Research Interests


Artificial intelligence (AI) and single-cell studies have been making waves in the science and technology communities. AI offers a broad range of methods that can be used to investigate diverse data- and hypothesis-driven questions in single-cell biology. The highly heterogeneous nature of single-cell data can be analyzed across a wide range of research topics by generalizing deep-learning model design and optimization in a hypothesis-free manner. Our lab focuses on the research of single-cell multi-omics data, aiming to develop cutting-edge computational tools to discover underlying mechanisms in diverse biological systems.
Ma, Q., Xu, D. Deep learning shapes single-cell data analysis. Nat Rev Mol Cell Biol (2022)

Highlighted Projects

Single-cell multi-omics (scMulti-omics) allows for the generation and quantification of multiple modalities simultaneously to fully capture the intricacy of complex molecular mechanisms and cellular heterogeneity. Such technology reshapes the investigation of cellular heterogeneity and yields novel insights in neuroscience, cancer biology, immuno-oncology, and therapeutic responsiveness. We seek to develop an end-to-end and hypotheses-free deep learning framework (DeepMAPS) to take the advantage of heterogeneous graphs and graph transformers in elucidating cellular heterogeneity and inferring cell-type-specific biological networks.  

Spatially resolved transcriptomics provides a new way to define spatial contexts and understand the pathogenesis of complex human diseases. It is challenging to accurately characterize tissue architectures and the underlying biological functions from spatial transcriptomic. Our project aims to use graph neural networks to reconstruct tissue architectures and identify spatially variable genes and specific regulatory relations. Another goal is to identify cell-cell communications as well as signal transduction regulatory networks from spatial transcriptome data.

Our lab focuses on developing computational methods to discover heterogeneous transcriptional regulatory mechanisms from single-cell sequencing data. Our efforts are split between inferring cell-type-specific regulatory signals and constructing reliable gene regulatory networks via the integration of single-cell multi-omics. We are also going into the development of novel computational algorithms for spatial transcriptomic data analysis in immuno-oncology and neuroscience.

We are developing enabling tools and databases, using metagenomic and metatranscriptomic data, to elucidate microbial systems and their interactions with human diseases. Our goal is to deliver reproducible and integrated analyses of complex gut microbiome data, detect functional and taxonomic abundances (biomarkers) in a microbial community, and infer significant associations between clinical measurements of human diseases and transformed microbial biomarkers.

Recent news

[May-06-2022] Mr. Mohnish Karthikeyan joins BMBL as a new high school student volunteer. Welcome!

[May-06-2022] Our review article “Single-cell multi-omics in immuno-oncology” has been officially accepted by Nature Communication and will be available online soon!

[Apr-21-2022] The article “A New Machine Learning-Based Framework for Mapping Uncertainty Analysis in RNA-Seq Read Alignment and Gene Expression Estimation” is among the topmost viewed articles in Frontiers in Genetics with 6778 views.

[Apr-14-2022] Our collaborative work with Dr. Zihai Li and PIIO, entitled “Androgen conspires with the CD8+ T cell exhaustion program and contributes to sex bias in cancer“, has been officially published in Science Immunology (IF= 17.73)!

[Apr-05-2022] Mr. Qin Ma has been invited to present at the CTSI Analytics Colloquium, University of Rochester Medical Center, on April 25th.  Online registration is now available. Check details here.

[Mar-31-2022] Our collaborative work (Wolframin is a novel regulator of tau pathology and neurodegeneration) with Dr. Hongjun Fu has been accepted by Acta neuropathological (IF= 18.17)!

[Feb-25-2022] Dr. Jing Zhao has received a new NSF-SCH grant (title: A deep learning framework to identify cancer associated microbial signatures). Congratulations!

[Feb-23-2022] Our Comment paper “Deep learning shapes single-cell data analysis” has been officially published online in Nature Review Molecular Cell Biology (IF=94.44)!

[Feb-21-2022] Dr. Qin Ma has been awarded two new Pelotonia Idea Grants as an MPI, together with Drs. Chung, Hanel, Vilgelm (Title: Integrating Biomimetic Tissue Engineering and Multi-Omics Systems Analysis to Overcome CTCL Drug Resistance), and Drs. Carson and Xin (Title: Targeting GPR84 to Overcome Macrophage Mediated Resistance to Immunotherapy for Breast Cancer). A new milestone of the collaboration between BMBL and PIIO. Congratulations!

[Feb-18-2022] Dr. Jing Zhao starts a new career chapter in Bristol Myers Squibb (New York) as a Senior Manager Biostatistics. Congratulations and set sail!

[Feb-17-2022] Mr. Sheen Bower, who majored in Mathematics, joins BMBL as a new undergraduate volunteer. Welcome!

[Feb-16-2022] Our collaborative paper entitled “Provable Second-order Riemannian Gauss-Newton Method for Low-rank Tensor Estimation” has been accepted at ICASSP 2022.

[Jan-26-2022] The web services at are unavailable due to server attacks. We are actively working on restoring the web services at our backup server. We apologize for the inconvenience and thank you for your understanding.

[Jan-05-2022] Yuzhou Chang has successfully completed his Ph.D. candidacy defense. Congratulations!


See more news here