“…In light of the observed correlations among data derived from various antioxidant activity assays, the adoption of a multitask learning strategy has the potential to enhance the predictive capabilities of the model. Multitask models for quantitative structure–biological effect relationships (mtk-QSBER) have been used to simultaneously predict activity, toxicity, and ADME end points across a range of biological targets and assay protocols. − For instance, these models have been used to identify new lead compounds with antileishmanial properties, design chemicals with dual pan-antiviral and anticytokine storm profiles, and discover multistrain inhibitors for antituberculosis therapy. − The mtk-QSBER models provide new perspectives and tools for drug design and biological effect prediction.…”