Inactivation of thermogenic UCP1 as a historical contingency in multiple placental mammal clades

Abstract

Mitochondrial uncoupling protein 1 (UCP1) is essential for nonshivering thermogenesis in brown adipose tissue and is widely accepted to have played a key thermoregulatory role in small-bodied and neonatal placental mammals that enabled the exploitation of cold environments. We map ucp1 sequences from 133 mammals onto a species tree constructed from a ~51-kb sequence alignment and show that inactivating mutations have occurred in at least 8 of the 18 traditional placental orders, thereby challenging the physiological importance of UCP1 across Placentalia. Selection and timetree analyses further reveal that ucp1 inactivations temporally correspond with strong secondary reductions in metabolic intensity in xenarthrans and pangolins, or in six other lineages coincided with a ~30 million-year episode of global cooling in the Paleogene that promoted sharp increases in body mass and cladogenesis evident in the fossil record. Our findings also demonstrate that members of various lineages (for example, cetaceans, horses, woolly mammoths, Steller's sea cows) evolved extreme cold hardiness in the absence of UCP1-mediated thermogenesis. Finally, we identify ucp1 inactivation as a historical contingency that is linked to the current low species diversity of clades lacking functional UCP1, thus providing the first evidence for species selection related to the presence or absence of a single gene product.

Fig. 1. Schematic illustrating disrupting mutations in ucp1 across the placental mammal phylogeny.

(A) Xenarthra, (B) Pholidota, (C) Cetacea [note insert from ~800 bp upstream of ucp1 exon 4 of beluga (orange)], (D) Suidae, (E) Paenungulata [*, putative start codon located 36 bp downstream; **, creates 15 downstream stop codons (not shown)], and (F) Equidae. The six coding exons of ucp1 are represented by open rectangles; missing data (black), deleted exons (gray), mutated start codons (green), nonsense mutations (red), deletions (magenta), insertions (cyan), splice site mutations (yellow), and a mutated stop codon (“TTA” in Cyclopes) are indicated.

Fig. 2. Large-scale deletions of the ucp1 locus in select placental species.

(A) Linear comparisons of ucp1 illustrating exon deletions in pangolin, armadillo, pig, and hyrax relative to the intact human locus. The coding exons of ucp1 are numbered and highlighted in red. (B) Patterns of conserved synteny in the genomic region flanking the ucp1 locus of select vertebrates illustrating the complete deletion of ucp1 in a common ancestor of the dolphin and killer whale. Coding exons are highlighted in red, intervening sequences are highlighted in gray, and sequencing gaps are denoted by white spaces. Distances in kilobases between the termination codons of the upstream (tbc1d9) and downstream (elmod2) loci are given for each species. Note that the platypus ucp1 locus contains an additional upstream exon relative to other vertebrate species. Artwork by C. Buell.

Fig. 3. UCP1 inactivation across a time-calibrated placental mammal phylogeny.

Functional ucp1 branches are denoted in black, pseudogenic branches in red, and mixed branches (where ucp1 inactivation occurred) in blue. Clades having intact ucp1 loci are collapsed. Red boxes indicate ucp1 inactivation date ranges as determined by d_N/d_S analyses (see table S3), whereas the dagger represents the complete deletion of this locus in the delphinid lineage (see Fig. 2B). Pre-Oligocene temperatures are based on a benthic foraminifera δ¹⁸O isotope data set assuming an ice-free ocean (–167). Note that most inactivations correspond to a period of intense global cooling (gray shading) following the Paleocene-Eocene thermal maximum (PETM). Within this window, ucp1 was inactivated earlier in the two aquatic species, consistent with the much higher thermal conductivity of water relative to air (~24.1× higher at 25°C). Because only remnants of ucp1 were identified from representative Pilosa (Bradypus, Choleopus, and Cyclopes), the presented inactivation range should be interpreted with caution, and it is possible that ucp1 pseudogenization preceded its divergence from Cingulata. Artwork by C. Buell.

Fig. 4. Body mass and taxon diversity relative to estimates of ucp1 inactivation in five lineages of eutherian mammals.

(A) Calculated ucp1 inactivation range (red shading) in relation to body size estimates (open and closed circles). The y axis is reduced in the insets to better visualize changes in body mass relative to ucp1 inactivation. (B) Calculated ucp1 inactivation range (red shading) in relation to records of the number of species (closed squares) and genera (open squares) per geological stage. Blue arrows denote current species diversity for each taxon.