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 ADR...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.展开更多
HIV-1 reverse transcriptase(RT)has received great attention as an attractive therapeutic target for acquired immune deficiency syndrome(AIDS),but the inevitable drug resistance and side effects have always been major ...HIV-1 reverse transcriptase(RT)has received great attention as an attractive therapeutic target for acquired immune deficiency syndrome(AIDS),but the inevitable drug resistance and side effects have always been major challenges faced by non-nucleoside reverse transcriptase inhibitors(NNRTIs).This work aimed to identify novel chemotypes of anti-HIV-1 agents with improved drugresistance profiles,reduced toxicity,and excellent druggability.A series of diarylpyrimidine(DAPY)derivatives were prepared via structural modifications of the leads K-5a2 and 25a.Among them,15a with dimethylphosphine oxide moiety showed the most prominent antiviral potency against all of the tested viral panel,being 1.6-fold(WT,EC_(50) Z 1.75 nmol/L),3.0-fold(L100I,EC_(50) Z 2.84 nmol/L),2.4-fold(K103N,EC_(50) Z 1.27 nmol/L),3.3-fold(Y181C,EC50 Z 5.38 nmol/L),2.9-fold(Y188L,EC_(50) Z 7.96 nmol/L),2.5-fold(E138K,EC_(50) Z 4.28 nmol/L),4.8-fold(F227L/V106A,EC_(50) Z 3.76 nmol/L)and 5.3-fold(RES056,EC_(50) Z 15.8 nmol/L)more effective than that of the marketed drug ETR.Molecular docking results illustrated the detailed interactions formed by compound 15a and WT,F227L/V106A,and RES056 RT.Moreover,15a-HCl carried outstanding pharmacokinetic(t1/2 Z 1.32 h,F Z 40.8%)and safety profiles(LD_(50)>2000 mg/kg),which demonstrated that 15a HCl is a potential anti-HIV-1 drug candidate.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.:22173065 and 21575094).
文摘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.
基金financial support from the National Natural Science Foundation of China(NSFC Nos.81973181,82273773)Shandong Provincial Natural Science Foundation(ZR2020YQ61,ZR2020JQ31,China)Qilu Young Scholars Program of Shandong University and Taishan Scholar Program at Shandong Province.
文摘HIV-1 reverse transcriptase(RT)has received great attention as an attractive therapeutic target for acquired immune deficiency syndrome(AIDS),but the inevitable drug resistance and side effects have always been major challenges faced by non-nucleoside reverse transcriptase inhibitors(NNRTIs).This work aimed to identify novel chemotypes of anti-HIV-1 agents with improved drugresistance profiles,reduced toxicity,and excellent druggability.A series of diarylpyrimidine(DAPY)derivatives were prepared via structural modifications of the leads K-5a2 and 25a.Among them,15a with dimethylphosphine oxide moiety showed the most prominent antiviral potency against all of the tested viral panel,being 1.6-fold(WT,EC_(50) Z 1.75 nmol/L),3.0-fold(L100I,EC_(50) Z 2.84 nmol/L),2.4-fold(K103N,EC_(50) Z 1.27 nmol/L),3.3-fold(Y181C,EC50 Z 5.38 nmol/L),2.9-fold(Y188L,EC_(50) Z 7.96 nmol/L),2.5-fold(E138K,EC_(50) Z 4.28 nmol/L),4.8-fold(F227L/V106A,EC_(50) Z 3.76 nmol/L)and 5.3-fold(RES056,EC_(50) Z 15.8 nmol/L)more effective than that of the marketed drug ETR.Molecular docking results illustrated the detailed interactions formed by compound 15a and WT,F227L/V106A,and RES056 RT.Moreover,15a-HCl carried outstanding pharmacokinetic(t1/2 Z 1.32 h,F Z 40.8%)and safety profiles(LD_(50)>2000 mg/kg),which demonstrated that 15a HCl is a potential anti-HIV-1 drug candidate.
