Machine Learning Models and New Computational Tool for the Discovery of Insect Repellents that Interfere with Olfaction

<strong>SI1_Supporting Information</strong> file (docx) brings together detailed information on the outstanding models obtained for each dataset analyzed in this study such as statistical and training parameters and outliers. There can be found the responses in spikes/s of the mosquito <em>Culex quinquefasciatus </em>to the 50 IRs. Besides, there is presented a full table of the up-to-date studies related to QSAR and insect repellency. <strong>SI2_EXP1_50IRs from Liu et al (2013)</strong> SDF file presents the structures of each of the 50 IRs analyzed. <strong>SI3_EXP2_Datasets</strong> gathers the four datasets as SDF files from Oliferenko <em>et al.</em> (2013), Gaudin<em> et al. </em>(2008), Omolo <em>et al.</em> (2004), and Paluch <em>et al.</em> (2009) used for the repellency modeling in <strong>EXP2</strong>. <strong>SI4_EXP3_Prospective analysis </strong>provides Malaria Box Library (400 compounds) as an SDF file, which were analyzed in our virtual screening to prospect potential virtual hits. <strong>SI5_QuBiLS-MIDAS MDs lists</strong> contain three TXT lists of 3D molecular descriptors used in QuBiLS-MIDAS to describe the molecules used in the present study. <strong>SI6_EXP1_Sensillar Modeling</strong> comprises two subfolders: Classification and Regression models for each of the six sensilla. Models built to predict the physiological interaction experimentally obtained from Liu <em>et al.</em> (2013). All of the models are implemented in the software SiLiS-PAPACS. Every single folder compiles a DOCX file with the detailed description of the model, an XLSX file with the output obtained from the training in Weka 3.9.4, an ARFF, and CSV files with the MDs for each molecule, and the SDF of the study dataset. <strong>SI7_EXP2_Repellency Modeling </strong>encompasses the four datasets in the study: Oliferenko <em>et al.</em> (2013), Gaudin<em> et al. </em>(2008), Omolo <em>et al.</em> (2004), and Paluch <em>et al.</em> (2009). Inside the subfolders, there are three models per type of MDs (duplex, triple, generic, and mix) selected that best predict each dataset. As well as the SI6 folder, each model includes six files: DOCX, XLSX, ARFF, CSV, and an SDF. <strong>SI8_Virtual Hits </strong>includes the cluster analysis results and physico-chemical properties of new IR virtual leads.<strong>SI1_辅助信息（Supporting Information）</strong>：该docx格式文件汇总了本研究各分析数据集所得到的最优模型详细信息，涵盖统计参数、训练参数与异常值相关内容。其中包含致倦库蚊<em>Culex quinquefasciatus</em>对50种离子型受体（Ionotropic Receptors, IRs）以每秒尖峰数（spikes/s）为单位的响应数据；此外还提供了与定量构效关系（Quantitative Structure-Activity Relationship, QSAR）及昆虫驱避性相关的最新研究完整汇总表。 <strong>SI2_EXP1_50种IR：来自Liu等（2013）的研究</strong>：该结构数据文件（Structure Data File, SDF）包含本次分析的50种IR的分子结构信息。 <strong>SI3_EXP2_数据集合集</strong>：该合集以SDF格式收录了用于<strong>EXP2_驱避性建模</strong>的4组数据集，分别来自Oliferenko等（2013）、Gaudin等（2008）、Omolo等（2004）以及Paluch等（2009）的研究成果。 <strong>SI4_EXP3_前瞻性分析</strong>：该部分以SDF格式提供了疟疾药物库（Malaria Box Library，包含400种化合物），本研究通过虚拟筛选对该库进行分析以挖掘潜在虚拟命中化合物（virtual hits）。 <strong>SI5_QuBiLS-MIDAS 分子描述符列表</strong>：该部分包含3个TXT格式列表，收录了本研究中使用QuBiLS-MIDAS软件计算得到的3D分子描述符（Molecular Descriptors, MDs）。 <strong>SI6_EXP1_感器建模</strong>：该部分包含两个子文件夹，分别为针对6种感器构建的分类模型与回归模型，用于预测Liu等（2013）研究中得到的实验生理相互作用结果。所有模型均通过SiLiS-PAPACS软件实现。每个子文件夹均包含以下文件：用于详细说明模型的DOCX文件、基于Weka 3.9.4训练得到的输出结果XLSX文件、包含各分子MDs的ARFF与CSV格式文件，以及本次研究数据集的SDF文件。 <strong>SI7_EXP2_驱避性建模</strong>：该部分涵盖本研究的4组数据集，即Oliferenko等（2013）、Gaudin等（2008）、Omolo等（2004）以及Paluch等（2009）的研究数据集。在其子文件夹中，针对每种MDs类型（双元、三元、通用与混合型描述符）各构建了3个最优预测模型以适配各组数据集。与SI6部分一致，每个模型均包含6类文件：DOCX、XLSX、ARFF、CSV格式文件以及SDF格式数据集文件。 <strong>SI8_虚拟活性化合物</strong>：该部分包含新型IR虚拟先导化合物的聚类分析结果及其理化性质参数。