MOTIVATION: Computational prediction of drug-target affinity (DTA) plays a critical role in modern drug discovery. However, the limited interpretability of traditional deep learning models and the heterogeneity of multimodal data from compounds and proteins hinder their reliability in practical drug development applications. RESULTS: We propose a novel Uncertainty-aware Multimodal Representation Learning (UAMRL) framework to address these challenges. UAMRL employs a dual-stream encoder to learn cross-modal association mappings between drugs and targets in a latent space and integrates heterogeneous information from different modalities. Moreover, an uncertainty quantification mechanism based on the Normal-Inverse-Gamma distribution is introduced to model the reliability of heterogeneous information and suppress less trustworthy contributions during fusion. Experiments show that UAMRL achieves superior predictive accuracy on multiple public DTA datasets, improving both prediction performance and decision transparency. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/Astraea2xu/UAMRL.

This paper presents a novel approach for aspect-level sentiment analysis by leveraging the relationships between dependent types and aspects. The proposed method involves simplifying the type-aware graph convolutional network and designing a graph convolution module specifically for extracting relations between aspect words. The process begins with constructing an ordinary dependency graph for each sentence using a dependency tree. This graph is then refined by considering syntactic dependencies between context words and aspect-specific words, resulting in an aspect-focused graph. The aspect-focused graph, along with the corresponding embedding matrices, is fed into the aspect-focused GCN to capture the essential aspects and context words. Moreover, an inter-aspect GCN is employed to extract the dependencies between aspect words and other aspect words, utilizing the representations learned by the focused aspect GCN based on the inter-aspect graph. The L-layer of the GCN incorporates a bidirectional attentional mechanism to extract interrelationships, thus enhancing sentiment polarity judgment. Through interactive learning of aspect-specific affective features, the model acquires an understanding of the relationships between important text and aspect words, as well as the relationships among aspect words. Experimental results on five benchmark datasets demonstrate the superior performance of our proposed method compared to state-of-the-art approaches, exhibiting a significant improvement over the regular GCN model.