Liu Chenglin, Su Jing, Yang Fei, Wei Kun, Ma Jinwen, Zhou Xiaobo
School of Mathematical Sciences and LMAM, Peking University, Beijing 100871, China.
Mol Biosyst. 2015 Mar;11(3):714-22. doi: 10.1039/c4mb00677a. Epub 2015 Jan 22.
The Library of Integrated Network-based Cellular Signatures (LINCS) L1000 big data provide gene expression profiles induced by over 10 000 compounds, shRNAs, and kinase inhibitors using the L1000 platform. We developed csNMF, a systematic compound signature discovery pipeline covering from raw L1000 data processing to drug screening and mechanism generation. The csNMF pipeline demonstrated better performance than the original L1000 pipeline. The discovered compound signatures of breast cancer were consistent with the LINCS KINOMEscan data and were clinically relevant. The csNMF pipeline provided a novel and complete tool to expedite signature-based drug discovery leveraging the LINCS L1000 resources.
基于综合网络的细胞特征库(LINCS)L1000大数据使用L1000平台提供了由超过10000种化合物、短发夹RNA(shRNAs)和激酶抑制剂诱导的基因表达谱。我们开发了csNMF,这是一个系统的化合物特征发现流程,涵盖从原始L1000数据处理到药物筛选和机制生成。csNMF流程表现出比原始L1000流程更好的性能。发现的乳腺癌化合物特征与LINCS激酶组扫描数据一致且具有临床相关性。csNMF流程提供了一种新颖且完整的工具,可利用LINCS L1000资源加速基于特征的药物发现。