Classification and nomenclature of all human homeobox genes

Abstract

Background: The homeobox genes are a large and diverse group of genes, many of which play important roles in the embryonic development of animals. Increasingly, homeobox genes are being compared between genomes in an attempt to understand the evolution of animal development. Despite their importance, the full diversity of human homeobox genes has not previously been described.

Results: We have identified all homeobox genes and pseudogenes in the euchromatic regions of the human genome, finding many unannotated, incorrectly annotated, unnamed, misnamed or misclassified genes and pseudogenes. We describe 300 human homeobox loci, which we divide into 235 probable functional genes and 65 probable pseudogenes. These totals include 3 genes with partial homeoboxes and 13 pseudogenes that lack homeoboxes but are clearly derived from homeobox genes. These figures exclude the repetitive DUX1 to DUX5 homeobox sequences of which we identified 35 probable pseudogenes, with many more expected in heterochromatic regions. Nomenclature is established for approximately 40 formerly unnamed loci, reflecting their evolutionary relationships to other loci in human and other species, and nomenclature revisions are proposed for around 30 other loci. We use a classification that recognizes 11 homeobox gene 'classes' subdivided into 102 homeobox gene 'families'.

Conclusion: We have conducted a comprehensive survey of homeobox genes and pseudogenes in the human genome, described many new loci, and revised the classification and nomenclature of homeobox genes. The classification scheme may be widely applicable to homeobox genes in other animal genomes and will facilitate comparative genomics of this important gene superclass.

Figure 1

Maximum likelihood phylogenetic tree of human ANTP-class homeodomains. Arbitrarily rooted phylogenetic tree of human ANTP-class homeodomains constructed using the maximum likelihood method. Bootstrap values supporting internal nodes with over 70% are shown. Homeodomain sequences derived from pseudogenes are excluded. The proposed division between the HOXL and NKL subclasses is indicated. The position of EN1 and EN2 is unstable; this tree places them in the NKL subclass, whereas neighbor-joining analysis of the same dataset places them at the base of the two subclasses (Additional file 3). Interrelationships of genes in the Nk4 and Nk2.2 families are also unstable (in this tree and Additional file 3 respectively); in these cases synteny within and between genomes clearly resolves gene families. Detailed relationships between different gene families should not be inferred from this tree.

Figure 2

Maximum likelihood phylogenetic tree of human PRD-class homeodomains. Arbitrarily rooted phylogenetic tree of human PRD-class homeodomains constructed using the maximum likelihood method. Bootstrap values supporting internal nodes with over 70% are shown. Homeodomain sequences derived from pseudogenes are excluded, as are the partial homeodomains of PAX2, PAX5 and PAX8, and the HOPX homeodomain because its extremely divergent sequence destabilizes the overall tree topology. Roman numeral suffixes are used to distinguish multiple homeodomains encoded by a single Dux-family gene. In this tree Dux-family homeodomains are not monophyletic, even within the same gene; however, monophyly is recovered by neighbor-joining analysis (Additional file 4). Detailed relationships between different gene families should not be inferred from this tree.

Figure 3

Maximum likelihood phylogenetic tree of human homeodomains excluding ANTP and PRD classes. Arbitrarily rooted phylogenetic tree of human homeodomains excluding the ANTP and PRD classes constructed using the maximum likelihood method. Bootstrap values supporting internal nodes with over 70% are shown. Homeodomain sequences derived from pseudogenes are excluded. Roman numeral suffixes are used to distinguish multiple homeodomains encoded by a single gene. Classes and/or families are color coded as shown in the key. The LIM and ZF classes are not recovered as two distinct monophyletic groups, a result also found by neighbor-joining analysis (Additional file 5). The multiple homeodomains of Zfhx-family proteins and Zhx/Homez-family proteins are also dispersed in the tree, presumably artefactually. Detailed relationships between different gene families should not be inferred from this tree.

Figure 4

Chromosomal distribution of human homeobox genes. Ideograms of human chromosomes showing the locations of human homeobox genes. Hox clusters are each shown as a single line for simplicity. Probable pseudogenes are not shown. Genes are color coded according to their class or family (see key). Map positions were obtained through the Ensembl Genome Browser.