Wei Zhang: Pioneering Research in Computational Biology at UCF
Wei Zhang is an accomplished associate professor of computer science at the University of Central Florida (UCF), where he also serves as the graduate program coordinator. His work focuses on computational biology, bioinformatics, and machine learning, particularly in the context of cancer transcriptome analysis, biomarker discovery, and drug sensitivity prediction.
Academic and Professional Journey
Wei Zhang's academic background is solid, with a Ph.D. and M.S. from the Computer Science and Engineering Department at the University of Minnesota-Twin Cities, where he was advised by Dr. Rui Kuang and Dr. Baolin Wu. He completed his Bachelor thesis in Computer Science at Winona State University under Dr. Mingrui Zhang's supervision. Before joining UCF in 2017, he was a research associate at the University of Minnesota for two years. He also has short-term working experience in a pharmaceutical company.
Research Focus and Contributions
Dr. Zhang's research interests lie primarily in computational biology, an interdisciplinary field that applies computational, mathematical, and statistical methods to solve complex biological problems. His research has centered on investigating the role of transcriptome variants in diseases, spanning from technique-driven research (e.g., algorithm development for disease outcome prediction), to the hypothesis-driven investigation of specific biological problems. Specifically, Dr. Zhang has developed several advanced machine learning algorithms and computational tools for mining biomarkers of different disease phenotypes from large-scale multi-omics data. The models and frameworks have been widely used by many research groups and biologists.
Key Areas of Research
Cancer Transcriptome Analysis: Dr. Zhang's work involves analyzing the complete set of RNA transcripts in cancer cells to understand the molecular mechanisms driving cancer development and progression.
Biomarker Discovery: He focuses on identifying specific molecules or genetic markers that can be used to diagnose diseases, predict treatment responses, or monitor disease progression.
Drug Sensitivity Prediction: Dr. Zhang develops computational models to predict how sensitive cancer cells are to different drugs, which can help personalize cancer treatment.
Noteworthy Publications and Projects
Dr. Zhang's extensive publication record demonstrates his significant contributions to the field. Here are some highlights:
MOADE: a multimodal autoencoder for dissociating bulk multi-omics data: This research, published in Genome Biology (2025), introduces a multimodal autoencoder for dissociating bulk multi-omics data.
Biological Pathway Guided Gene Selection Through Collaborative Reinforcement Learning: Presented at the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) in 2025, this study explores biological pathway-guided gene selection using collaborative reinforcement learning.
Computational Methods for Alternative Polyadenylation and Splicing in Post-Transcriptional Gene Regulation: Published in Experimental & Molecular Medicine (2025), this work reviews computational methods for alternative polyadenylation and splicing in post-transcriptional gene regulation.
Dichotomous Intronic Polyadenylation Profiles Reveal Multifaceted Gene Functions in the Pan-cancer Transcriptome: Featured in Experimental & Molecular Medicine (2024), this research highlights the multifaceted gene functions revealed by dichotomous intronic polyadenylation profiles in the pan-cancer transcriptome.
Integrating Spatial Transcriptomics and Bulk RNA-seq: Predicting Gene Expression with Enhanced Resolution through Graph Attention Networks: This study, published in Briefings in Bioinformatics (2024), focuses on integrating spatial transcriptomics and bulk RNA-seq to predict gene expression with enhanced resolution using graph attention networks.
Incomplete Time-Series Gene Expression in Integrative Study for Islet Autoimmunity Prediction: Published in Briefings in Bioinformatics (2022), this research addresses incomplete time-series gene expression in integrative studies for islet autoimmunity prediction.
APA-Scan: Detection and Visualization of 3'-UTR APA with RNA-seq and 3'-end-seq Data: Featured in BMC Bioinformatics (2022), APA-Scan aids in the detection and visualization of 3'-UTR APA with RNA-seq and 3'-end-seq data.
omicsGAT: Graph Attention Network for Cancer Subtype Analyses: Published in the International Journal of Molecular Sciences (2022), this paper introduces omicsGAT, a graph attention network for cancer subtype analyses.
Multi-omics Data Integration by Generative Adversarial Network: This study, published in Bioinformatics (2021), explores multi-omics data integration using a generative adversarial network.
