? Reply to this email and let me know what you'd like to see more of.

Until the next thing,

- Noah

p.s. Want to sign up for the One AI Thing newsletter or share it with a friend? You can find me here.