Diversity of Prdm9 zinc finger array in wild mice unravels new facets of the evolutionary turnover of this coding minisatellite

Abstract

In humans and mice, meiotic recombination events cluster into narrow hotspots whose genomic positions are defined by the PRDM9 protein via its DNA binding domain constituted of an array of zinc fingers (ZnFs). High polymorphism and rapid divergence of the Prdm9 gene ZnF domain appear to involve positive selection at DNA-recognition amino-acid positions, but the nature of the underlying evolutionary pressures remains a puzzle. Here we explore the variability of the Prdm9 ZnF array in wild mice, and uncovered a high allelic diversity of both ZnF copy number and identity with the caracterization of 113 alleles. We analyze features of the diversity of ZnF identity which is mostly due to non-synonymous changes at codons -1, 3 and 6 of each ZnF, corresponding to amino-acids involved in DNA binding. Using methods adapted to the minisatellite structure of the ZnF array, we infer a phylogenetic tree of these alleles. We find the sister species Mus spicilegus and M. macedonicus as well as the three house mouse (Mus musculus) subspecies to be polyphyletic. However some sublineages have expanded independently in Mus musculus musculus and M. m. domesticus, the latter further showing phylogeographic substructure. Compared to random genomic regions and non-coding minisatellites, none of these patterns appears exceptional. In silico prediction of DNA binding sites for each allele, overlap of their alignments to the genome and relative coverage of the different families of interspersed repeated elements suggest a large diversity between PRDM9 variants with a potential for highly divergent distributions of recombination events in the genome with little correlation to evolutionary distance. By compiling PRDM9 ZnF protein sequences in Primates, Muridae and Equids, we find different diversity patterns among the three amino-acids most critical for the DNA-recognition function, suggesting different diversification timescales.

Figure 1. The C2H2 zinc finger domain of PRDM9.

(A) PRDM9 contains several identified domains: an amino-terminal region which includes a Krüppel-associated box (KRAB) domain and an SSX repression domain (SSXRD); a PR/SET domain carrying methyltransferase activity, surrounded by a zinc knuckle and a zinc finger; and a long carboxy-terminal C2H2 zinc finger array. In this example, such as observed in the mouse laboratory strain C57BL/6, the array is composed of 12 zinc fingers. (B) Size distribution of the Prdm9 ZnF arrays (number of ZnF repeats) genotyped in the three subspecies of the house mouse

Figure 2. Inferred phylogeny of the Prdm9 ZnF domain alleles.

Taxon names on the branches include allele number, followed by the number of observations, then by taxon code (abbreviation of species name), country code, locality name and number of ZnF repeats. Numbers at the nodes indicate the level of confidence of the node (only values >0.5 reported).

Figure 3. Details of phylogenic tree.

The yellow (A), blue (B) and green (C) collapsed parts of the tree in Fig. 2 are expended and represent the different house mouse lineages. Taxon name encoding is as in Fig. 2.

Figure 4. Geographic distribution of groups of alleles in the house mouse.

The shape of the symbols indicates subspecies (square, M. m. domesticus, circles M. m. musculus, triangles M. m. castaneus). Colors indicate lineages as in Fig. 3.

Figure 5. Simplified triplet protein variants of the Prdm9 ZnF array in wild mice.

Sequence identifiers are highlighted with colors as in the phylogenetic tree of DNA alleles in Fig. 2 and 3. Alleles of laboratory strains previously sequenced are identified as in . Each ZnF is simplified to the three most variable codons −1, 3 and 6, and separated with a dash from the next ZnF. Sequences start at the first functional C2H2 ZnF (the second repeat) and end at the last carboxy-terminal ZnF of the protein. A few remarkable stretches of zinc fingers are highlighted: some are shared between most M. musculus protein variants (QNK-QDQ, red), some are shared between the twin species spicilegus and macedonicus (QNQ-ANK-**Q-QDQ, purple), some are shared between castaneus and musculus alleles (ANQ-ESK, yellow) and some others are specific or enriched in each of domesticus (QHQ-QDK, dark blue; AVQ-AVQ, light blue), castaneus (VVQ, green), M. spretus (ADK-VNQ; QNQ-ADK, grey); M. macedonicus (QHK-QNQ, purple) and M. spicilegus (QNQ-ADK, grey) groups of alleles.

Figure 6. Predicted DNA binding sites of mouse Prdm9 ZnF alleles and dispersed repeats.

(A) Distribution among Prdm9 alleles of the proportion of the coverage of hits of the predicted recognized DNA motifs that fall in dispersed repeated sequences, as annotated on the reference mouse genome. (B) Absolute proportion of hit coverage falling in a given repeat family for each of the sequenced allele. Red cross: expected proportion if hit coverage was proportional to the coverage of the family in the genome. Red circles: median, first and third quartile of the distribution across alleles. Note the log scales. (C) Projection of the alleles on the first two axes of the Principal Component Analysis on the relative proportion of hits of each allele in the different repeated families. Symbol colors refer to lineage colors as in Fig. 2 and 3. Symbol shapes are arbitrary. PC1 absorbs 35% of the variance, and PC2 13%.

Figure 7. Patterns of diversity of amino-acids –1, 3 and 6 of PRDM9 ZnFs across taxa, species and subspecies.

Number of ZnFs units sequenced, number of Prdm9 ZnF arrays sequenced and number of protein variants are indicated for each species or subspecies of Primates, Muridae and Equids. Variant amino-acids at each of the three positions −1, 3 and 6 of the PRDM9 ZnFs are shown for each group. Variants present in every allele sequenced are in bold case and variants found in less than 10% of ZnF units are in grey case (all in normal case when one allele is available). Some variants at position −1 and position 3 are shared by most species (highlighted in yellow), others are shared by one taxon (highlighted according to the colour of the taxon). Hs: Homo sapiens; Pp: Pan paniscus (bonobo); Pt: Pan troglodytes (chimpanzee); Ptt: P. T. troglodytes; Ptv: P. T. verus; Pts: P. T. schweininfurthii; Gg: Gorilla gorilla; Hol: Holobylatae; Nl: Nomascus leucogenys (Gibbon); Cerc: Cercopithecidae; Mm: Macaca mulata (Rhesus monkey); Calli: Callitrichidae; Cj: Callithrix jacchus (Ouistiti); Gal: Galagidae; Og: Otolemur garnettii (Lemur); Mm: Mus musculus; Mmd: Mus musculus domesticus; Mmm: M. m. musculus; Mmc: M. m. castaneus; Msp: Mus spretus; Mm/s: Mus macedonicus and spicigelus; Mpy: Mus Pyromys platythrix; Mfa: Mus famulus; As: Apodemus sylvaticus; Pl: Peromyscus leucopus; Rn: Rattus norvegicus; Ef: Equus ferus; Ea: Equus asinus; Eh: Equus hippotigris. Data was gathered for Mus ZnFs from this study, for Homo sapiens ZnFs from , , , for Pan ZnFs from , , for Equids from and retrieved from GenBank for other individual alleles (Gg, Nl, Mm, Cj, Og, Apos, Perol, Rn).