Our Researchers

Sebastian Maurer-Stroh studied theoretical biochemistry at the University of Vienna and wrote his master and PhD thesis at the Institute of Molecular Pathology (IMP). After FEBS and Marie Curie fellowships at the VIB-SWITCH lab in Brussels, he has been leading a group of experts in protein sequence analysis as a senior principal investigator in the A*STAR Bioinformatics Institute (BII) since 2007. He is Executive Director of BII since January 2021. His protein function analysis skills are supporting A*STAR’s efforts at the public-private interface and through computational analysis and modelling his team is critically contributing to national and global viral pathogen surveillance. He is also adjunct Professor at the National University of Singapore (NUS) and infectious disease expert for A*STAR ID labs and the National Public Health Laboratory of the Ministry of Health, Singapore.

Research Interests

Sebastian Maurer-Stroh's research interests lies in mapping the uncharted islands in functional protein sequence space. This includes inferring functions for uncharacterized genes/proteins based on remote evolutionary relationships, prediction of the 3-dimensional structure of proteins, identification of biologically important residues and disease-related mutations, as well as developing predictors for short functional motifs in protein sequences.

Group Members

Karnani Neerja is a molecular epidemiologist and clinical data scientist with 20 years of experience working with academia, industry and national platforms. She started her research career at University of Virginia, USA, where she contributed to the first functional annotation draft of the human genome (ENCODE consortium). She moved to Singapore in 2013 to join A* STAR’s Singapore Institute for Clinical Sciences (SICS). As the Systems Biology lead at SICS, she developed the multi-omics roadmap for Singapore’s National Birth (GUSTO) and Pre-conception (S-PRESTO) cohorts and identified biomarkers of metabolic and mental health adversities in expecting mothers and their offspring. These findings have been patented and licensed by prominent nutrition industries and are being translated into future interventions. She has also contributed to the research landscape and scientific vision of these cohorts by serving on their executive committees for over 6 years. Beyond the developmental and pregnancy cohorts, she is involved in Singapore National Precision Medicine (NPM) program’s SG10K-Health study and serves on its science and data access committees. To advance her interest in population health analysis and to connect it with the real-world data, she joined A*STAR’s Bioinformatics Institute (BII) in April 2021 as the Head of Clinical Data Engagement. Her team is developing omics based nextgen mobile applications that can provide patient health journey and actionable intervention roadmap for clinicians. Her contributions to the biomedical informatics field were recently highlighted by GovInsider in its special report on ‘Women in GovTech 2021’.

Group Members

Dr P Mukkesh Kumar is the Head of Data Management Platform at A*STAR’s Bioinformatics Institute (BII) and Singapore Institute for Clinical Sciences (SICS), leading the Multi-modal Data Management, Data Curation & Data Stewardship, Healthcare Data Analytics & Reporting and Healthcare Software Development teams. Dr P Mukkesh Kumar is a PhD alumnus of the NUS Saw Swee Hock School of Public Health, he has developed a predictive care framework for diabetes & maternal health, combining coalitional game theory concepts with machine learning. Forging collaborations with the National University Hospital (NUH) in Value-based Healthcare Strategy, the Early Screening for Gestational Diabetes Mellitus in a Low Risk Population (EaGeR) pilot study conducted at NUH for the real world deployment of early pregnancy GDM predictor AI model. Working in close partnership with Singapore’s Ministry of Health (MOH), Dr P Mukkesh Kumar is developing the core OMOP data curation team at A*STAR to support MOH-TRUST Strategic Research Data Contributors. Dr P Mukkesh Kumar has been mentoring the Data Managers at US Boston Children’s Hospital/Harvard Medical School for multi-centre clinical research studies, building talent and capabilities in the global research ecosystem.

Group Member

Mai Chan Lau earned her PhD from the National University of Singapore in 2015, focusing on high-performance GPU research. She began her postdoctoral training at the Singapore Immunology Network (ASTAR), focusing on single-cell immunology bioinformatics. Following this, she moved to Boston, USA, where she leveraged AI and machine learning for Molecular Pathological Epidemiology (MPE) studies, using tissue-based multi-marker technology at Dana-Farber Cancer Institute, Brigham and Women’s Hospital, and Harvard Medical School. In 2021, she returned to Singapore and joined the Institute of Molecular and Cell Biology (ASTAR), expanding her research to spatial transcriptomics and AI. In November 2022, she established her own laboratory at the Bioinformatics Institute (ASTAR), concentrating on advanced spatial multi-omics studies using AI and quantum computing. Concurrently, she leads the Computational Immunology Platform at the Singapore Immunology Network (ASTAR). She served as a program committee member for Clinical Translation of Medical Image Computing & Computer-Assisted Intervention (CLINICCAI) during 2022-2024. She holds an editorial board position for the World Scientific Annual Review of Cancer Immunology journal.

