Embedded Files
Welcome to CDAL!
Welcome to CDAL!
The increasing availability of digitized clinical data presents an unprecedented opportunity to study and gain deeper understanding of diseases, develop new treatments and improve healthcare ecosystems. Broadly, our aim is to develop accurate and scalable systems that effectively model health information of individuals at different levels - genomic, physiological and social - and from disparate sources. More details below.
Articles on our research from NUS Computing News:
News
News
14 Mar: Shivin successfully defended his PhD thesis. Congrats Shivin!
27 Feb: Debabrata successfully defended his PhD thesis. Congrats Deb!
Research Interests
Research Interests
We develop machine learning algorithms to improve various aspects of clinical data analysis. We are particularly interested in unsupervised learning and modeling challenges arising due to heterogeneity, high-dimensionality and temporality of clinical and biological data. See recent representative publications below.
Learning from Multiple Heterogeneous Sources for Clinical Applications
Learning from Multiple Heterogeneous Sources for Clinical Applications
Clinical measurements differ widely in modality, temporal resolution and noise characteristics. Knowledge graphs, created manually or automatically using NLP on biomedical literature also contain information that can guide model building. By effectively integrating these heterogeneous sources, we aim to improve clinical decision support applications ranging from predicting ICU complications to finding accurate genomic drug targets and enabling better patient triage.
Multi-view/multi-task/multi-modal learning
Combined knowledge-based and data-driven predictive models
Multi-Disease Predictive Analytics: A Clinical Knowledge-Aware Approach [PDF]
Adverse Drug Event Prediction using Noisy Literature-Derived Knowledge Graphs [PDF]
Patient Representation Learning from Heterogeneous Data Sources and Knowledge Graphs using Deep Collective Matrix Factorization: Evaluation Study [PDF]
Drug Target Prediction
Unsupervised Models for Biomedical Discovery
Unsupervised Models for Biomedical Discovery
Mining actionable knowledge from tons of biomedical data being generated today requires models that can effectively deal with high dimensionality, complex dependencies and heterogeneity. We are exploring unsupervised learning models - both deep representation learning as well as classical statistical models, and their applications in finding novel gene-disease associations, adverse drug events and disease subtypes.
Collective matrix factorization
Clustering and Pattern Mining
Avoiding inferior clusterings with misspecified Gaussian mixture models [PDF]
Gaussian Mixture Copulas for High-Dimensional Clustering and Dependency-based Subtyping [PDF]
Improved Inference of Gaussian Mixture Copula Model for Clustering and Reproducibility Analysis using Automatic Differentiation [PDF]
Current Group Members
Current Group Members
Principal Investigator
Principal Investigator
Vaibhav Rajan, Assistant Professor, DISA > SoC > NUS
Research Staff
Research Staff
Zhang Shu, Post doctoral fellow
Hansheng Xue, Research Assistant
Zhang Yanrong, Research Assistant
PhD Students
PhD Students
Suparna Ghanvatkar, DISA
Aishwarya Jayagopal, DISA
Master Project Students
Master Project Students
He Ziyang (2023-24), "Deep Learning Methods for Cancer Drug Response Prediction"
Bachelor Project Students
Bachelor Project Students
Eugene Lim (2023-24), "Deep learning models for Cancer Drug Response Prediction"
Software
Software
Our Bitbucket Repository: https://bitbucket.org/cdal/
Former Members
Former Members
PhD Students
[first job after NUS]PhD Students
Shivin Srivastava, DISA, "Combined Risk Modeling and Subtyping in Intensive Care Units"
Research Fellow, Institute of Operations Research and Analytics, NUS Business School
Debabrata Mahapatra, DCS (co-supervised with Jonathan Scarlett), "Gradient Ascent in Multi-Objective Minimization: Applications in Machine Learning"