Computational Methods to Study Human Transcript Variants in COVID-19 Infected Lung Cancer Cells: Featured in the International Journal of Molecular Sciences (2021), this research focuses on computational methods to study human transcript variants in COVID-19 infected lung cancer cells.
In Silico Model for miRNA-mediated Regulatory Network in Cancer: Published in Briefings in Bioinformatics (2021), this work presents an in silico model for miRNA-mediated regulatory networks in cancer.
AS-Quant: Detection and Visualization of Alternative Splicing Events with RNA-seq Data: Featured in the International Journal of Molecular Sciences (2021), AS-Quant aids in the detection and visualization of alternative splicing events with RNA-seq data.
Network-based Drug Sensitivity Prediction: Published in BMC Medical Genomics (2020), this study explores network-based drug sensitivity prediction.
A Large-Scale Comparative Study of Isoform Expressions Measured on Four Platforms: Featured in BMC Genomics (2020), this research provides a large-scale comparative study of isoform expressions measured on four platforms.
Platform-integrated mRNA Isoform Quantification: Published in Bioinformatics (2020), this paper focuses on platform-integrated mRNA isoform quantification.
Network-based Multi-Task Learning Models for Biomarker Selection and Cancer Outcome Prediction: This study, published in Bioinformatics (2020), explores network-based multi-task learning models for biomarker selection and cancer outcome prediction.
mTOR-regulated U2af1 tandem exon splicing specifies transcriptome features for translational control: Published in Nucleic Acids Research (2019), this research focuses on mTOR-regulated U2af1 tandem exon splicing and its specification of transcriptome features for translational control.
An Integrative Model for Alternative Polyadenylation, IntMAP, Delineates mTOR-modulated Endoplasmic Reticulum Stress Response: Featured in Nucleic Acids Research (2018), IntMAP delineates the mTOR-modulated endoplasmic reticulum stress response.
Network-based Machine Learning and Graph Theory Algorithms for Precision Oncology: Published in npj Precision Oncology (2017), this work explores network-based machine learning and graph theory algorithms for precision oncology.
Network-based Isoform Quantification with RNA-Seq Data for Cancer Transcriptome Analysis: Featured in PLoS Comput Biol (2015), this research focuses on network-based isoform quantification with RNA-Seq data for cancer transcriptome analysis.
mRNA 3'UTR Shortening is a Molecular Signature of mTORC1 Activation: Published in Nature Communications (2015), this study identifies mRNA 3'UTR shortening as a molecular signature of mTORC1 activation.
Network-based Survival Analysis Reveals Subnetwork Signatures for Predicting Outcomes of Ovarian Cancer Treatment: Featured in PLoS Comput Biol (2013), this research focuses on network-based survival analysis and reveals subnetwork signatures for predicting outcomes of ovarian cancer treatment.
Contributions to the Field
Dr. Zhang's work has led to the development of several advanced machine-learning algorithms and computational tools. These tools are used for mining biomarkers from large-scale multi-omics data. His models and frameworks have been widely adopted by various research groups and biologists, enhancing their ability to analyze complex biological datasets and make significant discoveries.
Research Impact and Recognition
During his time at UCF, Dr. Zhang has demonstrated his commitment to research and education. He has recruited and mentored numerous students, with five Ph.D. students, four master's students, and six undergraduate research trainees working in his lab. Together, they have published numerous journal articles and conference papers, contributing significantly to the field of computational biology. In the past four years, Dr. Zhang's work has been published in top-tier journals such as Briefings in Bioinformatics, Nucleic Acids Research, and Bioinformatics.
Teaching and Mentoring
As a graduate program coordinator and professor, Dr. Zhang plays a crucial role in shaping the next generation of computer scientists and bioinformaticians. He is committed to providing high-quality education and mentorship to his students, preparing them for successful careers in academia and industry.
Future Directions
Dr. Zhang's ongoing research promises to yield further insights into the molecular mechanisms of cancer and other diseases. By continuing to develop innovative computational methods and tools, he aims to improve disease diagnosis, treatment, and prevention. His work has the potential to make a significant impact.
tags: #wei #zhang #ucf #research
