Cancer Management and Research (Jul 2020)

Signatures of Mucosal Microbiome in Oral Squamous Cell Carcinoma Identified Using a Random Forest Model

  • Zhou J,
  • Wang L,
  • Yuan R,
  • Yu X,
  • Chen Z,
  • Yang F,
  • Sun G,
  • Dong Q

Journal volume & issue
Vol. Volume 12
pp. 5353 – 5363

Abstract

Read online

Jianhua Zhou,1,* Lili Wang,2,* Rongtao Yuan,1 Xinjuan Yu,2 Zhenggang Chen,1 Fang Yang,1 Guirong Sun,3 Quanjiang Dong2 1Department of Stomatology, Qingdao Municipal Hospital, Qingdao University, Qingdao 266071, Shandong, People’s Republic of China; 2Central Laboratories and Department of Gastroenterology, Qingdao Municipal Hospital, Qingdao University, Qingdao 266071, Shandong, People’s Republic of China; 3Clinical Laboratory, The Affiliated Hospital, Qingdao University, Qingdao 266011, Shandong, People’s Republic of China*These authors contributed equally to this workCorrespondence: Quanjiang DongCentral Laboratories and Department of Gastroenterology, Qingdao Municipal Hospital, Qingdao University, Qingdao 266071, Shandong, People’s Republic of ChinaTel +86-532-88905289Fax +86-532-85968434Email [email protected] SunClinical Laboratory, The Affiliated Hospital, Qingdao University, Qingdao 266011, Shandong, People’s Republic of ChinaEmail [email protected]: The aim of this study was to explore the signatures of oral microbiome associated with OSCC using a random forest (RF) model.Patients and Methods: A total of 24 patients with OSCC were enrolled in the study. The oral microbiome was assessed in cancerous lesions and matched paracancerous tissues from each patient using 16S rRNA gene sequencing. Signatures of mucosal microbiome in OSCC were identified using a RF model.Results: Significant differences were found between OSCC lesions and matched paracancerous tissues with respect to the microbial profile and composition. Linear discriminant analysis effect size analyses (LEfSe) identified 15 bacteria genera associated with cancerous lesions. Fusobacterium, Treponema, Streptococcus, Peptostreptococcus, Carnobacterium, Tannerella, Parvimonas and Filifactor were enriched. A classifier based on RF model identified a microbial signature comprising 12 bacteria, which was capable of distinguishing cancerous lesions and paracancerous tissues (AUC = 0.82). The network of the oral microbiome in cancerous lesions appeared to be simplified and fragmented. Functional analyses of oral microbiome showed altered functions in amino acid metabolism and increased capacity of glucose utilization in OSCC.Conclusion: The identified microbial signatures may potentially be used as a biomarker for predicting OSCC or for clinical assessment of oral cancer risk.Keywords: oral squamous cell carcinoma, microbiome, random forest machine learning, predicted functions

Keywords