Spatial transcriptomics (ST) aims to decode spatially resolved gene expression patterns while preserving tissue morphology. Current methods tend to use lower-cost deep learning approaches for gene expression prediction, yet face severe challenges. First, existing methods fail to give sufficient consideration to the spatial specificity of positional encoding inherent in ST; second, they neglect to leverage spatially coherent co-expression patterns across different domains; third, their reliance on linearly weighted aggregation induces vulnerability to noise and distribution shifts; and finally, these architectures exhibit limited parameter efficiency. To address these issues, we introduce prototype-guided network for spatial transcriptomics (PGST), which includes four parts: (1) oriented signal propagation through polar embedding strategy for spatial transcriptomics (PEST); (2) prototype-guided aggregation for global co-feature preservation; (3) global consistency enforcement via shared decoder with reconstruction loss; and (4) lightweight architectural design. Our framework integrates contrastive learning with graph neural networks to balance local-global spatial dependencies and cross-modal consistency. Experimental results on multiple datasets from ST demonstrate the superior performance of our PGST model than existing methods.

MOTIVATION: Effective computational methods for predicting the mechanism of action (MoA) of compounds are essential in drug discovery. Current MoA prediction models mainly utilize the structural information of compounds. However, high-throughput screening technologies have generated more targeted cell perturbation data for MoA prediction, a factor frequently disregarded by the majority of current approaches. Moreover, exploring the commonalities and specificities among different fingerprint representations remains challenging. RESULTS: In this paper, we propose IFMoAP, a model integrating cell perturbation image and fingerprint data for MoA prediction. Firstly, we modify the Res-Net to accommodate the feature extraction of five-channel cell perturbation images and establish a granularity-level attention mechanism to combine coarse- and fine-grained features. To learn both common and specific fingerprint features, we introduce an FP-CS module, projecting four fingerprint embeddings into distinct spaces and incorporating two loss functions for effective learning. Finally, we construct two independent classifiers based on image and fingerprint features for prediction and for weighting the two prediction scores. Experimental results demonstrate that our model achieves highest accuracy of 0.941 when using multimodal data. The comparison with other methods and explorations further highlights the superiority of our proposed model and the complementary characteristics of multimodal data. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/ s1mplehu/IFMoAP. The raw image data of Cell Painting can be accessed from Figshare (https://doi.org/10.17044/scilifelab.21378906).

Drug-induced liver injury is a leading cause of high attrition rates for both candidate drugs and marketed medications. Previous in silico models may not effectively utilize biological drug property information and often lack robust model validation. In this study, we developed a graph convolutional network embedded with a biological graph learning (BioGL) module-named BioGL-GCN(Biological Graph Learning-Graph Convolutional Network)-for drug-induced liver injury prediction using toxicogenomic profiles. The BioGL module learned the optimal graph representations of gene interactions by utilizing the constructed protein-protein interaction network, which represents initial gene relationships, and gene frequency information obtained from gene enrichment analysis. Finally, the graph convolutional network was used to identify drug hepatotoxicity. Our method pays more attention to gene-gene relationships compared to previous approaches, thereby achieving more accurate predictive performance. We applied BioGL-GCN to predict DILI risk for active components in the integrated traditional Chinese medicine (ITCM) database and validated these predictions through hepatotoxicity experiments using a 3D primary human hepatocyte (PHH) model. The results showed that our model achieved a prediction accuracy of 79%, thus further validating the reliability of the constructed model.

Cancer therapy-related cardiac dysfunction (CTRCD) is a potential complication associated with cancer treatment, particularly in patients with breast cancer, requiring monitoring of cardiac health during the treatment process. Tissue Doppler imaging (TDI) is a remarkable technique that can provide a comprehensive reflection of the left ventricle's physiological status. We hypothesized that the combination of TDI features with deep learning techniques could be utilized to predict CTRCD. To evaluate the hypothesis, we developed a temporal-multimodal pattern network for efficient training (TPNET) model to predict the incidence of CTRCD over a 24-month period based on TDI, function, and clinical data from 270 patients. Our model achieved an area under curve (AUC) of 0.83 and sensitivity of 0.88, demonstrating greater robustness compared to other existing visual models. To further translate our model's findings into practical applications, we utilized the integrated gradients (IG) attribution to perform a detailed evaluation of all the features. This analysis has identified key pathogenic signs that may have remained unnoticed, providing a viable option for implementing our model in preoperative breast cancer patients. Additionally, our findings demonstrate the potential of TPNET in discovering new causative agents for CTRCD.

