Laboratory for Structure-Function Based Drug Design, Orekhovich Institute of Biomedical Chemistry of the Russian Academy of Medical Sciences, Moscow, Russia.
Bioinformatics. 2013 Aug 15;29(16):2062-3. doi: 10.1093/bioinformatics/btt322. Epub 2013 Jun 5.
Experimentally found gene expression profiles are used to solve different problems in pharmaceutical studies, such as drug repositioning, resistance, toxicity and drug-drug interactions. A special web service, DIGEP-Pred, for prediction of drug-induced changes of gene expression profiles based on structural formulae of chemicals has been developed. Structure-activity relationships for prediction of drug-induced gene expression profiles were determined by Prediction of Activity Spectra for Substances (PASS) software. Comparative Toxicogenomics Database with data on the known drug-induced gene expression profiles of chemicals was used to create mRNA- and protein-based training sets. An average prediction accuracy for the training sets (ROC AUC) calculated by leave-one-out cross-validation on the basis of mRNA data (1385 compounds, 952 genes, 500 up- and 475 down-regulations) and protein data (1451 compounds, 139 genes, 93 up- and 55 down-regulations) exceeded 0.85.
Freely available on the web at http://www.way2drug.com/GE.
实验发现的基因表达谱可用于解决药物研究中的不同问题，如药物重定位、耐药性、毒性和药物相互作用。开发了一个特殊的网络服务 DIGEP-Pred，用于根据化学物质的结构式预测药物引起的基因表达谱变化。通过预测物质的活性光谱 (PASS) 软件确定了用于预测药物诱导基因表达谱的结构-活性关系。使用比较毒理学基因组学数据库，其中包含已知的化学药物诱导基因表达谱的数据，创建基于 mRNA 和蛋白质的训练集。基于 mRNA 数据（1385 种化合物、952 个基因、500 个上调和 475 个下调）和蛋白质数据（1451 种化合物、139 个基因、93 个上调和 55 个下调）的留一交叉验证计算的训练集的平均预测准确性（ROC AUC）超过 0.85。
http://www.way2drug.com/GE 可免费在线获取。
