Chengwei Lei

A novel link prediction algorithm for reconstructing protein–protein interaction networks by topological similarity

MOTIVATION Recent advances in technology have dramatically increased the availability of protein-protein interaction (PPI) data and stimulated the development of many methods for improving the systems level understanding the cell. However, those efforts have been significantly hindered by the high level of noise, sparseness and highly skewed degree distribution of PPI networks. Here, we present a novel algorithm to reduce the noise present in PPI networks. The key idea of our algorithm is that two proteins sharing some higher-order topological similarities, measured by a novel random walk-based procedure, are likely interacting with each other and may belong to the same protein complex. RESULTS Applying our algorithm to a yeast PPI network, we found that the edges in the reconstructed network have higher biological relevance than in the original network, assessed by multiple types of information, including gene ontology, gene expression, essentiality, conservation between species and known protein complexes. Comparison with existing methods shows that the network reconstructed by our method has the highest quality. Using two independent graph clustering algorithms, we found that the reconstructed network has resulted in significantly improved prediction accuracy of protein complexes. Furthermore, our method is applicable to PPI networks obtained with different experimental systems, such as affinity purification, yeast two-hybrid (Y2H) and protein-fragment complementation assay (PCA), and evidence shows that the predicted edges are likely bona fide physical interactions. Finally, an application to a human PPI network increased the coverage of the network by at least 100%. AVAILABILITY www.cs.utsa.edu/∼jruan/RWS/.

A Particle Swarm Optimization algorithm for finding DNA sequence motifs

Discovering short DNA motifs from a set of co-regulated genes is an important step towards deciphering the complex gene regulatory networks and understanding gene functions. Despite significant improvement in the last decade, it still remains one of the most challenging problems in both computer science and molecular biology. In this work, we propose a novel motif finding algorithm based on a population-based stochastic optimization technique called Particle Swarm Optimization (PSO), which has been shown to be effective in optimizing difficult multidimensional problems in many fields. However, PSO has mainly been applied to problems in continuous domains. The motif finding problem, which is essentially a multiple local alignment problem, is discrete, as a slight shift in one sequence completely changes the alignment. Therefore, we propose to use a word dissimilarity graph to remap the neighborhood structure of the solution space, which transforms the motif finding problem into a contiguous integer domain, and propose a modification of the naive PSO algorithm to accommodate integer variables. In order to improve efficiency, we also propose several strategies for escaping from local optima, and determining the termination criteria automatically. Experimental results on simulated challenge problems show that our method is both more efficient and more accurate than several existing algorithms. Applications to several sets of real promoter sequences also show that our approach is able to detect known transcription factor binding sites, and outperforms two of the most successful existing algorithms.

A particle swarm optimization-based algorithm for finding gapped motifs

BackgroundIdentifying approximately repeated patterns, or motifs, in DNA sequences from a set of co-regulated genes is an important step towards deciphering the complex gene regulatory networks and understanding gene functions.ResultsIn this work, we develop a novel motif finding algorithm (PSO+) using a population-based stochastic optimization technique called Particle Swarm Optimization (PSO), which has been shown to be effective in optimizing difficult multidimensional problems in continuous domains. We propose a modification of the standard PSO algorithm to handle discrete values, such as characters in DNA sequences. The algorithm provides several features. First, we use both consensus and position-specific weight matrix representations in our algorithm, taking advantage of the efficiency of the former and the accuracy of the latter. Furthermore, many real motifs contain gaps, but the existing methods usually ignore them or assume a user know their exact locations and lengths, which is usually impractical for real applications. In comparison, our method models gaps explicitly, and provides an easy solution to find gapped motifs without any detailed knowledge of gaps. Our method allows the presence of input sequences containing zero or multiple binding sites.ConclusionExperimental results on synthetic challenge problems as well as real biological sequences show that our method is both more efficient and more accurate than several existing algorithms, especially when gaps are present in the motifs.

