Lysine crotonylation (Kcr) is a newly discovered protein post-translational modification and has been proved to be widely involved in biological processes and serious diseases. Thus, the accurate and fast identification of this modification has become the preliminary task in researching their biological functions. In this study, we developed a novel human nonhistone Kcr predictor, dubbed iKcr_CNN, based on the convolutional neural network framework. To overcome the imbalance issue, we applied the focal loss technique instead of the standard cross-entropy loss function to optimize, which not only assigns different weights to samples belonging to different categories but also samples that are easy or difficult to classify. Ultimately, optimized model presented well-balanced predictive scores between positive and negative samples than existing tools. The user-friendly web server is accessible at https://ikcrcnn.webmalab.cn, and the involved datasets and Python scripts can be freely downloaded at https://github.com/lijundou/iKcr_CNN/. The proposed model may serve as an efficient tool to assist academicians with their experimental research.
Last updated: 2021-09-17