Unknown

Dataset Information

0

The MicroArray Quality Control (MAQC)-II study of common practices for the development and validation of microarray-based predictive models.


ABSTRACT: 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.

SUBMITTER: Shi L 

PROVIDER: S-EPMC3315840 | biostudies-literature | 2010 Aug

REPOSITORIES: biostudies-literature

altmetric image

Publications

The MicroArray Quality Control (MAQC)-II study of common practices for the development and validation of microarray-based predictive models.

Shi Leming L   Campbell Gregory G   Jones Wendell D WD   Campagne Fabien F   Wen Zhining Z   Walker Stephen J SJ   Su Zhenqiang Z   Chu Tzu-Ming TM   Goodsaid Federico M FM   Pusztai Lajos L   Shaughnessy John D JD   Oberthuer André A   Thomas Russell S RS   Paules Richard S RS   Fielden Mark M   Barlogie Bart B   Chen Weijie W   Du Pan P   Fischer Matthias M   Furlanello Cesare C   Gallas Brandon D BD   Ge Xijin X   Megherbi Dalila B DB   Symmans W Fraser WF   Wang May D MD   Zhang John J   Bitter Hans H   Brors Benedikt B   Bushel Pierre R PR   Bylesjo Max M   Chen Minjun M   Cheng Jie J   Cheng Jing J   Chou Jeff J   Davison Timothy S TS   Delorenzi Mauro M   Deng Youping Y   Devanarayan Viswanath V   Dix David J DJ   Dopazo Joaquin J   Dorff Kevin C KC   Elloumi Fathi F   Fan Jianqing J   Fan Shicai S   Fan Xiaohui X   Fang Hong H   Gonzaludo Nina N   Hess Kenneth R KR   Hong Huixiao H   Huan Jun J   Irizarry Rafael A RA   Judson Richard R   Juraeva Dilafruz D   Lababidi Samir S   Lambert Christophe G CG   Li Li L   Li Yanen Y   Li Zhen Z   Lin Simon M SM   Liu Guozhen G   Lobenhofer Edward K EK   Luo Jun J   Luo Wen W   McCall Matthew N MN   Nikolsky Yuri Y   Pennello Gene A GA   Perkins Roger G RG   Philip Reena R   Popovici Vlad V   Price Nathan D ND   Qian Feng F   Scherer Andreas A   Shi Tieliu T   Shi Weiwei W   Sung Jaeyun J   Thierry-Mieg Danielle D   Thierry-Mieg Jean J   Thodima Venkata V   Trygg Johan J   Vishnuvajjala Lakshmi L   Wang Sue Jane SJ   Wu Jianping J   Wu Yichao Y   Xie Qian Q   Yousef Waleed A WA   Zhang Liang L   Zhang Xuegong X   Zhong Sheng S   Zhou Yiming Y   Zhu Sheng S   Arasappan Dhivya D   Bao Wenjun W   Lucas Anne Bergstrom AB   Berthold Frank F   Brennan Richard J RJ   Buness Andreas A   Catalano Jennifer G JG   Chang Chang C   Chen Rong R   Cheng Yiyu Y   Cui Jian J   Czika Wendy W   Demichelis Francesca F   Deng Xutao X   Dosymbekov Damir D   Eils Roland R   Feng Yang Y   Fostel Jennifer J   Fulmer-Smentek Stephanie S   Fuscoe James C JC   Gatto Laurent L   Ge Weigong W   Goldstein Darlene R DR   Guo Li L   Halbert Donald N DN   Han Jing J   Harris Stephen C SC   Hatzis Christos C   Herman Damir D   Huang Jianping J   Jensen Roderick V RV   Jiang Rui R   Johnson Charles D CD   Jurman Giuseppe G   Kahlert Yvonne Y   Khuder Sadik A SA   Kohl Matthias M   Li Jianying J   Li Li L   Li Menglong M   Li Quan-Zhen QZ   Li Shao S   Li Zhiguang Z   Liu Jie J   Liu Ying Y   Liu Zhichao Z   Meng Lu L   Madera Manuel M   Martinez-Murillo Francisco F   Medina Ignacio I   Meehan Joseph J   Miclaus Kelci K   Moffitt Richard A RA   Montaner David D   Mukherjee Piali P   Mulligan George J GJ   Neville Padraic P   Nikolskaya Tatiana T   Ning Baitang B   Page Grier P GP   Parker Joel J   Parry R Mitchell RM   Peng Xuejun X   Peterson Ron L RL   Phan John H JH   Quanz Brian B   Ren Yi Y   Riccadonna Samantha S   Roter Alan H AH   Samuelson Frank W FW   Schumacher Martin M MM   Shambaugh Joseph D JD   Shi Qiang Q   Shippy Richard R   Si Shengzhu S   Smalter Aaron A   Sotiriou Christos C   Soukup Mat M   Staedtler Frank F   Steiner Guido G   Stokes Todd H TH   Sun Qinglan Q   Tan Pei-Yi PY   Tang Rong R   Tezak Zivana Z   Thorn Brett B   Tsyganova Marina M   Turpaz Yaron Y   Vega Silvia C SC   Visintainer Roberto R   von Frese Juergen J   Wang Charles C   Wang Eric E   Wang Junwei J   Wang Wei W   Westermann Frank F   Willey James C JC   Woods Matthew M   Wu Shujian S   Xiao Nianqing N   Xu Joshua J   Xu Lei L   Yang Lun L   Zeng Xiao X   Zhang Jialu J   Zhang Li L   Zhang Min M   Zhao Chen C   Puri Raj K RK   Scherf Uwe U   Tong Weida W   Wolfinger Russell D RD  

Nature biotechnology 20100730 8


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 man  ...[more]

Similar Datasets

2010-02-04 | GSE16716 | GEO
| PRJNA117475 | ENA
| PRJNA96213 | ENA
2006-09-08 | GSE5350 | GEO
| S-EPMC3272078 | biostudies-literature
| S-EPMC2707382 | biostudies-literature
| S-ECPF-GEOD-16716 | biostudies-other
2010-02-04 | E-GEOD-16716 | biostudies-arrayexpress
| S-EPMC2789385 | biostudies-literature
| S-EPMC2491643 | biostudies-literature