A sequence-based identification of the genes detected by probesets on the Affymetrix U133 plus 2.0 array

Abstract

One of the biggest problems facing microarray experiments is the difficulty of translating results into other microarray formats or comparing microarray results to other biochemical methods. We believe that this is largely the result of poor gene identification. We re-identified the probesets on the Affymetrix U133 plus 2.0 GeneChip array. This identification was based on the sequence of the probes and the sequence of the human genome. Using the BLAST program, we matched probes with documented and postulated human transcripts. This resulted in the redefinition of approximately 37% of the probes on the U133 plus 2.0 array. This updated identification specifically points out where the identification is complicated by cross-hybridization from splice variants or closely related genes. More than 5000 probesets detect multiple transcripts and therefore the exact protein affected cannot be readily concluded from the performance of one probeset alone. This makes naming difficult and impacts any downstream analysis such as associating gene ontologies, mapping affected pathways or simply validating expression changes. We have now automated the sequence-based identification and can more appropriately annotate any array where the sequence on each spot is known.

Figure 1

The signal captured by some probesets on the U133A array from 100 RNA samples collected from various tissues. Probeset 202029_x_at detects the expression of ribosomal protein L38. The other three probesets were designed to the complementary strand of the intended reference gene. Probeset 202028_s_at detects sequences complementary to the ribosomal protein L38. The plots for probesets 213619_at and 216868_s_at illustrate the difference between a probeset that detects a transcript and a probeset that does not detect a transcript. Although each plot is represented against a different scale, the relative expression levels are directly comparable.