A Comprehensive Phylogenetic Analysis of the Serpin Superfamily

Abstract

Serine protease inhibitors (serpins) are found in all kingdoms of life and play essential roles in multiple physiological processes. Owing to the diversity of the superfamily, phylogenetic analysis is challenging and prokaryotic serpins have been speculated to have been acquired from Metazoa through horizontal gene transfer due to their unexpectedly high homology. Here, we have leveraged a structural alignment of diverse serpins to generate a comprehensive 6,000-sequence phylogeny that encompasses serpins from all kingdoms of life. We show that in addition to a central "hub" of highly conserved serpins, there has been extensive diversification of the superfamily into many novel functional clades. Our analysis indicates that the hub proteins are ancient and are similar because of convergent evolution, rather than the alternative hypothesis of horizontal gene transfer. This work clarifies longstanding questions in the evolution of serpins and provides new directions for research in the field of serpin biology.

Keywords: evolution; phylogenetics; serpin.

Fig. 1.

Serpin fold and mechanistic diversity. (S) and (R) denote stressed and relaxed conformations, respectively. (A) Cartoon representation of the S to R state conformational transition, in alpha-1-antitrypsin (A1AT). The RCL in both native (exposed) and latent (inserted) conformations is highlighted, among other key structural components of the serpin fold, such as the breach, shutter, and A-sheet (PDBs: native stressed conformation 3NE4, latent relaxed conformation 1IZ2). (B) Noncovalent Michaelis complex between Manduca sexta serpin1B (MsSerp1B) and active trypsin protease (PDB: 1K9O). (C) Ternary michaelis complex between human antithrombin III (AT3) with heparin templated active thrombin (PDB: 1TB6). (D) Covalent complex between cleaved A1AT and inhibited trypsin, post-RCL cleavage (PDB: 1EZX).

Fig. 2.

A nonredundant sequence similarity network of the serpin superfamily. Nodes represent serpin sequences, or clusters of serpin sequences that share 75% pairwise sequence identity. Edges connect sequences that share >40% pairwise sequence identity. Nodes are colored by the taxonomic distribution of organisms that they belong to: nodes that represent chordate and Homo sapiens serpins are distinguished at the level of phylum and species for clarity. Sequences with reviewed annotations and solved structures are represented by enlarged circular and triangular nodes with black borders, respectively.

Fig. 3.

(A) An unrooted maximum likelihood phylogeny of the serpin superfamily. Tips are colored by taxonomic classification and nodes with branch supports (BS) >90 are represented as solid black circles. Well-characterized chordate serpin Groups A, B, C, D, E, F, G, H, and I, known a priori to belong to distinct lineages, are highlighted, as well as Groups K, L, M, and O. New families defined in this study are highlighted in bold. The phylogeny is available in Newick format with full branch support values in S.I. (B) View of the phylogeny presented in panel (A) with major clades collapsed and BS values overlaid. (C) Subtree of chordate serpin Groups A, D–I. Branch color distinguishes each group within the subtree and functionally characterized tips are labeled.

Fig. 4.

Genomic and molecular markers of horizontal gene transfer. Where available, codon usage for conserved Ser56, whole-genome sequence (WGS) GC%, and the ratio of serpin gene sequence GC% to WGS GC% are mapped to prokaryotic serpins belonging to Groups S–U. There are no systematic anomalous ratios in serpin gene GC% to WGS GC% over a wide range of whole-genome sequence GC contents (<30% to >70%). Likewise, there is no systematic evidence that Groups S–U were acquired from chordates from the pseudoconserved Ser56 codon usage in prokaryotes.

Fig. 5.

Structural evidence of convergent evolution in the serpin superfamily. (A) Cartoon representation of tengpin in the stressed native state. The N-terminal extension and its contacts in the A-sheet are highlighted, among other structurally important positions, such as the A-sheet and RCL (PDB: 2PEE). (B) Cartoon representation of PAI-1 in the stressed native conformation, stabilized by the SMB domain of vitronectin (highlighted in cyan) (PDB: 1OC0). (C) A structural alignment of tengpin (PDB: 2PEE), miropin (PDB: 5NCS), thermopin (PDB: 1SNG), SCCA-1 (PDB: 2ZV6), and AT3 (PDB: 3KCG) highlighting the convergent molecular mechanisms exploited to stabilize the native conformation. (D and E) View of analogous interactions in the C-terminal tails of miropin and thermopin that stabilize the breach, respectively.