Dataset Information

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.

SUBMITTER: Shannon NB

PROVIDER: S-EPMC8377048 | biostudies-literature | 2021 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Shannon Nicholas Brian NB Tan Laura Ling Ying LLY Tan Qiu Xuan QX Tan Joey Wee-Shan JW Hendrikson Josephine J Ng Wai Har WH Ng Gillian G Liu Ying Y Ong Xing-Yi Sarah XS Nadarajah Ravichandran R Wong Jolene Si Min JSM Tan Grace Hwei Ching GHC Soo Khee Chee KC Teo Melissa Ching Ching MCC Chia Claramae Shulyn CS Ong Chin-Ann Johnny CJ

Scientific reports 20210819 1

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 ...[more]

PMID: 34413360

Similar Datasets

Project description:ObjectiveThe aim of this paper was to describe the operative details for en bloc removal of the adnexal tumor, uterus, pelvic peritoneum, and rectosigmoid colon with colorectal anastomosis in advanced epithelial ovarian cancer patients with widespread pelvic involvement.MethodsThe patient presented with good performance status and huge pelvic tumor extensively infiltrating into adjacent pelvic organs and obliterating the cul-de-sac. The patient underwent en bloc pelvic resection as primary cytoreductive surgery. En bloc pelvic resection procedure is initiated by carrying a circumscribing peritoneal incision to include all pan-pelvic disease within this incision. After retroperitoneal pelvic dissection, the round ligaments and infundibulopelvic ligaments are divided. The ureters are dissected and mobilized from the peritoneum. After dissecting off the anterior pelvic peritoneum overlying the bladder with its tumor nodules, the bladder is mobilized caudally and the vesicovaginal space is developed. The uterine vessels are divided at the level of the ureters, and the paracervical tissues (or parametria) are divided. The proximal sigmoid colon is divided above the most proximal extent of gross tumor using a ligating and dividing stapling device. The sigmoid mesentery is ligated and divided including the superior rectal vessels. The pararectal and retrorectal spaces are further developed and dissected down to the level of the pelvic floor. The posterior dissection is progressed and moves to the right and then to the left of the rectum. The rectal pillars including the middle rectal vessels are ligated and divided. Hysterectomy is completed in a retrograde fashion. The distal rectum is divided using a linear stapler. The specimen is removed en bloc with the uterus, adnexa, pelvic peritoneum, rectosigmoid colon, and tumor masses leaving a macroscopically tumor-free pelvis. Colorectal anastomosis was completed using stapling device.ResultsEn bloc pelvic resection was performed by total abdominal hysterectomy, bilateral salpingo-oophorectomy, pelvic peritonectomy, and rectosigmoid colectomy with colorectal anastomosis using a stapling device. Complete clearance of pelvic disease leaving no gross residual disease was possible using en bloc pelvic resection.ConclusionEn bloc pelvic resection is effective for achieving maximal cytoreduction with the elimination of the pelvic disease in advanced primary ovarian cancer patients with extensive pelvic organ involvement.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets