Priscilla Chan sees AI models of cells like the next jump in biology and medicine

Finding the right medicine to treat conditions such as anxiety and depression can be complicated. Your doctor will start you on a medicine that is usually well tolerable and effective, but this can do nothing for you-or or have terrible side effects. Sometimes it takes months and a mistake to find something that works.

This is an incredibly common problem. Dr. Priscilla Chan told an audience south of southwest on Wednesday that this can be simplified if doctors can check medicines against a generative AI model of your cells and systems. Chan, who co -founder of Chan Zuckerberg initiative With her husband, founder and CEO of Meta Mark Zuckerberg, he said the use of AI could be the next major jump for biomedical research.

“The hope is for those models that we will be able to answer some of the most difficult questions in biology,” Chan said.

Artificial intelligence is a hot topic for almost everyone from the moment of breakthrough with Chatgpt debut Emitted At the end of 2022 this week, it was a major focus on SXSW in Austin, Texas, with conversations around confidence., accountability and workS

Last year, two scientists in AI Unit Deepmind on Google Won the Nobel Prize In chemistry for their work, using AI to predict protein structure.

As for how this technology can develop science and medicine, it can take years, if not decades. And these AI models will probably just accelerate actual laboratory tests, not replace it. But Chan sees a world of opportunities.

What we don’t know about ourselves

Chan, a pediatrician, said much of how the human body works still avoids understanding of science. Of course, it has been several decades since researchers cracked the human genome, but genetics only offers a road map. Chan uses the analogy of the Lego set of Millennium Falcon from Star Wars – the genetic code is the instructions package. However, we do not know how the individual pieces are collected to form the spacecraft. And when a part does not seem to fit properly, the medicine must enter there.

Beyond the gaps in scientific knowledge of biology, we also have a limited understanding of how biology works within individuals. Based on a small number of samples, we have extrapolations on how the body should work, but this is a small set of data that does not come close to presenting the pure diversity of humanity.

The AI ​​model can help describe what is happening in the cells of an individual – customization of medicine so that your treatment is different from mine.

“If we build the right data and AI models, we can better understand specifically what makes us healthy and what makes us sick,” Chan said.

Can AI speed up biomedical studies?

Current research techniques are also slow and expensive in developing new medicines and treatments. Ideas should be tested in a physical laboratory setting that takes a huge amount of time and resources.

Chan does not propose to eliminate existing physical studies of a wet laboratory. But the model of machine learning, a distinguishing feature of the AI, can help identify drug candidates with a greater likelihood of work, which means that it can take less tests in the real world to achieve a working solution.

Models are not always right. They will offer solutions and ideas that do not come up with, perhaps physically impossible ideas, but there must be a filter of real human scientists who deal with the ideas that the model produces.

“It won’t give us the full answer,” Chan said. “I don’t want to think that scientists will just talk to a model and get all the answers they need.”

Machines can help scientists find better questions, Chan said. “This will be the generator of hypotheses,” she said.

While many companies and researchers are looking for ways to use AI in hospitals and patient treatment, Chan’s emphasis is on the progress of basic biological studies, which makes future achievements possible. She sees AI as a potential major science jump similar to the invention of the microscope, X -ray, NMR or the sequencing of the human genome.

“Health and medicine, she moves in jumps,” she said. “There are decades when research is stuck and then someone invented a new technology that completely changes the way we see the human body.”