Characterizing secretion system effector proteins with structure-aware graph neural networks and pre-trained language models.
The type III secretion systems (T3SSs) play a pivotal role in host-pathogen interactions by mediating the secretion of type III secretion system effectors (T3SEs) into host cells. These T3SEs mimic host cell protein functions, influencing interactions between Gram-negative bacterial pathogens and their hosts. However, the functional attributes of proteins are intricately correlated with their 3D structures, and the structural characteristics of T3SEs are overlooked by existing methods. To this end, we proposed a multi-channel deep learning model called EDIFIER to predict T3SEs using protein 3D structure and sequence data. Furthermore, the test results demonstrate that the EDIFIER performance is superior to that of existing state-of-the-art methods. To improve user comfort and usability, without having to worry about complex algorithmic details and environmental configurations, we developed a free website to predict T3SEs using the proposed EDIFIER multi-channel model. |