Abstract
protein-protein interactions (PPIs) are crucial for understanding cellular processes and disease mechanisms. While experimental methods for detecting PPIs exist, computational approaches offer a more efficient alternative. However, current computational methods often rely on single feature types or simple feature concatenation, potentially missing the complex nature of protein interactions. This study proposes FFADW (Feature Fusion Method with Attributed DeepWalk), a novel approach that integrates sequence and network features using a weighted fusion strategy controlled by an adjustable α parameter. Specifically, sequence similarity is computed using Levenshtein distance, while network similarity is measured via a Gaussian kernel-based approach. These complementary features are fused through the weighting mechanism before being processed by the Attributed DeepWalk algorithm, which enhances protein representations by learning low-dimensional embeddings. The fused representations are then used to train classifiers for PPI prediction. Evaluation across three datasets using multiple classifiers demonstrated that FFADW significantly improves sample clustering and performs better than existing approaches, with the XGBoost classifier showing the best results. The weighted fusion approach effectively combines different aspects of protein data while reducing noise and redundancy, offering an improved technique for computational PPI prediction.