Prediction of Protein-Protein Interaction based on Interaction-Specific Learning and Hierarchical Information

Опубликована: Апрель 10, 2025

Background: Prediction of protein–protein interactions (PPIs) is fundamental for identifying drug targets and understanding cellular processes. The rapid growth PPI studies necessitates the development efficient accurate tools automated prediction PPIs. In recent years, several robust deep learning models have been developed found widespread application in proteomics research. Despite these advancements, current computational still face limitations modeling both pairwise hierarchical relationships between proteins. Results: We present HI-PPI, a novel method that integrates representation network interaction-specific protein-protein interaction prediction. HI-PPI extracts information by embedding structural relational into hyperbolic space. A gated then employed to extract features Experiments on multiple benchmark datasets demonstrate outperforms state-of-the-art methods, improves MicroF1 scores 2.62%–7.09% over second-best method. Moreover, offers explicit interpretability organization within network. distance origin computed naturally reflects level Conclusions: Overall, proposed effectively addresses existing methods. By leveraging structure network, significantly enhances accuracy robustness predictions.

Язык: Английский

GAN-ML: Advancing anticancer peptide prediction through innovative Deep Convolution Generative Adversarial Network data augmentation technique

Chemometrics and Intelligent Laboratory Systems, Год журнала: 2025, Номер unknown, С. 105390 - 105390

Опубликована: Апрель 1, 2025

Язык: Английский

NeuroPred-AIMP: Multimodal Deep Learning for Neuropeptide Prediction via Protein Language Modeling and Temporal Convolutional Networks

Journal of Chemical Information and Modeling, Год журнала: 2025, Номер unknown

Опубликована: Апрель 21, 2025

Neuropeptides are key signaling molecules that regulate fundamental physiological processes ranging from metabolism to cognitive function. However, accurate identification is a huge challenge due sequence heterogeneity, obscured functional motifs and limited experimentally validated data. Accurate of neuropeptides critical for advancing neurological disease therapeutics peptide-based drug design. Existing neuropeptide methods rely on manual features combined with traditional machine learning methods, which difficult capture the deep patterns sequences. To address these limitations, we propose NeuroPred-AIMP (adaptive integrated multimodal predictor), an interpretable model synergizes global semantic representation protein language (ESM) multiscale structural temporal convolutional network (TCN). The introduced adaptive fusion mechanism residual enhancement dynamically recalibrate feature contributions, achieve robust integration evolutionary local information. experimental results demonstrated proposed showed excellent comprehensive performance independence test set, accuracy 92.3% AUROC 0.974. Simultaneously, good balance in ability identify positive negative samples, sensitivity 92.6% specificity 92.1%, difference less than 0.5%. result fully confirms effectiveness strategy task recognition.

Язык: Английский