Emergence and evolution of an interaction between intrinsically disordered proteins

Abstract

Protein-protein interactions involving intrinsically disordered proteins are important for cellular function and common in all organisms. However, it is not clear how such interactions emerge and evolve on a molecular level. We performed phylogenetic reconstruction, resurrection and biophysical characterization of two interacting disordered protein domains, CID and NCBD. CID appeared after the divergence of protostomes and deuterostomes 450-600 million years ago, while NCBD was present in the protostome/deuterostome ancestor. The most ancient CID/NCBD formed a relatively weak complex (K_d∼5 µM). At the time of the first vertebrate-specific whole genome duplication, the affinity had increased (K_d∼200 nM) and was maintained in further speciation. Experiments together with molecular modeling using NMR chemical shifts suggest that new interactions involving intrinsically disordered proteins may evolve via a low-affinity complex which is optimized by modulating direct interactions as well as dynamics, while tolerating several potentially disruptive mutations.

Keywords: Affinity; Evolution; Protein-protein interaction; biophysics; computational biology; intrinsically disordered proteins; molecular dynamics; none; phylogenetic reconstruction; structural biology; systems biology.

Figure 1.. General approach to investigate the evolution of a protein-protein interaction involving intrinsically disordered domains.

Multiple sequence alignment forms the basis for the phylogeny, which is used to predict ancient variants of two interacting protein domains, CID and NCBD, respectively. The ancient variants are then resurrected by expression in Escherichia coli and purified to homogeneity. Finally, the resurrected as well as present-day variants of CID and NCBD are subjected to biophysical and computational characterization to assess the evolution of structure-function relationships. DOI: http://dx.doi.org/10.7554/eLife.16059.003

Figure 2.. Reconstruction of the evolution of the interacting NCBD and CID domains.

(A) Sequence alignments of extant and reconstructed ancient NCBD (top) and CID domains (bottom). The positions of helices are according to the NMR structure of the complex between extant CREBBP NCBD (blue) and NCOA3 CID (yellow). Free NCBD (protein data base code 2KKJ) and the CID/NCBD complex (1KBH) are NMR structures, whereas the picture of free CID is a hypothetical modified structure made from the NCOA1 CID/NCBD complex (2C52). The first residue in the NCBD alignment is referred to as position 2062 in the text and the first residue in the CID alignment as 1040. The color coding of the sequences reflects similarities in chemical properties of the amino acid side chains and is a guide for the eye to see patterns of conservation. (B) Schematic tree of life with selected animal groups depicting the evolution of the NCBD domain (blue) in both protostomes and deuterostomes and the CID domain (yellow) in the deuterostome lineage only. See Figure 2—figure supplements 1–4 for detailed alignments and trees. DOI: http://dx.doi.org/10.7554/eLife.16059.004

Figure 2—figure supplement 1.. Sequence alignment of NCBD domains of CREBBP/p300 used in the phylogenetic reconstruction.

The whole CREBBP/p300 gene alignment was used to create the phylogenetic tree and then with the use of that tree the NCBD domain could be resurrected. The categories to the right should only be seen as guidelines to which group the individual species sequences belongs. Amino acids are colored based on chemical properties of the side chain according to eBioX standard. The tree in Figure 2—figure supplement 3 has the correct grouping information. DOI: http://dx.doi.org/10.7554/eLife.16059.007

Figure 2—figure supplement 2.. Sequence alignment of the CID domains of NCOA1-3 used in the phylogenetic reconstruction.

The whole NCOA1-3 gene alignment was used to create the phylogenetic tree and then with the use of that tree the CID domain could be resurrected. The categories to the right should only be seen as guidelines to which group the individual species sequences belongs. Amino acids are colored based on chemical properties of the side chain according to eBioX standard. The tree in Figure 2—figure supplement 4 has the correct grouping information. DOI: http://dx.doi.org/10.7554/eLife.16059.008

Figure 2—figure supplement 3.. Phylogenetic tree of CREBBP/p300 proteins that contain the NCBD domain.

