Comparative transcriptomics of Eastern African cichlid fishes shows signs of positive selection and a large contribution of untranslated regions to genetic diversity

Abstract

The hundreds of endemic species of cichlid fishes in the East African Great Lakes Tanganyika, Malawi, and Victoria are a prime model system in evolutionary biology. With five genomes currently being sequenced, eastern African cichlids also represent a forthcoming genomic model for evolutionary studies of genotype-to-phenotype processes in adaptive radiations. Here we report the functional annotation and comparative analyses of transcriptome data sets for two eastern African cichlid species, Astatotilapia burtoni and Ophthalmotilapia ventralis, representatives of the modern haplochromines and ectodines, respectively. Nearly 647,000 expressed sequence tags were assembled in more than 46,000 contigs for each species using the 454 sequencing technology, largely expanding the current sequence data set publicly available for these cichlids. Total predicted coverage of their proteome diversity is approximately 50% for both species. Comparative qualitative and quantitative analyses show very similar transcriptome data for the two species in terms of both functional annotation and relative abundance of gene ontology terms expressed. Average genetic distance between species is 1.75% when all transcript types are considered including nonannotated sequences, 1.33% for annotated sequences only including untranslated regions, and decreases to nearly half, 0.95%, for coding sequences only, suggesting a large contribution of noncoding regions to their genetic diversity. Comparative analyses across the two species, tilapia and the outgroup medaka based on an overlapping data set of 1,216 genes (∼526 kb) demonstrate cichlid-specific signature of disruptive selection and provide a set of candidate genes that are putatively under positive selection. Overall, these data sets offer the genetic platform for future comparative analyses in light of the upcoming genomes for this taxonomic group.

FIG. 1.—

Ten most represented GO terms per biological category and absolute number of ESTs assigned to each term. Overall representation of GO terms is nearly equal between AB and OV.

FIG. 2.—

ML phylogeny based on four-species concatenated alignment of 1,216 genes (526,113 bp). The tree is rooted using medaka as outgroup. All nodes had a 100 bootstrap value support. For each branch, individual dN and dS values (in brackets, respectively) and the corresponding dN/dS ratios (in red) were calculated under the free-ratio model (codeml). Indel events per branch (specified by number followed by “i”) were mapped by maximum parsimony.