Comparative phylogenomic analyses of teleost fish Hox gene clusters: lessons from the cichlid fish Astatotilapia burtoni

Abstract

Background: Teleost fish have seven paralogous clusters of Hox genes stemming from two complete genome duplications early in vertebrate evolution, and an additional genome duplication during the evolution of ray-finned fish, followed by the secondary loss of one cluster. Gene duplications on the one hand, and the evolution of regulatory sequences on the other, are thought to be among the most important mechanisms for the evolution of new gene functions. Cichlid fish, the largest family of vertebrates with about 2500 species, are famous examples of speciation and morphological diversity. Since this diversity could be based on regulatory changes, we chose to study the coding as well as putative regulatory regions of their Hox clusters within a comparative genomic framework.

Results: We sequenced and characterized all seven Hox clusters of Astatotilapia burtoni, a haplochromine cichlid fish. Comparative analyses with data from other teleost fish such as zebrafish, two species of pufferfish, stickleback and medaka were performed. We traced losses of genes and microRNAs of Hox clusters, the medaka lineage seems to have lost more microRNAs than the other fish lineages. We found that each teleost genome studied so far has a unique set of Hox genes. The hoxb7a gene was lost independently several times during teleost evolution, the most recent event being within the radiation of East African cichlid fish. The conserved non-coding sequences (CNS) encompass a surprisingly large part of the clusters, especially in the HoxAa, HoxCa, and HoxDa clusters. Across all clusters, we observe a trend towards an increased content of CNS towards the anterior end.

Conclusion: The gene content of Hox clusters in teleost fishes is more variable than expected, with each species studied so far having a different set. Although the highest loss rate of Hox genes occurred immediately after whole genome duplications, our analyses showed that gene loss continued and is still ongoing in all teleost lineages. Along with the gene content, the CNS content also varies across clusters. The excess of CNS at the anterior end of clusters could imply a stronger conservation of anterior expression patters than those towards more posterior areas of the embryo.

Figure 1

Sequenced BAC clones and the annotated genes drawn to scale. Hox and Evx genes are shown in color, neighboring genes are drawn in black. Abbreviations used are according to [38], the surrounding genes are identical to those found in Takifugu rubipes. The HoxBa cluster is incomplete, sequence data stops at 12 kb downstream of hoxb5a. Sequence data for the remaining four Hox genes and the non-coding regions of remaining parts of the cluster have been gathered by PCR, indicating that the clustered structure still exists.

Figure 2

Maximum likelihood tree based on 20,009 nucleotide positions of Hox genes. Values above branches are Maximum Likelihood bootstraps; two asterisks indicate posterior probabilities of 1.00 as obtained by MrBayes 3.1.

Figure 3

Hox cluster of teleost model fish species and the event of gene loss plotted on a phylogeny. Hox and Evx genes are shown as arrows, pseudogenes are shown without coloration and missing delineation indicates missing sequence data of most likely existing genes. MicroRNAs are drawn as small diamonds and were added according to our analyses. Data for H. sapiens were copied from [86] and the mir-10-db of Danio rerio according to [85].

Figure 4

Percentage of CNS within intergenic regions of the Hox clusters of Neoteleost fishes. Starting from the complete length of analyzed sequence, we calculated the relative amounts of genes (including introns), PFC (as identified by Tracker) and marked the remaining sequence as "junk". The footprint cliques were further divided as shared by all six fish species included (teleost), shared by all species except zebrafish (neoteleost), shared by medaka, cichlid and stickleback (Ol-Ab-Ga) or shared by cichlid and stickleback (Ab-Ga). Against our expectations there were usually no or only very few cliques shared only between cichlid and medaka except for HoxDb.

Figure 5

"Proportional" analyses of the Hox clusters of Astatotilapia burtoni. Large error bars for anterior regions of HoxCa cluster are explained by missing data from the pufferfish, which lost the hoxc3a gene.