Accurate prediction of molecular toxicity is vital for drug development. Most mainstream methods rely on fingerprints or graph-based feature extraction, the emergence of large language models (LLMs) offers new prospects for molecular representation learning in toxicity prediction. Although several studies attempt to leverage LLMs to integrate molecular sequence data for pretraining molecular representations, certain limitations remain. Current LLM-based approaches usually utilize solely on class embedding features, overlooking the rich information in sequence embedding. Moreover, integrating pre-trained molecular representations with multi-modal molecular data may further enhance performance in toxicity prediction. To address these challenges, we propose BFGTP, a BERT-guided two-stage molecular representation learning framework for toxicity prediction. Firstly, we design independent encoders for molecular descriptions of three modalities, where the fingerprint encoder with dual level attention mechanisms effectively integrates multi-category fingerprints. Then, the two-stage guide strategy is introduced to fully utilize the prior knowledge of LLMs, employing contrastive learning to align and fuse the tri-modal representations and knowledge distillation to align predicted value distributions. BFGTP ultimately combines fingerprint and graph representations to predict molecular toxicity. Experiments on seven toxicity datasets show that BFGTP outperforms baselines, achieving the highest AUC on five datasets and the best average performance across five evaluation metrics. Ablation studies, t-SNE visualization and case study confirm the effectiveness of BFGTP's components and its ability to capture meaningful molecular representations.

MOTIVATION: Effective computational methods to predict drug-protein interactions (DPIs) are vital for drug discovery in reducing the time and cost of drug development. Recent DPI prediction methods mainly exploit graph data composed of multiple kinds of connections among drugs and proteins. Each node in the graph usually has topological structures with multiple scales formed by its first-order neighbors and multi-order neighbors. However, most of the previous methods do not consider the topological structures of multi-order neighbors. In addition, deep integration of the multi-modality similarities of drugs and proteins is also a challenging task. RESULTS: We propose a model called ALDPI to adaptively learn the multi-scale topologies and multi-modality similarities with various significance levels. We first construct a drug-protein heterogeneous graph, which is composed of the interactions and the similarities with multiple modalities among drugs and proteins. An adaptive graph learning module is then designed to learn important kinds of connections in heterogeneous graph and generate new topology graphs. A module based on graph convolutional autoencoders is established to learn multiple representations, which imply the node attributes and multiple-scale topologies composed of one-order and multi-order neighbors, respectively. We also design an attention mechanism at neighbor topology level to distinguish the importance of these representations. Finally, since each similarity modality has its specific features, we construct a multi-layer convolutional neural network-based module to learn and fuse multi-modality features to obtain the attribute representation of each drug-protein node pair. Comprehensive experimental results show ALDPI's superior performance over six state-of-the-art methods. The results of recall rates of top-ranked candidates and case studies on five drugs further demonstrate the ability of ALDPI to discover potential drug-related protein candidates. CONTACT: [email protected].

MOTIVATION: Accurate identification of proteins interacted with drugs helps reduce the time and cost of drug development. Most of previous methods focused on integrating multisource data about drugs and proteins for predicting drug-target interactions (DTIs). There are both similarity connection and interaction connection between two drugs, and these connections reflect their relationships from different perspectives. Similarly, two proteins have various connections from multiple perspectives. However, most of previous methods failed to deeply integrate these connections. In addition, multiple drug-protein heterogeneous networks can be constructed based on multiple kinds of connections. The diverse topological structures of these networks are still not exploited completely. RESULTS: We propose a novel model to extract and integrate multi-type neighbor topology information, diverse similarities and interactions related to drugs and proteins. Firstly, multiple drug-protein heterogeneous networks are constructed according to multiple kinds of connections among drugs and those among proteins. The multi-type neighbor node sequences of a drug node (or a protein node) are formed by random walks on each network and they reflect the hidden neighbor topological structure of the node. Secondly, a module based on graph neural network (GNN) is proposed to learn the multi-type neighbor topologies of each node. We propose attention mechanisms at neighbor node level and at neighbor type level to learn more informative neighbor nodes and neighbor types. A network-level attention is also designed to enhance the context dependency among multiple neighbor topologies of a pair of drug and protein nodes. Finally, the attribute embedding of the drug-protein pair is formulated by a proposed embedding strategy, and the embedding covers the similarities and interactions about the pair. A module based on three-dimensional convolutional neural networks (CNN) is constructed to deeply integrate pairwise attributes. Extensive experiments have been performed and the results indicate GCDTI outperforms several state-of-the-art prediction methods. The recall rate estimation over the top-ranked candidates and case studies on 5 drugs further demonstrate GCDTI's ability in discovering potential drug-protein interactions.

Identification of interactions between drugs and target proteins plays a critical role not only in drug discovery but also in drug repositioning. Deep integration of inter-connections and intra-similarities between heterogeneous multi-source data about drugs and targets, however, is a challenging issue. We propose a drug-target interaction (DTI) prediction model by learning from drug and protein related multi-scale attributes and global topology formed by heterogeneous connections. A drug-protein-disease heterogeneous network (RPD-Net) is firstly constructed to associate diverse similarities, interactions and associations across nodes. Secondly, we propose a multi-scale pairwise deep representation learning module consisting of a new embedding strategy to integrate diverse inter-relations and intra-relations, and dilation convolutions for multi-scale deep representation extraction. A global topology learning module is proposed which is composed of strategy based on non-negative matrix factorization (NMF) to extract topology from RPD-Net, and a new relational-level attention mechanism for discriminative topology embedding. Experimental results using public dataset demonstrate improved performance over state-of-the-art methods and contributions of our major innovations. Evaluation results by top k recall rates and case studies on five drugs further show the effectiveness of our method in retrieving potential target candidates for drugs.