Skip to Content

Tag: Regina Barzilay

Explainable AI for Rational Antibiotic Discovery

Researchers now employ artificial intelligence (AI) models based on deep learning to make functional predictions about big datasets. While the concepts behind these networks are well established, their inner workings are often invisible to the user. The emerging area of explainable AI (xAI) provides model interpretation techniques that empower life science researchers to uncover the underlying basis on which AI models make such predictions.

In this month’s episode, Deanna MacNeil from The Scientist spoke with Jim Collins from the Massachusetts Institute of Technology to learn how researchers are using explainable AI and artificial neural networks to gain mechanistic insights for large scale antibiotic discovery. Learn more

A new computational technique could make it easier to engineer useful proteins

To engineer proteins with useful functions, researchers usually begin with a natural protein that has a desirable function, such as emitting fluorescent light, and put it through many rounds of random mutation that eventually generate an optimized version of the protein.

This process has yielded optimized versions of many important proteins, including green fluorescent protein (GFP). However, for other proteins, it has proven difficult to generate an optimized version. MIT researchers have now developed a computational approach that makes it easier to predict mutations that will lead to better proteins, based on a relatively small amount of data.

Using this model, the researchers generated proteins with mutations that were predicted to lead to improved versions of GFP and a protein from adeno-associated virus (AAV), which is used to deliver DNA for gene therapy. They hope it could also be used to develop additional tools for neuroscience research and medical applications.

“Protein design is a hard problem because the mapping from DNA sequence to protein structure and function is really complex. There might be a great protein 10 changes away in the sequence, but each intermediate change might correspond to a totally nonfunctional protein. It’s like trying to find your way to the river basin in a mountain range, when there are craggy peaks along the way that block your view. The current work tries to make the riverbed easier to find,” says Ila Fiete, a professor of brain and cognitive sciences at MIT, a member of MIT’s McGovern Institute for Brain Research, director of the K. Lisa Yang Integrative Computational Neuroscience Center, and one of the senior authors of the study.

Regina Barzilay, the School of Engineering Distinguished Professor for AI and Health at MIT, and Tommi Jaakkola, the Thomas Siebel Professor of Electrical Engineering and Computer Science at MIT, are also senior authors of an open-access paper on the work, which will be presented at the International Conference on Learning Representations in May. MIT graduate students Andrew Kirjner and Jason Yim are the lead authors of the study. Other authors include Shahar Bracha, an MIT postdoc, and Raman Samusevich, a graduate student at Czech Technical University. Learn more
Still of Regina Barzilay from AI Revolution

A.I. Revolution

Can we harness the power of artificial intelligence to solve the world’s most challenging problems without creating an uncontrollable force that ultimately destroys us? ChatGPT and other new A.I. tools can now answer complex questions, write essays, and generate realistic-looking images in a matter of seconds. They can even pass a lawyer’s bar exam. Should we celebrate? Or worry? Or both? Correspondent Miles O’Brien investigates how researchers are trying to transform the world using A.I., hunting for big solutions in fields from medicine to climate change. (Premiering March 27 at 9 pm on PBS) Learn more
Antibodies (pink) bind to influenza virus proteins (yellow) (artist’s conception)

‘A landmark moment’: scientists use AI to design antibodies from scratch

Researchers have used generative artificial intelligence (AI) to help them make completely new antibodies for the first time.

The proof-of-principle work, reported this week in a preprint on bioRxiv, raises the possibility of bringing AI-guided protein design to the therapeutic antibody market, which is worth hundreds of billions of dollars.

Antibodies — immune molecules that strongly attach to proteins implicated in disease — have conventionally been made using brute-force approaches that involve immunizing animals or screening vast numbers of molecules.

AI tools that can shortcut those costly efforts have the potential to “democratize the ability to design antibodies”, says study co-author Nathaniel Bennett, a computational biochemist at the University of Washington in Seattle. “Ten years from now, this is how we’re going to be designing antibodies.”

“It’s a really promising piece of research” that represents an important step in applying AI protein-design tools to making new antibodies, says Charlotte Deane, an immuno-informatician at the University of Oxford, UK. Learn more
Portrait of Regina Barzialy

NOVA ‘A.I. REVOLUTION’ Dives Into the Past, Present, and Future of One of the Most Consequential Technological Advancements of Our Time

BOSTON, MA; Feb.12, 2024 — The award-winning PBS science series, NOVA, a production of GBH, will premiere the one-hour film “A.I. REVOLUTION” Wednesday, March 27 at 9 p.m. ET/8 p.m. CT on PBS. Can we harness the power of artificial intelligence to solve some of the world’s most challenging problems without creating an uncontrollable force that ultimately destroys us? New A.I. tools like ChatGPT can now answer complex questions, write essays, and generate realistic-looking images in a matter of seconds. In “A.I. REVOLUTION,” which will also be available for streaming at, NOVA on YouTube, and the PBS App, correspondent Miles O’Brien meets some of the scientists who are at the forefront of A.I. advancement and explores the promise, perils, and possible future of this unprecedented technology taking the world by storm.

Beyond drug discovery and prosthetics, the film explores several other ways that A.I. is transforming science. Computer scientist Regina Barzilay at Massachusetts General Hospital has trained a neural network to detect breast cancer from mammograms years before they are detectable by human eyes with over 85% accuracy. A.I. is also being used to help detect lung cancer. Lives are even being saved from natural disasters, as A.I. is now being deployed in California to detect wildfires early before they rage out of control. Learn more
Screenshot of Zoom interview between Eric Topol (left) and Jim Collins (right)

Jim Collins: Discovery of the First New Structural Class of Antibiotics in Decades, Using A.I.

Jim Collins is one of the leading biomedical engineers in the world. He’s been elected to all 3 National Academies (Engineering, Science, and Medicine) and is one of the founders of the field of synthetic biology. In this conversation, we reviewed the seminal discoveries that he and his colleagues are making at the Antibiotics-AI Project at MIT. Learn more
Illustration of apple falling onto a pie

What Am I Thankful for This Year? Amazing Scientific Discoveries.

I’ll wager that the event of 2023 that will change our lives the most in coming years is not the sighting of a Chinese spy balloon, the failure of Silicon Valley Bank, the fall of Kevin McCarthy’s speakership or any of the other eruptions that transfixed us this year.

More likely, the event that’s judged most transformative will be some scientific or technological advance that only a handful of people know about right now — because that’s how things almost always go. The first time the word “transistor” appeared in print was in an article in The New York Times in 1948, on Page 46, following a report on two new radio shows, “Mr. Tutt” and “Our Miss Brooks.” I think we can agree that the transistor has had more impact on our daily lives in the 75 years since than either of those bits of entertainment. Learn more
Person wearing a lab coat, goggles, and gloves looking at a screen atop a microscope.

9 new breakthroughs in the fight against cancer

Lung cancer kills more people in the US yearly than the next three deadliest cancers combined. It's notoriously hard to detect the early stages of the disease with X-rays and scans alone. However, MIT scientists have developed an AI learning model to predict a person's likelihood of developing lung cancer up to six years in advance via a low-dose CT scan. Learn more
image description