MambaDTA: a novel Drug-Target Affinities prediction method with State-Space Model

The calculation of the drug-target affinity (DTA) is of paramount importance in drug discovery. Recently, there exist various deep learning methodologies geared towards extracting features from drug-target interactions to ascertain their mutual existence. The majority of these methods utilize sequences of targets and drugs as descriptors, potentially resulting in suboptimal performance in feature extraction by the networks. Recently, particularly with the Mamba, the Selective Structured State Space Model has demonstrated significant potential in modeling long-range dependencies with linear complexity. Inspired by the aforementioned, and to mitigate the high computational complexity faced by long biological sequences in deep learning, we propose a novel DTA prediction method named MambaDTA. Specifically, we design a novel drug sequence feature extraction module based on Mamba, which achieves knowledge extraction through the effective selection of feature information, enabling the model to extract more representative features from the data. Furthermore, we combine convolutional layers and Convolutional Block Attention Module (CBAM) to extract more important features from target sequences. We evaluate MambaDTA on three benchmarks and compare with state-of-the-art methods to ensure its performance and consistency. The results show that the proposed method demonstrate excellent performance, showcasing significant performance advantages over other state-of-the-art methods when handling DT sequence data. Last, we performed interpretability studies by incorporating a weighted attention mechanism into the network. By visualizing the interactions through attention weights, the results demonstrate that our model can provide valuable guidance for drug discovery.