Interaction network

About: Interaction network is a research topic. Over the lifetime, 2700 publications have been published within this topic receiving 113372 citations.

A cell surface interaction network of neural leucine-rich repeat receptors

Abstract: The vast number of precise intercellular connections within vertebrate nervous systems is only partly explained by the comparatively few known extracellular guidance cues. Large families of neural orphan receptor proteins have been identified and are likely to contribute to these recognition processes but due to the technical difficulty in identifying novel extracellular interactions of membrane-embedded proteins, their ligands remain unknown. To identify novel neural recognition signals, we performed a large systematic protein interaction screen using an assay capable of detecting low affinity extracellular protein interactions between the ectodomains of 150 zebrafish receptor proteins containing leucine-rich-repeat and/or immunoglobulin superfamily domains. We screened 7,592 interactions to construct a network of 34 cell surface receptor-ligand pairs that included orphan receptor subfamilies such as the Lrrtms, Lrrns and Elfns but also novel ligands for known receptors such as Robos and Unc5b. A quantitative biochemical analysis of a subnetwork involving the Unc5b and three Flrt receptors revealed a surprising quantitative variation in receptor binding strengths. Paired spatiotemporal gene expression patterns revealed dynamic neural receptor recognition maps within the developing nervous system, providing biological support for the network and revealing likely functions. This integrated interaction and expression network provides a rich source of novel neural recognition pathways and highlights the importance of quantitative systematic extracellular protein interaction screens to mechanistically explain neural wiring patterns.

GraphNAS: Graph Neural Architecture Search with Reinforcement Learning

Abstract: Graph Neural Networks (GNNs) have been popularly used for analyzing non-Euclidean data such as social network data and biological data. Despite their success, the design of graph neural networks requires a lot of manual work and domain knowledge. In this paper, we propose a Graph Neural Architecture Search method (GraphNAS for short) that enables automatic search of the best graph neural architecture based on reinforcement learning. Specifically, GraphNAS first uses a recurrent network to generate variable-length strings that describe the architectures of graph neural networks, and then trains the recurrent network with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation data set. Extensive experimental results on node classification tasks in both transductive and inductive learning settings demonstrate that GraphNAS can achieve consistently better performance on the Cora, Citeseer, Pubmed citation network, and protein-protein interaction network. On node classification tasks, GraphNAS can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy.

Learning on Weighted Hypergraphs to Integrate Protein Interactions and Gene Expressions for Cancer Outcome Prediction

Abstract: Building reliable predictive models from multiple complementary genomic data for cancer study is a crucial step towards successful cancer treatment and a full understanding of the underlying biological principles. To tackle this challenging data integration problem, we propose a hypergraph-based learning algorithm called HyperGene to integrate microarray gene expressions and protein-protein interactions for cancer outcome prediction and biomarker identification. HyperGene is a robust two-step iterative method that alternatively finds the optimal outcome prediction and the optimal weighting of the marker genes guided by a protein-protein interaction network. Under the hypothesis that cancer-related genes tend to interact with each other, the HyperGene algorithm uses a protein-protein interaction network as prior knowledge by imposing a consistent weighting of interacting genes. Our experimental results on two large-scale breast cancer gene expression datasets show that HyperGene utilizing a curated protein-protein interaction network achieves significantly improved cancer outcome prediction. Moreover, HyperGene can also retrieve many known cancer genes as highly weighted marker genes.

The evolutionary dynamics of the Saccharomyces cerevisiae protein interaction network after duplication

Abstract: Gene duplication is an important mechanism in the evolution of protein interaction networks. Duplications are followed by the gain and loss of interactions, rewiring the network at some unknown rate. Because rewiring is likely to change the distribution of network motifs within the duplicated interaction set, it should be possible to study network rewiring by tracking the evolution of these motifs. We have developed a mathematical framework that, together with duplication data from comparative genomic and proteomic studies, allows us to infer the connectivity of the preduplication network and the changes in connectivity over time. We focused on the whole-genome duplication (WGD) event in Saccharomyces cerevisiae. The model allowed us to predict the frequency of intergene interaction before WGD and the post duplication probabilities of interaction gain and loss. We find that the predicted frequency of self-interactions in the preduplication network is significantly higher than that observed in today's network. This could suggest a structural difference between the modern and ancestral networks, preferential addition or retention of interactions between ohnologs, or selective pressure to preserve duplicates of self-interacting proteins.