MIT Jameel Clinic

Universal flu vaccine: How scientists are closing in on the virus's 'weak spots' While current flu shots need to be updated each season, scientists are finding new ways to make vaccine that could last much longer and cover more strains.

Can we make a better flu vaccine with AI? @aihealthmit.bsky.social AI faculty lead Regina Barzilay spoke with BBC about how she designed an AI model that outperforms the @who.int when it comes to flu vaccine selection. www.bbc.com/future/artic...

Researchers @aihealthmit.bsky.social & Meta were recently selected to give an oral presentation @iclr-conf.bsky.social on GLASS Flows, a method for improving the computational efficiency of flow matching and diffusion models.
📄 Paper: openreview.net/pdf?id=vH7OA... #AISky

MIT scientists investigate memorization risk in the age of clinical AI MIT Jameel Clinic scientists have designed a series of tests to ensure that foundation models trained on electronic health records don't leak sensitive patient information when prompted by a bad ...

Clinical AI models may inadvertently leak patient data to attackers. 🔐 MIT researchers including Sana Tonekaboni & @marzyehghassemi.bsky.social propose a risk evaluation framework to help prevent memorization of sensitive info. 🧠💡 Read more: news.mit.edu/2026/mit-sci... #AISafety #PatientPrivacy

GEN Editors Reflect on Six of the Biggest Stories of the Year For the scientific enterprise, 2025 was marked by setbacks and challenges. But scientists are no strangers to adversity—the ability to overcome obstacles is built into our training. In turn, research ...

Boltz-2 is one of GEN News's six biggest stories of 2025! 📰Congrats to the Boltz-2 team and thank you @faylinphd.bsky.social for the recognition!
www.genengnews.com/industry-new... #AISky

AI steps in to detect the world's deadliest infectious disease There's a global shortage of radiologists. Now artificial intelligence is helping speed up the diagnosis of tuberculosis in hard-to-reach communities.

MIT Jameel Clinic AI faculty lead Regina Barzilay predicts that AI adoption will be much faster in countries w/ developing economies. "They have serious unmet needs and the clinician understands they need other help." @gabrielleemanuel.bsky.social @npr.org #MedSky www.npr.org/sections/goa...

Blue and white graphic overlaid with text that reads "Introducing BoltzGen: Toward Universal Binder Design" followed by headshots and names of the speakers starting from the top "Hannes Stark, PhD student, MIT; Regina Barzilay, AI Faculty Lead, MIT Jameel Clinic; Tommi Jaakkola, Principal Investigator, MIT Jameel Clinic" Followed by event details: "When: Thursday, Oct. 30, 5pm-6pm; Where: 32-123, Stata Center; RSVP jclinic.mit.edu/events/boltzgen/"

Join us today at MIT from 5pm-6pm for a seminar for BoltzGen, which is free and open to the public! Looking forward to seeing you all later today! 🤩 If you plan to attend, don't forget to RSVP so we can plan accordingly: luma.com/7474iho2
#AISky #AcademicSky

Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project is collaborating with a broad network of leading wetlabs that test BoltzGen at an unprecedented scale, showing success on many novel targets and pushing the model to its limits!

Photo of Regina Barzilay seated at her desk looking at the camera. The photo is framed by a black and red graphic that also reads "TIME100/AI 2025"

We're thrilled to share that @aihealthmit.bsky.social faculty lead Regina Barzilay has been included in TIME's list of #TIME100AI for 2025! 👏
📢Full Announcement: jclinic.mit.edu/regina-barzi...
📰More from TIME: time.com/collections/... #AISky

Can artificial intelligence cause medical errors? This MIT researcher shows it can. - The Boston Globe As hospitals rush to embrace AI systems that help diagnose diseases, Marzyeh Ghassemi's research suggests the technology is still rife with flaws and biases.

How can small errors in medical notes lead AI to misdiagnose patients? @bostonglobe.com's Tech Columnist Hiawatha Bray explores @aihealthmit.bsky.social PI @marzyehghassemi.bsky.social's pioneering research on AI bias in healthcare in a new feature published today. bostonglobe.com/2025/08/27/b...

Redefining druggable targets with artificial intelligence - @wcmenglanderipm.bsky.social @aihealthmit.bsky.social go.nature.com/4fHNMYi

3 ways AI helps to empower health care clinicians | MIT Sloan In health care, AI is speeding up administrative tasks, improving the accuracy of diagnoses, and curtailing unnecessary treatment.

