Using manifold embedding for assessing and predicting protein interactions from high-throughput experimental data

Abstract

Motivation: High-throughput protein interaction data, with everincreasing volume, are becoming the foundation of many biological discoveries, and thus high-quality protein-protein interaction (PPI) maps are critical for a deeper understanding of cellular processes. However, the unreliability and paucity of current available PPI data are key obstacles to the subsequent quantitative studies. It is therefore highly desirable to develop an approach to deal with these issues from the computational perspective. Most previous works for assessing and predicting protein interactions either need supporting evidences from multiple information resources or are severely impacted by the sparseness of PPI networks. Results: We developed a robust manifold embedding technique for assessing the reliability of interactions and predicting new interactions, which purely utilizes the topological information of PPI networks and can work on a sparse input protein interactome without requiring additional information types. After transforming a given PPI network into a low-dimensional metric space using manifold embedding based on isometric feature mapping (ISOMAP), the problem of assessing and predicting protein interactions is recasted into the form of measuring similarity between points of its metric space. Then a reliability index, a likelihood indicating the interaction of two proteins, is assigned to each protein pair in the PPI networks based on the similarity between the points in the embedded space. Validation of the proposed method is performed with extensive experiments on densely connected and sparse PPI network of yeast, respectively. Results demonstrate that the interactions ranked top by our method have high-functional homogeneity and localization coherence, especially our method is very efficient for large sparse PPI network with which the traditional algorithms fail. Therefore, the proposed algorithm is a much more promising method to detect both false positive and false negative interactions in PPI networks. Availability: MATLAB code implementing the algorithm is available from the web site

Minimum curvilinearity to enhance topological prediction of protein interactions by network embedding

“…However, such experiments are time consuming and expensive. Because of this, researchers have developed computational approaches for predicting novel interactions (You et al , 2010), intended also to guide wet lab experiments. The topological prediction of new interactions is a novel and useful option based exclusively on the structural information provided by the PPI network (PPIN) topology.…”

“…The set of candidate interactions is then ranked. The main problem with these techniques is that their performance is poor when applied to sparse and noisy networks (You et al , 2010). …”

Using Biological Networks in Protein Function Prediction and Gene Expression Analysis

“…Finally, an index like CD u,v is applied to this graph to estimate the likelihood that proteins u and v interact. Experiments have confirmed that, for sparse protein interaction networks, this additional step of manifold-embedding has led to much better performance [92].…”

“…A recent idea [42,92] to overcome this problem is using a larger interaction neighbourhood via a manifold embedding. Here, a protein-protein similarity matrix is first computed based on the shortest distancein terms of number of hops in the initial protein interaction network-between each pair of proteins.…”

Using Chou's amphiphilic Pseudo-Amino Acid Composition and Extreme Learning Machine for prediction of Protein-protein interactions

“…However, ELM randomly chooses the input weights and bias, it only requires setting the number of hidden neurons and the activation function. In theory, ELM tends to provide the best generalization performance at extreme fast learning speed [18] [19].…”