MIT Jameel Clinic for AI & Health

The epicenter of AI and health at MIT | Now on BlueSky: | Follow us on LinkedIn and Instagram.

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

Thanks to everyone who joined us at #MoML2026 yesterday! We had a blast 🤩 And congrats again to @MIT PhD student Tally Portnoi on being awarded the Best Paper Prize for her work on "zPocket: Finding Pockets with Frozen Cofolding Features"! 🏆

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

Industry talk #2! Danaher’s Andrey Tovchigrechko talks about how his team used @boltz_bio’s BoltzGen to design beta-zipper mini binder interfaces while using agentic tools to optimize the in silico pass rate in BoltzGen. #MoML2026

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

How are industry experts using ML in their research? @ByteDanceSeed_’s @chengyenhsieh presents on Protein Autoregressive Modeling: Taking initiative from the hierarchical nature of proteins, PAR generates backbones by forming a global topology & performing refinements. #MoML2026

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

Up next, @YaleMed’s @MarkGerstein talks about building world models to predict protein folding pathways 🧬 #MoML2026

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

Starting now, @ISTAustria’s Alex Bronstein talks about developing a general inference time optimization framework that can maximize log-likelihood and incorporate external constraints while eliminating dependence on diffusion length and removing initialization bias. #MoML2026

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

How can we improve target discovery for better drugs? @omenndarlingbio’s @idmjky talks about how EVOLVEpro demonstrates the usefulness of language models in optimizing protein function. He also introduces MESSI, for immunogenicity aware binder design.

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

Now hearing from @FU_Berlin’s @CecClementi on the short-sightedness of GNNs and potential solutions. She introduces a framework for efficiently and accurately simulating biomolecular complexes. #MoML2026

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

Poster Session I is in progress! Top 4 posters will be up all day! Who do you think will win the Best Paper Prize? 👀 #MoML2026

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

#MoML2026 Top 4: @PaulSharoubeem presents Electro-Prot, 6.7M-parameter encoder-decoder transformer trained on 162,980 APBS calculated fields to predict Poisson-Boltzmann potentials at arbitrary points around a protein!

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

#MoML2026 Top 4: @Northeastern and @broadinstitute’s Yikun Zhang presents on MolSAGE, a framework that accumulates and and reuses experience across tasks to build state-of-the-art drug models efficiently!

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

#MoML2026 Top 4: @mit’s Tally Portnoi introduces PocketWatch, a curated dataset of biologically relevant ligand pockets, and using this dataset to develop zPocket, which trains pocket-prediction heads on top of frozen features from co-folding models.

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

#MoML2026 Top 4: first up is MIRAGE, presented by @UCF’s Mehdi Yazdani-Jahromi. MIRAGE is a plug-in benchmark that applies the family-support axis to affinity and pose prediction.

[Dhananjay Bhaskar @dbhaskar92]

Can we design proteins from motion? Check out SPINET, our cellular sheaf-based inverse folding network: https://t.co/THiwkL4gmV

Curious how it works? Stop by poster #40 at the #MoML conference tomorrow (Oct 14) organized by @AIHealthMIT to meet co-first author Jens Lundsgaard!

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

👀 Next up: @pas_saro and @NoahBGetz from @boltz_bio present on their approaches to maximizing performance on structure and affinity prediction in the Boltz model series, and their work on using BoltzMol-1 to identify a target inhibiting DNA damage repair. #MoML2026

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

How can dynamic biomarkers improve patient care? @cityofhope’s Andrea Bild shares how evolutionary models can transform cancer therapeutics.

[Mark Gerstein @MarkGerstein]

Posting my talk tomorrow at MoML 2026 at @MIT (organized by @AIHealthMIT https://t.co/LKnt6bApyw New slides on World Modeling for drug dev. & its integration with @daifengwang's drug repurposing

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

#MoML2026 is underway! #JameelClinic faculty lead @BarzilayRegina opens the conference with a presentation on the state-of-the-art in molecular modeling.

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

We're excited to hear from @YaleMed's @MarkGerstein on Wednesday, Oct. 14 for #MoML2026! <20 tickets left!
🎟️ Register now before tickets are sold out: https://t.co/lzl4hTohHY

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

"We need to figure out the best way to ensure that women at increased risk don't panic, and that women at low risk don't become so indifferent that they forgo future screening altogether," says Allweis. 3/3

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

How do you communicate risk to a patient? To kick off #BreastCancerAwarenessMonth, we're excited to share that @Hadassah_Med has started using Mirai in clinical trials to assess breast cancer risk + how women feel about personalized risk assessment, w/ Tanir Allweis @ the helm 🧵

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

Allweis, who was a '25 Visiting Professor @AIHealthMIT and the current Chair of the Dept of Breast Surgery @Hadassah_Med believes that understanding women's attitudes towards AI-based risk assessment is key to understanding how best to communicate risk to patients. 2/3