Applied Scientist, Amazon
Siva Rajesh Kasa, DISA, "Modeling Dependencies with Mixture Models and Copulas"
Applied Scientist, Amazon
Herty Liany, DCS, "Identifying and Exploiting Synthetic Lethality for Cancer Therapeutics"
Bioinformatics Specialist, National Cancer Centre, Singapore
Lin Qiu, DISA (co-supervised with Bernard Tan), "Examining the Health Impacts of Digital Technologies"
Assistant Professor, Department of Information Systems and Management Engineering, College of Business, Southern University of Science and Technology (SUSTech), China
Cui Wei, DISA (co-supervised with Jack Jiang), "Enhancing User Engagement with Online Information: The Impacts of Online Advertisement Layout and Serendipitous Recommendation"
Lecturer, Department of Information Systems & Analytics, School of Computing, NUS
MComp Dissertation/Capstone Students
MComp Dissertation/Capstone Students
Jiang Liu (2017-23), "Detection of Adverse Drug Events using Electronic Health Records"
Hu Yijie (2022-23), "Automatic Differentiation for Mixture Model Inference"
Krishna Kumar Hariprasannan, DISA (2021-22), "Deep Learning Methods for Discovering Targeted Cancer Therapeutics"
Meng Ziwei, SoC (2021-22),"Analytics with biomedical images: case studies with genomic spatial data and electronic health records"
Alicia Nanelia, DISA (2021-22), "Privileged Domain Adaptation for Drug Response Prediction"
Aishwarya Jayagopal, SoC (2021-22), "Leveraging Multi-View Neural Representation Learning Methods for Biomedical Applications"
Suraj Yadav, Department of Mathematics, IISER Pune (2020-21), "Improving Neural Network based Spectral Clustering"
Lakshmanan Rakkappan, DCS (2017-18), "Context-Aware Sequential Models using Stacked Recurrent Neural Networks"
Bachelor Project Students
Bachelor Project Students
Shi Yingfei (2022-23), "Deep learning models for Cancer Drug Response Prediction"
Nicole Ren Jiahui (2022-23), "Deep learning models for Cancer Drug Response Prediction"
Xie Ran (2022-23), "Decision support system for behavioural therapists managing Autism"
Vinod Jaya Kumar (2022-23), "Individualised Education Plan recommendation for managing Autism"
Lyndon Lim, FYP, DISA (2021-22), "Multi-objective optimization for training deep neural networks"
Goh Jia Yi, FYP, DISA (2021-22),"Detecting adverse drug reactions using deep neural models"
Li Minzhi, FYP, DISA (2021-22), "Detecting adverse drug reactions using deep neural models"
Yan Boshen, FYP, DOS (2021-22), "Explainable Personalized Drug Recommendations for Cancer"
Risa Lim Ning, FYP, DISA (2020 - 21), "Combined Knowledge-Based and Data-Driven Deep Learning Models for Clinical Decision Support" Won the NUS Outstanding Undergraduate Researcher Prize!
Wang Tengda, FYP, DISA (2020 - 21), "Deep Learning Models for Analysis of Clinical Notes"
Ong Yi Chong, FYP, DCS (2020), "Sepsis Treatment Planning with Inverse Reinforcement Learning"
Neil Apoorva Shah, SIP@NUS, DISA (2020), "Deep Multi-view Learning for Integrated Analysis of Clinical Data and Biomedical Knowledge Graphs"
Ho Zong Sien, ATAP@NUS, DCS (2020), "Deep Representation Learning from Heterogeneous Biomedical Networks for Precision Medicine"
Yuan Sin Yi, FYP, DISA (2019-20), "Deep learning models for analysis of clinical notes"
Abel Lim, FYP, DCS (2018-19), "Combined Data-driven and Knowledge-guided Computational Phenotyping of Diseases"
Research Staff and Interns
Research Staff and Interns
Ragunathan Mariappan, Research Associate, 2018-23
Adithya Rajgopal, Intern (2021-22), from NIT, Trichy, India
Soham Dasgupta, Intern, Mallya Aditi International School, Bangalore, India (Summer 2021)
Aishwarya Jayagopal, Research Assistant, NUS MComp (Summer 2021)
Suparna Ghanvatkar, Intern, Research Assistant (2018-19), From IIIT Bangalore, India
Sruthi Gorantla, Intern (Summer 2018), From IISc, Bangalore, India
Siva Rajesh Kasa, Research Assistant (Summer 2018), From IIM, Bangalore, India
Google Sites
Report abuse