Abstract
Background: Using by machine learning algorithms, we aimed to identify the mutated gene set from the whole exome sequencing (WES) data of blood in the cancer, which is associated with overall survival in breast cancer patients.Methods: WES data from 1,181 female breast cancer patients within the UK Biobank cohort was collected. The number of mutations for each gene was summed and defined as the blood-based mutation burden per patient. Using by Long short-term memory (LSTM) machine learning algorithm and a XGBoost—a gradient-boosted tree algorithm, we developed the model to predict patient overall survival. Results: From the UK biobank-breast cancer cohort, most altered genes in blood samples were related with the TP53 pathway. In the LSTM model, the minimum 50 genes were found to predict high vs. low mutation burden. In the XGBoost survival model, the gene-set could predict overall survival showing the concordance index of 0.75 and the scaled Brier-score of 0.146 from the held-out testing set (20%, N=236). In older patients (≥ 56 years), the high mutation group based on this gene-set showed inferior overall survival compared to the low mutation group (log-rank test, P=0.042)Conclusion: The machine learning algorithms revealed the gene-signature in the UK biobank breast cancer cohort. Mutational burden observed in blood was associated with overall survival in relatively old patients. This gene-signature should be verified in prospective setting.
The Symbolic Relevance of Feedback: Return and Disclosure of Genomic Research Results of Breast Cancer Patients in Belgium, Germany and the UK
