Molecular Subtypes of Oral Squamous Cell Carcinoma Based on Immunosuppression Genes Using a Deep Learning Approach

Medientyp: E-Artikel

Titel: Molecular Subtypes of Oral Squamous Cell Carcinoma Based on Immunosuppression Genes Using a Deep Learning Approach

Beteiligte: Li, Simin [Verfasser:in]; Mai, Zhaoyi [Verfasser:in]; Gu, Wenli [Verfasser:in]; Chukwunonso Ogbuehi, Anthony [Verfasser:in]; Acharya, Aneesha [Verfasser:in]; Pelekos, George [Verfasser:in]; Ning, Wanchen [Verfasser:in]; Liu, Xiangqiong [Verfasser:in]; Deng, Yupei [Verfasser:in]; Li, Hanluo [Verfasser:in]; Lethaus, Bernd [Verfasser:in]; Savkovic, Vuk [Verfasser:in]; Zimmerer, Rüdiger [Verfasser:in]; Ziebolz, Dirk [Verfasser:in]; Schmalz, Gerhard [Verfasser:in]; Wang, Hao [Verfasser:in]; Xiao, Hui [Verfasser:in]; Zhao, Jianjiang [Verfasser:in]

Erschienen: Lausanne: Frontiers Research Foundation, [2023]

Sprache: Englisch

Schlagwörter: immunosuppression ; oral squamous cell carcinoma ; survival ; deep learning ; bioinformatics

Entstehung:

Anmerkungen:

Beschreibung: Background: The mechanisms through which immunosuppressed patients bearincreased risk and worse survival in oral squamous cell carcinoma (OSCC) are unclear.Here, we used deep learning to investigate the genetic mechanisms underlyingimmunosuppression in the survival of OSCC patients, especially from the aspect ofvarious survival-related subtypes.Materials and methods: OSCC samples data were obtained from The CancerGenome Atlas (TCGA), International Cancer Genome Consortium (ICGC), and OSCCrelatedgenetic datasets with survival data in the National Center for BiotechnologyInformation (NCBI). Immunosuppression genes (ISGs) were obtained from the HisgAtlasand DisGeNET databases. Survival analyses were performed to identify the ISGswith significant prognostic values in OSCC. A deep learning (DL)-based modelwas established for robustly differentiating the survival subpopulations of OSCCsamples. In order to understand the characteristics of the different survival-risksubtypes of OSCC samples, differential expression analysis and functional enrichmentanalysis were performed.Results: A total of 317 OSCC samples were divided into one inferring cohort (TCGA)and four confirmation cohorts (ICGC set, GSE41613, GSE42743, and GSE75538).Eleven ISGs (i.e., BGLAP, CALCA, CTLA4, CXCL8, FGFR3, HPRT1, IL22, ORMDL3,TLR3, SPHK1, and INHBB) showed prognostic value in OSCC. The DL-based modelprovided two optimal subgroups of TCGA-OSCC samples with significant differences(p = 4.91E-22) and good model fitness [concordance index (C-index) = 0.77]. The DLmodel was validated by using four external confirmation cohorts: ICGC cohort (n = 40,C-index = 0.39), GSE41613 dataset (n = 97, C-index = 0.86), GSE42743 dataset(n = 71, C-index = 0.87), and GSE75538 dataset (n = 14, C-index = 0.48). Importantly,subtype Sub1 demonstrated a lower probability of survival and thus a more aggressivenature compared with subtype Sub2. ISGs in subtype Sub1 were enriched in the tumorinfiltratingimmune cells-related pathways and cancer progression-related pathways,while those in subtype Sub2 were enriched in the metabolism-related pathways.Conclusion: The two survival subtypes of OSCC identified by deep learning canbenefit clinical practitioners to divide immunocompromised patients with oral cancerinto two subpopulations and give them target drugs and thus might be helpful forimproving the survival of these patients and providing novel therapeutic strategies inthe precision medicine area.

Zugangsstatus: Freier Zugang

Rechte-/Nutzungshinweise: Namensnennung (CC BY)

Nur in Feld suchen:

Zuletzt gesuchte Begriffe: