Xiaobo Sun
- Department of Human Genetics
Assistant Professor
- (470) 439-9968
- xiaobo.sun@emory.edu
- Department of Human Genetics
-
Emory University
Department of Human Genetics
615 Michael St NE
Overview
Artificial Intelligence (AI) is emerging as a transformative force in scientific research, especially when integrated with the rapidly expanding body of data in biomedical and health sciences. A central challenge lies in effectively leveraging AI to accelerate data-driven scientific discovery. Dr. Xiaobo Suns research is positioned at this critical interface, combining advances in core deep learning with applications in biology and medicine.
AI for Biology
Dr. Sun's research in AI for biology focuses on developing novel methodologies to address key computational challenges in biomedical data analysis. His work includes:
* Biological Language Modeling: Designing language model-based algorithms to learn biologically meaningful, semantics-enriched representations of biomolecules at multiple molecular levels. These models utilize multimodal data sources (e.g., multi-omics) and facilitate a wide range of analytical and data mining tasks.
* Multimodal Data Integration: Developing multimodal learning algorithms capable of effectively integrating heterogeneous biomedical data (e.g., genomics, transcriptomics, proteomics), enabling more comprehensive and interpretable biological insights.
* Causal Inference in Multi-Omics: Creating methods for causal discovery and inference to uncover complex biological relationships, such as regulatory pathways and molecular interaction networks, from multi-omics datasets.
* Reinforcement Learning for Biological Design: Applying reinforcement learning to problems in biological prediction and therapeutic design, including protein function prediction, antigen design, and T-cell receptor (TCR) engineering for CAR-T cell therapies.
Foundational AI and Deep Learning
On the algorithmic and theoretical side, Dr. Sun's research also contributes to the advancement of core AI methodologies, with emphases on:
* Computer Vision, Natural Language Processing, and Reinforcement Learning: Developing cutting-edge techniques with applications both within and beyond the biomedical domain.
* Theoretical Foundations: Establishing rigorous theoretical underpinnings for new algorithms, including provable guarantees and analyses of generalization performance.
* Cross-Domain Generalization: Demonstrating the transferability of developed methods to general data types such as natural language and image data, beyond their initial biomedical applications.
Publications and Venues
Dr. Sun aims to disseminate his work through leading journals in genetics and bioinformaticssuch as Nature Communicationsas well as top-tier AI conferences including NeurIPS, ICML, and AAAI.
Academic Appointment
- Assistant Professor, Human Genetics, Emory University School of Medicine
Education
Degrees
- PhD Computer Scienc from Emory University
- MS Quantitative and Computational Finance from Georgia Institute of Technology
- BS Biotechnology from Wuhan University
Research
Publications
-
Detecting anomalous anatomic regions in spatial transcriptomics with STANDS.
Nat Commun Volume: 15 Page(s): 8223
09/19/2024 Authors: Xu K; Lu Y; Hou S; Liu K; Du Y; Huang M; Feng H; Wu H; Sun X -
A cofunctional grouping-based approach for non-redundant feature gene selection in unannotated single-cell RNA-seq analysis.
Brief Bioinform Volume: 24
03/19/2023 Authors: Deng T; Chen S; Zhang Y; Xu Y; Feng D; Wu H; Sun X -
A comprehensive comparison of supervised and unsupervised methods for cell type identification in single-cell RNA-seq.
Brief Bioinform Volume: 23
03/10/2022 Authors: Sun X; Lin X; Li Z; Wu H -
A machine learning approach to brain epigenetic analysis reveals kinases associated with Alzheimer's disease.
Nat Commun Volume: 12 Page(s): 4472
07/22/2021 Authors: Huang Y; Sun X; Jiang H; Yu S; Robins C; Armstrong MJ; Li R; Mei Z; Shi X; Gerasimov ES -
Optimized distributed systems achieve significant performance improvement on sorted merging of massive VCF files.
Gigascience Volume: 7
06/01/2018 Authors: Sun X; Gao J; Jin P; Eng C; Burchard EG; Beaty TH; Ruczinski I; Mathias RA; Barnes K; Wang F -
Omicseq: a web-based search engine for exploring omics datasets.
Nucleic Acids Res Volume: 45 Page(s): W445 - W452
07/03/2017 Authors: Sun X; Pittard WS; Xu T; Chen L; Zwick ME; Jiang X; Wang F; Qin ZS -
CRISPR/Cas9-mediated gene editing ameliorates neurotoxicity in mouse model of Huntington's disease.
J Clin Invest Volume: 127 Page(s): 2719 - 2724
06/30/2017 Authors: Yang S; Chang R; Yang H; Zhao T; Hong Y; Kong HE; Sun X; Qin Z; Jin P; Li S