ITUAI Seminar Series – Prof. Reza Abbasi-Asl

We are excited to announce that our next speaker in ITU AI Seminar series is Prof. Reza Abbasi-Asl.

Topic: CellTransformer: Data-driven fine-grained region discovery in the mouse brain with transformers

Onsite Event: 10 November 2025, 14:15 - 15:15, Istanbul Technical University, Ayazaga Campus, Faculty of Computer & Informatics Engineering, Z17 - A2 Lecture Hall

Abstract

The analysis of organ-scale spatial transcriptomic datasets, which often exceed millions of cells, presents a major computational bottleneck. Existing methods have difficulties scaling to identify distinct tissue domains from this massive data. To address this challenge, we developed CellTransformer, a self-supervised workflow that learns high-level tissue features from molecular patterns. We applied CellTransformer to whole mouse brain data, demonstrating its ability to accurately rediscover known anatomical structures while also identifying previously uncataloged subregions in the mouse brain. This work provides a scalable and robust solution for fine-grained domain discovery in complex, large-scale spatial data..

Short Bio

Reza Abbasi-Asl is an associate professor of neurology, bioengineering and therapeutic sciences at the University of California, San Francisco. His lab investigates the role of interpretable machine learning in understanding brain functions and related disorders. He has led multiple studies on artificial intelligence for neuroanatomy and health technology, including the creation of one of the most detailed maps of the mouse brain using transformer-based models, published in 2025. He earned his Ph.D. and M.Sc. in electrical engineering and computer sciences at the University of California, Berkeley in 2018. He also holds an M.Sc. in biomedical engineering from Sharif University of Technology (2013) and a B.Sc. in electrical engineering from Amirkabir University of Technology (2010). Prior to joining the University of California, San Francisco, he was a scientist at the Allen Institute for Brain Science.