Research Interests

Our research sits at the intersection of AI, spatial biology, and clinical oncology, with the goal of making AI-driven precision oncology realizable — by building models that are robust, interpretable, and trustworthy enough for clinical adoption. Specifically, I develop AI models integrating spatial omics, histopathology, and clinical data to discover clinically actionable biomarkers — moving precision immune-oncology beyond black-box prediction towards transparent, trustworthy insight. Key projects and contributions:

1. Generative AI for Transparent Tumour Immune Microenvironment (TIME) Modelling: We developed a generative AI framework that synthesises context-specific H&E cellular phenotypes from patient tissue, enabling interpretable, patient-specific modelling and virtual perturbation of the tumour immune microenvironment (TIME). By extending computational pathology beyond static tissue characterisation, this framework supports spatial biomarker discovery and provides a scalable, tissue-sparing complement to resource-intensive in vivo and organoid experiments. 
2. AI-Driven Virtual Spatial Phenotyping from H&E Histology: We developed deep learning models that predict spatial protein-marker and gene-expression distributions from routine H&E histology, enabling virtual characterisation of the tumour immune microenvironment without costly spatial-omics assays. Together with a visualisation tool that overlays prediction masks onto H&E images, this work establishes a scalable and interpretable approach to population-scale spatial phenotyping and clinically trustworthy AI deployment. (Supported by MOH-OFYIRG23jan-0049; BII_C250314072)
3. Bioinformatics Algorithms for Spatial TIME Analysis: We developed bioinformatics algorithms and interactive tools for robust, interpretable analysis of complex spatial tumour immune microenvironment data. These include TIPC for unsupervised discovery of tumour–immune spatial patterns, HepatoMap and iCellSight for code-free analysis of spatial transcriptomic and high-plex protein-imaging data, and a Bayesian model integrating clinicopathological and genomic features for colorectal cancer risk prediction. Together, these tools enable scalable spatial phenotyping, broaden access for laboratory and clinical researchers, and support data-driven patient stratification.

Recent/ Notable Publications

1. Choo J, Zhao JJ, Yim WWY, Lau MC [co-first author], et al. Spatial predictors of response to chemo-immunotherapy in microsatellite stable metastatic colorectal cancer. Nat Commun 17, 6294 (2026). https://doi.org/10.1038/s41467-026-72204-2
2. Lau MC [first author], Borowsky J, Väyrynen JP, et al. Tumor-immune partitioning and clustering algorithm for identifying tumor-immune cell spatial interaction signatures within the tumor microenvironment. PLoS Comput Biol. 2025 Feb 18;21(2):e1012707. doi: 10.1371/journal.pcbi.1012707. PMID: 39965007; PMCID: PMC11849983.
3. Melissa Zhao, Lau MC [co-first author], Haruki K, et al. Bayesian risk prediction model for colorectal cancer mortality through integration of clinicopathologic and genomic data. npj Precis. Oncol. 7.1 (2023): 57. Doi: 10.1038/s41698-023-00406-8.
4. Azam AB, …, Lau MC [co-corresponding author], Cai Y. Training immunophenotyping deep learning models with the same-section ground truth cell label derivation method improves virtual staining accuracy. Front Immunol. 2024 Jun 28;15:1404640. doi: 10.3389/fimmu.2024.1404640. PMID: 39007128; PMCID: PMC11239356.

Group Members

Xing Yi Woo obtained her PhD in Chemical Engineering from the Joint-PhD program of University of Illinois at Urbana Champaign and National University of Singapore. She did her postdoctoral fellowship in the Genome Institute of Singapore under the mentorship of Professors Edison Liu and Guillaume Bourque. Subsequently, she joined The Jackson Laboratory as a computational scientist and made significant contributions in a wide range of computational projects, including analysis pipeline development, clinical curation and downstream analysis of large-scale datasets of cancer and patient-derived xenografts. She has led analysis projects in cancer resources and consortiums, and contributed to publications in high impact journals, including Nature Genetics, Proceedings of the National Academy of Sciences, Cancer Research and Genome Research.

Research Interests

The Research Data Integration Group at the Bioinformatics Institute (BII), A*STAR, bridges computational biology, data science, and clinical research to drive discovery and translational impact. Our goal is to integrate and analyze multi-omics, imaging, and clinical datasets generated by A*STAR institutes, healthcare partners, and national initiatives in Singapore, focusing on cancer, metabolic, eye, and skin diseases, and biomanufacturing, for the Asian population. Through harnessing the potential of biomedical data, building intelligent agentic AI systems, and developing novel digital tools, we aim to accelerate biological discoveries and improve patient outcomes via therapeutic discoveries and precision medicine strategies.

