Dr. Xu Liao
Postdoctoral Research Scientist in Biostatistics
I am a Postdoctoral Research Scientist in Biostatistics at Columbia University, working with Prof. Wenpin Hou. I develop statistical methods and computational tools for single-cell and spatial transcriptomics data, with expertise in RNA velocity analysis and deep generative modeling.
Publications
Research contributions in single-cell genomics and machine learning
Single-cell and Spatial Transcriptomics Data-driven Methods
Multivariate stochastic modeling for transcriptional dynamics with cell-specific latent time using SDEvelo
Nature Communications, 15, 10849
Probabilistic embedding, clustering, and alignment for integrating spatial transcriptomics data with PRECAST
Nature Communications, 14(1), 296
Single Cell Gene Expression Prediction via Prototype-based Proximal Neural Factorization
IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Joint dimension reduction and clustering analysis of single-cell RNA-seq and spatial transcriptomics data
Nucleic Acids Research, 50(12), e72-e72
The statistical practice of the GTEx Project: from single to multiple tissues
Quantitative Biology, 1-17
Deep Learning and Statistical Learning Methodologies
Schrödinger-Föllmer Sampler
IEEE Transactions on Information Theory, 71(2), 1283-1299
Deep Dimension Reduction for Supervised Representation Learning
IEEE Transactions on Information Theory, 70(5), 3583–3598
Deep Estimation for Q* with Minimax Bellman Error Minimization
Information Sciences, 648, 119565
Rescaled Boosting in Classification
IEEE transactions on neural networks and learning systems, 30(9), 2598-2610
Invariant and Sufficient Supervised Representation Learning
The International Joint Conference on Neural Networks (IJCNN), (pp. 1-8). IEEE
*: equal contributions; †: alphabetical order
Talks & Presentations
Selected presentations and invited talks on computational biology and biostatistics
High-dimensional deep learning approaches for single-cell and spatial transcriptomics
Ph.D. Thesis Defense
Duke-NUS Medical School, Singapore
Deep Learning in Genomics: Pioneering Methods & Future Horizons
Columbia University
Online
SDEvelo: a deep generative approach for transcriptional dynamics with cell-specific latent time and multivariate stochastic modeling
Xi'an Jiaotong University
Online
Single-cell RNA Velocity Analysis
16th National Symposium on Survival Analysis and Applied Statistics
Hangzhou, China
Multivariate stochastic modeling for transcriptional dynamics with cell-specific latent time using SDEvelo
Wuhan University
Wuhan, China
Stochastic Differential Equations Informed RNA Velocity with SDEvelo
12th ICSA Conference
Hong Kong, China
Stochastic Differential Equations Informed RNA Velocity with SDEvelo
1st Duke-NUS Health Data Science Symposium
Singapore
Invariant and Sufficient Supervised Representation Learning
IJCNN
Queensland, Australia
Deep Dimension Reduction for Supervised Representation Learning
Xi'an Jiaotong University
Xi'an, China
Contact
Get in touch for collaborations and research opportunities
Location
New York, United States
Institution
Columbia University
Department of Biostatistics
Visitor Map
