Q. You’re known for collaborating with colleagues across MIT, and at other institutions. How have these collaborations and affiliations helped you together with your research?Â
A: Collaboration has been central to the work in my lab. On the MIT Jameel Clinic for Machine Learning in Health, I formed a collaboration with Regina Barzilay [the Delta Electronics Professor in the MIT Department of Electrical Engineering and Computer Science and affiliate faculty member at IMES] and Tommi Jaakkola [the Thomas Siebel Professor of Electrical Engineering and Computer Science and the Institute for Data, Systems, and Society] to make use of deep learning to find recent antibiotics. This effort combined our expertise in artificial intelligence, network biology, and systems microbiology, resulting in the invention of halicin, a potent recent antibiotic effective against a broad range of multidrug-resistant bacterial pathogens. Our results were published in in 2020 and showcased the ability of bringing together complementary skill sets to tackle a worldwide health challenge.
On the Wyss Institute, I’ve worked closely with Donald Ingber [the Judah Folkman Professor of Vascular Biology at Harvard Medical School and the Vascular Biology Program at Boston Children’s Hospital, and Hansjörg Wyss Professor of Biologically Inspired Engineering at Harvard], leveraging his organs-on-chips technology to check the efficacy of AI-discovered and AI-generated antibiotics. These platforms allow us to check how drugs behave in human tissue-like environments, complementing traditional animal experiments and providing a more nuanced view of their therapeutic potential.
The common thread across our many collaborations is the flexibility to mix computational predictions with cutting-edge experimental platforms, accelerating the trail from ideas to validated recent therapies.
Q. Your research has led to many advances in designing novel antibiotics, using generative AI and deep learning. Are you able to speak about a few of the advances you’ve been an element of in the event of medication that may battle multi-drug-resistant pathogens, and what you see on the horizon for breakthroughs on this arena?
A: In 2025, our lab published a study in demonstrating how generative AI might be used to design completely recent antibiotics from scratch. We used genetic algorithms and variational autoencoders to generate hundreds of thousands of candidate molecules, exploring each fragment-based designs and completely unconstrained chemical space. After computational filtering, retrosynthetic modeling, and medicinal chemistry review, we synthesized 24 compounds and tested them experimentally. Seven showed selective antibacterial activity. One lead, NG1, was highly narrow-spectrum, eradicating multi-drug-resistant , including strains immune to first-line therapies, while sparing commensal species. One other, DN1, targeted methicillin-resistant (MRSA) and cleared infections in mice through broad membrane disruption. Each were non-toxic and showed low rates of resistance.
Looking ahead, we’re using deep learning to design antibiotics with drug-like properties that make them stronger candidates for clinical development. By integrating AI with high-throughput biological testing, we aim to speed up the invention and design of antibiotics which can be novel, protected, and effective, ready for real-world therapeutic use. This approach could transform how we reply to drug-resistant bacterial pathogens, moving from a reactive to a proactive strategy in antibiotic development.
Q. You’re a co-founder of Phare Bio, a nonprofit organization that uses AI to find recent antibiotics, and the Collins Lab has helped to launch the Antibiotics-AI Project in collaboration with Phare Bio. Are you able to tell us more about what you hope to perform with these collaborations, and the way they tie back to your research goals?
A: We founded Phare Bio as a nonprofit to take essentially the most promising antibiotic candidates emerging from the Antibiotics-AI Project at MIT and advance them toward the clinic. The thought is to bridge the gap between discovery and development by collaborating with biotech corporations, pharmaceutical partners, AI corporations, philanthropies, other nonprofits, and even nation states. Akhila Kosaraju has been doing an excellent job leading Phare Bio, coordinating these efforts and moving candidates forward efficiently.
Recently, we received a grant from ARPA-H to make use of generative AI to design 15 recent antibiotics and develop them as pre-clinical candidates. This project builds directly on our lab’s research, combining computational design with experimental testing to create novel antibiotics which can be ready for further development. By integrating generative AI, biology, and translational partnerships, we hope to create a pipeline that may respond more rapidly to the worldwide threat of antibiotic resistance, ultimately delivering recent therapies to patients who need them most.