The tree follows what is generally accepted regarding species evolution and whole genome duplications. Cnidarian CREBBP/p300 contains the NCBD domain. Since these species are distantly related to the other animals in the tree Cnidarian CREBBP/p300 proteins are used as outgroup in the analysis. After the divergence of Cnidaria from other metazoans, deuterostomes and protostomes diverged from each other. The node between the deuterostomes and protostomes (marked with a dark blue circle) is the oldest time point that we resurrect. Protostomes contain groups such as insects and molluscs, while deuterostomes contain all vertebrates. At the beginning of vertebrate evolution two whole genome duplications occurred. Thus, at this point all vertebrate genes were duplicated twice resulting in four copies, but many were rapidly lost. For CREBBP/p300, two copies remained, namely CREBBP and p300. The node corresponding to the ancestral CREBBP/p300 protein is marked with a green circle and referred to as 1R/2R in the text, since we cannot distinguish these events for CREBBP/p300. The most recent node that we resurrect is the separation of Teleost fish CREBBP from Tetrapod CREBBP (marked with a light blue circle). A third round of whole genome duplications later occurred in the fish lineage (not indicated) resulting in the two variants CREBBP1 and CREBBP2. The indicated resurrected nodes correspond to the same nodes as in the simplified Figure 2 in the main text. DOI: http://dx.doi.org/10.7554/eLife.16059.009

Figure 2—figure supplement 4.. Phylogenetic tree of NCOA1-3 proteins that contain the CID domain.

The tree follows what is generally accepted regarding species evolution and whole genome duplications. The CID domain could be identified in Hemicordata and Echinodermata NCOA proteins, and since these species are more distantly related to the other animals in the tree they were used as outgroups in the analysis. After the divergence of these groups from the rest of the deuterostomes, the two vertebrate-specific whole genome duplications occurred. Our analysis suggests that the ancestral NCOA gene was first split into NCOA-1 and the ancestor of NCOA2 and 3, which were subsequently split into NCOA2 and NCOA3 in the second whole genome duplication. (The second copy of NCOA1 was lost from the genomes) The nodes are marked with a dark (1R) and light green circle (2R), respectively. The most recent node that we resurrected is the separation of Teleost fish NCOA3 from Tetrapod NCOA3 (marked with a light blue circle). A third round of whole genome duplications occurred later in the fish lineage (not marked) but the resulting NCOA proteins were not retained in the genome. The indicated resurrected nodes correspond to the same nodes as in the simplified Figure 2 in the main text. DOI: http://dx.doi.org/10.7554/eLife.16059.010

Figure 3.. Amino acid substitutions in different domains in CREBBP/p300 and NCOA as a function of time.

The predicted ancient sequences for distinct domains in CREBBP/p300 (A and B) and NCOA (C) were used to calculate the number of substitutions and indels between each evolutionary node (Deuterostome/protostome, D/P; 1R; 2R; Fish/tetrapod, F/T; and present day) in a particular lineage (human and zebrafish CREBBP and human and zebrafish NCOA3, respectively). The alignment and trees used to resurrect HAT, KIX, RING/PHD and TAZ1 were the ones optimized for NCBD. Similarly, the alignment and trees used to resurrect Pas-A were the ones optimized for the CID domain. The number of substitutions plus indels were normalized against the number of amino acid residues in each domain and the accumulated fraction of sequence changes plotted versus historical time. Both 1R and 2R occurred around 450 million Myr ago and the distance between them in panel C (10 Myr) is arbitrary. DOI: http://dx.doi.org/10.7554/eLife.16059.011

Figure 4.. Structural alignment of two CID/NCBD complexes.

(A) Superimposition of the structures of two complexes solved by NMR: CREBBP NCBD (Light blue)-NCOA1 CID (Yellow) (2C52) and CREBBP NCBD (Dark blue)-NCOA3 CID (Red) (1KBH). The complexes contain a hydrophobic core formed by residues from the respective protein domain. (B) Superimposition of NCBD from the complexes shows that in particular Nα1 and Nα2 align very well. (C) Superimposition of the NCBD-bound conformations of NCOA1 CID and NCOA3 CID. Whereas Cα1 from both complexes align well, the C-terminal regions of the CID domains occupy different positions. DOI: http://dx.doi.org/10.7554/eLife.16059.012

Figure 5.. Biophysical characterization of ancient and extant CID and NCBD domains.

(A) Affinity of CID/NCBD complexes was measured by isothermal titration calorimetry (three examples are shown including the low-affinity D/P NCBD, 1R CID interaction). (B) The affinities (K_d values) were normalized against the interaction between extant human NCOA2 CID and p300 NCBD. The relative affinity for D/P NCBD, 1R CID was calculated using the average K_d values of all D/P NCBD variants (5 ± 2 µM). (C) Propensity for helix formation for ancient and extant CID domains as measured by circular dichroism at 222 nm upon addition of the helix stabilizer 1,1,1-trifluoroethanol. (D) Global stability of NCBD domains as measured by circular dichroism at 222 nm (reflecting the fraction folded NCBD) upon addition of the denaturant urea. Hsa, Homo sapiens; Dre, Danio rerio (zebrafish); Pme, Petromyzon marinus, (sea lamprey); Dmel, Drosophila melanogaster (fruit fly). DOI: http://dx.doi.org/10.7554/eLife.16059.013

Figure 6.. Characterization of alternative variants at position 2062 in D/P NCBD.

