PHCDTI: A multichannel parallel high-order feature crossover model for DTIs prediction

The exploration of non-covalent interactions between drugs and proteins (NCIs) has significantly improved the performance of drug–target interactions (DTIs) prediction models. However, existing methods for simulating NCIs are limited to single or multiple interactions, ignoring the combinatorial effects (i.e., high-order crossover between drugs and proteins (HOC-D&P)) that can arise when multiple NCIs coexist. To overcome this limitation, a multi-channel parallel high-order prediction model (PHCDTI) is proposed, aiming to simulate the complex interactions between drugs and proteins, thereby modeling HOC-D&P. Firstly, a tri-channel parallel model structure is constructed, allowing each channel to independently learn the interaction patterns between drug molecules and amino acid groups. Secondly, the three channels are designed from low-order to high-order, incorporating linear, inner-product, and pair-interaction feature crossover methods to simulate the complex interactions between drug molecules and amino acid groups. The stacking of residual connections enables the model to effectively model HOC-D&P. Additionally, by utilizing multi-head attention mechanisms for inner product and squeeze-excitation networks (SENET) for pair-interaction, the interpretability of the NCIs modeling process and the specific representation of drug molecules or amino acid groups are achieved. PHCDTI was evaluated on three benchmark datasets in four experimental settings, and the results indicated that it outperformed the most recent baseline model. In all cases, the average accuracy, precision, recall, AUC, and AUPR of PHCDTI are improved over the best baseline model by 3.56%, 6.06%, 3.99%, 2.50%, and 8.11%, respectively. Moreover, strong information filtering capabilities were exhibited by PHCDTI, with the effectiveness of the three-channel design confirmed by ablation studies. Finally, a case study on the human γ -aminobutyric acid receptors (GABARs) demonstrated that PHCDTI can serve as a powerful tool for real-world drug screening and design.