Toropova Alla P, Toropov Andrey A
IRCCS, Istituto di Ricerche Farmacologiche Mario Negri, Via La Masa 19, 20156 Milano, Italy.
IRCCS, Istituto di Ricerche Farmacologiche Mario Negri, Via La Masa 19, 20156 Milano, Italy.
J Theor Biol. 2017 Mar 7;416:113-118. doi: 10.1016/j.jtbi.2017.01.012. Epub 2017 Jan 11.
The prediction of biochemical endpoints is an important task of the modern medicinal chemistry, cell biology, and nanotechnology. Simplified molecular input-line entry system (SMILES) is a tool for representation of the molecular structure. In particular, SMILES can be used to build up the quantitative structure - property/activity relationships (QSPRs/QSARs). The QSPR/QSAR is a tool to predict an endpoint for a new substance, which has not been examined in experiment. Quasi-SMILES are representation of eclectic data related to an endpoint. In contrast to traditional SMILES, which are representation of the molecular structure, the quasi-SMILES are representation of conditions (in principle, the molecular structure also can be taken into account in quasi-SMILES). In this work, the quasi-SMILES were used to build up model for cell viability under impact of the metal-oxides nanoparticles by means of the CORAL software (http://www.insilico.eu/coral). The eclectic data for the quasi-SMILES are (i) molecular structure of metals-oxides; (ii) concentration of the nanoparticles; and (iii) the size of nanoparticles. The significance of different eclectic facts has been estimated. Mechanistic interpretation and the domain of applicability for the model are suggested. The statistical quality of the models is satisfactory for three different random distribution of available data into the training (sub-training and calibration) and the validation sets.
生物化学终点的预测是现代药物化学、细胞生物学和纳米技术的一项重要任务。简化分子线性输入系统（SMILES）是一种表示分子结构的工具。特别地，SMILES可用于建立定量结构-性质/活性关系（QSPRs/QSARs）。QSPR/QSAR是一种预测新物质终点的工具，该新物质尚未经过实验检验。准SMILES是与终点相关的综合数据的表示形式。与表示分子结构的传统SMILES不同，准SMILES是条件的表示形式（原则上，分子结构也可在准SMILES中予以考虑）。在本工作中，通过CORAL软件（http://www.insilico.eu/coral），利用准SMILES建立了金属氧化物纳米颗粒作用下细胞活力的模型。准SMILES的综合数据包括：（i）金属氧化物的分子结构；（ii）纳米颗粒的浓度；以及（iii）纳米颗粒的尺寸。已评估了不同综合因素的重要性。提出了该模型的机理解释和适用范围。对于可用数据在训练集（子训练集和校准集）和验证集之间的三种不同随机分布，模型的统计质量令人满意。
