Cancer drug resistance presents a challenge for precision medicine. Drug-resistant mutations are always emerging. In this study, we explored the relationship between drug-resistant mutations and drug resistance from the perspective of protein structure. By combining data from previously identified drug-resistant mutations and information of protein structure and function, we used machine learning-based methods to build models to predict cancer drug resistance mutations. The performance of our combined model achieved an accuracy of 86%, a Matthews correlation coefficient score of 0.57, and an F1 score of 0.66. We have constructed a fast, reliable method that predicts and investigates cancer drug resistance in a protein structure. Nonetheless, more information is needed concerning drug resistance and, in particular, clarification is needed about the relationships between the drug and the drug resistance mutations in proteins. Highly accurate predictions regarding drug resistance mutations can be helpful for developing new strategies with personalized cancer treatments. Our novel concept, which combines protein structure information, has the potential to elucidate physiological mechanisms of cancer drug resistance.
Background: Studies have showed that MicroRNA (miRNA) plays an important role in cancer development and progression. We aimed to identify signature for predicting prognosis and response to treatment in breast cancer, which would help in making treatment decisions. Patients and Methods: We retrospectively analyzed miRNA expression profiles by a custom miRNA microarray in 422 archived paraffin-embedded breast cancers and 62 non-cancer breast tissues obtained from the Department of Pathology, Sun Yat-Sen University Cancer Center (Guangzhou, China). The patients with breast cancer were randomly divided into training set (211samples) and test set (211samples). The miRNA signature identified in training set was verified in test set and further confirmed by qRT-PCR method in another independent set including 161 breast cancers acquired from a different medical center. Results: A signature consisting of 36 miRNAs that were differently expressed between breast cancer and breast tissue was established in training set with an accuracy of 99.5% for distinguishing breast cancer from non-cancer breast tissues. The 36-miRNA signature was corroborated in test set with the same accuracy (99.5%). Then 5 miRNAs, which were significantly associated with patient survival, were constructed a signature and used to compute risk score in training set. Patients were divided into high- or low-risk group using the median risk score as a cutoff. Survival analysis showed that patients with high risk scores had poor prognosis in the training set, which was confirmed in the test set and independent set. This 5-miRNA signature was proven to be an independent prognostic predictor and could significantly improve the prognostic accuracy of TNM staging system. More important, the 5-miRNA signature could predict response to chemotherapy/radiotherapy in breast cancer patients after radical mastectomy. Conclusion: We identified a 36-miRNA signature that could distinguish breast cancer from non-tumor breast tissue, and a 5-miRNA signature that could predict survival and response to treatment, which could guide neoadjuvant therapy in breast cancer patients. The results in this study suggest that 5-miRNA signature will have a huge potential clinical implication in management of patients with breast cancer. Funding: National Natural Science Foundation of China/Joint Research Fund for Oversea Scholar (Grant No: 81228104 to Yibing Kang and Hui-Yun Wang). Citation Format: Jing-Ye Hu, Jun Tang, Wei Yi, Rong Deng, Mei-Yin Zhang, Guo-Liang Huang, Hui-Zhong Zhang, Jie-Hua He, X.F. Steven Zheng, Yibing Kang, Hui-Yun Wang. A 5-microRNA signature for prediction of prognosis and response to treatment in breast cancer. [abstract]. In: Proceedings of the 106th Annual Meeting of the American Association for Cancer Research; 2015 Apr 18-22; Philadelphia, PA. Philadelphia (PA): AACR; Cancer Res 2015;75(15 Suppl):Abstract nr 4013. doi:10.1158/1538-7445.AM2015-4013
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.