Unlocking the future: mitochondrial genes and neural networks in predicting ovarian cancer prognosis and immunotherapy response.

Abstract

Background: Mitochondrial genes are involved in the tumor metabolism of ovarian cancer (OC), affecting immune cell infiltration and treatment response. We aimed to utilize mitochondrial genes to predict OC prognosis and immunotherapy response.

Methods: The prognosis data, immunotherapy efficacy and next generation sequencing data of OC patients were downloaded from The Cancer Genome Atlas Program (TCGA) and Gene Expression Omnibus (GEO). Mitochondrial genes were sourced from the MitoCarta3.0 database. Seventy percent of the patients were randomly selected as the discovery cohort for model construction, while the remaining 30% constituted the validation cohort for model assessment. Using the expression of mitochondrial genes as the predictor variable and based on the neural network algorithm, the overall survival (OS) time and immunotherapy efficacy (complete or partial response) of the included patients were predicted.

Results: There were 375 OC patients included to construct the prognostic model, and 26 patients were included to construct the immune efficacy model. The average area under the receiver operating characteristic curve (AUC) of the prognostic model was: 0.7268 [95% confidence interval (CI), 0.7258-0.7278] in the discovery cohort and 0.6475 (95% CI: 0.6466-0.6484) in the validation cohort. The average AUC of the immunotherapy efficacy model was: 0.9444 (95% CI: 0.8333-1.0000) in the discovery cohort and 0.9167 (95% CI: 0.6667-1.0000) in the validation cohort.

Conclusions: The application of mitochondrial genes and neural networks shows potential in predicting the prognosis and immunotherapy response in OC patients. And this approach could provide valuable insights for personalized treatment strategies.