Show simple item record

AuthorSekaran, Karthik
AuthorVarghese, Rinku Polachirakkal
AuthorGopikrishnan, Mohanraj
AuthorAlsamman, Alsamman M.
AuthorEl Allali, Achraf
AuthorZayed, Hatem
AuthorDoss C, George Priya
Available date2023-06-21T07:13:47Z
Publication Date2023-04-18
Publication NameGenes
Identifierhttp://dx.doi.org/10.3390/genes14040936
CitationSekaran, K., Varghese, R. P., Gopikrishnan, M., Alsamman, A. M., El Allali, A., Zayed, H., & Doss C, G. P. (2023). Unraveling the Dysbiosis of Vaginal Microbiome to Understand Cervical Cancer Disease Etiology—An Explainable AI Approach. Genes, 14(4), 936.
ISSN2073-4425
URIhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85154542825&origin=inward
URIhttp://hdl.handle.net/10576/44640
AbstractMicrobial Dysbiosis is associated with the etiology and pathogenesis of diseases. The studies on the vaginal microbiome in cervical cancer are essential to discern the cause and effect of the condition. The present study characterizes the microbial pathogenesis involved in developing cervical cancer. Relative species abundance assessment identified Firmicutes, Actinobacteria, and Proteobacteria dominating the phylum level. A significant increase in Lactobacillus iners and Prevotella timonensis at the species level revealed its pathogenic influence on cervical cancer progression. The diversity, richness, and dominance analysis divulges a substantial decline in cervical cancer compared to control samples. The β diversity index proves the homogeneity in the subgroups’ microbial composition. The association between enriched Lactobacillus iners at the species level, Lactobacillus, Pseudomonas, and Enterococcus genera with cervical cancer is identified by Linear discriminant analysis Effect Size (LEfSe) prediction. The functional enrichment corroborates the microbial disease association with pathogenic infections such as aerobic vaginitis, bacterial vaginosis, and chlamydia. The dataset is trained and validated with repeated k-fold cross-validation technique using a random forest algorithm to determine the discriminative pattern from the samples. SHapley Additive exPlanations (SHAP), a game theoretic approach, is employed to analyze the results predicted by the model. Interestingly, SHAP identified that the increase in Ralstonia has a higher probability of predicting the sample as cervical cancer. New evidential microbiomes identified in the experiment confirm the presence of pathogenic microbiomes in cervical cancer vaginal samples and their mutuality with microbial imbalance.
SponsorThe authors acknowledge the Indian Council of Medical Research (ICMR), the Government of India agency, for the research grant No. BMI/12(13)/2021, ID No: 2021-6359, and grant No. VIR/COVID-19/31/2021/ECD-I, ID. NO: 2021-5570.
Languageen
PublisherMultidisciplinary Digital Publishing Institute (MDPI)
Subjectcervical cancer
eXplainable AI
SHapley Additive exPlanations
vaginal microbiome
TitleUnraveling the Dysbiosis of Vaginal Microbiome to Understand Cervical Cancer Disease Etiology—An Explainable AI Approach
TypeArticle
Issue Number4
Volume Number14
dc.accessType Open Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record