Format

Send to

Choose Destination
See comment in PubMed Commons below
Bioinformatics. 2003 Sep 22;19(14):1808-16.

Controlling false-negative errors in microarray differential expression analysis: a PRIM approach.

Author information

1
Department of Medicine, Immunology, and Molecular Genetics, David Geffen School of Medicine at UCLA, Los Angeles, CA 90095-1678, USA. coles@ucla.edu

Abstract

MOTIVATION:

Theoretical considerations suggest that current microarray screening algorithms may fail to detect many true differences in gene expression (Type II analytic errors). We assessed 'false negative' error rates in differential expression analyses by conventional linear statistical models (e.g. t-test), microarray-adapted variants (e.g. SAM, Cyber-T), and a novel strategy based on hold-out cross-validation. The latter approach employs the machine-learning algorithm Patient Rule Induction Method (PRIM) to infer minimum thresholds for reliable change in gene expression from Boolean conjunctions of fold-induction and raw fluorescence measurements.

RESULTS:

Monte Carlo analyses based on four empirical data sets show that conventional statistical models and their microarray-adapted variants overlook more than 50% of genes showing significant up-regulation. Conjoint PRIM prediction rules recover approximately twice as many differentially expressed transcripts while maintaining strong control over false-positive (Type I) errors. As a result, experimental replication rates increase and total analytic error rates decline. RT-PCR studies confirm that gene inductions detected by PRIM but overlooked by other methods represent true changes in mRNA levels. PRIM-based conjoint inference rules thus represent an improved strategy for high-sensitivity screening of DNA microarrays.

AVAILABILITY:

Freestanding JAVA application at http://microarray.crump.ucla.edu/focus

PMID:
14512352
[Indexed for MEDLINE]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Loading ...
    Support Center