Isothermal titration calorimeter and circular dichroism experiments of D/P NCBD with (A) Ile and (B) Val at position 2062. See Figure 5A for Thr2062 and Table 1 for K_d values. DOI: http://dx.doi.org/10.7554/eLife.16059.014

Figure 7.. Far-UV Circular dichroism experiments.

(A–C) CD spectra of CID variants display a profile typical for disordered proteins. (D–E) CD spectra of NCBD variants show a qualitatively similar shape for all variants. (G–I) Thermal denaturations of NCBD variants show a similar apparent non-cooperative transition. DOI: http://dx.doi.org/10.7554/eLife.16059.016

Figure 8.. The helical propensity of CID variants as predicted by AGADIR.

(A) CID domains from extant human NCOA1, 2 and 3. (B) Ancestral CID domains: 1R, 2R and the fish/tetrapod ancestor. DOI: http://dx.doi.org/10.7554/eLife.16059.017

Figure 9.. The CID/NCBD complex displays minor structural changes upon evolution.

(A) Free-energy surfaces (in kJ/mol) as a function of the fraction of helix content and the Rg, for the most ancient complex (D/P NCBD and 1R CID), the 1R/2R complex and one extant complex (human NCOA3 CID/CREBBP NCBD). For each free-energy surface, the position of the minimum and a set of representative structures are shown: CID in yellow and NCBD in blue. N- and C- termini (NT and CT, respectively) are labeled for the central ensemble. (B) Per residue helix population of the protein ensembles of the most ancient (blue circles), 1R/2R (green squares) and extant (red bars) variants as predicted by δ2D from the chemical shifts. (C) Average root-mean-square fluctuation for the three variants showing a weak correlation between historical age and conformational heterogeneity of the complex. DOI: http://dx.doi.org/10.7554/eLife.16059.020

Figure 9—figure supplement 1.. Heteronuclear single quantum correlation (¹H/¹⁵N) spectra for the ancient complex between 1R CID and D/P NCBD (red peaks) and the extant complex between human NCOA3 CID and CREBBP NCBD (blue peaks).

The spectra were recorded such that either the CID domain was NMR active (panel A) or the NCBD was NMR active (panel B). DOI: http://dx.doi.org/10.7554/eLife.16059.022

Figure 10.. Contact analysis for ancient and extant CID/NCBD complexes.

The probability contact maps are shown for each pair of residues for (upper left) the most ancient complex (1R CID and D/P NCBD), (upper right) the 1R/2R complex and (lower right) the extant NCOA3 CID/CREBBP NCBD complex. Inter-domain contacts are framed by gray rectangles. Given two residues in a certain conformation, a contact is defined as a distance within 0.5 nm (excluding hydrogen atoms). Lower left panels: The total number of inter-domain contacts (left) and the inter-domain average contact formation (right) are reported as the number of residues with a contact populated more than 5% and the average over population for the same contacts, respectively. DOI: http://dx.doi.org/10.7554/eLife.16059.023

Figure 11.. NCBD Interface contact analysis.

The normalized number of interface contacts per residue is calculated from the simulations of the three historical CID/NCBD complexes (upper three panels) and compared with two extant complexes formed by CREBBP NCBD and alternative protein ligands, p53TAD (pdb code 2L14) (Lee et al., 2010) and a binding domain from IRF-3 (pdb code 1ZOQ) (Qin et al., 2005), respectively. In the IRF-3 complex (bottom panel), NCBD adopts a distinct tertiary structure as compared to complexes with CID and p53. The Gly-Ser residues at the N-terminus of the NCBD sequences result from the expression construct used in the study. DOI: http://dx.doi.org/10.7554/eLife.16059.024

Figure 12.. Isothermal titration calorimeter experiments between human NCOA2 CID and 'reverse mutants' in human CREBBP NCBD.

(A) A2106Q, (B) Y2108Q and (C) A2106Q/Y2108Q. Below are CD spectra of the respective NCBD variant. DOI: http://dx.doi.org/10.7554/eLife.16059.025

Figure 13.. Analysis of the convergence of the simulations.

Free-energy plots along the dRMSD collective variable for the second half of the simulations are shown for (A) the most ancient complex (1R CID and D/P NCBD), (B) the 1R/2R complex and (C) the extant NCOA3 CID/CREBBP NCBD complex. The solid black curve is the final free energy obtained by averaging over the second half of the simulations. Overall, all the simulations are converged within 3 kJ/mol. DOI: http://dx.doi.org/10.7554/eLife.16059.026