iKcr_CNN: A novel computational tool for imbalance classification of human nonhistone crotonylation sites based on convolutional neural networks with focal loss

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Lysine crotonylation (Kcr) is a newly discovered protein post-translational modification and has been proved to be widely involved in various biological processes and human diseases. Thus, the accurate and fast identification of this modification became the preliminary task in investigating the related biological functions. Due to the long duration, high cost and intensity of traditional high-throughput experimental techniques, constructing bioinformatics predictors based on machine learning algorithms is treated as a most popular solution. Although dozens of predictors have been reported to identify Kcr sites, only two, nhKcr and DeepKcrot, focused on human nonhistone protein sequences. Moreover, due to the imbalance nature of data distribution, associated detection performance is severely biased towards the major negative samples and remains much room for improvement. In this research, we developed a convolutional neural network framework, dubbed iKcr_CNN, to identify the human nonhistone Kcr modification. To overcome the imbalance issue (Kcr: 15,274; non-Kcr: 74,018 with imbalance ratio: 1:4), we applied the focal loss function instead of the standard cross-entropy as the indicator to optimize the model, which not only assigns different weights to samples belonging to different categories but also distinguishes easy- and hard-classified samples. Ultimately, the obtained model presents more balanced prediction scores between real-world positive and negative samples than existing tools. The user-friendly web server is accessible at ikcrcnn.webmalab.cn/ , and the involved Python scripts can be conveniently downloaded at github.com/lijundou/iKcr_CNN/ . The proposed model may serve as an efficient tool to assist academicians with their experimental researches.
Funding Information
  • National Natural Science Foundation of China (61902259)
  • National Natural Science Foundation of China (61922020)
  • National Natural Science Foundation of China (62002242)
  • Natural Science Foundation of Guangdong Province (2018A0303130084)

This publication has 42 references indexed in Scilit: