Abbreviations inhibitor Imatinib Mesylate TNF: Tumor necrosis factor; PCR: Polymerase chain reaction; MRI: Magnetic resonance imaging; ESR: Erythrocyte sedimentation rate; CRP: C-reactive protein; HIV: Human immunodeficiency virus; DNA: Deoxyribonucleic acid; PAS: Periodic acid-Schiff. Consent Written informed consent was obtained from the patient for publication of this case report and accompanying images. A copy of the written consent is available for review by the Editor-in-Chief of this journal. Competing interests The authors declare that they have no competing interests. Authors’ contributions All authors treated the patient during the years 2002 to 2008. Each of them have made substantial contributions to data acquisition and interpretation. All have been involved in drafting the manuscript.

UAW critically revised the manuscript for important intellectual content and has given final approval of the version to be published. All authors read and approved the final manuscript.
Six data sets with different sources of batch (group) effects were used in this paper (Table 1). All the data sets are available through GEO from the MAQC web site: http://www.fda.gov/nctr/science/centers/toxicoinformatics/maqc/ or ArrayTrack http://www.fda.gov/nctr/science/centers/toxicoinformatics/ArrayTrack/. These six data sets are described below. Table 1 Summary of data sets A Breast Cancer data set was provided by the MD Anderson Cancer Center at the University of Texas (Houston, TX, USA). Hess et al.10 performed gene expression analysis on a subset of this data set.

Gene expression data from 230 stage I�CIII breast cancers were generated from fine needle aspirates of newly diagnosed breast cancers before any therapy. Among the 230 samples, training/test split was performed according to hybridization dates, the first 130 samples assayed were used as training set and the remaining 100 samples were used as test set. There are two endpoints associated with this data set: pathological complete response (pCR) and estrogen receptor status. A toxicogenomic data set (Iconix) was provided by Iconix Biosciences (Mountain View, CA, USA). The study is aimed at evaluating hepatic tumor induction by non-genotoxic chemicals after short-time exposure.11 The training set consists of 216 samples treated for 5 days with one of 76 structurally and mechanistically diverse non-genotoxic hepatocarcinogens and non-hepatocarcinogens.

The test set consists of 201 samples treated for 5 days with one of 68 structurally Carfilzomib and mechanistically diverse non-genotoxic hepatocarcinogens. Gene expression data were profiled using the GE Codelink microarray platform. The separation of the training set and the test set was based on the time when the microarray data were collected. There are three batches in the training set and two batches in the test set.