Recent/ Notable Publications

1. Luong JHC, Beggs J, Ferris J, Furuta K, Gorse A-D, Jefferson E, Aung KMM, Sullivan C, Woo XY, The HEALTHWISE Consortium, Cheong IH, Kozlakidis Z, Quinlan PR and Beck T (2026) A maturity model framework for federated networks of trusted research environments. Front. Digit. Health 8:1699125. doi: 10.3389/fdgth.2026.1699125
2. Sharon Pei Yi Chan, Janice Jia Ni Goh, Wai Yee Wong, Nur Nadiah Bite Ismail, Baiwen Luo, Benjamin Jieming Chen, Brandon Xue Ming Phua, Xing Yi Woo, Tan Boon Toh, Edward Kai-Hua Chow, Valerie Shiwen Yang. Ex vivo drug testing identifies a novel drug pair in targeting soft tissue sarcoma. NPJ Precision Oncology 9: 83 (2025). https://doi.org/10.1038/s41698-025-00851-7
3. Mark Yong Siang See*, Janice Jia Ni Goh*, Chen Ee Low, Chun En Yau, Whee Sze Ong, Ru Xin Wong, Nur Fazlin Mohamed Noor, Mohamed Haniffa Bin Hasan Mohamed, Jannatul Tajrin Suha, Alisa Noor Hidayah Sairi, Go Wei Lin, Xing Yi Woo, Valerie Shiwen Yang. Head and Neck Sarcoma Assessor (HaNSA) for treatment decisions using real-world data. ESMO Real World Data and Digital Oncology 5: 100069 (2024). DOl: 10.1016/j.esmorw.2024.100069 HANSA App: https://research-data-integration.shinyapps.io/HeadAndNeckSarcomaAssessor/
4. Brian S White, Xing Yi Woo*, Soner Koc, Todd Sheridan, Steven B Neuhauser, Shidan Wang, Yvonne A Evrard, John David Landua, R Jay Mashl, Sherri R Davies, Bingliang Fang, Maria Gabriela Raso, Kurt W Evans, Matthew H Bailey, Yeging Chen, Min Xiao, Jill Rubinstein, Ali Foroughi pour, Lacey Elizabeth Dobrolecki, Maihi Fujita, Junya Fujimoto, Guanghua Xiao, Ryan C Fields, Jacqueline L Mudd, Xiaowei Xu, Melinda G Hollingshead, Shahanawaz Jiwani, PDXNet consortium, Brandi Davis-Dusenbery, Tiffany A Wallace, Jeffrey A Moscow, James H Doroshow, Nicholas Mitsiades, Salma Kaochar, Chong-xian Pan, Moon S Chen Jr, Luis G Carvajal-Carmona, Alana L Welm, Bryan E Welm, Ramaswamy Govindan, Shunqiang Li, Michael A Davies, Jack A Roth, Funda Meric-Bernstam, Yang Xie, Meenhard Herlyn, Li Ding, Michael T Lewis, Carol J Bult, Dennis A Dean II, Jeffrey H Chuang. A pan-cancer PDX histology image repository with genomic and pathological annotations for deep learning analysis. Cancer Research 84 (13): 2060-2072 (2024). https://doi.org/10.1158/0008-5472.CAN-23-1349

Group Member

Dennis Wang is a Senior Principal Scientist at the A*STAR Singapore Institute for Clinical Sciences and Bioinformatics Institute, and also the Academy of Medical Sciences Professor (Chair in Data Science) at Imperial College London. Having worked in both academia and industry, he enjoys mentoring early-career data scientists and clinical researchers wanting to make an impact on human health using data-driven techniques. Prior to the pandemic, he was a researcher at the University of Sheffield, AstraZeneca and Microsoft Research. He obtained his Bachelor of Science in Computer Science and Microbiology from The University of British Columbia, and his MPhil in Computational Biology and PhD in Biostatistics from the University of Cambridge.

Group Member

James Lu is the Drug Discovery Programme lead and a Senior Principal Investigator at A*STAR Bioinformatics Institute (BII). Prior to his return to Asia in 2025, he served as a Distinguished AI Scientist at Genentech Inc., where he led pioneering efforts at the intersection of machine learning, pharmacology and clinical development. With over a decade of global biopharma industry experience in computational roles spanning Genentech (USA), AstraZeneca (UK) and Roche (Switzerland), Dr. Lu has advanced AI-driven approaches for PK/PD, systems pharmacology, digital health analytics and disease progression modeling across multiple therapeutic areas. Dr. Lu currently serves as an Associate Editor of CPT: Pharmacometrics & Systems Pharmacology and is on the Editorial Board of Clinical and Translational Science (CTS). He chaired the Scientific Programming Committee for the 2025 American Conference on Pharmacometrics (ACoP) and serves on the Scientific Organizing Committee of the annual Population Approach Group Europe (PAGE) conference since 2025. He served as a co-chair of the AI/ML Working Group (2021-2023) and subsequently for the Machine Learning Advisory Committee (2024-2025) at the International Consortium for Innovation and Quality in Pharmaceutical Development (IQ Consortium).

Research Interests

Discovering and developing novel drugs fundamentally involves generalizing beyond what we have seen: from one chemical space to another; one dosing regimen to the next; one indication or one patient population to another. While data-driven models excel within the domain of the known, grounding machine learning (ML) models in pharmacology, physics, and biology gives it a principled way to reason beyond available training data. In addition, because no model is perfect, decision-makers need more than just a predicted number: they need uncertainty quantification to consider the risk of relying on the computational predictions within the context of use. These questions form the main thrusts of my group’s research.

My research group focuses on developing Pharmacology-Informed, Physics-Informed, and Biology-Informed Machine Learning methods, that embed mechanistic knowledge directly into how models represent and learn from data. This domain knowledge shapes not only what models predict, but also how confidently the decision-makers can act upon the model predictions to advance molecules across stages of drug discovery & development.

Select Projects

Agentic AI Target Funnel: An agentic AI system that reasons in a multifaceted manner across safety, efficacy, druggability and other evidence to eliminate weak targets early and prioritize the ones worth betting on, turning target selection from guesswork into principled intelligence.

Uncertainty Quantification and Active Learning for Molecular Property Prediction: Models that provide assessment of what they do not know - guiding experiments toward the molecules that will be the most informative while optimizing their designs in a multi-objective manner (e.g., considerations for ADME & tox).

AI-Enabled Pharmacometrics, Quantitative Systems Pharmacology, and Disease Modeling: Fusing AI/ML with causality-aware, mechanistic computational models to close the loop between the lab and clinic - using what we learn from the lab to help develop medicines for patients (translational modeling), as well as to learn from gaps in existing therapies via patient treatment data to help design the next generation of medicines (reverse translation).

