DeepBLI: A Transferable Multichannel Model for Detecting β-Lactamase-Inhibitor Interaction

Pathogens producing fi-lactamase pose a great challenge to antibiotic-resistant infection treatment; thus, it is urgent to discover novel fi-lactamase inhibitors for drug develop-ment. Conventional high-throughput screening is very costly, and structure-based virtual screening is limited with mechanisms. In this study, we construct a novel multichannel deep neural network (DeepBLI) for fi-lactamase inhibitor screening, pretrained with a label reversal KIBA data set and fine-tuned on fi-lactamase-inhibitor pairs from BindingDB. First, the pairs of encoders (Conv and Att) fuse the information spatially and sequentially for both enzymes and inhibitors. Then, a co-attention module creates the connection between the inhibitor and enzyme embeddings. Finally, multichannel outputs fuse with an element-wise product and then are fed into 3-layer fully connected networks to predict interactions. Comparing the state-of-the-art methods, DeepBLI yields an AUROC of 0.9240 and an AUPRC of 0.9715, which indicates that it can identify new fi-lactamase-inhibitor interactions. To demonstrate its prediction ability, an application of DeepBLI is described to screen potential inhibitor compounds for metallo-fi- lactamase AIM-1 and repurpose rottlerin for four classes of fi-lactamase targets, showing the possibility of being a broad-spectrum inhibitor. DeepBLI provides an effective way for antibacterial drug development, contributing to antibiotic-resistant therapeutics.

Automated summary

A novel multichannel deep neural network, DeepBLI, was developed for screening β-lactamase inhibitors. Compared to state-of-the-art methods, DeepBLI showed better performance, indicating its potential in antibacterial drug development and contribution to antibiotic-resistant therapeutics.