A meta-learning approach to improving radiation response prediction in cancers. (November 2022)

• Record Type: Journal Article
• Authors: Zhang, Yuening; Qiu, Li; Ren, Yongyong; Cheng, Zhiwei; Li, Leijie; Yao, Siqiong; Zhang, Chengdong; Luo, Zhiguo; Lu, Hui
• Is Part Of: Computers in biology and medicine. Volume 150(2022)
• Publication Date: 2022-11
• Subjects: Meta-learning -- Radiation response -- Radiosensitivity -- Pan-cancer -- Gene expression -- DNA methylation; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.106163
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Purpose: Predicting the efficacy of radiotherapy in individual patients has drawn widespread attention, but the limited sample size remains a bottleneck for utilizing high-dimensional multi-omics data to guide personalized radiotherapy. We hypothesize the recently developed meta-learning framework could address this limitation. Methods and materials: By combining gene expression, DNA methylation, and clinical data of 806 patients who had received radiotherapy from The Cancer Genome Atlas (TCGA), we applied the Model-Agnostic Meta-Learning (MAML) framework to tasks consisting of pan-cancer data, to obtain the best initial parameters of a neural network for a specific cancer with smaller number of samples. The performance of meta-learning framework was compared with four traditional machine learning methods based on two training schemes, and tested on Cancer Cell Line Encyclopedia (CCLE) and Chinese Glioma Genome Atlas (CGGA) datasets. Moreover, biological significance of the models was investigated by survival analysis and feature interpretation. Results: The mean AUC (Area under the ROC Curve) [95% confidence interval] of our models across nine cancer types was 0.702 [0.691–0.713], which improved by 0.166 on average over other the four machine learning methods on two training schemes. Our models performed significantly better ( p < 0.05) in seven cancer types and performed comparable to the other predictors in the rest of two cancer types. The more pan-cancer samples were used to transfer meta-knowledge, the greater the performance improved ( p < 0.05). The predicted response scores that our models generated were negatively correlated with cell radiosensitivity index in four cancer types ( p < 0.05), while not statistically significant in the other three cancer types. Moreover, the predicted response scores were shown to be prognostic factors in seven cancer types and eight potential radiosensitivity-related genes were identified. Conclusions: For the first time, we established the meta-learning approach to improving individual radiation response prediction by transferring common knowledge from pan-cancer data with MAML framework. The results demonstrated the superiority, generalizability, and biological significance of our approach. Graphical abstract: Image 1 Highlights: For the first time, we proposed the meta-learning approach to improving individual radiation response prediction. Our approach achieved superior or comparable performance in nine cancer types of TCGA compared to other four traditional machine learning methods. The proposed models generated predicted response scores as promising prognostic factors and identified potential radiosensitivity-related genes.