Systematic identification of functional modules and cis-regulatory elements in Arabidopsis thaliana

BackgroundSeveral large-scale gene co-expression networks have been constructed successfully for predicting gene functional modules and cis-regulatory elements in Arabidopsis (Arabidopsis thaliana). However, these networks are usually constructed and analyzed in an ad hoc manner. In this study, we propose a completely parameter-free and systematic method for constructing gene co-expression networks and predicting functional modules as well as cis-regulatory elements.ResultsOur novel method consists of an automated network construction algorithm, a parameter-free procedure to predict functional modules, and a strategy for finding known cis-regulatory elements that is suitable for consensus scanning without prior knowledge of the allowed extent of degeneracy of the motif. We apply the method to study a large collection of gene expression microarray data in Arabidopsis. We estimate that our co-expression network has ~94% of accuracy, and has topological properties similar to other biological networks, such as being scale-free and having a high clustering coefficient. Remarkably, among the ~300 predicted modules whose sizes are at least 20, 88% have at least one significantly enriched functions, including a few extremely significant ones (ribosome, p < 1E-300, photosynthetic membrane, p < 1.3E-137, proteasome complex, p < 5.9E-126). In addition, we are able to predict cis-regulatory elements for 66.7% of the modules, and the association between the enriched cis-regulatory elements and the enriched functional terms can often be confirmed by the literature. Overall, our results are much more significant than those reported by several previous studies on similar data sets. Finally, we utilize the co-expression network to dissect the promoters of 19 Arabidopsis genes involved in the metabolism and signaling of the important plant hormone gibberellin, and achieved promising results that reveal interesting insight into the biosynthesis and signaling of gibberellin.ConclusionsThe results show that our method is highly effective in finding functional modules from real microarray data. Our application on Arabidopsis leads to the discovery of the largest number of annotated Arabidopsis functional modules in the literature. Given the high statistical significance of functional enrichment and the agreement between cis-regulatory and functional annotations, we believe our Arabidopsis gene modules can be used to predict the functions of unknown genes in Arabidopsis, and to understand the regulatory mechanisms of many genes.

A novel swarm intelligence algorithm for finding DNA motifs.

Discovering DNA motifs from co-expressed or co-regulated genes is an important step towards deciphering complex gene regulatory networks and understanding gene functions. Despite significant improvement in the last decade, it still remains one of the most challenging problems in computational molecular biology. In this work, we propose a novel motif finding algorithm that finds consensus patterns using a population-based stochastic optimisation technique called Particle Swarm Optimisation (PSO), which has been shown to be effective in optimising difficult multidimensional problems in continuous domains. We propose to use a word dissimilarity graph to remap the neighborhood structure of the solution space of DNA motifs, and propose a modification of the naive PSO algorithm to accommodate discrete variables. In order to improve efficiency, we also propose several strategies for escaping from local optima and for automatically determining the termination criteria. Experimental results on simulated challenge problems show that our method is both more efficient and more accurate than several existing algorithms. Applications to several sets of real promoter sequences also show that our approach is able to detect known transcription factor binding sites, and outperforms two of the most popular existing algorithms.

Network-based classification of recurrent endometrial cancers using high-throughput DNA methylation data

DNA methylation, a well-studied mechanism of epigenetic regulation, plays important roles in cancer. Increased levels of global DNA methylation is observed in primary solid tumors including endometrial carcinomas and is generally associated with silencing of tumor suppressor genes. The role of DNA methylation in cancer recurrence after therapeutic intervention is not clear. Here, we developed a novel computational method to analyze whole-genome DNA methylation data for endometrial tumors within the context of a human protein-protein interaction (PPI) network, in order to identify subnetworks as potential epigenetic biomarkers for predicting tumor recurrence. Our method consists of the following steps. First, differentially methylated (DM) genes between recurrent and non-recurrent tumors are identified and mapped onto a human PPI network. Then, a PPI subnetwork consisting of DM genes and genes that are topologically important for connecting the DMs on the PPI network, termed epigenetic connectors (ECs), are extracted using a Steiner-tree based algorithm. Finally, a random-walk based machine learning method is used to propagate the DNA methylation scores from the DMs to the ECs, which enables the ECs to be used as features in a support vector machine classifier for predicting recurrence. Remarkably, we found that while the DMs are not enriched in any cancer-related pathways, the ECs are enriched in many well-known tumorgenesis and metastasis pathways and include known epigenetic regulators. Moreover, combining the DMs and ECs significantly improves the prediction accuracy of cancer recurrence and outperforms several alternative methods. Therefore, the network-based method is effective in identifying gene subnetworks that are crucial both for the understanding and prediction of tumor recurrence.

