作者
L Shi, G Campbell, W Jones, F Campagne, Z Wen, S Walker, Z Su, T Chu, F Goodsaid, L Pusztai, J Shaughnessy, A Oberthuer, R Thomas, R Paules, M Fielden, B Barlogie, W Chen, P Du, M Fischer, Cesare Furlanello, B Gallas, X Ge, D Megherbi, W Symmans, M Wang, J Zhang, H Bitter, B Brors, P Bushel, M Bylesjo, M Chen, J Cheng, J Chou, T Davison, M Delorenzi, Y Deng, V Devanarayan, D Dix, J Dopazo, K Dorff, F Elloumi, J Fan, S Fan, X Fan, H Fang, N Gonzaludo, K Hess, H Hong, J Huan, R Irizarry, R Judson, D Juraeva, S Lababidi, C Lambert, L Li, Y Li, Z Li, S Lin, G Liu, E Lobenhofer, J Luo, W Luo, M Mccall, Y Nikolsky, G Pennello, R Perkins, R Philip, V Popovici, N Price, F Qian, A Scherer, T Shi, W Shi, J Sung, D Thierry Mieg, J Thierry Mieg, V Thodima, J Trygg, L Vishnuvajjala, S Wang, J Wu, Y Wu, Q Xie, W Yousef, L Zhang, X Zhang, S Zhong, Y Zhou, S Zhu, D Arasappan, W Bao, A Bergstrom, F Berthold, R Brennan, A Buness, J Catalano, C Chang, R Chen, Y Cheng, J Cui, W Czika, F Demichelis, X Deng, D Dosymbekov, R Eils, Y Feng, J Fostel, S Fulmer Smentek, J Fuscoe, L Gatto, W Ge, D Goldstein, L Guo, D Halbert, J Han, S Harris, C Hatzis, D Herman, J Huang, R Jensen, R Jiang, C Johnson, Giuseppe Jurman, Y Kahlert, S Khuder, M Kohl, J Li, M Li, Q Li, S Li, J Liu, Y Liu, Z Liu, L Meng, M Madera, F Martinez Murillo, I Medina, J Meehan, K Miclaus, R Moffitt, D Montaner, P Mukherjee, G Mulligan, P Neville, T Nikolskaya, B Ning, G Page, J Parker, R Parry, X Peng
发表日期
2010
期刊
Nature biotechnology
卷号
28
期号
8
页码范围
827-838
简介
Gene expression data from microarrays are being applied to predict preclinical and clinical endpoints, but the reliability of these predictions has not been established. In the MAQC-II project, 36 independent teams analyzed six microarray data sets to generate predictive models for classifying a sample with respect to one of 13 endpoints indicative of lung or liver toxicity in rodents, or of breast cancer, multiple myeloma or neuroblastoma in humans. In total, >30,000 models were built using many combinations of analytical methods. The teams generated predictive models without knowing the biological meaning of some of the endpoints and, to mimic clinical reality, tested the models on data that had not been used for training. We found that model performance depended largely on the endpoint and team proficiency and that different approaches generated models of similar performance. The conclusions and recommendations from MAQC-II should be useful for regulatory agencies, study committees and independent investigators that evaluate methods for global gene expression analysis.
引用总数
20092010201120122013201420152016201720182019202020212022202320241718155545521