Mass-balanced randomization of metabolic networks

MOTIVATION: Network-centered studies in systems biology attempt to integrate the topological properties of biological networks with experimental data in order to make predictions and posit hypotheses. For any topology-based prediction, it is necessary to first assess the significance of the analyzed property in a biologically meaningful context. Therefore, devising network null models, carefully tailored to the topological and biochemical constraints imposed on the network, remains an important computational problem. RESULTS: We first review the shortcomings of the existing generic sampling scheme-switch randomization-and explain its unsuitability for application to metabolic networks. We then devise a novel polynomial-time algorithm for randomizing metabolic networks under the (bio)chemical constraint of mass balance. The tractability of our method follows from the concept of mass equivalence classes, defined on the representation of compounds in the vector space over chemical elements. We finally demonstrate the uniformity of the proposed method on seven genome-scale metabolic networks, and empirically validate the theoretical findings. The proposed method allows a biologically meaningful estimation of significance for metabolic network properties.     

Using Sequence Similarity Networks for Visualization of Relationships Across Diverse Protein Superfamilies

The dramatic increase in heterogeneous types of biological data—in particular, the abundance of new protein sequences—requires fast and user-friendly methods for organizing this information in a way that enables functional inference. The most widely used strategy to link sequence or structure to function, homology-based function prediction, relies on the fundamental assumption that sequence or structural similarity implies functional similarity. New tools that extend this approach are still urgently needed to associate sequence data with biological information in ways that accommodate the real complexity of the problem, while being accessible to experimental as well as computational biologists. To address this, we have examined the application of sequence similarity networks for visualizing functional trends across protein superfamilies from the context of sequence similarity. Using three large groups of homologous proteins of varying types of structural and functional diversity—GPCRs and kinases from humans, and the crotonase superfamily of enzymes—we show that overlaying networks with orthogonal information is a powerful approach for observing functional themes and revealing outliers. In comparison to other primary methods, networks provide both a good representation of group-wise sequence similarity relationships and a strong visual and quantitative correlation with phylogenetic trees, while enabling analysis and visualization of much larger sets of sequences than trees or multiple sequence alignments can easily accommodate. We also define important limitations and caveats in the application of these networks. As a broadly accessible and effective tool for the exploration of protein superfamilies, sequence similarity networks show great potential for generating testable hypotheses about protein structure-function relationships.     

Bioactivity assessment of natural compounds using machine learning models trained on target similarity between drugs

Natural compounds constitute a rich resource of potential small molecule therapeutics. While experimental access to this resource is limited due to its vast diversity and difficulties in systematic purification, computational assessment of structural similarity with known therapeutic molecules offers a scalable approach. Here, we assessed functional similarity between natural compounds and approved drugs by combining multiple chemical similarity metrics and physicochemical properties using a machine-learning approach. We computed pairwise similarities between 1410 drugs for training classification models and used the drugs shared protein targets as class labels. The best performing models were random forest which gave an average area under the ROC of 0.9, Matthews correlation coefficient of 0.35, and F1 score of 0.33, suggesting that it captured the structure-activity relation well. The models were then used to predict protein targets of circa 11k natural compounds by comparing them with the drugs. This revealed therapeutic potential of several natural compounds, including those with support from previously published sources as well as those hitherto unexplored. We experimentally validated one of the predicted pair’s activities, viz., Cox-1 inhibition by 5-methoxysalicylic acid, a molecule commonly found in tea, herbs and spices. In contrast, another natural compound, 4-isopropylbenzoic acid, with the highest similarity score when considering most weighted similarity metric but not picked by our models, did not inhibit Cox-1. Our results demonstrate the utility of a machine-learning approach combining multiple chemical features for uncovering protein binding potential of natural compounds.     

Information Content-Based Gene Ontology Functional Similarity Measures: Which One to Use for a Given Biological Data Type?

The current increase in Gene Ontology (GO) annotations of proteins in the existing genome databases and their use in different analyses have fostered the improvement of several biomedical and biological applications. To integrate this functional data into different analyses, several protein functional similarity measures based on GO term information content (IC) have been proposed and evaluated, especially in the context of annotation-based measures. In the case of topology-based measures, each approach was set with a specific functional similarity measure depending on its conception and applications for which it was designed. However, it is not clear whether a specific functional similarity measure associated with a given approach is the most appropriate, given a biological data set or an application, i.e., achieving the best performance compared to other functional similarity measures for the biological application under consideration. We show that, in general, a specific functional similarity measure often used with a given term IC or term semantic similarity approach is not always the best for different biological data and applications. We have conducted a performance evaluation of a number of different functional similarity measures using different types of biological data in order to infer the best functional similarity measure for each different term IC and semantic similarity approach. The comparisons of different protein functional similarity measures should help researchers choose the most appropriate measure for the biological application under consideration.     

A reduction-based exact algorithm for the contact map overlap problem.

