Multi_CycGT: a DL-based multimodal model for membrane permeability prediction of cyclic peptides

Abstract

As a highly versatile therapeutic modality, cyclic peptides have gained significant attention due to their exceptional binding affinity, minimal toxicity and capacity to target the surface of conventionally "undruggable" proteins. However, the development of cyclic peptides with therapeutic effects by targeting intracellular biological targets has been hindered by the issue of limited membrane permeability. In this paper, we have conducted an extensive benchmarking analysis of a proprietary dataset consisting of 6941 cyclic peptides, employing machine learning and deep learning models. In addition, we propose an innovative multimodal model called Multi_CycGT which combines a Graph Convolutional Network (GCN) and a Transformer to extract 1D and 2D features. These encoded features are then fused for the prediction of cyclic peptide permeability. The cross-validation experiments demonstrate that the proposed Multi_CycGT model achieved the highest level of accuracy on the test set, with an accuracy value of 0.8206 and an AUC value of 0.8650. This paper introduces a pioneering deep learning-based approach that demonstrates enhanced effectiveness in predicting the membrane permeability of cyclic peptides. It also represents the first attempt in this field. We hope that this work will help to accelerate the design of cyclic peptide active drugs in medicinal chemistry and chemical biology applications.