Biophysical prediction of protein-peptide interactions and signaling networks using machine learning.

In mammalian cells, much of signal transduction is mediated by weak protein-protein interactions between globular peptide-binding domains (PBDs) and unstructured peptidic motifs in partner proteins. The number and diversity of these PBDs (over 1,800 are known), their low binding affinities and the sensitivity of binding properties to minor sequence variation represent a substantial challenge to experimental and computational analysis of PBD specificity and the networks PBDs create. Here, we introduce a bespoke machine-learning approach, hierarchical statistical mechanical modeling (HSM), capable of accurately predicting the affinities of PBD-peptide interactions across multiple protein families. By synthesizing biophysical priors within a modern machine-learning framework, HSM outperforms existing computational methods and high-throughput experimental assays. HSM models are interpretable in familiar biophysical terms at three spatial scales: the energetics of protein-peptide binding, the multidentate organization of protein-protein interactions and the global architecture of signaling networks.

A multiscale statistical mechanical framework integrates biophysical and genomic data to assemble cancer networks.

Functional interpretation of genomic variation is critical to understanding human disease, but it remains difficult to predict the effects of specific mutations on protein interaction networks and the phenotypes they regulate. We describe an analytical framework based on multiscale statistical mechanics that integrates genomic and biophysical data to model the human SH2-phosphoprotein network in normal and cancer cells. We apply our approach to data in The Cancer Genome Atlas (TCGA) and test model predictions experimentally. We find that mutations mapping to phosphoproteins often create new interactions but that mutations altering SH2 domains result almost exclusively in loss of interactions. Some of these mutations eliminate all interactions, but many cause more selective loss, thereby rewiring specific edges in highly connected subnetworks. Moreover, idiosyncratic mutations appear to be as functionally consequential as recurrent mutations. By synthesizing genomic, structural and biochemical data, our framework represents a new approach to the interpretation of genetic variation.

Phosphotyrosine signaling proteins that drive oncogenesis tend to be highly interconnected.

Mutation and overexpression of receptor tyrosine kinases or the proteins they regulate serve as oncogenic drivers in diverse cancers. To better understand receptor tyrosine kinase signaling and its link to oncogenesis, we used protein microarrays to systematically and quantitatively measure interactions between virtually every SH2 or PTB domain encoded in the human genome and all known sites of tyrosine phosphorylation on 40 receptor tyrosine kinases and on most of the SH2 and PTB domain-containing adaptor proteins. We found that adaptor proteins, like RTKs, have many high affinity bindings sites for other adaptor proteins. In addition, proteins that drive cancer, including both receptors and adaptor proteins, tend to be much more highly interconnected via networks of SH2 and PTB domain-mediated interactions than nononcogenic proteins. Our results suggest that network topological properties such as connectivity can be used to prioritize new drug targets in this well-studied family of signaling proteins.