John leads a research programme at Duke-NUS Medical School that aims to decode and reprogram human cell states using single-cell genomics and artificial intelligence. His work integrates large-scale data generation with machine learning models to uncover the regulatory circuits that drive immune dysfunction in ageing, cancer, and autoimmune diseases. By combining computational predictions with experimental validation, his group seeks to develop new strategies to reverse pathological cell states and enable precision therapeutics.

Yi Yang Lim is a bioinformatician with training in biological sciences. He received his undergraduate degree from Nanyang Technological University, where he developed a strong interest in applying quantitative and computational methods to complex biological questions. He is currently a Research Assistant at Duke-NUS Medical School, where he continues to pursue data-driven approaches to biological research. He is particularly interested in understanding biological systems through systems-level and data-driven analysis. He enjoys working with computational and biological data, and is motivated by questions that require integrating machine learning, deep learning, and statistical approaches to extract meaningful insights from high-dimensional datasets. His strengths include computational modelling, scalable data analysis workflows, and applying machine learning to biological problems. He values careful analytical design, reproducible workflows, and collaborative problem-solving. He is especially excited by research environments that encourage open discussion and interdisciplinary thinking—particularly when tackling problems that bridge computation and biology.

Xinyi is a PhD student in the Quantitative Biology and Medicine (QBM) programme at Duke–NUS Medical School. She has a background in Computational Biology from the National University of Singapore. Her research uses single-cell technologies and deep learning to study transcriptomic signatures and dysregulated processes in leukemic malignancies. When she is not in the lab, you will find her hiking mountain trails, climbing rocks, or chasing waves.

Hannah is a research assistant with a background in biology from Nanyang Technological University. Her research interests focus on the development and application of computational tools for analysing high-dimensional biological data, particularly in the context of single-cell and multi-omics technologies. She is especially interested in integrating bioinformatics, machine learning, and deep learning methodologies to uncover mechanistic insights underlying complex diseases and biological systems. Motivated by translational research, Hannah seeks to bridge computational discoveries with clinical applications, emphasizing approaches that enhance disease characterization, diagnosis, and therapeutic development. Her core skills include computational biology, data visualization, reproducible workflow design, and interdisciplinary collaboration. Hannah values open scientific exchange and the advancement of research practices that promote reproducibility and clinical relevance. She is particularly drawn to collaborative research environments that foster innovation and the translation of computational methods into actionable biomedical insights.

Xinpeng is a final-year undergraduate in Life Sciences at the National University of Singapore, with formal training in computational biology and bioinformatics grounded in molecular and cell biology. My research focuses on applying machine learning to understand cellular responses to drug perturbations, particularly through variational autoencoder models that integrate transcriptomic data. This work has shaped my interest in generative modelling approaches that capture the complexity and heterogeneity of single-cell responses. I am especially motivated by questions that connect transcriptome to phenotypic outcome, and by the potential of computational models to bridge chemical space and gene expression in the context of drug discovery. My strengths lie in single-cell transcriptomics analysis and machine learning applied to high-dimensional biological data, spanning data processing, model development, and critical evaluation. I value interdisciplinary collaboration and rigorous, reproducible analysis, and am motivated by the goal of extracting new biological insight from existing data.