A machine learning approach to identify predictive molecular markers for cisplatin chemosensitivity following surgical resection in ovarian cancer

Abstract

Ovarian cancer is associated with poor prognosis. Platinum resistance contributes significantly to the high rate of tumour recurrence. We aimed to identify a set of molecular markers for predicting platinum sensitivity. A signature predicting cisplatin sensitivity was generated using the Genomics of Drug Sensitivity in Cancer and The Cancer Genome Atlas databases. Four potential biomarkers (CYTH3, GALNT3, S100A14, and ERI1) were identified and optimized for immunohistochemistry (IHC). Validation was performed on a cohort of patients (n = 50) treated with surgical resection followed by adjuvant carboplatin. Predictive models were established to predict chemosensitivity. The four biomarkers were also assessed for their ability to prognosticate overall survival in three ovarian cancer microarray expression datasets from The Gene Expression Omnibus. The extreme gradient boosting (XGBoost) algorithm was selected for the final model to validate the accuracy in an independent validation dataset (n = 10). CYTH3 and S100A14, followed by nodal stage, were the features with the greatest importance. The four gene signature had comparable prognostication as clinical information for two-year survival. Assessment of tumour biology by means of gene expression can serve as an adjunct for prediction of chemosensitivity and prognostication. Potentially, the assessment of molecular markers alongside clinical information offers a chance to further optimise therapeutic decision making.

Clinical significance of metabolism-related genes and FAK activity in ovarian high-grade serous carcinoma

“…By using machine learning including deep learning, in recent years, many studies on applying machine learning in cancer research have been performed [ 26 , 29 , 30 , 33 , 62 , 63 ]. Using machine learning, predicting the prognoses of ovarian cancer patients and the therapeutic effects of platinum-containing drugs can be widely performed [ 64 – 72 ]. In most cases, machine learning from results such as RNA-seq results is first applied [ 26 , 30 ].…”

Effect of HIPEC on Peritoneal Recurrence in Peritoneal Metastasis Treated With Cytoreductive Surgery: A Systematic Review

“…As existing literature has suggested, it is now ever so much more important to consider personalized treatment plans for patients with PM moving forward, which incorporates both clinical and molecular stratification into the patient selection process. As demonstrated in various cancer types, the discovery of prognostic gene signatures could provide clinicians with tools for better disease management (52)(53)(54). The potential utility of unique signatures on extracellular vesicles and glycans could also be harnessed for patient prognostication (55).…”

Cisplatin for cancer therapy and overcoming chemoresistance

“…Ovarian cancer (OC) is a malignancy among the repertoire of familial cancers affecting the female populations worldwide that also recurs in up to 80% of the patients leading to high mortality [ 145 ]. It is the most fatal among the gynaecological cancers and the highest in gynaecological cancer-related deaths [ 146 ].…”

“…It is the most fatal among the gynaecological cancers and the highest in gynaecological cancer-related deaths [ 146 ]. Platinum -based therapies are its most effective cure with most patients, up to 70% responding well to cisplatin therapy, yet relapse upon developing drug resistance [ 145 ]. The annual incidence of OC worldwide was around 300,000 new cases with a mortality of 200,000 patients as per the GLOBOCAN statistics of the year 2020.…”