Junbo (Jacob) Shen
CS '24 St. Louis, MOI graduated summa cum laude with B.S. in Computer Science from Washington University.
See details in [CV].
Research Interests
I work on ML for healthcare, with research experience across different areas:
- LLMs & foundation models for biomedicine
Clinical text/images, EHR, genomic/protein sequence modeling for drug discovery.
- Probabilistic & graphical models for biomedical data
Structured modeling of high-dimensional biomedical data.
I do not limit myself to a single direction, always open to exploring new problems, aiming for future research with genuine real-world impact.
News
- 2026Our work on antimicrobial peptide discovery appeared in Nature Biomedical Engineering. I contributed data and experiment analysis and visualization.
- 2026Our cardiac-specific CT foundation model was accepted by Nature Communications. I contributed foundation-model baselines and experiments.
- LangPatch, our work linking neuronal transcriptomes and electrophysiology through language, is available as a preprint.
- “A Novel Generative Multi-Task Representation Learning Approach for Predicting Postoperative Complications in Cardiac Surgery Patients” accepted by Journal of the American Medical Informatics Association (JAMIA)
Earlier updates
- Received B.S. in Computer Science with Summa Cum Laude (GPA 3.98/4.00)
- Received Outstanding Senior Award at WashU McKelvey School of Engineering
- “Unbiased organism-agnostic and highly sensitive signal peptide predictor with deep protein language model” accepted by Nature Computational Science
Selected Publications & Manuscripts
Google Scholar
Language as the interface: Foundation-model contrastive learning links transcriptomes and electrophysiology
Under review at ICLR 2027 · 2026
A Novel Generative Multi-Task Representation Learning Approach for Predicting Postoperative Complications in Cardiac Surgery Patients
Journal of the American Medical Informatics Association (JAMIA) · 2025
Unbiased organism-agnostic and highly sensitive signal peptide predictor with deep protein language model
Nature Computational Science · 2024
Uncovering evolutionarily remote and highly potent antimicrobial peptides with protein language models
Nature Biomedical Engineering · 2026
My contribution to Uncovering evolutionarily remote and highly potent antimicrobial peptides with protein language models
Contributed data and experiment analysis and scientific visualization.
A cardiac-specific CT foundation model for heart transplantation
Nature Communications · Accepted · 2026
My contribution to A cardiac-specific CT foundation model for heart transplantation
Implemented CT segmentation foundation-model baselines (SAM, MedSAM and SegVol) and ran their experiments.
Deep Learning Predicts Synergy Effect of Antibacterial Drug Combinations
Manuscript in preparation
* equal contribution
Research Experience
details in CVSep 2026 - Present
Chinese University of Hong Kong
Research Assistant · Computer Science and Engineering
PI: Prof. Yu Li
LLM-based multi-agent system for AMP discovery Co-Lead
LLM-based multi-agent pipeline that automates discovery of novel antimicrobial peptides from human metagenomic data by orchestrating sequence models, AMP/SP predictors, and filtering tools into a unified workflow.
Oct 2025 - Present
Beijing Academy of Artificial Intelligence
ML Engineer Intern (Research, full-time) · Brainµ team
Mentor: Dr. Bo Lei
Aligning neuronal transcriptomes and electrophysiology Lead
Developed LangPatch, aligning Patch-seq transcriptomes and electrophysiology through gene descriptions and verbalized electrophysiological features embedded by one frozen text encoder.
Achieved the highest mean transcriptome-to-electrophysiology correlation among the evaluated methods on mouse visual, mouse motor and human cortex data; 39-49% lower cross-modal matching error than JAMIE on the mouse cohorts, with approximately 70% / 47% correlation retention in transfer to motor / human cortex.
Feb 2023 - Dec 2024
Washington University AIHealth, School of Medicine / CSPL
Research Intern
PIs: Chenyang Lu, Joanna Abraham
surgVAE - Generative multi-task model for cardiac surgery outcome prediction Lead
Probabilistic VAE-based framework for preoperative prediction of six critical postoperative complications in high-risk cardiac surgery patients, leveraging cross-surgery EHR (89k+ cases), disentangled latent spaces, and multi-task learning to improve both performance and interpretability on modifiable risk factors.
Deep learning for broadband spectrum reconstruction Contributor
Optical conv2seq model for reconstructing broadband spectra from crystal responses, with GPT-style baselines and noise-robustness experiments.
Jun 2024 - Nov 2024
University of Washington, Seattle
Research Intern
PI: Sheng Wang
Slide-level pretraining for pathology WSI FMs Co-Lead
Developed slide-level pretraining for pathology FMs by representing each WSI as a variable-length sequence of ViT tile embeddings and training a slide encoder with DINO/DINOv2-style self-distillation.
CT segmentation foundation models Contributor
Implemented SAM, MedSAM, and SegVol pipelines for CT segmentation foundation models.
Jun 2022 - Jun 2025
Chinese University of Hong Kong, CSE
Research Intern
PI: Yu Li
USPNet - Unbiased signal peptide prediction with protein language models Lead
Organism-agnostic SP prediction framework leveraging MSA Transformer and ESM2 with a label distribution-aware margin loss to handle severe class imbalance and domain shift; outperforms prior methods on SP classification and cleavage prediction and discovers hundreds of novel SP candidates from metagenomes.
Genome-drug foundation model for AMR prediction Lead
Genome-drug paired FM that predicts AMR phenotypes from full bacterial genomes and antibiotic structures using genomic LLM pretraining, multi-modal binding, and multi-instance learning.
DNA-FM + molecular-FM for antibacterial drug combination synergy Co-Lead
Framework that predicts synergy of antibacterial drug combinations by combining pre-trained molecular graph models for drugs with genomic foundation models for full bacterial genomes.
Education
Washington University, St. Louis, MO
McKelvey School of Engineering
B.S. in Computer Science
Summa cum laude · GPA 3.98 / 4.00
Aug 2022 - May 2024
- Outstanding Senior Award (Awarded to 2 seniors at WashU CSE)
- Tau Beta Pi Engineering Honor Society
- Dean's Lists
Before transferring, I was in CUHK's CS ELITE Stream
Leadership & Service
Reviewer
American Medical Informatics Association (AMIA)
Dec 2025
Reviewed paper submissions for the AMIA 2026 Annual Symposium
Teaching Assistant
Washington University
Jan 2023 - May 2024
Data Mining (Spring 2024), Intro. to AI (Fall 2023), Intro. to Cryptography (Spring 2023)
Random Misc.
I grew up Korean Chinese (ethnic minority in China), so I know a bit of Korean.
Favorite J-pop band is Mrs. GREEN APPLE — their songs support me at my darkest.
My primary drive for research is fun.
I prefer not to work on research that feels purely incremental.