I
Computational Molecular Design
- Computer-aided drug design
- AI for drug development
NTU CSIE · Est. 2006
Computational Molecular Design and Metabolomics Lab
Prof. Yufeng Jane Tseng · Department of Computer Science and Information Engineering
We develop algorithms and tools to identify and design molecular structures for targeted use, to detect biomarkers in clinical metabolomics cohorts, and to carry the same methods into environmental chemistry and clinical assessment. The work is published in international journals and runs in public tools and commissioned systems.
Research Pillars
II
Metabolomics
- Biomarker detection
- Precision medicine
III
Quantum Computing
- Quantum algorithms for drug discovery and patent search
- Variational quantum eigensolver (VQE) for molecular properties
- Evaluation of quantum programming platforms
IV
Medical Image Computing
- Video-based movement and motor-symptom quantification
- Parkinsonian and movement-disorder assessment
- Clinical image analysis and image-to-image translation
- Semi-supervised learning for clinical image interpretation
V
AI Agent Systems
- Scientific literature analysis and citation agents
- Regulatory and chemical risk assessment automation
- Retrieval-augmented generation (RAG) knowledge bases
- Large language models (LLM) for clinical assessment
Lab Record
The lab studies molecules and metabolites by computation, developing algorithms and software tools and applying them to drug development, environmental and regulatory chemistry, and clinical assessment. Its two founding directions -- computational molecular design and biomarker detection in metabolomics -- have grown to five, the others being quantum computing, medical image computing and AI agent systems.
The method work spans drug-property prediction, environmental analysis and clinical assessment: recent examples include predicting P-glycoprotein substrates with interpretable graph neural networks, curating a CYP450 interaction dataset that covers most of phase I drug metabolism, and using deep learning to speed up the non-targeted annotation of per- and polyfluoroalkyl substances. The output is not only papers: the datasets and the tools are themselves the product.
The lab also runs commissioned systems. Since September 2021 it has delivered GreenN (SAS), the Searching, Assessment and Screening System for Safer Alternative Chemicals, for the Chemicals Administration of the Ministry of Environment: it helps companies weigh a chemical's hazard, how closely it is regulated, and what it can be replaced with, and the project is ongoing. "AI-Powered Green Chemistry Diagnostic Advisor", built on that framework, received a Team Excellence Award at the Presidential Hackathon 2025.
| Director | Prof. Yufeng Jane Tseng |
|---|---|
| Affiliation | NTU CSIE · BEBI · GSB · MHI · GINM |
| Public tools | 8 services under cmdm.tw |
| Publications | 113 since 2006 |
| Alumni | 97 since 2008 |
| People | 38 current members |
News
- 2025, Professor Yufeng Jane Tseng spoke at the invitation of Chang Gung University's College of Intelligence Computing and its Artificial Intelligence Research Center on "Artificial Intelligence in Drug Discovery and Drug Development: Applications and Prospects" [Chang Gung University]
- Since September 2021 the lab has run GreenN (SAS), the Searching, Assessment and Screening System for Safer Alternative Chemicals, commissioned by the Chemicals Administration of the Ministry of Environment and ongoing [GreenN (SAS)]
- 2018, Professor Yufeng Jane Tseng spoke at the invitation of the Development Center for Biotechnology (DCB) on "The Impact of AI and Machine Learning on Clinical Data Science in Drug Development"
- 2018, Professor Yufeng Jane Tseng was invited to speak at the Healthcare Expo Taiwan (DCB X AI) on "AI for drug development: What's ready to go !"
- 2018, Professor Yufeng Jane Tseng was invited to speak at the symposium on high-throughput microchannel chemical synthesis on "Predictive Toxicology"
Recent Publications
Movement Anywhere: An Open-Source Distributed 2D Video-Based Movement Analysis Platform Empowered by Active Learning
Publisher →A robust and interpretable graph neural network-based protocol for predicting p-glycoprotein substrates
Publisher →Advantages of two quantum programming platforms in quantum computing and quantum chemistry
Publisher →Altered gut microbial networks and metabolic pathways in multiple system atrophy: a comparative 16S rRNA study
Publisher →Selected Awards
2026, a faculty and student team supervised by Professor Yufeng Jane Tseng received the year's only Special Award in the NTU Electrical Engineering Class of 1975 Alumni Endowed Award for Technology Research Innovation, for "AI-Powered Green Chemistry Diagnostic Advisor".