Predicting Drug Resistance in Gastric Cancer with Mutation in the Human Epidermal Growth Factor Receptor 2 (HER2) And Machine Learning Technique

Abstract

Gastric cancer with mutations in the human epidermal growth factor receptor (HER2) can be regarded as one of the leading causes of cancer mortality in the world. Targeted tyrosine kinase inhibitors (TKIs) developed against HER2 yielded optimistic results in improving patients' survival rates and life quality. Nevertheless, drug resistance can influence the critical supportive documents of treatment plans and decrease the treatment effectiveness after about one year. Predicting the efficacy of HER2-TKI drugs or therapies for patients with HER2-mutated gastric cancer is a critical research field. In the present study, a personalized drug response prediction model based on molecular dynamics simulations and machine learning is presented to predict response to first-generation drugs approved by the Ministry of Health in patients with gastric cancer. In the molecular dynamics simulation, the patient's mutation status is considered. The patient's unique mutation status was modeled using molecular dynamics simulations to extract geometric features at the molecular level.Furthermore, additional clinical features are incorporated into the machine learning model to predict drug response. The complete features encompass demographic and clinical characteristics, geometrical properties of the drug-target binding site, and binding free energy (RBFE) of the drug-target complex from molecular dynamics simulations. Drug response prediction utilizes the XGBoost classifier, which achieved leading-edge performance for a 4-level drug response prediction task (PDRP) with 97.5% accuracy, 93% sensitivity, 96.5% specificity, and 94% F1 score. The present research has demonstrated that modeling the binding cavity geometry, in tandem with the binding free energy, can effectively predict drug response. Interestingly, the clinical information, while significant, did not significantly influence the model's performance. This exciting finding opens up new avenues for testing the proposed model on various types of cancers, potentially revolutionizing drug development strategies. DOI: https://doi.org/10.52783/pst.391