Impacts of protein-protein interaction domains on organism and network complexity

Abstract

It has been a puzzle that genome or proteome sizes are not correlated with the complexity of the organisms. Although alternative splicing and noncoding and regulatory elements explain some of the differences, the complexity of the protein interaction network and regulatory network may provide additional explanations. Here, we collected 642 domains that mediate protein-protein interactions (PPIs) and examined the evolution of the PPI domains and its impact on organismal complexity and PPI network complexity. In agreement with previous more general studies of protein domains, a significant expansion of PPI domains per proteome was found in metazoa. We also found both the number and coverage of PPI domains per protein increased. However, a better correlation with complexity was seen with increasing PPI domain coverage per protein, so that proteins in complex organisms are more compact and specialized in PPI. Such a structural adaptation of the proteins is correlated with the number of interactions that the proteins can make in PPI networks, and seems to be a more favorable way to increase network connectivity than other structural adaptations.

Figure 1.

Evolutionary structural adaptations toward PPI domain expansion at the individual protein level. (A) The percentage of proteins with PPI domains (maroon blocks), other non-PPI domains (cyan blocks) among all proteins with domain annotation in each organism (above X-axis), and those without any annotated domains (beige blocks) in the proteomes of different organisms (below X-axis). The organisms that are significantly under- or overannotated for domains are indicated by asterisks or pound signs before their names. (B) Percentage of proteins with single (cyan) or multiple (maroon) PPI domains in different organisms among PPI domain-containing proteins. (C) Percentage of proteins with single (cyan) or multiple (maroon) non-PPI domains in different organisms among non-PPI domain-containing proteins. (D) The relationship of the number of PPI domains per protein to the number of cell types in an organism in each of the leave-one-out nine-group combinations (LO1 ∼ 10). The 10 regression lines, PCCs, and linear regression slope P-values result from 10 leave-one-out analyses, one for each nine out of the 10 random protein groups (same for G and H). (E) Distribution of PPI domain coverage. Proteins in each organism are divided into 10 groups based on their PPI domain coverage. The boundaries of each PPI domain coverage interval are shown on the top of the plot. The numbers in the grid give the percentage of the total domain-annotated proteins in each organism that belong to a certain PPI domain coverage interval. The color intensity in each cell is proportional to the relative percentages within each organism (row). (F) Distribution of non-PPI domain coverage. The color intensity and number inside each grid are denoted as in E, except that PPI domains are replaced by non-PPI domains. (G) The relationship of average PPI domain coverage to the number of cell types in an organism in each of the leave-one-out nine-group combinations (LO1 ∼ 10). (H) The relationship of average length of PPI domains to the number of cell types in an organism in each of the leave-one-out nine-group combinations (LO1 ∼ 10).

Figure 2.

Examples of increasing domain coverage on orthologous proteins through evolution. PPI domain length increase (A), loss of the domain-free sequences at orthologous proteins’ N termini (B), C termini (C), and PPI domain insertion (D) that contribute to increased PPI domain coverage through evolution. Each protein is labeled with its SwissProt identifier. A protein’s name suffixed by the abbreviation of its species name is included inside the parentheses. Within each group, orthologous proteins are ordered by taxonomy. Colored blocks stand for different domains and their annotations are listed at the bottom of each figure. PPI domains are indicated in the block-color legend.

Figure 3.

Relationships of PPI domain coverage, number, and length to PPI degrees by leave-one out analysis. The average human and yeast PPI degrees of proteins in each of the nine out of 10 group combinations within each interval of PPI domain coverage (A,B), PPI domain number (C,D), or PPI domain length (E,F) are plotted against their average values within the intervals. The 10 regression lines, PCCs, and linear regression slope P-values result from 10 leave-one-out analyses (LO1 ∼ 10), one for each nine out of the 10 random protein groups.

Figure 4.

Distribution of PPI domain number and PPI domain coverage among human and yeast protein hubs and non-hubs. Proteins in human (A,B) and yeast (C,D) PPI networks are divided into hubs (k ≥ 5) and non-hubs (k < 5). The fraction of hubs and non-hubs with a certain number of PPI domains or PPI domain coverage are plotted against the PPI domain number (A,C) and average PPI domain coverage (B,D).