Our next lightning talk is 🧑‍🏫 “What Can a Node Learn from Its Neighbors in Graph Neural Networks?” by @AstropowerDev, Chongwei Chen, Matthew Xu, and @WangQianwenToo.

Excited to share TxGNN, a model that identifies potential therapies from existing medicines for thousands of diseases. Trained across 17,080 diseases, TxGNN predicts drug candidates for conditions with limited or no treatment options, including rare diseases @NatureMedicine paper: Globally, there are over 7,000 rare and undiagnosed diseases, yet only 5 to 7 percent have treatments, leaving the majority untreated or undertreated. Even for more common diseases, new drugs could offer alternatives with fewer side effects or replace drugs that are ineffective for certain patients TxGNN generates new insights on its own in the form of multi-hop interpretable rationales, applies them to diseases it was not trained for, and offers explanations for its predictions Human evaluation showed that TxGNN's predictions perform well across multiple axes of performance Many of TxGNN's predictions align with off-label prescriptions used in a large healthcare system Many thanks to a fantastic research team @KexinHuang5 @payal_chandak @WangQianwenToo @_toolazyto_ @AkhilVaidMD @jure @girish_nadkarni @BenGlicksberg @HarvardDBMI @harvardmed @KempnerInst @harvard_data @broadinstitute @cziscience @harvardmed News and Gazette: Thanks @EkaterinaPeshev

@UMNComputerSci is offering a 10-week summer @NSF REU program for undergraduate students who are interested in research on Human-Centered Computing for Social Good. Stipend is provided. Apply by Apr 10; applications will be accepted until filled

Colloquium continues next Monday with @WangQianwenToo from @UMNews. The talk titled "Interpreting and Steering AI Explanations with Interactive Visualizations" will be held in Keller Hall 3-210. Full abstract: