Amgen launched the first episode of its four-part podcast series called The Generative Biology Revolution.
The two executives detail how generative biology, a new approach to drug development that uses artificial intelligence and machine learning to design protein therapeutics, makes the process of drug creation more predictable, shortens timelines and increases success rates of bringing medicines to patients who need them most.
While the podcast aims to reach scientists, Deshaies and Russell explain AI and machine learning in a way most interested parties could understand.
Amgen has developed an AI that can predict the functions of proteins based on the previous sequence and structure the machine has learned. Russell compared the previously used technology that has been replaced with the AI to the Face ID feature on the iPhone, where facial recognition improves the more it is used because the machine is “learning” your face.
While the AI can predict the actions of proteins, the scientists’ responsibility is to figure out how they can utilize this technology to continue advancing in medicine. Russell explained this with a metaphor to surfing, comparing AI to the waves and pointing to the surfboard as how they will use the waves.
“What the team did is they simply said, ‘OK, for each one of these waves, what are the surfboards? How do we build them? What do we need to put in place? How can we do our experiments in different ways? How can we create the systems that will generate the data that will power the algorithms? How do we deploy the automation? Finally, what’s the foundation upon which we can build?’” he said.
This discussion of studying the way biological systems work and how to harness them with AI will be continued in podcast serials set to be released in September and October.