Dr. Guanjue Xiang

About Me

I am a researcher with expertise in computational biology, machine learning, and genomics. My research focuses on developing innovative computational methods for analyzing complex biological data, particularly in epigenomics and gene regulation.

My recent work includes developing machine learning systems for enhancer-promoter pair prediction and optimizing Anti-Sense Oligonucleotides design. I've published several high-impact papers in journals such as Nucleic Acids Research, Genome Research, and Nature Communications, with significant contributions to computational methods. My expertise spans from traditional statistical approaches to cutting-edge deep learning applications in genomics.

Experience

Senior Data Scientist | CAMP4 Therapeutics Corporation

Cambridge, MA | 2022 - Present

• Enhancer-Promoter Pair Prediction:
  • Developed novel batch effect correction methods for multi-dimensional data normalization across cell-types/species
  • Built machine learning systems using epigenetic features and Enformer LLM model, achieving 30% improvement over ABC score
  • Applied single-cell Perturb-seq data for enhancer-promoter pair identification
• ASO Design Optimization:
  • Led development of Active Learning models for ASO chemical modification design, improving efficiency 10x
  • Implemented SHAP analysis for interpreting ML models and biological mechanisms
  • Developed pipelines using RNA-FM and DNABERT-2 models for sequence feature extraction

Postdoctoral Research Fellow | Harvard T.H. Chan School of Public Health & Dana-Farber Cancer Institute

Boston, MA | 2020 - 2022

Mentors: Dr. X. Shirley Liu and Dr. Jun Liu

• Single-cell RNA-seq Analysis:
  • Developed ICA-based methods for single-cell RNA-seq data projection
  • Created models for joint TAD identification from single-cell and multi-conditional chromatin data
  • Analyzed immune-related gene modules and regulatory networks
• Interspecies Epigenomics:
  • Developed novel NMF-based approach for cross-species epigenetic profile comparison
  • Identified conserved cis-regulatory elements across human and mouse
  • Implemented TF binding prediction using DNA sequence and chromatin accessibility data

Graduate Student Researcher | Pennsylvania State University

University Park, PA | 2015 - 2020

Mentors: Dr. Yu Zhang and Dr. Ross C. Hardison

• VISION Project Leadership:
  • Led data analysis for VISION consortium project on hematopoietic epigenomes
  • Developed novel methods for cross-cell-type epigenomic data normalization
  • Created models for cCRE identification and clustering
  • Implemented Bayesian models for integrating multi-dimensional epigenomic data
  • Discovered novel CTCF binding degradation dynamics through integrated analysis

Education

Ph.D. in Bioinformatics and Genomics

Minor in Applied Statistics

Penn State University, 2015-2020

Thesis: Computational Tools for Normalization, Integration, and Gene Regulatory Inference of Multi-Dimensional Epigenomic and Transcriptomic Data

Selected Publications

Xiang, G., et al. (2024). "JMnorm: a novel joint multi-feature normalization method for integrative and comparative epigenomics." Nucleic Acids Research 52.2: e11-e11.

Figure: Overview of the JMnorm method for joint multi-feature normalization

Xiang, G., et al. (2024). "Interspecies regulatory landscapes and elements revealed by novel joint systematic integration of human and mouse blood cell epigenomes." Genome Research: gr-277950.

Figure: Interspecies regulatory landscapes and elements in human and mouse blood cells

Zhang, Y., Xiang, G., et al. (2023). "MetaTiME integrates single-cell gene expression to characterize the meta-components of the tumor immune microenvironment." Nature Communications 14.1: 2634.

Figure: Overview of MetaTiME

Luan, J., Xiang, G., et al. (2021). "Distinct properties and functions of CTCF revealed by a rapidly inducible degron system." Cell Report 34.8: 108783.

Figure: Highly variable CTCF persistence on chromatin following auxin-mediated degradation

Xiang, G., et al. (2023). "Snapshot: a package for clustering and visualizing epigenetic history during cell differentiation." BMC Bioinformatics 24.1: 102.

Figure: Overview of Snapshot package workflow

Xiang, G., et al. (2021). "S3V2-IDEAS: a package for normalizing, denoising and integrating epigenomic datasets across different cell types." Bioinformatics 37.13: 1847-1849.

Figure: Overview of S3V2-IDEAS package workflow

Xiang, G., Zhang, Y.*, Hardison, R.* (2020). "S3norm: simultaneous normalization of sequencing depth and signal-to-noise ratio in epigenomic data." Nucleic Acids Research 48.8: e43-e43.

Figure: Overview of S3norm method

Xiang, G., Keller, C., et al. (2020). "An integrative view of the regulatory and transcriptional landscapes in mouse hematopoiesis." Genome Research 30.3: 472-484.

Figure: Overview of mouse hematopoiesis regulatory landscape

Technical Skills