SubGE-DDI: A new prediction model for drug-drug interaction established through biomedical texts and drug-pairs knowledge subgraph enhancement.

Biomedical texts provide important data for investigating drug-drug interactions (DDIs) in the field of pharmacovigilance. Although researchers have attempted to investigate DDIs from biomedical texts and predict unknown DDIs, the lack of accurate manual annotations significantly hinders the performance of machine learning algorithms. In this study, a new DDI prediction framework, Subgraph Enhance model, was developed for DDI (SubGE-DDI) to improve the performance of machine learning algorithms. This model uses drug pairs knowledge subgraph information to achieve large-scale plain text prediction without many annotations. This model treats DDI prediction as a multi-class classification problem and predicts the specific DDI type for each drug pair (e.g. Mechanism, Effect, Advise, Interact and Negative). The drug pairs knowledge subgraph was derived from a huge drug knowledge graph containing various public datasets, such as DrugBank, TwoSIDES, OffSIDES, DrugCentral, EntrezeGene, SMPDB (The Small Molecule Pathway Database), CTD (The Comparative Toxicogenomics Database) and SIDER. The SubGE-DDI was evaluated from the public dataset (SemEval-2013 Task 9 dataset) and then compared with other state-of-the-art baselines. SubGE-DDI achieves 83.91% micro F1 score and 84.75% macro F1 score in the test dataset, outperforming the other state-of-the-art baselines. These findings show that the proposed drug pairs knowledge subgraph-assisted model can effectively improve the prediction performance of DDIs from biomedical texts.

A real-world disproportionality analysis of anti-VEGF drugs from the FDA Adverse Event Reporting System.

BACKGROUND: The association between anti-vascular endothelial growth factor (VEGF) drugs and ocular adverse events (AEs) has been reported, but large real-world studies of their association with systemic AEs are still lacking. METHODS: A disproportionality analysis of reports from the FDA Adverse Event Reporting System from January 2004 to September 2021 was conducted to detect the significant ADR signals with anti-VEGF drugs (including aflibercept, bevacizumab, brolucizumab, pegaptanib, and ranibizumab). RESULTS: A total of 2980 reported cases with 7125 drug-AEs were included. Five drugs were all associated with eye disorders, and pegaptanib and ranibizumab were also associated with cardiac disorders. For ranibizumab, pegaptanib, bevacizumab and aflibercept, the proportions of cardiac AEs were 8.57%, 5.62%, 3.43% and 3.20%, respectively, and the proportions of central nervous AEs were 8.81%, 7.41, 5.86% and 5.68%, respectively. In multiple comparisons, ranibizumab was significantly higher than bevacizumab and aflibercept in the proportion of cardiac AEs (P < 0.001), and ranibizumab was significantly higher than aflibercept in central nervous AEs (P < 0.001). CONCLUSIONS: Our findings support the associations between anti-VEGF drugs and ocular AEs, cardiac AEs, and central nervous AEs. After intravitreal injection, attention should not only be paid to ocular symptoms, but also to systemic symptoms.