A random walk based approach for improving protein-protein interaction network and protein complex prediction

Recent advances in high-throughput technology have dramatically increased the quantity of available protein-protein interaction (PPI) data and stimulated the development of many methods for predicting protein complexes, which are important in understanding the functional organization of protein-protein interaction networks in different biological processes. However, automated protein complex prediction from PPI data alone is significantly hindered by the high level of noise, sparseness, and highly skewed degree distribution of PPI networks. Here we present a novel network topology-based algorithm to remove spurious interactions and recover missing ones by computational predictions, and to increase the accuracy of protein complex prediction by reducing the impact of hub nodes. The key idea of our algorithm is that two proteins sharing some high-order topological similarities, which are measured by a novel random walk-based procedure, are likely interacting with each other and may belong to the same protein complex. Applying our algorithm to a yeast protein-protein interaction network, we found that the interactions in the reconstructed PPI network have more significant biological relevance than the original network, assessed by multiple types of information, including gene ontology, gene expression, essentiality, conservation between species, and known protein complexes. Comparison with several existing methods show that the network reconstructed by our method has the highest quality. Finally, using two independent graph clustering algorithms, we found that the reconstructed network has resulted in significantly improved prediction accuracy of protein complexes.

Fully automated protein complex prediction based on topological similarity and community structure

To understand the function of protein complexes and their association with biological processes, a lot of studies have been done towards analyzing the protein-protein interaction (PPI) networks. However, the advancement in high-throughput technology has resulted in a humongous amount of data for analysis. Moreover, high level of noise, sparseness, and skewness in degree distribution of PPI networks limits the performance of many clustering algorithms and further analysis of their interactions.In addressing and solving these problems we present a novel random walk based algorithm that converts the incomplete and binary PPI network into a protein-protein topological similarity matrix (PP-TS matrix). We believe that if two proteins share some high-order topological similarities they are likely to be interacting with each other. Using the obtained PP-TS matrix, we constructed and used weighted networks to further study and analyze the interaction among proteins. Specifically, we applied a fully automated community structure finding algorithm (Auto-HQcut) on the obtained weighted network to cluster protein complexes. We then analyzed the protein complexes for significance in biological processes. To help visualize and analyze these protein complexes we also developed an interface that displays the resulting complexes as well as the characteristics associated with each complex.Applying our approach to a yeast protein-protein interaction network, we found that the predicted protein-protein interaction pairs with high topological similarities have more significant biological relevance than the original protein-protein interactions pairs. When we compared our PPI network reconstruction algorithm with other existing algorithms using gene ontology and gene co-expression, our algorithm produced the highest similarity scores. Also, our predicted protein complexes showed higher accuracy measure compared to the other protein complex predictions.

Finding gapped motifs by a novel evolutionary algorithm

Identifying approximately repeated patterns, or motifs, in biological sequences from a set of co-regulated genes is an important step towards deciphering the complex gene regulatory networks and understanding gene functions. In this work, we develop a novel motif finding algorithm based on a population-based stochastic optimization technique called Particle Swarm Optimization (PSO), which has been shown to be effective in optimizing difficult multidimensional problems in continuous domains. We propose a modification of the standard PSO algorithm to handle discrete values, such as characters in DNA sequences. Our algorithm also provides several unique features. First, we use both consensus and position-specific weight matrix representations in our algorithm, taking advantage of the efficiency of the former and the accuracy of the later. Furthermore, many real motifs contain gaps, but the existing methods usually ignore them or assume a user know their exact locations and lengths, which is usually impractical for real applications. In comparison, our method models gaps explicitly, and provides an easy solution to find gapped motifs without any detailed knowledge of gaps. Our method also allows some input sequences to contain zero or multiple binding sites. Experimental results on synthetic challenge problems as well as real biological sequences show that our method is both more efficient and more accurate than several existing algorithms, especially when gaps are present in the motifs.