Machine learning and integrative analysis identify the common pathogenesis of azoospermia complicated with COVID-19

被引:3
|
作者
He, Jiarong [1 ]
Zhao, Yuanqiao [2 ]
Zhou, Zhixian [3 ]
Zhang, Mingming [1 ]
机构
[1] Cent South Univ, Xiangya Hosp 2, Dept Neurosurg, Changsha, Hunan, Peoples R China
[2] Cent South Univ, Xiangya Hosp 2, Dept Urol, Changsha, Hunan, Peoples R China
[3] Cent South Univ, Xiangya Hosp 2, Dept Obstet & Gynecol, Changsha, Hunan, Peoples R China
来源
FRONTIERS IN IMMUNOLOGY | 2023年 / 14卷
关键词
azoospermia; COVID-19; single-cell sequencing; machine learning; WGCNA; MALE-INFERTILITY; EXPRESSION; SEMEN;
D O I
10.3389/fimmu.2023.1114870
中图分类号
R392 [医学免疫学]; Q939.91 [免疫学];
学科分类号
100102 ;
摘要
BackgroundAlthough more recent evidence has indicated COVID-19 is prone to azoospermia, the common molecular mechanism of its occurrence remains to be elucidated. The aim of the present study is to further investigate the mechanism of this complication. MethodsTo discover the common differentially expressed genes (DEGs) and pathways of azoospermia and COVID-19, integrated weighted co-expression network (WGCNA), multiple machine learning analyses, and single-cell RNA-sequencing (scRNA-seq) were performed. ResultsTherefore, we screened two key network modules in the obstructive azoospermia (OA) and non-obstructive azoospermia (NOA) samples. The differentially expressed genes were mainly related to the immune system and infectious virus diseases. We then used multiple machine learning methods to detect biomarkers that differentiated OA from NOA. Enrichment analysis showed that azoospermia patients and COVID-19 patients shared a common IL-17 signaling pathway. In addition, GLO1, GPR135, DYNLL2, and EPB41L3 were identified as significant hub genes in these two diseases. Screening of two different molecular subtypes revealed that azoospermia-related genes were associated with clinicopathological characteristics of age, hospital-free-days, ventilator-free-days, charlson score, and d-dimer of patients with COVID-19 (P < 0.05). Finally, we used the Xsum method to predict potential drugs and single-cell sequencing data to further characterize whether azoospermia-related genes could validate the biological patterns of impaired spermatogenesis in cryptozoospermia patients. ConclusionOur study performs a comprehensive and integrated bioinformatics analysis of azoospermia and COVID-19. These hub genes and common pathways may provide new insights for further mechanism research.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] Machine Learning to Identify Fake News for COVID-19
    Isaakidou, Marianna
    Zoulias, Emmanouil
    Diomidous, Marianna
    PUBLIC HEALTH AND INFORMATICS, PROCEEDINGS OF MIE 2021, 2021, 281 : 108 - 112
  • [2] Using machine learning probabilities to identify effects of COVID-19
    Ramlall, Vijendra
    Gisladottir, Undina
    Kefeli, Jenna
    Tanaka, Yutaro
    May, Benjamin
    Tatonetti, Nicholas
    PATTERNS, 2023, 4 (12):
  • [3] Unsupervised Machine Learning to Identify Convalescent COVID-19 Phenotypes
    Adamo, Sarah
    Ricciardi, Carlo
    Ambrosino, Pasquale
    Maniscalco, Mauro
    Biancardi, Arcangelo
    Cesarelli, Giuseppe
    Donisi, Leandro
    D'Addio, Giovanni
    2022 IEEE INTERNATIONAL SYMPOSIUM ON MEDICAL MEASUREMENTS AND APPLICATIONS (MEMEA 2022), 2022,
  • [4] Using Network Analysis and Machine Learning to Identify Virus Spread Trends in COVID-19
    Pinheiro, Carlos Andre Reis
    Galati, Matthew
    Summerville, Natalia
    Lambrecht, Mark
    BIG DATA RESEARCH, 2021, 25
  • [5] An improved machine learning technique for identify informative COVID-19 tweets
    Malla, Sreejagadeesh
    Alphonse, P. J. A.
    INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT, 2022,
  • [6] Performance Analysis of Machine Learning Algorithms in Detection of COVID-19 from Common Symptoms
    Arslan, Hilal
    Aygun, Betul
    29TH IEEE CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS (SIU 2021), 2021,
  • [7] Plasma Proteomics Identify Biomarkers and Pathogenesis of COVID-19
    Shu, Ting
    Ning, Wanshan
    Wu, Di
    Xu, Jiqian
    Han, Qiangqiang
    Huang, Muhan
    Zou, Xiaojing
    Yang, Qingyu
    Yuan, Yang
    Bie, Yuanyuan
    Pan, Shangwen
    Mu, Jingfang
    Han, Yang
    Yang, Xiaobo
    Zhou, Hong
    Li, Ruiting
    Ren, Yujie
    Chen, Xi
    Yao, Shanglong
    Qiu, Yang
    Zhang, Ding-Yu
    Xue, Yu
    Shang, You
    Zhou, Xi
    IMMUNITY, 2020, 53 (05) : 1108 - +
  • [8] Analysis on Prediction of COVID-19 with Machine Learning Algorithms
    Sathyaraj, R.
    Kanthavel, R.
    Cavaliere, Luigi Pio Leonardo
    Vyas, Sumit
    Maheswari, S.
    Gupta, Ravi Kumar
    Raja, M. Ramkumar
    Dhaya, R.
    Gupta, Mukesh Kumar
    Sengan, Sudhakar
    INTERNATIONAL JOURNAL OF UNCERTAINTY FUZZINESS AND KNOWLEDGE-BASED SYSTEMS, 2022, 30 (SUPP01) : 67 - 82
  • [9] Covid-19 analysis by using machine and deep learning
    Yadav D.
    Maheshwari H.
    Chandra U.
    Sharma A.
    Studies in Big Data, 2020, 80 : 31 - 63
  • [10] Analysis and Prediction of COVID-19 using Machine Learning
    Parthiban, M.
    Alphy, Anna
    2024 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATION AND APPLIED INFORMATICS, ACCAI 2024, 2024,