Dr Jinmiao Chen is a computational biologist with solid background in single-cell analysis and artificial intelligence (AI). She received her Bachelor degree in Data and Computer Science from Sun Yat- Sen (Zhongshan) University, China in 2002, PhD degree in artificial intelligence and computational biology from Nanyang Technological University, Singapore in 2007. During her PhD, she invented novel artificial neural network algorithms and published 1st-authored papers in top tier AI journals including IEEE Trans on Neural Network. After her PhD, she joined the Bioinformatics core of SIgN, A * STAR Singapore and she was able to analyse a wide range of data types including single- cell omics, flow/mass cytometry, microarray, next generation sequencing, microbiome/metagenomics and etc. Over the years, she has been an important pillar of the institute for Bioinformatics. In 2014, she became a Project Leader after a thorough selection and established her own research lab focusing on single-cell computational/system immunology. Since 2017, she has been a very productive and innovative Principal Investigator and leading the Single-Cell & AI for Precision Immunology (SCAIPI) lab. In her current team, she is supervising 8 postdoctoral research fellows, 2 data scientists, and 3 PhD students. One of her postdocs was awarded with Career Development Award in 2020. Since 2016, she has been an adjunct assistant professor at Department of Microbiology and Immunology, NUS.
Characterization of immune cell heterogeneity and cell-cell interactions at single-cell resolution is critical for understanding the fundamental mechanisms used by immune cells to promote or prevent disease progression and response to treatment. Single-cell multi/spatial-omics technology, an ideal tool for immunology, is rapidly advancing and generating big, complex and heterogeneous datasets, which poses significant challenges on data analysis and integration, meanwhile also provides opportunities for the development of data-driven, bio-inspired artificial intelligence (AI). CJM lab combines single-cell multi/spatial-omics with AI for precision immunology research. Her research spans 3 themes:
Theme 1: Build human single cell atlases by deep integration of public single-cell omics data (DISCO).
The application of single-cell omics technologies has resolved cell heterogeneity at increasing scale and resolution, leading to the identification of new subpopulations in both healthy and diseased states and across various tissues. Most recently, these technologies, have been exploited to generate several cross-tissue human cell atlases. However, comparison between these atlases and extraction of fundamental commonalties is difficult owing to the plethora of sequencing protocols and analytical pipelines employed. Moreover, the associated metadata, in particular the cell type labels, are not harmonized, with non-standard formatting and naming conventions. There is an unmet need for unified analysis, integration and annotation of public datasets in order to reveal synergy between studies and to avoid duplication of effort and irregularities of nomenclature. CJM lab develops and deploys unified pipelines to re-analyse, integrate and annotate all public datasets to build a comprehensive consensus global atlas as well as sub-atlases for tissues, diseases and cell types.
Our current release of DISCO atlas (http://www.immunesinglecell.org/) integrates more than 18 million cells from 4450 samples in 351 projects, covering 107 tissues / cell lines / organoids, 158 diseases, and 20 platforms. All the data hosted on DISCO were processed from raw fastq files using a standardized pipeline. Leveraging on the large number of public cell type annotations, we developed CELLiD and applied it to annotate the cell types in an automatic and standardized way. To integrate the single cell data and create consensus reference maps, we developed FastIntegrate, which scales well with large numbers of cells and batches, and returns batch corrected gene expression values for downstream analyses. DISCO is also equipped with online tools, enabling users to perform custom data integration, and to upload their own data for cell type annotation and mapping onto the available atlases.
As single cell technological developments continue apace, we intend to continuously update and upgrade DISCO. We will update DISCO as new studies are published. New sub-atlases will also be constructed and annotation updated as needed to reflect any new developments. We also plan to expand the scope of DISCO to encompass other single-cell omics data, such as scATAC-seq, scTCR/BCR-seq, and spatial omics. The different omics data will be integrated to create a single cell multi-omics reference atlas.
Theme 2: Develop and deploy deep multimodal representation learning methods for the analysis and integration of single-cell multi-omics.
Single-cell multi-omics simultaneously measures multiple-omes of a cell including its genome, transcriptome, epigenome, methylome, proteome, immune receptor repertoires and etc, providing a holistic view of individual cells and holds an unprecedented potential for dissecting cellular heterogeneity. Compared to single-omics, multi-omics is able to identify subtler differences between cells and reveal links across omes. When analysing such data, combining the multiple-omes to learn a low-dimensional discriminative representation for each cell is crucial. Specifically, joint embeddings of the multiple data modalities are essential for various down-stream analysis tasks such as visualization, clustering, trajectory inference, and batch integration. CJM lab builds AI models to learn each data modality by dedicated deep neural network and then jointly train them with multi-view learning to produce an unsupervised embedded deep representation of cells. With this, we seek to achieve higher resolution of cell type identification; discover new cell populations & their associated functions; uncover relationships across-omics and predict across modalities.
Theme 3: Build human spatial omics atlas and construct cell-cell interactomes.
In current single cell analysis, cell-cell interactions are computationally predicted solely based on ligand and receptor expression and without spatial information. The emerging spatial omics technologies enable simultaneous measurement of gene/protein expression and cell locations, which is critical for characterizing cell-cell interactions. We first build human spatial omics atlas by integrating public datasets and in-house spatial omics data generated for human tissues. To analyse spatial omics for cell-cell interactions, we develop deep graph neural network models to predict which cell types are interacting via which ligand-receptor pairs.
Software and database
|SIgN Fellows ||Postdocs (Ph.D)
||Research Officers ||PhD Students |
|Jing Jing LING ||Kok Siong ANG
||Sethi RAMAN ||Samuel CHUAH|
| ||Kelvin CHONG
||Chengwei ZHONG||Nicole LEE|
| ||Xiaomeng ZHANG
|| ||Jia Chi TAN|
| ||Mengwei LI
|| || |
| ||Yahui LONG|| || |
| ||Hang XU|| || |
| || || || |
Jinmiao Chen's SIgN affiliated publications (last updated 30 November 2022)