On QSAR-based cardiotoxicity modeling with the expressiveness-enhanced graph learning model and dual-threshold scheme.

Introduction: Given the direct association with malignant ventricular arrhythmias, cardiotoxicity is a major concern in drug design. In the past decades, computational models based on the quantitative structure-activity relationship have been proposed to screen out cardiotoxic compounds and have shown promising results. The combination of molecular fingerprint and the machine learning model shows stable performance for a wide spectrum of problems; however, not long after the advent of the graph neural network (GNN) deep learning model and its variant (e.g., graph transformer), it has become the principal way of quantitative structure-activity relationship-based modeling for its high flexibility in feature extraction and decision rule generation. Despite all these progresses, the expressiveness (the ability of a program to identify non-isomorphic graph structures) of the GNN model is bounded by the WL isomorphism test, and a suitable thresholding scheme that relates directly to the sensitivity and credibility of a model is still an open question. Methods: In this research, we further improved the expressiveness of the GNN model by introducing the substructure-aware bias by the graph subgraph transformer network model. Moreover, to propose the most appropriate thresholding scheme, a comprehensive comparison of the thresholding schemes was conducted. Results: Based on these improvements, the best model attains performance with 90.4% precision, 90.4% recall, and 90.5% F1-score with a dual-threshold scheme (active: <1µM; non-active: >30µM). The improved pipeline (graph subgraph transformer network model and thresholding scheme) also shows its advantages in terms of the activity cliff problem and model interpretability.

Molecularly imprinted hollow spheres for the solid phase extraction of estrogens.

Solid phase extraction (SPE) is widely used in many different areas, such as environmental, biological, and food analysis, where cleaning and pre-concentration of samples are key steps in the analytical protocol. New materials have significant impact on the development of solid phase extraction. In this paper, mono-dispersed molecularly imprinted hollow spheres (MIHSs) of ß-estradiol (E2) were synthesized using silica nanospheres particles as the sacrificial matrix. Compared to the corresponding non-imprinted hollow spheres (NIHSs), the MIHSs with uniform size of 290 nm have outstanding affinity in aqueous solution. Static saturation adsorption required only 15min to achieve equilibrium, with a binding capacity (Qmax) of 44.5 µmol g(-1). The extraction of E2, ethinyl estradiol (EE), diethylstilbestrol (DES), ethisterone (ES) and estrone (E1) from water samples by MIHSs was also investigated. In the spiked samples of tap water, Qinghe river water and Zhanjiang river water, more than 90.42% of E2, but less than 79% of EE, DES, ES and E1 were recovered. The limits of detection (LOD) ranged from 0.1 to 0.26 µmol L(-1) after solid phase extraction by MIHSs and HPLC-UV analysis. The adsorption capacity of the MIHSs showed no significant deterioration after six rounds of regeneration.