Answers are grounded in this paper and cite their sources.
Experimental study reveals machine learning models predict immunoassay cross-reactivity for 26 fluoroquinolones, indicating 3D descriptors are vital to distinguish enantiomers.
Detection systems for antibiotics of the (fluoro)quinolone (FQ) group are in high demand among food safety regulators and agricultural inspectors. At the same time, the application of developed test systems may be complicated by the significant structural diversity of related FQs (including enantiomeric forms), which necessitates the careful evaluation of their selectivity. In this study, five polyclonal antibodies were generated by immunizing rabbits with the S- and R-enantiomers of ofloxacin (OFL) and its racemic mixture used as haptens. The cross-reactivity (CR) of the obtained antibodies toward 26 FQs, structural analogs of OFL, was evaluated using an indirect competitive enzyme-linked immunosorbent assay. Structure–activity relationship models were developed to analyze the obtained CR data. Three machine learning (ML) methods were applied: random forest classifier (RFC), logistic regression (LR), and a support vector classifier (SVC). The SVC model demonstrated the highest predictive performance in terms of the Log Loss metric. In contrast, the LR models showed the best overall balance across six statistical metrics, including precision, recall, and F1 score. Three-dimensional topological descriptors enabled discrimination between the S- and R-isomers of OFL, whereas constitutional and two-dimensional descriptors were less effective. The obtained results contribute to the development of FQ immunoassay systems and their computational analysis using ML approaches.
No takes yet. Share an insight, caveat, or question.
Chebotaev et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: