Interactome INSIDER: a structural interactome browser for genomic studies

Abstract

We present Interactome INSIDER, a tool to link genomic variant information with structural protein-protein interactomes. Underlying this tool is the application of machine learning to predict protein interaction interfaces for 185,957 protein interactions with previously unresolved interfaces in human and seven model organisms, including the entire experimentally determined human binary interactome. Predicted interfaces exhibit functional properties similar to those of known interfaces, including enrichment for disease mutations and recurrent cancer mutations. Through 2,164 de novo mutagenesis experiments, we show that mutations of predicted and known interface residues disrupt interactions at a similar rate and much more frequently than mutations outside of predicted interfaces. To spur functional genomic studies, Interactome INSIDER (http://interactomeinsider.yulab.org) enables users to identify whether variants or disease mutations are enriched in known and predicted interaction interfaces at various resolutions. Users may explore known population variants, disease mutations, and somatic cancer mutations, or they may upload their own set of mutations for this purpose.

Figure 1

The current size of structural interactomes. (a) The plot shows the coverage (number of protein interactions) of known high quality binary interactomes with pre-computed co-complexed protein structures. (b) The number of interactions from the 8 largest interactomes with experimentally solved structures.

Figure 2

ECLAIR prediction results. (a) Workflow for classifying interfaces for all interactions in 8 species. Interactions without experimentally determined or homology modeled interfaces are classified by ECLAIR. (b) ROC and precision-recall curves comparing ECLAIR with the indicated interface residue prediction methods. (c) Fraction of interactions disrupted by the introduction of random population variants in known and predicted interfaces. (Significance determined by two-sided Z-test; n.s. denotes not significant)

Figure 3

Workflow for calculating mutation and variant enrichment using Interactome INSIDER (http://interactomeinsider.yulab.org). Users may submit mutations or select sets of known disease and cancer mutations to assess their enrichment in interface domains and residues, or may compute 3D atomic clusters of mutations in proteins and across interfaces.

Figure 4

Functional properties of predicted interfaces. (a) Enrichment of disease mutations in predicted and known interfaces. In a–c, enrichment (log odds ratio) is the odds of mutations and variants to appear in and outside of predicted and known interfaces compared to the odds of any residues to exist in these categories. (b) Enrichment of recurrent cancer mutations in predicted and known interfaces. (c) Enrichment of rare and common population variants in predicted and known interfaces. (d, e) Predicted deleteriousness of population variants in known and predicted interfaces using PolyPhen-2 (d) or EVmutation (e). (In b, significance determined by two-sided Z-test. In d-e, significance determined by a two-sided U-test. IRES=interface residues)

Figure 5

Interaction partner-specific interface prediction. (a) The top schematic depicts the TGF-β/BMP signaling pathway. The bottom schematic illustrates that atomic clustering reveals a mutation hotspot for juvenile polyposis syndrome at the interface of SMAD8 and SMAD4. At right, yeast two-hybrid experiments test the interactions of one of the SMAD4 mutations (Y353S) with SMAD8 and RASSF5. The mutation is not predicted by ECLAIR to be at the SMAD4-RASS5 interface. (b) Superimposed docking results of two different interaction partners with TK1. The differentially predicted interfaces of TK1 with each of its partners correspond with the orientation of the docked poses. (c) The plot shows the fraction of disease mutation pairs in known (blue) or predicted (orange) interfaces that cause the same disease when mutations are within a given interaction interface compared to when mutations are not within an interaction interface. (d) The plot shows the fraction of disease mutation pairs in known (blue) or predicted (orange) interfaces that cause different diseases when mutations are in the same interaction interface compared to in different interaction interfaces (interaction with other proteins is not shown). (Significance determined by two-sided Z-test)

Figure 6

The hypertrophic cardiomyopathy (HCM) pathway. The schematic on the left shows the interaction of proteins in the HGM KEGG pathway (hsa04510). On the right is shown a network of KEGG pathway proteins and their structurally-resolved interactions from Interactome INSIDER. Proteins that harbor HCM mutations are colored in red. Interfaces are noted for their enrichment of HCM mutations.