Recent/ Notable Publications

1. Lu, James, and Rajat Desikan. "Quantitative Systems Pharmacology Modeling Amid the Rise of Agentic AI." CPT: Pharmacometrics & Systems Pharmacology 15.4 (2026): e70249.
2. 2. Harun, Rashed, et al. "Machine learning‐based quantification of patient factors impacting remission in patients with ulcerative colitis: insights from etrolizumab phase III clinical trials." Clinical Pharmacology & Therapeutics 115.4 (2024): 815-824.
3. Terranova, Nadia, et al. "Artificial intelligence for quantitative modeling in drug discovery and development: an innovation and quality consortium perspective on use cases and best practices." Clinical Pharmacology & Therapeutics 115.4 (2024): 658-672.
4. Laurie, Mark, and James Lu. "Explainable deep learning for tumor dynamic modeling and overall survival prediction using neural-ODE." npj Systems Biology and Applications 9.1 (2023): 58. 5. Lu, James, et al. "Deep learning prediction of patient response time course from early data via neural-pharmacokinetic/pharmacodynamic modelling." Nature machine intelligence 3.8 (2021): 696-704.

Group Members

Chandra Verma joined the Bioinformatics Institute (BII) A*STAR, Singapore, in November 2003. He heads the division of Biomolecular Modelling and Design and leads a group that applies physics-based models to understand the links between protein sequence, structure and biological function. His group works closely with experimental laboratories where the hypotheses generated are tested. In addition, the group is also involved in designing peptides and small molecules (through virtual screening) both for interrogating biology as well as for therapeutic purposes. Prior to joining Singapore, he worked at the Structural Biology Laboratory in York, UK. He obtained his undergraduate degree at the Indian Institute of Technology, India and his D. Phil at the University of York. He has cofounded two spinoffs: Sinopsee Therapeutics combines a yeast-based platform and modelling with colleagues in A*STAR at IMCB and BTI to screen for and develop new molecules against targets in oncology and opthalmology. Series A funding is being explored for a novel potential therapeutic (eye drop). & Aplomex (design small molecules, peptides, proteins/enzymes and antibodies).

Group Members

Sebastian Maurer-Stroh studied theoretical biochemistry at the University of Vienna and wrote his master and PhD thesis at the Institute of Molecular Pathology (IMP). After FEBS and Marie Curie fellowships at the VIB-SWITCH lab in Brussels, he has been leading a group of experts in protein sequence analysis as a senior principal investigator in the A*STAR Bioinformatics Institute (BII) since 2007. He is Executive Director of BII since January 2021. His protein function analysis skills are supporting A*STAR’s efforts at the public-private interface and through computational analysis and modelling his team is critically contributing to national and global viral pathogen surveillance. He is also adjunct Professor at the National University of Singapore (NUS) and infectious disease expert for A*STAR ID labs and the National Public Health Laboratory of the Ministry of Health, Singapore.

Research Interests

Sebastian Maurer-Stroh's research interests lies in mapping the uncharted islands in functional protein sequence space. This includes inferring functions for uncharacterized genes/proteins based on remote evolutionary relationships, prediction of the 3-dimensional structure of proteins, identification of biologically important residues and disease-related mutations, as well as developing predictors for short functional motifs in protein sequences.

Group Members

Peter J. Bond is a Senior Principal Investigator of the Multiscale Simulation, Modeling and Design (MSMD) group at the Bioinformatics Institute (BII) A*STAR, Singapore, and Adjunct Associate Professor at the National University of Singapore (NUS).

Research Interests

His research interests include host-pathogen interactions, receptor signaling, and virus dynamics. Following his graduation in Biochemistry at the University of Oxford in 2001, Peter moved to the Laboratory of Molecular Biophysics to read for a DPhil, supported by a Wellcome Trust Prize Studentship, and was subsequently awarded an EMBO Long-Term Fellowship hosted at the Max Planck Institute of Biophysics in Frankfurt. In 2010, he became a University Lecturer at the University of Cambridge, before moving to Singapore in late 2013.

Recent/ Notable Publications

1. Masirevic S et al. (2026). A Multiscale Framework for Uncovering Surfactant Mediated Viral Capsid Disruption. Cell Reports Physical Science 7, 103324.
2. Palur VR et al. (2026). Multiscale Simulations and Cryo-Electron Microscopy Reveal the Transition Pathway of Dengue Virus-like Particle Nanoassembly. ACS Nano 20, 6845–6863.
3. Idris F et al. (2025). Glycans on non-structural protein 1 prevent premature T-cell mediated dengue virus clearance. EMBO Molecular Medicine 17, 2995–3020.
4. Palur VR et al. (2025). An integrative approach to rational engineering of dengue virus-like particles. Cell Reports Physical Science 6, 102814.
5. Koh J et al. (2024). Exploring bat-inspired cyclic tryptophan diketopiperazines as ABCB1 Inhibitors. Communications Chemistry 7, 158.
6. Tram NDT et al. (2024). Structure-Guided Bacteria Specificity and Wide Activity Spectrum of Endotoxin-Responsive Peptide Nanonets. Nano Letters 24, 13574–13582.
7. Shivgan AT et al. (2024). Coarse-Grained Model of Glycosaminoglycans for Biomolecular Simulations. Journal of Chemical Theory and Computation 20, 3308–3321.
8. Samsudin F et al. (2024). Mechanisms of allostery at the viral surface through the eyes of molecular simulation. Current Opinion in Structural Biology 84, 102761.
9. Tulsian NK et al. (2023). Defining neutralization and allostery by antibodies against COVID-19 variants. Nature Communications 14, 6967.
10. Petruk G et al. (2023). Targeting Toll-like receptor-driven systemic inflammation by engineering an innate structural fold into drugs. Nature Communications 14, 6097.
11. Puthia M et al. (2023). Bioactive suture with added innate defense functionality for the reduction of bacterial infection and inflammation. Advanced Healthcare Materials, e2300987.
12. Dutta C et al. (2023). Nature-inspired synthetic oligourea foldamer channels allow water transport with high salt rejection. Chem 9, 2237–2254. 
13. Zuzic L et al. (2022). Uncovering cryptic pockets in the SARS-CoV-2 spike glycoprotein. Structure 30, 1062–1074.e4.
14. Tram NDT et al. (2021). Manipulating turn residues on de novo designed beta-hairpin peptides for selectivity against drug-resistant bacteria. Acta Biomaterialia 135, 214–224. 15.    Kaur H et al. (2021). The antibiotic darobactin mimics a beta-strand to inhibit outer membrane insertase. Nature 593, 125–129.

