Insights into social insects from the genome of the honeybee Apis mellifera

Abstract

Here we report the genome sequence of the honeybee Apis mellifera, a key model for social behaviour and essential to global ecology through pollination. Compared with other sequenced insect genomes, the A. mellifera genome has high A+T and CpG contents, lacks major transposon families, evolves more slowly, and is more similar to vertebrates for circadian rhythm, RNA interference and DNA methylation genes, among others. Furthermore, A. mellifera has fewer genes for innate immunity, detoxification enzymes, cuticle-forming proteins and gustatory receptors, more genes for odorant receptors, and novel genes for nectar and pollen utilization, consistent with its ecology and social organization. Compared to Drosophila, genes in early developmental pathways differ in Apis, whereas similarities exist for functions that differ markedly, such as sex determination, brain function and behaviour. Population genetics suggests a novel African origin for the species A. mellifera and insights into whether Africanized bees spread throughout the New World via hybridization or displacement.

Figure 1. Evolutionary relationships

Evolutionary relationships of Apis mellifera, other insects and related arthropods for which the genome sequence has been published (red), is in draft assembly form (blue), or is approved for sequencing (green), with approximate divergence times,. Recent work suggests that the Hymenoptera are basal to the Coleoptera in the Endopterygota (also known as Holometabola),.

Figure 2. Chromosomal spreads, ideogram and karyotype of Apis mellifera

The ideogram (in blue) shows average chromosome lengths, positions and sizes of DAPI-positive (heterochromatin) bands. The percentage of heterochromatin reflects the time of appearance of heterochromatic bands (100% observed in all preparations; lower percentages seen only in early prophase spreads). Lines to the right of chromosomes represent BACs shown by FISH to bind in relative order and positions predicted from the genetic and physical maps. Binding sites of rDNA probes (distal short arms of chromosomes 6 and 12) are shown in red. The karyotype (below the ideogram) is based on the rightmost spread.

Figure 3. Base composition in Apis, Drosophila and Anopheles

a, G+C-content domain length versus G+C percentage in A. mellifera (green), A. gambiae (blue) and D. melanogaster (red). The dashed line at 20% G+C content indicates the large number of low-G+C domains in A. mellifera. b, Gene length (top) and transcript length (bottom) versus G+C percentage of G+C content domains in which genes are embedded. Gene length was computed as the genomic distance from start to stop codon of the longest splice variant of each gene. Transcript length was computed as the distance between start and stop codon on the transcript sequence.

Figure 4. Comparison of Apis telomeres with other insects

Organization of centromeric-proximal telomeres on the short arm of the 15 acrocentric chromosomes in Apis is hypothetical based on FISH studies. (The blue checked area represents the 176-bp tandem AluI repeats (see text).) Bombyx and Drosophila telomeres are based on one or two telomeres in each species. Regions of non-LTR retrotransposons are indicated. For the Drosophila subtelomeric region (telomere-associated sequence repeats, TAS), shading indicates the presence of short (50–130 bp) repeat sequence blocks. Telomeres of A. gambiae and Chironomus midges consist of complex tandem repeats, as indicated.

Figure 5. Orthology assignment in insects and vertebrates

At the extremes, genes might be part of the metazoan core proteome (darkest band, bottom) or unique to a species with currently no counterpart in other organisms (white band, top). The striped boxes indicate insect- and vertebrate-specific genes and show that there are far fewer in insects. ‘1:1:1’ indicates universal single-copy genes, but absence or duplication in a single genome is tolerated as we cannot exclude incomplete genomes or very recent duplications. This explains uneven numbers between species of these very conserved metazoan core genes. ‘X:X:X’ indicates any other orthologous group (miss in one species allowed), with X meaning one or more orthologues per species. ‘Patchy’ indicates other orthologues that are present in at least one insect and one vertebrate genome. ‘Homology’ indicates partial homology detected with E < 10⁻⁶ but no orthology classified.

Figure 6. Comparative evolutionary rates of orthologues

Comparison of single-copy orthologues in honeybee, fly and mosquito versus human in terms of: average protein identity; retained fraction of ‘patchy’ orthologous groups, as defined in Fig. 5; and fraction of retained ancient introns (those that are found in at least one of the vertebrate orthologues; positional conservation was counted within sliding windows of ±10 bases to allow for intron sliding). The standard error of the mean is about 0.3% and is shown by the error bars.

Figure 7. Protein domains

The top five most prominent expansions and contractions of InterPro-defined protein or domain families in A. mellifera, D. melanogaster and H. sapiens. The families are ordered by the chi-squared test significance of the family size difference with respect to the predicted number of genes, 10,157 and 13,450, respectively. Absent families are marked. 7TM, seven transmembrane.

Figure 8. Sex-determining pathways of Drosophila and Apis

Sex in the honeybee is determined by the allelic composition of a single gene, the complementary sex determiner (csd). Eggs develop into males when csd is hemizygous (haploid) or homozygous, or females when csd is heterozygous. Honeybees lack sex chromosomes and X-specific dosage compensation. Sex-specific information is transferred in both species from diverged initial signals to the final gene, dsx, via switch genes that are active (on) in the females, but inactive (off) in the males. Most Drosophila pathway genes are present in the honeybee genome despite the marked differences (see text).

Figure 9. Phylogenetic analysis of the SID-1 proteins of insects and diverse other organisms

The maximum likelihood phylogram (Phylip) is based on the alignments of the conserved carboxy-terminal transmembrane domain of SID-1 proteins from insects, vertebrates, nematodes and other eukaryotes. Sequences were aligned with Clustalw. The sequences are identified by species name and, where multiple genes exist in a genome, by a further identifier (see Supplementary Information). A long basal branch from Dictyostelium to the other sequences is truncated (thick bar).

Figure 10. Population genetic structure of honeybees collected from native ranges in Europe, Africa and the Near East

Neighbour-joining tree using Nei genetic distance. Ten geographical subspecies (N = 9–21 individuals each) can be partitioned into four regional groups. Branches separating regional groups are supported by 100% bootstrap.