Prediction and analysis of multiple protein lysine modified sites based on conditional wasserstein generative adversarial networks

BMC Bioinformatics

Xiaobo Wang¹  Yingxi Yang¹  Yan Xu¹  Wen Li¹  Hui Wang²  Yulong Liu³  Shizhao Wei³ 

[1] Department of Information and Computer Science, University of Science and Technology Beijing, 100083, Beijing, China;Institute of Computing Technology, Chinese Academy of Sciences, 100080, Beijing, China;No. 15 Research Institute, China Electronics Technology Group Corporation, 100083, Beijing, China;

关键词: Post-translational modification;    Deep learning;    Generative adversarial networks;    Random forest;   

DOI  :  10.1186/s12859-021-04101-y

来源: Springer

【 摘 要 】

BackgroundProtein post-translational modification (PTM) is a key issue to investigate the mechanism of protein’s function. With the rapid development of proteomics technology, a large amount of protein sequence data has been generated, which highlights the importance of the in-depth study and analysis of PTMs in proteins.MethodWe proposed a new multi-classification machine learning pipeline MultiLyGAN to identity seven types of lysine modified sites. Using eight different sequential and five structural construction methods, 1497 valid features were remained after the filtering by Pearson correlation coefficient. To solve the data imbalance problem, Conditional Generative Adversarial Network (CGAN) and Conditional Wasserstein Generative Adversarial Network (CWGAN), two influential deep generative methods were leveraged and compared to generate new samples for the types with fewer samples. Finally, random forest algorithm was utilized to predict seven categories.ResultsIn the tenfold cross-validation, accuracy (Acc) and Matthews correlation coefficient (MCC) were 0.8589 and 0.8376, respectively. In the independent test, Acc and MCC were 0.8549 and 0.8330, respectively. The results indicated that CWGAN better solved the existing data imbalance and stabilized the training error. Alternatively, an accumulated feature importance analysis reported that CKSAAP, PWM and structural features were the three most important feature-encoding schemes. MultiLyGAN can be found at https://github.com/Lab-Xu/MultiLyGAN.ConclusionsThe CWGAN greatly improved the predictive performance in all experiments. Features derived from CKSAAP, PWM and structure schemes are the most informative and had the greatest contribution to the prediction of PTM.

【 授权许可】

CC BY