Group Members

Dr. Jinmiao Chen, a Senior Principal Scientist I at the Bioinformatics Institute (BII), leads cutting-edge research focused on AI-powered single-cell and spatial omics analysis. Her work is instrumental in advancing precision medicine by developing tools and methodologies that make complex biological data more accessible and interpretable for scientists worldwide. 

Dr. Chen’s contributions have earned her numerous accolades, including being named an EMBO Global Investigator (2024-2027), a Highly Cited Researcher by Clarivate Analytics (2020-2023), and an A*STAR Fellow (2023-2026). Her work is also recognized in the SG 100 Women in Tech initiative.

Dr. Chen's work stands at the forefront of integrating AI with biological research, and her contributions are poised to make a lasting impact on the field of precision medicine, offering new tools and insights that are accessible to a wide range of researchers.

Beyond her publications and tool development, Dr. Chen is dedicated to sharing her findings and tools with the broader scientific community. The DISCO Data Hub and the ezSingleCell platform established by her lab offer open-access resources for single-cell and spatial omics. These platforms facilitate collaboration, data sharing, and analysis across institutions worldwide. Their global reach ensures that valuable data and tools are accessible to researchers everywhere, accelerating the pace of discovery.

Group Members

Dr. Roland G. Huber is a Senior Pricipal Investigator and the A*STAR Bioinformatics Institute. His research sits at the interface of computational biology, RNA structure and RNA therapeutics with a view towards translational impact. The team focuses on developing and applying advanced computational methods to study RNA structure, stability, translation and therapeutics design, with direct implications for RNA-based medicines and gene therapies, bridging the gap between foundational molecular discovery with applied biomedical translation. His team integrates large-scale omics data, molecular simulations, and AI/ML approaches to uncover the principles underlying RNA structure, RNA interactions, stability and expression control. A central theme across his work is the translation of molecular insights into predictive models that can inform RNA design and therapeutic development, particularly in the space of infectious diseases, RNA virology, and more recently cancer biology. Roland has served as lead PI and theme PI for a number of high-profile projects, including the NRF Competitive Research Program (CRP) and strategic thematic initiatives such as PREPARE for pandemic preparedness by the National Center for Infectious Disease (NCID), NRF AI4Science Grand Challenge and the AI in Drug Discovery (AIDD) initiative as well as international consortia such as the RNA, Readiness and Response (R3) initiative funded by Wellcome Trust under their LEAP programme.

Research Interests

Roland G. Huber’s research focuses on the structure and function of RNA. The key focus in on integrating sequence, structural, and computational methods to elucidate key functional regions of viral and human RNA. RNA adopts a wide diversity of structure, but at the same time exhibits a high degree of flexibility and a plurality of interactions. This makes functional RNA structures challenging to approach with classical biomolecular structure elucidation techniques alone, and calls for new integrative data analysis approaches.

Recent/ Notable Publications

1. A programmable ribozyme for RNA signal transduction (https://www.nature.com/articles/s41467-025-68175-5) Nature Communications 17 (2026)
2. A conserved long-range RNA interaction in SARS-CoV-2 recruits ADAR1 to enhance virus proliferation (https://www.nature.com/articles/s41467-025-63297-2) Nature Communications 16, 8460 (2025)
3. RiNALMo: general-purpose RNA language models can generalize well on structure prediction tasks (https://www.nature.com/articles/s41467-025-60872-5) Nature Communications 16, 5671 (2025).

Group Members

Tan Yaw Sing graduated with a B.Sc. (Hons) from the National University of Singapore in 2009, with a double major in Chemistry and Life Sciences. Funded by the A*STAR Graduate Scholarship, he proceeded to pursue his postgraduate studies at the University of Cambridge, where he obtained his PhD in Chemistry in 2014. In the same year, he joined Chandra Verma’s group at the Bioinformatics Institute (BII) as a postdoctoral research fellow. He now leads his own group in BII after he was promoted to the position of Assistant Principal Investigator in April 2021.

Research Interests
Our research lies at the interface of computational chemistry, structural biology, and artificial intelligence. A central focus of our work is understanding how proteins recognise and interact with other biomolecules and small molecules and applying these insights to therapeutic development and precision medicine.

