Identification of Dynamic Gene Expression Profiles During Sequential Vaccination with ChAdOx1/BNT162b2 Using Machine Learning Methods

Aug 5, 2026

Upload by Logic

COVID-19 remains a major global public health threat, and vaccine-induced immunity varies with vaccination number and timing. This study identifies genes that may trigger and regulate immune responses across sequential vaccination scenarios. Machine learning methods analyze blood transcriptomes from 161 individuals grouped by ChAdOx1 prime and BNT162b2 (or limited ChAdOx1) boost dosing schedules. Using feature-ranking and incremental feature selection, the approach extracts essential immune-associated genes and summarizes expression rules supporting vaccine-driven antiviral immunity.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Problem background and vaccination rationale

Methods

Study design and sample grouping

Feature ranking and incremental feature selection

Classification algorithms

Results

Essential gene identification

Expression rules across vaccination scenarios

Conclusion

Implications for antiviral immunity mechanism

TYPE Original Research PUBLISHED 17 March 2023 DOI 10.3389/fmicb.2023.1138674 OPEN ACCESS EDITED BY Lihong Peng, Hunan University of Technology, China REVIEWED BY Nizhuan Wang, ShanghaiTech University, China Qi Dai, Zhejiang Sci-Tech University, China *CORRESPONDENCE Tao Huang [tohuangtao@126.com](tohuangtao@126.com)[ ](tohuangtao@126.com)Yu-Dong Cai [cai_yud@126.com](cai_yud@126.com) †These authors have contributed equally to this work SPECIALTY SECTION This article was submitted to Systems Microbiology, a section of the journal Frontiers in Microbiology RECEIVED 06 January 2023 ACCEPTED 01 March 2023 PUBLISHED 17 March 2023 CITATION Li J, Ren J, Liao H, Guo W, Feng K, Huang T and Cai Y-D (2023) Identification of dynamic gene expression profiles during sequential vaccination with ChAdOx1/BNT162b2 using machine learning methods. Front. Microbiol. 14:1138674 . doi: 10.3389/fmicb.2023.1138674 COPYRIGHT © 2023 Li, Ren, Liao, Guo, Feng, Huang and Cai. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Identification of dynamic gene expression profiles during sequential vaccination with ChAdOx1/BNT162b2 using machine learning methods Jing Li 1†, JingXin Ren 2†, HuiPing Liao3†, Wei Guo4, KaiYan Feng 5, Tao Huang 6, 7* and Yu-Dong Cai 2* 1School of Computer Science, Baicheng Normal University, Baicheng, Jilin, China, 2School of Life Sciences, Shanghai University, Shanghai, China, 3Changping Laboratory, Beijing, China, 4 Key Laboratory of Stem Cell Biology, Shanghai Jiao Tong University School of Medicine (SJTUSM) and Shanghai Institutes for Biological Sciences (SIBS), Chinese Academy of Sciences (CAS), Shanghai, China, 5 Department of Computer Science, Guangdong AIB Polytechnic College, Guangzhou, China, 6CAS Key Laboratory of Computational Biology, Bio-Med Big Data Center, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Science, Shanghai, China, 7CAS Key Laboratory of Tissue Microenvironment and Tumor, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, China To date, COVID-19 remains a serious global public health problem. Vaccination against SARS-CoV-2 has been adopted by many countries as an effective coping strategy. The strength of the body’s immune response in the face of viral infection correlates with the number of vaccinations and the duration of vaccination. In this study, we aimed to identify specific genes that may trigger and control the immune response to COVID-19 under different vaccination scenarios. A machine learning-based approach was designed to analyze the blood transcriptomes of 161 individuals who were classified into six groups according to the dose and timing of inoculations, including I-D0, I-D2-4, I-D7 (day 0, days 2–4, and day 7 after the first dose of ChAdOx1, respectively) and II-D0, II-D1-4, II-D7-10 (day 0, days 1–4, and days 7–10 after the second dose of BNT162b2, respectively) . Each sample was represented by the expression levels of 26,364 genes. The first dose was ChAdOx1, whereas the second dose was mainly BNT162b2 (Only four individuals received a second dose of ChAdOx1) . The groups were deemed as labels and genes were considered as features. Several machine learning algorithms were employed to analyze such classification problem. In detail, five feature ranking algorithms (Lasso, LightGBM, MCFS, mRMR, and PFI) were first applied to evaluate the importance of each gene feature, resulting in five feature lists. Th

FAQs

How were vaccination scenarios and sample groups defined in the study?

Participants were classified into six groups based on the dose and timing of inoculations, including schedules after the first dose of ChAdOx1 and the second dose of BNT162b2 (with only four receiving a second ChAdOx1).

What role did machine learning play in identifying key genes?

The study used multiple feature ranking algorithms to evaluate gene importance, then applied incremental feature selection with classification algorithms to extract essential genes, derive classification rules, and build optimal classifiers.

Which genes were reported as essential and associated with immune response?

The essential genes highlighted were NRF2, RPRD1B, NEU3, SMC5, and TPX2, previously linked to immune responses.

Aug 5, 2026

Upload by Logic