In an effort to better understand how protein language models (PLMs) think and better judge their reliability, MIT researchers applied a tool called sparse autoencoders, which can be used to make large language models more interpretable. The findings “may help scientists better understand how PLMs come to certain conclusions and increase researchers’ trust in them," writes Andrea Luis for The Scientist.
Prof. Pierre Azoulay speaks with WBUR’s Martha Bebinger about a new study examining the potential impact of NIH budget cuts on the development of new medicines. Azoulay and his colleagues found that “more than half of drugs approved by the FDA since 2000 used NIH-funded research that would likely not have happened if the NIH had operated with a 40% smaller budget,” Bebinger explains.
Fierce Biotech reporter Darren Incorvaia writes that a new study by MIT researchers demonstrates how potential NIH budget cuts could endanger the development of new medications. The researchers found that if the NIH budget had been 40% smaller from 1980 to 2007, the level of NIH cuts currently being proposed, “the science underlying numerous drugs approved in the 21st century would not have been funded,” Incorvaia explains. The findings suggest that “massive cuts of the kind that are being contemplated right now could endanger the intellectual foundations of the drugs of tomorrow,” explains Professor Pierre Azoulay.
A new study co-authored by MIT researchers finds that more than half of the drugs approved by the FDA since 2000 are connected to NIH research that would be impacted by proposed 40 percent budget cuts, reports Genetic Engineering & Biotechnology News.
MIT researchers have developed Boltz-2, an AI algorithm “that unites protein folding and prediction of small-molecule binding affinity in one package,” reports Laura Howes for Chemical & Engineering News. “The researchers say their new AI model approaches the level of accuracy achieved by traditional computational chemistry—such as methods involving free-energy perturbation calculations—but much more quickly and cheaply,” explains Howes.
Researchers at MIT and elsewhere have developed Boltz-2, an open-source generative AI model that can help researchers find new medicines faster, reports Alex Knapp for Forbes. The tool “can not only predict the structure of proteins, it can also predict its binding affinity–that is, how well a potential drug is able to interact with that protein,” explains Knapp. “This is crucial in the early stages of developing a new medicine.”
Wall Street Journal reporter Dominique Mosbergen spotlights how Prof. James Collins and his lab have built their “own algorithms to trawl chemical databases, such as those of existing pharmaceutical drugs, for potential antibacterial compounds.” Collins’ His lab is “also experimenting with using generative AI to design completely new molecules that could kill bacteria,” writes Mosbergen.
Former postdoctoral associate Wen Shuhao and postdoctoral fellows Ma Jian and Lai Lipeng co-founded Xtalpi, a biotech startup that “uses AI and quantum physics-based calculations to find suitable structures that are fit for drug making,” reports Zinnia Lee for Forbes. The company plans to expand their technology to other industries such as solar panels and electric vehicle batteries.
Cofounded by postdoctoral associate Wen Shuhao and postdoctoral fellows Ma Jian and Lai Lipeng, biotech startup Xtalpi "combines AI, quantum physics, cloud computing and robotic automation to find novel molecules that could be developed into new medicines,” reports Zinnia Lee for Forbes. “Xtalpi has also recently expanded into discovering new chemical compounds for applications such as agriculture, cosmetics, healthcare, as well as petrochemicals and new materials for electric vehicle batteries,” writes Lee.
Prof. Regina Barzilay joins The Economist’s “Babbage” podcast to discuss how artificial intelligence could enable health care providers to understand and treat diseases in new ways. Host Alok Jha notes that Barzilay is determined to “overcome those challenges that are standing in the way of getting AI models to become useful in health care.” Barzilay explains: “I think we really need to change our mindset and think how we can solve the many problems for which human experts were unable to find a way forward.”
In a new paper, MIT researchers detail how they have used AI techniques to discover a class of “of antibiotics capable of killing methicillin-resistant Staphylococcus aureus (MRSA),” reports Helen Floresh for Fierce Biotech. “This paper announces the first AI-driven discovery of a new class of small molecule antibiotics capable of addressing antibiotic resistance, and one of the few to have been discovered overall in the past 60 years,” says postdoctoral fellow Felix Wong.
Researchers at MIT have used artificial intelligence to uncover, “a new class of antibiotics that can treat infections caused by drug-resistant bacteria,” reports Jeremy Hsu for New Scientist. “Our [AI] models tell us not only which compounds have selective antibiotic activity, but also why, in terms of their chemical structure,” says postdoctoral fellow Felix Wong.
Postdoctoral associate Wen Shuhao and postdoctoral fellows Ma Jian and Lai Lipeng co-founded Xtalpi, a biotech startup that uses “artificial intelligence to find chemical compounds that could be developed into new drugs,” reports Zinnia Lee for Forbes. “By combining AI, quantum physics, cloud computing and robotic automation, Xtalpi said it helps increase the efficiency and success rate of identifying novel drug compounds,” writes Lee. “The company has recently expanded into discovering new chemical compounds for agricultural technology, cosmetics and other applications.”
Researchers at MIT and elsewhere have used artificial intelligence to develop a new antibiotic to combat Acinetobacter baumannii, a challenging bacteria known to become resistant to antibiotics, reports Hannah Kuchler for the Financial Times. “It took just an hour and a half — a long lunch — for the AI to serve up a potential new antibiotic, an offering to a world contending with the rise of so-called superbugs: bacteria, viruses, fungi and parasites that have mutated and no longer respond to the drugs we have available,” writes Kuchler.
Researchers from MIT and McMaster University have used artificial intelligence to identify a new antibiotic that can fight against a drug-resistant bacteria commonly found in hospitals and medical offices, reports Ken Alltucker for USA Today. The researchers believe the AI “process used to winnow thousands of potential drugs to identify one that may work is an approach that can work in drug discovery,” writes Alltucker.