Our work spans three main areas:

Computational fragment-based drug design. We develop fragment-based computational methods for binding-site prediction and structure-based drug design. These approaches help identify and characterise ligand-binding sites, including cryptic and allosteric pockets, which could enable the drugging of targets that have traditionally been categorised as undruggable, such as protein–protein interactions, RNAs, and protein–RNA complexes. Our methods have been applied to projects supported by the Singapore Therapeutics Development Review (STDR), which funds high-value drug discovery and development projects with strong potential for clinical and commercial translation.

Protein structure and dynamics. We use computational structural biology methods to investigate the molecular mechanisms underlying human diseases. By studying how disease-associated mutations alter protein structure, dynamics, and function, we elucidate mechanistic insights that provide a foundation for  developing targeted therapeutic interventions. In particular, we collaborate closely with the Institute of Molecular and Cell Biology (IMCB) in projects funded by the National Medical Research Council (NMRC) to study the molecular mechanisms of diabetes-causing mutations. Our work helps to shed light on the complex molecular pathogenesis of diabetes, identify new drug targets for personalised therapy, and aid the development of precision medicine approaches with improved clinical outcomes.

AI for molecular design. More recently, our research has expanded into the development and application of generative artificial intelligence for molecular design. In particular, we are interested in developing physics-informed generative models that integrate structural and interaction constraints to design therapeutic molecules. These efforts are supported by the national programme for the utilisation of AI in drug discovery (AIDD) and a multidisciplinary project funded by the Industry Alignment Fund – Pre-Positioning Programme (IAF-PP).

Recent/ Notable Publications

1. Chong NHH, Tan EZT, Tan CHE, Ilangovan H, Lim YJ, Srivastava A, Tan YS. Evaluation of protein–RNA docking web servers for template-free docking and comparison with the AlphaFold Server. J Chem Theory Comput. 22, 3746-3760 (2026)
2. Chen S, Huang Z, Wang Y, Li Y, Tan YS, Deng L, Wu M. MVRBind: multi-view learning for RNA–small molecule binding site prediction. Brief Bioinform. 26, bbaf489 (2025)
3. Ng NHJ, Ghosh S, Bok CM, Ching C, Low BSJ, Chen JT, Lim E, Miserendino MC, Tan YS, Hoon S, Teo AKK. HNF4A and HNF1A exhibit tissue specific target gene regulation in pancreatic beta cells and hepatocytes. Nat Commun. 15, 4288 (2024)
4. Ng JT, Tan YS. Accelerated ligand-mapping molecular dynamics simulations for the detection of recalcitrant cryptic pockets and occluded binding sites. J. Chem. Theory Comput. 18, 1969-1984 (2022)
5. Tan YS, Verma CS. Straightforward incorporation of multiple ligand types into molecular dynamics simulations for efficient binding site detection and characterization. J. Chem. Theory Comput. 16, 6633-6644 (2020)
6. Tan YS, Lane DP, Verma CS. Stapled peptide design: principles and roles of computation Drug Discov. Today 10, 1642-1653 (2016)
7. Tan YS, Reeks J, Brown CJ, Thean D, Ferrer Gago FJ, Yuen TY, Goh ET, Lee XE, Jennings CE, Joseph TL, Lakshminarayanan R, Lane DP, Noble ME, Verma CS. Benzene probes in molecular dynamics simulations reveal novel binding sites for ligand design. J. Phys. Chem. Lett. 7, 3452-3457 (2016)

Group Members

Dr. Loo Lit Hsin is a Senior Principal Investigator at the Bioinformatics Institute (BII), A*STAR, Singapore. He is also an adjunct Assistant Professor at the Department of Pharmacology, Yong Loo Lin School of Medicine, National University of Singapore. Dr. Loo’s background is in computational and systems pharmacology/toxicology. He was the recipient of the Lush Prize – Science Award (2016), Award for Excellence in Postdoctoral Research (2010) and the Alfred Gilman Award (2009) by the University of Texas Southwestern (UTSW) Medical Center, and the Doctoral Award in Mathematical Sciences and Engineering (2005) by Drexel University. Dr. Loo was a postdoctoral fellow in the Bauer Center for Genomics Research at Harvard University (2005), and then in the Department of Pharmacology at the UTSW Medical Center, USA (2005-2010).

Research Interests

Loo's research focuses on investigating the spatial organization and phenotypic plasticity of cells and tissues and predicting their responses to therapeutic or toxic agents. His research team develops AI-enabled cellular/tissue image analysis methods and tools to make cellular phenotypes and tissue histology quantifiable and amenable to automated analyses. By partnering with clinical, regulatory, and industrial collaborators, the team is translating these spatial profiles of cells and tissues into novel diagnostic, therapeutic, or safety-assessment strategies and methods. Dr. Loo is also a co-founder of ImmunoQs, a techbio start-up that provides commercial biomarker discovery services based on the HPA platform developed by his team. Dr. Loo received the Lush Prize Science Award from Ethical Consumer, UK, in 2016, as well as the Award for Excellence in Postdoctoral Research in 2010 and the Alfred Gilman Award in 2009 from the University of Texas Southwestern Medical Center (UTSW), USA.