🤖 Rapid advancements in AI have resulted in job replacement anxiety, even in medicine. But how can AI empower clinicians to improve medicine? 🩺 Jameel Clinic AI faculty lead Regina Barzilay shares her insights with MIT Sloan Exec Ed.
📰 Read: mitsloan.mit.edu/ideas-made-t... #AISky #MedSky

Blue graphic overlaid with black text that reads "'For outstanding contributions to the integration of computers and communications.' | 2025 IEEE Koji Kobayashi Computers and Communications Award | Dina Katabi, PhD | MIT Jameel CLinic" with a photo of the Koji Kobayashi medal on the left and a headshot of Dina Katabi on the right.

Please join us in congratulating #JameelClinic PI Dina Katabi on being awarded with the prestigious 2026 IEEE Koji Kobayashi Computers and Communications Award 👏
📰 Announcement: jclinic.mit.edu/ieee-award-2... #MachineLearning #AcademicSky

📣 Calling all students and postdoctoral researchers in the field of molecular machine learning: submit your work to #MoML2025 @ MIT for free admission!
📄Submit: moml.mit.edu/submit
🐦 Register Early Bird for 40% off your ticket: moml.mit.edu/event-detail... #MachineLearning #moleculardesign

White text overlaid on a blue graphic that reads "MIT-MGB AI Cures 2025 | Monday, September 22 | Samberg Conference Center

📢We’re thrilled to announce the return of #AICures2025 on Monday, Sept. 22! This year’s conference features a new workshops focused on deploying AI tools in clinical care and more!
📄Call for abstracts: forms.gle/mxtLqzD9aPy6...
🎟️Register now: mitmgb.ai

Cesar de la Fuente-Nunez (left), Jim Collins (right)

🦠 "Common infections could once again become fatal." A new essay in Physical Review Letters by @delafuentelab.bsky.social & @aihealthmit.bsky.social faculty lead Jim Collins on how AI could transform antibiotic discovery. journals.aps.org/prl/abstract...

Top row (left to right): Yuexing Hao, Zhiwen Qiu, Jason Holmes, Corinna E. Löckenhoff Bottom row (left to right): Wei Liu, Marzyeh Ghassemi, Saleh Kalantari

💬 The use of LLMs for cancer care has grown rapidly in recent years. But a recent meta-analysis published in npj Digital Medicine, co-authored by @aihealthmit.bsky.social PI @marzyehghassemi.bsky.social revealed gaps in the clinical readiness of this technology. #MedSky nature.com/articles/s41...

Top row (left to right): Felix Wong, Alicia Li, Satotaka Omori, Ryan Lach, Jose Nunez, Yunke Ren Middle row (left to right): Sean Brown, Vipul Singhal, Brent Lyda, Taivan Batjargal, Ethan Dickson, Jose Roberto Rodrigues Reyes Bottom row (left to right): Juan Manual Uruena Vargas, Shalaka Wahane, Hahn Kim, Jim Collins, Maxwell Wilson

💡 Did you know that all cells have an integrated stress response (ISR), which helps cells survive stressors? In a new paper published in @cellpress.bsky.social, researchers introduce a new light-based tool (an optogenetic platform) that controls the ISR in cells.
📄: www.cell.com/cell/abstrac...

6 film festivals and series to check out this summer From Boston to Provincetown, WBUR film critic Erin Trahan highlights the many places to enjoy documentaries, indie films, and local shorts this season.

🎞️ ATTN Boston-area science professionals & film lovers: The Woods Hole Film Festival (July 26 - Aug. 2) will screen “Cracking the Code: Phil Sharp and the Biotech Revolution" on July 31, a documentary about @aihealthmit.bsky.social Chair and Nobel Laureate Phil Sharp! www.wbur.org/news/2025/06...

🔮 A new deep learning model called ORAKLE can predict which sepsis patients are at-risk of MAKE30 i.e. Major Adverse Kidney Events within 30 days, defined by the following: 1️⃣ requiring dialysis 2️⃣ persistent kidney dysfunction 3️⃣ death.
📄: link.springer.com/article/10.1... #MedSky #AISky

Microsoft Says Its New AI System Diagnosed Patients 4 Times More Accurately Than Human Doctors The tech giant poached several top Google researchers to help build a powerful AI tool that can diagnose patients and potentially cut health care costs.

