TMU AIBioMed Lab

TMU AIBioMed Lab

Artificial Intelligence for Biomedicine

Grants

Research at TMU AIBioMed Lab is supported by competitive research grants and institutional funding from the National Science and Technology Council (NSTC), Ministry of Education (MOE), National Health Research Institutes (NHRI), Taipei Medical University (TMU), and collaborating institutions.

The following projects highlight our research activities in artificial intelligence, bioinformatics, computational biology, medical imaging, genomics, and interdisciplinary biomedical research:

Toward trustworthy large language model-assisted cell type annotation in single-cell RNA sequencing

Artificial Intelligence–Assisted Stool Phenotyping and Gut Biomarkers for Predicting Sleep Disturbances in Children with Constipation Spectrum Disorders: An Integrative Multimodal Study

Foundation Models in Action: Transforming Protein-Ligand Interaction Predictions for Drug Design

Assessment of Nutritional Deficiency Patterns and Pharmacotherapy Outcomes in Patients admitted to Emergency and Intensive Care Units

A Microbial Insights and Stool Imaging Approach to the Interplay Between Gastrointestinal Discomforts and Sleep Disturbances in Children: A Pathway to Personalized Pediatric Care

Towards interpretable genotyping of non-small cell lung cancer: an explainable AI approach leveraging CT-based radiomics

The Development and Validation of a Prediction Algorithm for First-Onset and Recurrence of Major Depression in General Population: A Genetic, Epigenetic and Drug Repurposing Approach

Develop IL-19 antibody immunotherapy and unravel immunosuppressive mechanism in peritumoral region of glioblastoma by single cell transcriptome analysis

Sequence-based protein function prediction using graph transformers and deep representative learning

Development of innovation optoelectronic AI detection technology, antibacterial materials, and machine learning database construction for catheterization-associated urinary tract infection in patients

The application of artificial inteligence to predict the clinical outcome through MRI imaging in patients with nasopharyngeal carcinoma

Incorporating transfer learning and CT radiomics in classifying molecular subtypes of NSCLC

The development and validation of a prediction algorithm for first onset of major depression in general population: a genetic, epigenetic and drug-driven approach

Machine learning algorithm for classification of Ductal carcinoma in situ and minimal invasive breast cancer on mammography

Research Grant for “110 Top International Journal Award”

DeepNLP-DNA: a pre-trained NLP model for DNA sequence representation using deep transformers and 2D convolutional neural networks

Incorporating radiogenomics and NLP to improve the predictive performance of lung cancer recurrence

An artificial intelligence system for precision lung cancer based on clinical big data

Incorporating radiogenomics and NLP to improve the predictive performance of lung cancer recurrence

Research Grant for Newly Hired Faculty

GPU Grant