Recent/ Notable Publications

1. Lee JJ, Zhang J, …, Wang Y, Loo LH, Chow PK. Spatially-guided metabolomics profiling of metabolic regions in human tumor tissues. Mol Syst Biol. 2026 Jul;22(7):1132-1160. doi: 10.1038/s44320-026-00205-w.
2. Zhao JJ, Lee CK, …, Loo LH, …, Rodríguez Martínez M, Rha SY, Sundar R. Spatial organisation of tumor-infiltrating B-cells informs immune checkpoint inhibitor response in Claudin 18.2-expressing gastric cancer. Clin Cancer Res. 2026 Aug 7. doi: 10.1158/1078-0432.CCR-26-1382.
3. Yiu SPT, Chang Y, …, Loo LH, …, Rodig SJ, Ma Q, Jiang S. Same-Slide Spatial Multiomics Integration with IN-DEPTH Reveals Tumor Virus-Linked Spatial Reorganization of the Tumor Microenvironment. Cancer Discov. 2026 Aug 3;16(8):1611-1648. doi: 10.1158/2159-8290.CD-25-0775.

Group Members

Dr. Lee Hwee Kuan is a Senior Principal Investigator of the Imaging Informatics division in Bioinformatics Institute. His current research work involves developing of computer vision aglorithms for clinical and biological studies. Dr. Lee obtained his Ph.D. in 2001 in Theoretical Physics from Carnegie Mellon University with a thesis on liquid-liquid phase transitions and quasicrystals. He then held a joint postdoctoral position with Oak Ridge National Laboratory (USA) and University of Georgia where he worked on developing advanced Monte Carlo methods and nano-magnetism. In 2003, with an award from the Japan Society for Promotion of Science, Hwee Kuan moved to Tokyo Metropolitan University where he developed solutions to extremely long time scaled problems and a reweighting method for nonequilibrium systems. In 2005, Dr. Lee returned to Singapore and join Data Storage Institute, A*STAR on investigating novel recording methods such as hard disk recording via magnetic resonance. In 2006, Dr. Lee transferred to BII, A*STAR as Principal Investigator and he leaded the Imaging Informatics Division.

Recent/ Notable Publications

1. Liu J, Lin L, Saw TY, Chou N, Goh JLJ, Kwa JE, et al. Spatial architecture of autism pathogenesis reveals mosaic structural disarray during early development. Nature Communications (2026). https://doi.org/10.1038/s41467-026-74320-5
2. Zhang B, Zhang TY, Xue QC, Liu ZY, Liao DK, Antoni T, et al. DiffBulk: Enhancing Spatial Transcriptomic Prediction with Diffusion-Based Training. IEEE Transactions on Medical Imaging (2026). https://doi.org/10.1109/TMI.2026.3688322
3. Sng ECY, Kha MB, Wong MJ, Lee NKH, Goh JCY, Park SJ, et al. Can 3D T1 post-contrast MRI in a radiomics-machinelearning model distinguish infective from neoplastic ring-enhancing brain lesions? An exploratory study. Diagnostics (2026). https://doi.org/10.3390/diagnostics16060926
4. Wang X, Zhong L, Tan SY, Te LLS, Huang W, Lee HK, et al. Epicardial adipose tissue signatures in Asian coronary artery disease: insights from cardiac CT. American Journal of Preventive Cardiology (2026). https://doi.org/10.1016/j.ajpc.2026.101453
5. Park SJ, Liu Wei, Lauw SJ, Kwak W, Verma CS, Lee HK. Scalable Neural Network Driven Molecular Dynamics Simulation. Computer Physics Communications (2026). https://doi.org/10.1016/j.cpc.2026.110036
6. Channarayapatna Srinivasa A, Bhat SS, Baduwal D, et al. GAN-MRI enhanced multi-organ MRI segmentation: a deep learning perspective. Radiological Physics and Technology (2025). https://doi.org/10.1007/s12194-025-00938-7
7. Leng S, Cheng N, Tan E, Baskaran L, Teo L, Yew MS, et al. Deep learning-based quantification of epicardial adipose tissue volume from non-contrast computed tomography images: a multi-centre study. European Heart Journal – Digital Health (2025); ztaf116. https://doi.org/10.1093/ehjdh/ztaf116
8. Liu W, Li JG, Verma CS, Lee HK. Systematic benchmarking of 13 AI methods for predicting cyclic peptide membrane permeability. Journal of Cheminformatics (2025); 17:129. https://doi.org/10.1186/s13321-025-01083-4
9. Sng ECY, Chan LL, Conceicao EP, Wong MJ, Ng DHL, Lee HK, et al. Clinicodemographic and radiological features of infective ring-enhancing brain lesions: a 4-year retrospective study at a tertiary referral center. Open Forum Infectious Diseases (2025); 12(3):ofaf095.
10. Chen T, Ren Y, Liu W, Yap J, Yeo KK, Cham TJ, et al. Computational methods for analysing X-ray-guided coronary angiography: from key frame selection to vessel segmentation, stenosis detection and classification. Journal of the Asian Pacific Society of Cardiology (2025); 4:e22.
11. Liu W, Delikoyun K, Chen Q, Yildiz A, Myo SK, Kuan WS, et al. OAH-Net: a deep neural network for hologram reconstruction of off-axis digital holographic microscope. Biomedical Optics Express (2025); 16(3):894–909. https://doi.org/10.1364/BOE.547292
12. Gupta M, Lei M, Cham TJ, Lee HK. D-LORD for motion stylization. IEEE Transactions on Systems, Man, and Cybernetics: Systems (2025); 55(2):1374–1387. https://doi.org/10.1109/TSMC.2024.3502498

