EDLMPPI: Learning the Protein Language of Proteome-wide Protein-protein Binding Sites via Explainable Ensemble Deep Learning
Xiangtao Li, Zilong Hou, Yuning Yang, Zhiqiang Ma, Ka‐Chun Wong · Research Square · 2022
Abstract Protein-protein interactions (PPIs) govern cellular pathways and processes, by significantly influencing the functional expression of proteins. Therefore, accurate identification of protein-protein interaction binding sites has become a key step in the functional analysis of proteins. We develop an ensemble deep learning model (EDLMPPI)-based protein-protein interaction site identification method. In particular, we propose to apply a transformer structure-based dynamic word embedding model (ProtT5) to extract potential associations between protein primary structures, capturing their functional and structural properties from readily available sequence data alone. After that, EDLMPPI is based on BiLSTM in order to sufficiently learn the contextual associations between features and to preserve the contextual information through a capsule network to further improve the generalization performance. To address the unbalanced dataset, we employ ensemble learning to train multiple models and then integrate them to further enhance the performance of the algorithm. Evaluation results show that EDLMPPI can achieve the best results on all datasets. Meanwhile, we compared EDLMPPI with other PPI site prediction models and observed that EDLMPPI outperformed the state-of-the-art models by nearly 10% in terms of average accuracy. In addition, the biological and interpretable analyses provide new insights into proteins binding site identification and characterization mechanisms from different perspectives.