Tumor Mutation Burden Prediction Model in Egyptian Breast Cancer patients based on Next Generation Sequencing

Abstract

Objectives: This study aimed to identify the tumor mutation burden (TMB) value in Egyptian breast cancer (BC) patients. Moreover, to find the best TMB prediction model based on the expression of estrogen (ER), progesterone (PR), human epidermal growth factor receptor 2 (HER-2), and proliferation index Ki-67. Methods: The Ion AmpliSeq Comprehensive Cancer Panel was used to determine TMB value of 58 Egyptian BC tumor tissues. Different machine learning models were used to select the optimal classification model for prediction of TMB level according to patient’s receptor status. Results: The measured TMB value was between 0 and 8.12/Mb. Positive expression of ER and PR was significantly associated with TMB ≤ 1.25 [(OR =0.35, 95% CI: 0.04–2.98), (OR = 0.17, 95% CI= 0.02-0.44)] respectively. Ki-67 expression positive was significantly associated with TMB >1.25 than those who were Ki-67 expression negative (OR = 9.33, 95% CI= 2.07-42.18). However, no significant differences were observed between HER2 positive and HER2 negative groups. The optimized logistic regression model was TMB = −27.5 −1.82 ER – 0.73 PR + 0.826 HER2 + 2.08 Ki-67. Conclusion: Our findings revealed that TMB value can be predicted based on the expression level of ER, PR, HER-2, and Ki-67.