AcrPred: a hybrid optimization with enumerated machine learning algorithm to predict anti-CRISPR proteins

• Main Authors: Dao, Fu-Ying, Liu, Meng-Lu, Su, Wei, Lv, Hao, Zhang, Zhao-Yue, Lin, Hao, Liu, Li
• Other Authors: School of Biological Sciences
• Format: Article
• Language: English
• Published: 2023
• Subjects: Science::Biological sciences; Anti-CRISPR Protein; Machine Learning
• Online Access: https://hdl.handle.net/10356/172143
• Institution: Nanyang Technological University

CRISPR-Cas, as a tool for gene editing, has received extensive attention in recent years. Anti-CRISPR (Acr) proteins can inactivate the CRISPR-Cas defense system during interference phase, and can be used as a potential tool for the regulation of gene editing. In-depth study of Anti-CRISPR proteins is of great significance for the implementation of gene editing. In this study, we developed a high-accuracy prediction model based on two-step model fusion strategy, called AcrPred, which could produce an AUC of 0.952 with independent dataset validation. To further validate the proposed model, we compared with published tools and correctly identified 9 of 10 new Acr proteins, indicating the strong generalization ability of our model. Finally, for the convenience of related wet-experimental researchers, a user-friendly web-server AcrPred (Anti-CRISPR proteins Prediction) was established at http://lin-group.cn/server/AcrPred, by which users can easily identify potential Anti-CRISPR proteins.