Join us!

We're always interested in possible postdocs & students. If interested, please email me for more information.

In 2025, we're organizing the Text Mining COSI at ISMB & Workshop on Generative AI and LLMs at PSB. Come and join us for these scientific events!

Our 2024 JAMIA special issue on LLMs in Biomedicine is now out. See here

Selected publications

1. Matching Patients to Clinical Trials with LLMs, Editors' Highlights at Nat Comm, 2024.
2. Tracking genetic variants in biomedical literature using LitVar 2.0, Nat Genet, 2023.
3. Predicting myocardial infarction through retinal scans, Nature Mach Intell 2022.
4. LitCovid: Keep up with the latest coronavirus research, Nature 2020.
5. How user intelligence is improving PubMed, Nature Biotechnology 2018.

Recent NLP/AI tools

1. TrialGPT: LLM for patient-to-trial matching. Featured in NIH News & NIH Director's Blog
2. MedCPT: foundation models for embedding bio-texts. See details in Bioinformatics.
3. DeepSeeNet, automated AMD diagnosis & prognosis. See details in Ophthalmology.

Web-based Lit Search Tools

1. PubTator: Automated concept annotation for full-text articles. NAR 2013, 2019, 2024
2. TeamTat: a collaborative text/corpus annotation tool. NAR 2020.
3. LitSuggest: a system for literature recommendation and curation. NAR 2021.
4. LitSense: Making sense of biomedical literature at sentence level. NAR 2019.
5. LitVar: a semantic literature search engine for genomic variants. NAR 2018.

ChestX-ray14 Data Release

ChestX-ray14, one of the largest chest x-ray datasets, is now publicly available. Check out our CVPR paper and the recent NIH press release. This work received 2017 NIH Clinical Center Director's Award.