Suay-Garcia Beatriz, Falcó Antonio, Bueso-Bordils J Ignacio, Anton-Fos Gerardo M, Pérez-Gracia M Teresa, Alemán-López Pedro A
Departamento de Matemáticas, Física y Ciencias Tecnológicas, Universidad Cardenal Herrera-CEU, CEU Universities, Alfara del Patriarca, 46115 Valencia, Spain.
Departamento de Farmacia Universidad Cardenal Herrera-CEU, CEU Universities, Alfara del Patriarca, 46115 Valencia, Spain.
Pharmaceuticals (Basel). 2020 Nov 28;13(12):431. doi: 10.3390/ph13120431.
Drug repurposing appears as an increasing popular tool in the search of new treatment options against bacteria. In this paper, a tree-based classification method using Linear Discriminant Analysis (LDA) and discrete indexes was used to create a QSAR (Quantitative Structure-Activity Relationship) model to predict antibacterial activity against Escherichia coli. The model consists on a hierarchical decision tree in which a discrete index is used to divide compounds into groups according to their values for said index in order to construct probability spaces. The second step consists in the calculation of a discriminant function which determines the prediction of the model. The model was used to screen the DrugBank database, identifying 134 drugs as possible antibacterial candidates. Out of these 134 drugs, 8 were antibacterial drugs, 67 were drugs approved for different pathologies and 55 were drugs in experimental stages. This methodology has proven to be a viable alternative to the traditional methods used to obtain prediction models based on LDA and its application provides interesting new drug candidates to be studied as repurposed antibacterial treatments. Furthermore, the topological indexes and have proven to have the ability to group active compounds effectively, which suggests a close relationship between them and the antibacterial activity of compounds against .
药物重新利用似乎是寻找新型抗细菌治疗方案中越来越受欢迎的工具。在本文中，一种使用线性判别分析（LDA）和离散指标的基于树的分类方法被用于创建一个定量构效关系（QSAR）模型，以预测对大肠杆菌的抗菌活性。该模型由一个层次决策树组成，其中使用一个离散指标根据化合物在该指标上的值将其分为不同组，以便构建概率空间。第二步是计算一个判别函数，该函数决定模型的预测。该模型被用于筛选药物银行数据库，识别出134种药物作为可能的抗菌候选药物。在这134种药物中，8种是抗菌药物，67种是已被批准用于不同病症的药物，55种是处于实验阶段的药物。这种方法已被证明是用于获得基于LDA的预测模型的传统方法的可行替代方案，其应用提供了有趣的新型候选药物，可作为重新利用的抗菌治疗方法进行研究。此外，拓扑指标 和 已被证明有能力有效地对活性化合物进行分组，这表明它们与化合物对 的抗菌活性之间存在密切关系。