Group Members

Winston is a bioengineer who obtained his PhD and MS in Bioengineering from Stanford University, after completing his BS in Bioengineering at Imperial College London. After his PhD, Winston joined Molecular Stethoscope, a startup based on his doctoral work, where he worked as a research scientist and scientific consultant. Returning to Singapore and A*STAR, Winston pursued postdoctoral training in the Molecular Engineering Lab under the leadership of Prof Sydney Brenner. His work in the lab led him to receive the NMRC OF-YIRG award, enabling him to spearhead research on RNA-based liquid biopsies, an emerging field that focuses on non-invasive diagnostic testing, since then Winston's work has been covered applications on prenatal, cancer, and infectious disease diagnostics. He combines liquid biopsies with bioinformatics techniques to achieve accurate and efficient diagnostic outcomes. Alongside his expertise in non-invasive diagnostics, Winston has also delved into machine learning applications for clinical genomics data. He serves as a scientific consultant for local startups, assisting them in operationalizing artificial intelligence for multi-modal genomic datasets, such as single-cell RNA sequencing.

Research Interests

Hic current lab works on two coupled thrusts:

Representation learning across bio / chemical modalities. We treat biosynthetic gene sequence space and small-molecule chemical space as projections of a shared latent structure, and learn joint embeddings supporting bidirectional retrieval: from a metabolite to the gene cluster plausibly encoding it, from a cluster to its predicted chemistry, from a functional query to the enzymes that satisfy it. Combining protein language model representations, contrastive cross-modal alignment, and approximate nearest-neighbour search at library scale reframes enzyme mining as constrained retrieval over a learned manifold rather than sequence homology-driven screening. This has recovered functionally novel enzymes with no annotated close relatives.

Enzyme redesign. The same representations become a design prior rather than a search index. We generate variant libraries in embedding space, filter on structural, evolutionary, and biophysical criteria, and return measured expression, activity, and stability data to the model in a closed agentic loop. The framework is property-agnostic by construction, and we have engineered both directions of the stability axis, from deliberately labile nucleases to thermostabilised, solubility-tuned plastic-degrading hydrolases.

Recent/ Notable Publications

1. Liu, G., Li, Y., Ong, G., Wong, F. T., Tay, D. W. P., Lim, Y. H., Foo, C. S., & Koh, W. (2026). Unified genomic and chemical representations enable bidirectional biosynthetic gene cluster and natural product retrieval. Scientific Reports, 16(1), 21291. https://doi.org/10.1038/s41598-026-49955-5
2. Design of a labile RNase A using protein language models. (2026). ACS Synthetic Biology, 15(1), 37-46. https://doi.org/10.1021/acssynbio.5c00287

Group Members

Dr. Yu Weimiao, an expert in bioimage informatics and computational digital pathology, leads two pioneering groups as a joint Principal Investigator at BII and IMCB. After his Ph.D. in image processing and machine vision from the National University of Singapore, Dr. Yu has been with A*STAR since 2007, advancing to lead the Computational Digital Pathology Lab at BII and the Computational & Molecular Pathology Lab at IMCB. His research, published in top peer reviewed journals like Nature Cell Biology, Nature Materials, Nature Communications, Bioinformatics, focuses on AI-driven computational biomedical image analysis and quantitative imaging informatics.

Dr. Yu’s teams, with over 18 years of experience, excel in developing robust cellular image analysis and molecular diagnosis solutions for clinical application. They integrate diverse methodologies, including signal processing, machine learning, and AI, to create accurate and efficient digital pathology algorithms. Their collaborations with hospitals, biotech, and pharmaceutical companies enhance their expertise in medical algorithm development and validation, aimed at improving patient care. His previous research outcomes were successfully commercialized and made an impact in the medical diagnosis and drug discovery.

An entrepreneur as well, Dr. Yu co-founded A!maginostic Pte. Ltd. to advance the application of AI in clinical diagnostics. He collaborates closely with Singapore General Hospital, National University Hospital, and Tan Tock Seng Hospital, ensuring a seamless R&D pipeline. His world-class joint lab for immunodiagnosis at the tissue level provides intelligent, quantitative imaging analysis solutions, including ImmunoHistoChemistry, Hematoxylin & Eosin, and Multiplex Fluorescence stained images. This integrated platform enables comprehensive profiling of patient immune signatures, aiding in diagnosis, prognosis, and drug response studies.

Group Members

Lawrence Carin studied electrical engineering at the University of Maryland, College Park, where he earned BS, MS and PhD degrees. His field of study for the PhD was electrophysics. Since earning the PhD, he has self-trained in computer science and applied statistics, and over the last two decades has focused on development of fundamental machine learning (ML) and AI methodology. From 1989-1995 he was an assistant and then associate professor at Brooklyn Polytechnic University (now part of NYU). From 1995-2026 he was an associate professor and then full professor at Duke University, where he also held Distinguished Professor endowed chairs. In addition to his research activities, he served in administrative roles, as the Department Chair in the ECE Department at Duke, and as the Vice President for Research at Duke. He was also the Provost at KAUST. He was the founder of two startups: Signal Innovation Group, which focused on security applications of AI and was acquired by BAE Systems, and Infinia ML, which employed large language models and was acquired by Aspirion.

Research Interests

Lawrence Carin has focused on fundamental methodology connected to ML and AI. Areas of emphasis include nonparametric Bayesian ML methods, and more recently deep learning. Significant recent attention has been placed on causal inference. In addition to these fundamental areas of ML/AI, he has directed significant research toward applying such technology to human health, in neuroscience, pathology, ophthalmology, radiology, dermatology and infectious disease.

Group Members