Sheng Wang Assistant Professor Paul G. Allen School of Computer Science & Engineering University of Washington, Seattle Email: swang [at] cs (dot) washington (dot) edu

I am interested in using generative AI methods to solve biomedical problems:

Use off-the-shelf language models to solve biomedical problems. See BioTranslator, an intermediate layer that can translate between text data and bio data, which enables us to apply LMs (e.g., PubMedBERT) to non-text biodata.
Build large-scale pre-trained (language) model for biological data (e.g., Hi-C, ATAC-seq, RNA-seq).
See our recent Nature paper GigaPath. We use generative AI techniques to embed extremely large whole-slide pathology images (40,000 * 40,000 pixels!).
Media coverage: Forbes, Yahoo, Becker’s hospital review, Fierce biotech, CTOL digital solutions, HIT consultant, GeekWire, Cosmic log, HealthXL, RamaOnHealthcare, Providence, nikkei, cryptorank

Teaching: AI for Drug Discovery (Spring) and AI for Medicine (Fall).

Publications
Group

Education and experience

Postdoctoral Researcher, Stanford University (Jan 2021)
Advisor: Prof. Russ Altman.
Ph.D. in Computer Science, University of Illinois at Urbana-Champaign (May 2018)
Advisors: Prof. ChengXiang Zhai and Prof. Jian Peng.
Thesis: Leveraging knowledge network for precision cancer therapy.
B.S. in Computer Science, Peking University (May 2013)