RESUMEN
The functional annotation of gene lists is a common analysis routine required for most genomics experiments, and bioinformatics core facilities must support these analyses. In contrast to methods such as the quantitation of RNA-Seq reads or differential expression analysis, our research group noted a lack of consensus in our preferred approaches to functional annotation. To investigate this observation, we selected 4 experiments that represent a range of experimental designs encountered by our cores and analyzed those data with 6 tools used by members of the Association of Biomolecular Resource Facilities (ABRF) Genomic Bioinformatics Research Group (GBIRG). To facilitate comparisons between tools, we focused on a single biological result for each experiment. These results were represented by a gene set, and we analyzed these gene sets with each tool considered in our study to map the result to the annotation categories presented by each tool. In most cases, each tool produces data that would facilitate identification of the selected biological result for each experiment. For the exceptions, Fisher's exact test parameters could be adjusted to detect the result. Because Fisher's exact test is used by many functional annotation tools, we investigated input parameters and demonstrate that, while background set size is unlikely to have a significant impact on the results, the numbers of differentially expressed genes in an annotation category and the total number of differentially expressed genes under consideration are both critical parameters that may need to be modified during analyses. In addition, we note that differences in the annotation categories tested by each tool, as well as the composition of those categories, can have a significant impact on results.