Are we approaching medical superintelligence? 🤖 @wired.com's @willknight.bsky.social interviewed @aihealthmit.bsky.social PI David Sontag to understand what @microsoft.com's MAI-DxO means for the future of healthcare.
📰: www.wired.com/story/micros... #MedSky #AISky

Congrats to @aihealthmit.bsky.social PI Connor Coey on becoming one of 11 faculty members to be granted tenure @mit.edu!
📰 More in MIT News: news.mit.edu/2025/tenured...
📖 More on Connor Coley and his research: jclinic.mit.edu/team-member/... #AcademicSky #AISky

Q&A: A roadmap for revolutionizing health care through data-driven innovation "The Analytics Edge in Healthcare," co-written by MIT Vice Provost for Open Learning Dimitris Bertsimas and two MIT alumni, explores how analytics is driving decisions and outcomes in health...

How can hospitals reduce patient length of stay or the turnover of its nurses? If you're looking for a health-focused #SummerRead ☀️ try "The Analytics Edge in Healthcare," a new book co-authored by @aihealthmit.bsky.social faculty lead Dimitris Bertsimas: news.mit.edu/2025/qa-road... #MedSky

Blue graphic overlaid with white text that reads "Newsweek AI Impact Awards 2025" followed by "Phare Bio 'Most Innovative AI Technology or Service, Extraordinary Impact in AI Innovation'"

Congratulations to @aihealthmit.bsky.social faculty lead Jim Collins' lab and Phare Bio for being awarded w/ @newsweek.com's AI Impact Award for their landmark contribution to AI-driven antibiotic discovery! 🔥
📰 Read more: jclinic.mit.edu/ai-impact-aw...
#AISky

First row, from top (left to right): Zhengkai Tu,Sourabh J. Choure, Mun Hong Fong, Jihye Roh, Itai Levin Second row (left to right): Kevin Yu, Joonyoung F. Joung, Nathan Morgan, Shih-Cheng Li, Xiaoqi Sun Third row (left to right): Huiqian Lin, Mark Murnin, Jordan P. Liles, Thomas J. Struble, Michael E. Fortunato Bottom row (left to right): Mengjie Liu, William H. Green, Klavs F. Jensen, Connor W. Coley

Since the 1960s, chemists have sought the aid of computer-aided synthesis planning (CASP) in chemical synthesis 🧪 Researchers @aihealthmit.bsky.social published a new paper introducing ASKCOS, an open source CASP tool performing a wide range of tasks.
📄: pubs.acs.org/doi/full/10.... #ChemSky #AISky

Top row (left to right): Vivek Gopalakrishnan, Neel Dey, Polina Golland Bottom row: diagrams showing a 3D image of the top portion of a skeleton, from the shoulders to the head with accompanying X-rays and CT scans.

Matching X-rays to 3D images is critical for delicate procedures. Vivek Gopalakrishnan, Neel Dey, & @aihealthmit.bsky.social PI Polina Golland present PolyPose, which matches 2D X-rays to 3D scans, maintaining robust performance w/o additional tuning. #MedSky pmc.ncbi.nlm.nih.gov/articles/PMC...

Boltz-2 virtual seminar · Luma Join us for on online seminar where we will share the details of our new model Boltz-2 and discuss the future of biomolecular modeling 🧬 The Zoom link will…

Tue, 6/17 12pm ET on Zoom 🎦 Saro Passaro, @gcorso.bsky.social, @jeremywohlwend.bsky.social will present Boltz-2! Models + careful affinity data handling result in an affinity predictor approaching FEP accuracy @ 1000x the speed 🔥
Details: portal.valencelabs.com/starklyspeak...
🗓️RSVP: lu.ma/4bpuwbsr

Can AI Predict Breast Cancer? NAM Feature Story

What if a mammogram could predict breast cancer risk years in advance?

@aihealthmit.bsky.social‬'s Regina Barzilay and her team built MIRAI, a machine learning model that uses mammograms to identify a patient's risk long before signs are visible on a scan.

MIT and Recursion partner for AI drug discovery tool Freely available Boltz-2 algorithm can predict small-molecule binding affinities

A team led by Regina Barzilay, a computer science professor at MIT, has launched Boltz-2, an algorithm that unites protein folding and prediction of small-molecule binding affinity in one package. cen.acs.org/pharmaceutic... #chemsky 🧪

Boltz-2: democratising the future of drug design Open source structure prediction with binding affinity

Move over AlphaFold3. Boltz-2 has arrived, bringing affinity prediction for protein-small molecule interactions!

Can’t wait to see what this group does next. Congrats to all @gcorso.bsky.social

Was a pleasure writing this:
www.cancergrandchallenges.org/news/boltz-2...

What a turnout! 🤯 Thank you to the 400+ attendees who came to listen to the first-ever Boltz-2 presentation in-person and for asking great questions! We look forward to seeing how Boltz-2 will empower future research in biomolecular structure prediction! 🧬🔥 #AIsky