AUTHOR=Geng Tianxiang , Zheng Mengxue , Wang Yongfeng , Reseland Janne Elin , Samara Athina 

TITLE=An artificial intelligence prediction model based on extracellular matrix proteins for the prognostic prediction and immunotherapeutic evaluation of ovarian serous adenocarcinoma

JOURNAL=Frontiers in Molecular Biosciences

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/molecular-biosciences/articles/10.3389/fmolb.2023.1200354

DOI=10.3389/fmolb.2023.1200354

ISSN=2296-889X

ABSTRACT=Background: Ovarian Serous Adenocarcinoma (OV) is a malignant tumor originating from epithelial cells and one of the most common causes of death from gynecological cancers. In this study, artificial intelligence approaches were used to create an extracellular matrix protein-based prediction model, to assist clinicians in the prognosis of OV overall survival and the effectiveness of immunotherapy.
Methods: The TCGA-OV dataset was employed as the study subject and validation of the TCGA-Pancancer dataset. The  prognostic importance of 1068 known extracellular matrix proteins for OV were determined by the random forest algorithm and the Lasso algorithm, and establishing the ECMs risk score. Based on the gene expression data from the dataset, the differences in gene expression, tumor mutation burden (TMB) and tumor microenvironment (TME) between the high- and low-risk groups were analyzed.
Results: By combining multiple artificial intelligence algorithms, we were able to identify 15 key extracellular matrix genes (AMBN, CXCL11, PI3, CSPG5, TGFBI, TLL1, HMCN2, ESM1, IL12A, MMP17, CLEC5A, FREM2, ANGPTL4, PRSS1, FGF23), and confirm the validity of this ECMs risk score for overall survival prediction. Several characteristics were found as independent prognostic factors for OV by multivariate COX analysis. We discovered that TG-targeted immunotherapy was more effective in the high ECMs risk score group, while the low ECMs risk score group was more sensitive to RYR2 gene-related immunotherapy. Additionally, the patients with low ECMs risk scores had higher immune checkpoint gene expression and immunophenoscore levels, and they responded better to immunotherapy.
Conclusion: The ECMs risk score can be used to assess the patient's sensitivity to immunotherapy and forecast prognosis in OV.