PmxPred: A data-driven approach for the identification of active polymyxin analogues against gram-negative bacteria

Xiaoyu Wang, Nitin Patil, Fuyi Li, Zhikang Wang, Haolan Zhan, Daniel Schmidt, Philip Thompson, Yuming Guo, Cornelia B. Landersdorfer, Hsin-Hui Shen, Anton Y. Peleg, Jian Li, Jiangning Song

Abstract: Highlights•A hybrid deep learning model to predict polymyxin's antimicrobial activity.•PmxPred integrates molecule-level and residue-level features.•A new embedding method for all amino acids including non-proteinogenic amino acids.•Provide a novel insight into the mechanism of polymyxin's antimicrobial activity.