Jun Wen(文俊)
Scholar

Jun Wen(文俊)

Google Scholar ID: Gw2ekPsAAAAJ
Harvard University | Zhejiang University
AI for precision medicineComputational geneticsEHR data analysisBiomedical informatics
Citations & Impact
All-time
Citations
1,025
 
H-index
17
 
i10-index
24
 
Publications
20
 
Co-authors
0
 
Publications
20 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • Published 'Phenotypic Prediction of Missense Variants via Deep Contrastive Learning' in Nature Biomedical Engineering (accepted, 2025)
  • Published 'LATTE: Label-efficient Incident Phenotyping from Longitudinal EHR' as a cover article in Patterns (Cell Press, 2024)
  • Published 'Multimodal Representation Learning for Predicting Molecule–Disease Relations' and 'Heterogeneous Entity Representation for Medicinal Synergy Prediction' in Bioinformatics (2023, 2025)
  • Published 'DOME: Directional Medical Embeddings from EHR' in Journal of Biomedical Informatics (2025)
  • Published 'Label-efficient Phenotyping for Long COVID Using EHR' in npj Digital Medicine (2025)
  • Published 'Deep Learning from EHR to Identify RCC Recurrence' in Annals of Oncology (2024)
  • Developed multiple AI frameworks/models including PheMART, INTERLACE, HERMES, CaSBRE, LATTE, SeDDLeR, and DOME for drug repurposing, phenotyping, and risk prediction
Background
  • Currently a Postdoctoral Research Fellow at the Department of Biomedical Informatics, Harvard Medical School, working with Professor Tianxi Cai
  • Also serves as a Data Scientist at the Veterans Affairs Boston Healthcare System, collaborating with Dr. Kelly Cho
  • Will join the Department of Computational Biology at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) as an Assistant Professor in January 2026
  • Founding the PAI Lab (Precision-medicine AI Lab) at MBZUAI to advance AI for precision medicine
  • Research focuses on developing network-based AI frameworks that integrate multimodal biomedical data—including knowledge graphs, electronic health records (EHRs), and biobank data—to improve diagnosis, treatment, and drug discovery
Co-authors
0 total
Co-authors: 0 (list not available)