Article

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

National Center for Toxicological Research, US Food and Drug Administration, Jefferson, Arkansas, USA.
Nature Biotechnology (Impact Factor: 32.44). 08/2010; 28(8):827-38. DOI: 10.1038/nbt.1665
Source: PubMed

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.

1 Bookmark
 · 
371 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A new approach for variable influence on projection (VIP) is described, which takes full advantage of the orthogonal projections to latent structures (OPLS) model formalism for enhanced model interpretability. This means that it will include not only the predictive components in OPLS but also the orthogonal components. Four variants of variable influence on projection (VIP) adapted to OPLS have been developed, tested and compared using three different data sets, one synthetic with known properties and two real-world cases. Copyright © 2014 John Wiley & Sons, Ltd.
    Journal of Chemometrics 05/2014; · 1.94 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Toxicological research faces the challenge of integrating knowledge from diverse fields and novel technological developments generally in the biological and medical sciences. We discuss herein the fact that the multiple facets of cancer research, including discovery related to mechanisms, treatment and diagnosis, overlap many up and coming interest areas in toxicology, including the need for improved methods and analysis tools. Common to both disciplines, in vitro and in silico methods serve as alternative investigation routes to animal studies. Knowledge on cancer development helps in understanding the relevance of chemical toxicity studies in cell models, and many bioinformatics-based cancer biomarker discovery tools are also applicable to computational toxicology. Robotics-aided cell-based high throughput screening, microscale immunostaining techniques, and gene expression profiling analyses are common tools in cancer research, and when sequentially combined, form a tiered approach to structured safety evaluation of thousands of environmental agents, novel chemicals or engineered nanomaterials. Comprehensive tumour data collections in databases have been translated into clinically useful data, and this concept serves as template for computer-driven evaluation of toxicity data into meaningful results. Future "cancer research-inspired knowledge management" of toxicological data will aid the translation of basic discovery results and chemicals- and materials-testing data to information relevant to human health and environmental safety. This article is protected by copyright. All rights reserved.
    Basic & Clinical Pharmacology & Toxicology 04/2014; · 2.18 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The soil worm Enchytraeus crypticus (Oligochaeta) is an ecotoxicology model species that, until now, was without genome or transcriptome sequence information. The present research aims at studying the transcriptome of Enchytraeus crypticus, sampled from multiple test conditions, and the construction of a high-density microarray for functional genomic studies. Over 1.5 million cDNA sequence reads were obtained representing 645 million nucleotides. After assembly, 27,296 contigs and 87,686 singletons were obtained, from which 44% and 25% are annotated as protein-coding genes, respectively, sharing homology with other animal proteomes. Concerning assembly quality, 84% of the contig sequences contain an open reading frame with a start codon while E. crypticus homologs were identified for 92% of the core eukaryotic genes. Moreover, 65% and 77% of the singletons and contigs without known homologs, respectively, were shown to be transcribed in an independent microarray experiment. An Agilent 180 K microarray platform was designed and validated by hybridizing cDNA from 4 day zinc- exposed E. crypticus to the concentration corresponding to 50% reduction in reproduction after three weeks (EC50). Overall, 70% of all probes signaled expression above background levels(mean signal + 1x standard deviation). More specifically, the probes derived from contigs showed a wider range of average intensities when compared to probes derived from singletons. In total, 522 significantly differentially regulated transcripts were identified upon zinc exposure. Several significantly regulated genes exerted predicted functions (e.g. zinc efflux, zinc transport) associated with zinc stress. Unexpectedly, the microarray data suggest that zinc exposure alters retro transposon activity in the E. crypticus genome. An initial investigation of the E. crypticus transcriptome including an associated microarray platform for future studies proves to be a valuable resource to investigate functional genomics mechanisms of toxicity in soil environments and to annotate a potentially large number of lineage specific genes that are responsive to environmental stress conditions.
    BMC Genomics 04/2014; 15(1):302. · 4.40 Impact Factor

Full-text

View
41 Downloads
Available from
May 20, 2014