Accurate prediction of drug-induced adverse drug reactions (ADRs) is crucial for drug safety evaluation, as it directly impacts public health and safety. While various models have shown promising results in predicting ADRs, their accuracy still needs improvement. Additionally, many existing models often lack interpretability when linking molecular structures to specific ADRs and frequently rely on manually selected molecular fingerprints, which can introduce bias. To address these challenges, we propose ToxBERT, an efficient transformer encoder model that leverages attention and masking mechanisms for simplified molecular input line entry system (SMILES) representations. Our results demonstrate that ToxBERT achieved area under the receiver operating characteristic curve (AUROC) scores of 0.839, 0.759, and 0.664 for predicting drug-induced QT prolongation (DIQT), rhabdomyolysis, and liver injury, respectively, outperforming previous studies. Furthermore, ToxBERT can identify drug substructures that are closely associated with specific ADRs. These findings indicate that ToxBERT is not only a valuable tool for understanding the mechanisms underlying specific drug-induced ADRs but also for mitigating potential ADRs in the drug discovery pipeline.

Objective To investigate the expression of cyclin D3 and proliferating cell nuclear antigen (PCNA) and their clinical significance in mal ignant melanoma. Methods The expression of cyclin D3 and PCNA was measured by streptavidin-peroxidase complex immunohistochemical technique in 57 cases of pri mary cutaneous malignant melanoma (CMM), 37 cases of metastatic melanoma and 20 cases of benign nevi. Results The positive expression rate of cyclin D3 in CM M and metastatic melanoma were 35.1% and 59.5% respectively, while the high expr ession rate of PCNA were 57.9% and 78.6% respectively. Compared with that in ben ign nevi, the expression of cyclin D3 and PCNA was significantly increased. The expression of cyclin D3 and PCNA in CMM was positively related to Clark′s grade and the metastasis to lymph nodes. The 3-year survival rate in patients with ne gative expression of cyclin D3 was significantly higher than that with positive expression in superficial melanomas. The 3-year survival rate of patients with l ow expression of PCNA was significantly higher than that with high expression in CMM. The expression of cyclin D3 was positively correlated with the high expres sion of PCNA in superficial and metastatic melanomas. Conclusions The expressi on of cyclin D3 and PCNA may be involved in the carcinogenesis process and progr ession of CMM and have important implications in the selection of therapeutic re gimens and prognostic assessment. The expression level of cyclin D3 may be regar ded as a prognostic factor for superficial melanoma.