Finding the right remedy for treating conditions as anxiety and depression can be tricky. The doctor will start you on a medicine that is usually well tolerated and effective, but can do nothing for you-or have terrible side effects. Sometimes months of rehearsal and mistake it takes to find something that works.
It's an incredibly common question. Dr. Priscilla Jan in front of the audience south of the southwest on Wednesday can be directed if doctors could check drugs against the generative AI model of your cells and systems. Chan, who co-founded Initiative Jan Zuckerberg With her husband, Meta's founder and CEO, Mark Zuckerberg, said the use of AI could be the next big jump for biomedical research.
“Hope is with those models that we will be able to answer some of the most difficult questions in biology,” Jan said.
Artificial Intelligence is a Hot Thread for All of its Moment Bandage With Chatgpt's Debut Broadcast At the end of 2022. This week was a big focus on SXSW in Austin, Texas, with talks about trust, responsibility And The future of work.
Last year, two scientists in Google's DeepMind Unit won the Nobel Prize In chemistry for their work using AI to predict the structure of the protein.
As for how this technology can advance science and medicine, it can last for years, if not decades. And these AI models are likely to speed up the true research in the laboratory, not to replace it. But Jan sees a world of opportunities.
What we do not know about ourselves
Han, a pediatrician, said a lot about how the human body works still avoids understanding science. Of course, there have been decades since the researchers fired the human genome, but genetics only offers a roadmap. Han used the LEGO analogy of the Millennium Falcon of “Starwells War” – the genetic code is an instruction package. However, we still do not know how individual pieces are collected to form the spacecraft. And when it seems that one part does not fit properly, this is where medicine should enter.
Outside the gaps in scientific knowledge of biology, we also have a limited understanding of how biology works within individual people. Based on a small number of specimens, we have extrapolations on how the body should work, but it is a small database that does not approach the pure diversity of mankind.
Ai model can help describe what happens in a person's cells – personalizing medicine so that your treatment differs from mine.
“If we build the right data and AI models, we can better understand what makes us healthy and what makes us sick,” Jan said.
Can AI speed up research on biomedicine?
Current research techniques are also slow and expensive in developing new drugs and treatments. Ideas should be tested in a physical laboratory environment, which lasts for a great deal of time and resources.
Jan does not propose eliminating the existing physical “wet laboratory” research. But the model of machine learning-notes of AI-can help identify candidates for more probability of work, which means that it can take less tests in the real world to achieve a feasible solution.
Models will not always be correct. They will offer solutions and ideas that do not work, perhaps physically impossible ideas, but there should be a filter of real human scientists who handle the ideas created by the model.
“It will not give us the whole answer,” Jan said. “I don't want to think that scientists will only talk to the model and get all the answers they need.”
Machines can help scientists find better questions, Jan said. “It is a generator of hypotheses,” she said.
While many companies and researchers are considering ways to use AI in hospitals and patient treatment, Jan's focus is on promoting basic biological research that make future progress. She sees AI as a potential big jump in science, similar to the invention of the microscope, X-rays, MRI or sequencing the human genome.
“Health and medicine, moving in jumps,” she said. “There are decades when the research gets stuck, and then someone invents new technology that completely changes the way we see the human body.”