Bt Research 2024, Vol.15, No.5, 240-247 http://microbescipublisher.com/index.php/bt 240 Research Perspective Open Access Artificial Intelligence in Predicting Bt Toxin-Insect Interactions JiaXuan Institute of Life Science, Jiyang College of Zhejiang A&F University, Zhuji, 311800, Zhejiang, China Corresponding email: 1931515591@qq.com Bt Research, 2024, Vol.15, No.5 doi: 10.5376/bt.2024.15.0024 Received: 18 Aug., 2024 Accepted: 30 Sep., 2024 Published: 16 Oct., 2024 Copyright © 2024 Xuan, This is an open access article published under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Preferred citation for this article: Xuan J., 2024, Artificial intelligence in predicting Bt toxin-insect interactions, Bt Research, 15(5): 240-247 (doi: 10.5376/bt.2024.15.0024) Abstract This study reviews the traditional research methods used to investigate Bt toxin-insect interactions and delves into the application of AI in toxin prediction, including machine learning algorithms, deep learning models, and advanced techniques for integrating multi-omics data. The involvement of AI not only enables the identification of genetic markers of insect resistance but also facilitates the development of AI-based models to track resistance development in field populations, providing an early warning system for resistance management. Case studies demonstrate how AI predicts insect resistance to Bt toxins, identifies novel Bt toxins, and determines their target specificity. The research shows that AI technologies can enhance the effectiveness of Bt toxins in pest control while also delaying the onset of resistance. However, data limitations, biological complexity, and computational challenges remain major obstacles in applying AI to Bt research. This study also suggests possible future directions for integrating AI into pest control strategies to promote sustainable agriculture. Keywords Bt toxins; Artificial intelligence; Insect resistance; Machine learning; Sustainable agriculture 1 Introduction Bacillus thuringiensis (Bt) is a bacterium that produces a variety of toxins, notably Cry and Cyt proteins, which are highly effective against a range of insect pests. These toxins function by binding to specific receptors in the insect midgut, leading to cell lysis and ultimately the death of the insect. Cry proteins, in particular, have been extensively studied and are widely used in agricultural pest control due to their specificity and effectiveness. However, the emergence of resistance in insect populations poses a significant challenge to the long-term efficacy of Bt toxins (Badran et al., 2016; Heckel, 2021). Understanding the molecular mechanisms of Bt toxin action and resistance is crucial for developing strategies to mitigate resistance and enhance the sustainability of Bt-based pest control (Chen et al., 2015; Wang et al., 2018). Artificial Intelligence (AI) has revolutionized various fields of scientific research, including biology. AI tools such as machine learning algorithms and predictive modeling have enabled researchers to analyze complex biological data with unprecedented accuracy and speed. In the context of Bt toxin research, AI has been employed to predict protein structures, identify novel toxin sequences, and understand the interactions between Bt toxins and insect receptors (Shikov et al., 2020; Torres et al., 2023). For instance, Alphafold-2 has been used to predict the oligomeric structures of Cry toxins, providing insights into their membrane insertion mechanisms. AI-driven tools like CryProcessor facilitate the mining of sequencing data to discover new Bt toxins, thereby expanding the arsenal of available bioinsecticides. This study will utilize artificial intelligence tools to elucidate the structural dynamics of Bt toxins, identify new toxin sequences, and predict resistance mechanisms in insect populations, with a focus on developing innovative solutions to maintain the effectiveness of Bt-based pest control. The research aims to enhance the precision and efficiency of pest management strategies by integrating artificial intelligence into Bt toxin research, addressing the challenges posed by insect resistance. 2 Current Methods for Studying Bt Toxin-Insect Interactions 2.1 Traditional experimental approaches Traditional experimental approaches to studying Bacillus thuringiensis (Bt) toxin-insect interactions primarily
RkJQdWJsaXNoZXIy MjQ4ODYzNA==