Artificial intelligence (AI)-assisted prediction of adverse drug reactions (ADRs) has significant potential for improving drug safety and reducing financial costs. Early studies often relied on limited dimensions such as the molecular structure of drugs or interactions with biomolecules. In contrast, integrating these characteristics provides valuable insights into ADR predictions from multiple perspectives, enhancing the comprehensiveness and accuracy of the prediction models. In addition, previous studies have focused on whether a specific adverse drug reaction occurs with a particular drug, ignoring the fact that multiple adverse drug reactions may occur concurrently with a single drug. To address these, we developed a predictor that identifies ADRs early in drug discovery, using a deep learning model designed to fuse multiple drug characteristics. Our approach employed four modules to extract one- and two-dimensional sequence structure information of drug molecules, drug–protein interaction data, and drug similarity. A fusion model integrated these characteristics to predict the precise probability of ADRs. The receiver operating characteristic–area under curve (ROC-AUC), area under precision–recall curve (AUPR), and F1 scores on the benchmark dataset are 0.7002, 0.6619, and 0.6330, respectively. The AUPR is significantly improved compared to the conventional multi-label classifier (from 64.02% to 66.19%). In addition, we compared the results with the state-of-the-art methods on LIU’s dataset and the AUPR increased from 34.65% to 68.82%, which shows that our model outperforms them in terms of accuracy and robustness. Ablation experiments further validated the effectiveness of the individual modules. This model accurately predicted the probability of various ADR classes by integrating comprehensive information, thereby offering significant value in enhancing monitoring measures for new drug development and clinical use.

Background: Hepatocellular carcinoma (HCC), a prevalent form of primary liver malignancy, arises from liver-specific hepatocytes. Senecio scandens Buch.-Ham(Climbing senecio) is a bitter-tasting plant of the Compositae family with anti-tumor properties. This study aims to identify the molecular targets and pathways through which Climbing senecio regulates HCC. Methods: Active ingredients of Climbing senecio were collected from four online databases and mapped to relevant target databases to obtain predicted targets. After recognizing the key pathways through which Climbing senecio acts in HCC. Gene expression data from GSE54238 Underwent differential expression and weighted gene correlation network analyses to identify HCC-related genes. The “Climbing senecio-Hepatocellular Carcinoma Targets” network was constructed using Cytoscape 3.10.1 software, followed by topology analysis to identify core genes. The expression and distribution of key targets were evaluated, and the differential expression of each key target between normal and diseased samples was calculated. Moreover, single-cell data from the Gene Expression Omnibus (GSE202642) were used to assess the distribution of Climbing senecio’s bioactive targets within major HCC clusters. An intersection analysis of these clusters with pharmacological targets and HCC-related genes identified Climbing senecio’s primary targets for this disease. Cell communication, receiver operating characteristic (ROC)analysis, survival analysis, immune filtration analysis, and molecular docking studies were conducted for detailed characterization. Results: Eleven components of Climbing senecio were identified, along with 520 relevant targets, 300 differentially expressed genes, and 3765 co-expression module genes associated with HCC. AKR1B1, CA2, FOS, CXCL2, SRC, ABCC1, and PLIN1 were identified within the intersection of HCC-related genes and Climbing senecio targets. TGFβ, IL-1, VEGF, and CXCL were identified as significant factors in the onset and progression of HCC. These findings underscore the anti-HCC potential and mode of action of Climbing senecio, providing insights into multi-targeted treatment approaches for HCC. Conclusions: This study revealed that Climbing senecio may target multiple pathways and genes in the process of regulating HCC and exert potential drug effects through a multi-target mechanism, which provides a new idea for the treatment of HCC. However, the research is predicated on network database analysis and bioinformatics, offering insights into HCC therapeutic potential while emphasizing the need for further validation.