Aligning proteins based on their structural similarity is a fundamental problem in molecular biology with applications in many settings, including structure classification, database search, function prediction, and assessment of folding prediction methods. Structural alignment can be done via several methods, including contact map overlap (CMO) maximization that aligns proteins in a way that maximizes the number of common residue contacts. In this paper, we develop a reduction-based exact algorithm for the CMO problem. Our approach solves CMO directly rather than after transformation to other combinatorial optimization problems. We exploit the mathematical structure of the problem in order to develop a number of efficient lower bounding, upper bounding, and reduction schemes. Computational experiments demonstrate that our algorithm runs significantly faster than existing exact algorithms and solves some hard CMO instances that were not solved in the past. In addition, the algorithm produces protein clusters that are in excellent agreement with the SCOP classification. An implementation of our algorithm is accessible as an on-line server at http://eudoxus.scs.uiuc.edu/cmos/cmos.html.     

Computational drug repositioning using meta-path-based semantic network analysis

Background

Drug repositioning is a promising and efficient way to discover new indications for existing drugs, which holds the great potential for precision medicine in the post-genomic era. Many network-based approaches have been proposed for drug repositioning based on similarity networks, which integrate multiple sources of drugs and diseases. However, these methods may simply view nodes as the same-typed and neglect the semantic meanings of different meta-paths in the heterogeneous network. Therefore, it is urgent to develop a rational method to infer new indications for approved drugs.

Results

In this study, we proposed a novel methodology named HeteSim_DrugDisease (HSDD) for the prediction of drug repositioning. Firstly, we build the drug-drug similarity network and disease-disease similarity network by integrating the information of drugs and diseases. Secondly, a drug-disease heterogeneous network is constructed, which combines the drug similarity network, disease similarity network as well as the known drug-disease association network. Finally, HSDD predicts novel drug-disease associations based on the HeteSim scores of different meta-paths. The experimental results show that HSDD performs significantly better than the existing state-of-the-art approaches. HSDD achieves an AUC score of 0.8994 in the leave-one-out cross validation experiment. Moreover, case studies for selected drugs further illustrate the practical usefulness of HSDD.

Conclusions

HSDD can be an effective and feasible way to infer the associations between drugs and diseases using on meta-path-based semantic network analysis.

     

Exploiting multi-layered information to iteratively predict protein functions

BackgroundSimilarity based computational methods are a useful tool for predicting protein functions from protein–protein interaction (PPI) datasets. Although various similarity-based prediction algorithms have been proposed, unsatisfactory prediction results have occurred on many occasions. The purpose of this type of algorithm is to predict functions of an unannotated protein from the functions of those proteins that are similar to the unannotated protein. Therefore, the prediction quality largely depends on how to select a set of proper proteins (i.e., a prediction domain) from which the functions of an unannotated protein are predicted, and how to measure the similarity between proteins. Another issue with existing algorithms is they only believe the function prediction is a one-off procedure, ignoring the fact that interactions amongst proteins are mutual and dynamic in terms of similarity when predicting functions. How to resolve these major issues to increase prediction quality remains a challenge in computational biology.ResultsIn this paper, we propose an innovative approach to predict protein functions of unannotated proteins iteratively from a PPI dataset. The iterative approach takes into account the mutual and dynamic features of protein interactions when predicting functions, and addresses the issues of protein similarity measurement and prediction domain selection by introducing into the prediction algorithm a new semantic protein similarity and a method of selecting the multi-layer prediction domain. The new protein similarity is based on the multi-layered information carried by protein functions. The evaluations conducted on real protein interaction datasets demonstrated that the proposed iterative function prediction method outperformed other similar or non-iterative methods, and provided better prediction results.ConclusionsThe new protein similarity derived from multi-layered information of protein functions more reasonably reflects the intrinsic relationships among proteins, and significant improvement to the prediction quality can occur through incorporation of mutual and dynamic features of protein interactions into the prediction algorithm.     

Network methods for describing sample relationships in genomic datasets: application to Huntington’s disease

Background

We consider the possibility of engineering metabolic pathways in a chassis organism in order to synthesize novel target compounds that are heterologous to the chassis. For this purpose, we model metabolic networks through hypergraphs where reactions are represented by hyperarcs. Each hyperarc represents an enzyme-catalyzed reaction that transforms set of substrates compounds into product compounds. We follow a retrosynthetic approach in order to search in the metabolic space (hypergraphs) for pathways (hyperpaths) linking the target compounds to a source set of compounds.

Results

To select the best pathways to engineer, we have developed an objective function that computes the cost of inserting a heterologous pathway in a given chassis organism. In order to find minimum-cost pathways, we propose in this paper two methods based on steady state analysis and network topology that are to the best of our knowledge, the first to enumerate all possible heterologous pathways linking a target compounds to a source set of compounds. In the context of metabolic engineering, the source set is composed of all naturally produced chassis compounds (endogenuous chassis metabolites) and the target set can be any compound of the chemical space. We also provide an algorithm for identifying precursors which can be supplied to the growth media in order to increase the number of ways to synthesize specific target compounds.

Conclusions

We find the topological approach to be faster by several orders of magnitude than the steady state approach. Yet both methods are generally scalable in time with the number of pathways in the metabolic network. Therefore this work provides a powerful tool for pathway enumeration with direct application to biosynthetic pathway design.     

A machine learning information retrieval approach to protein fold recognition

MOTIVATION: Recognizing proteins that have similar tertiary structure is the key step of template-based protein structure prediction methods. Traditionally, a variety of alignment methods are used to identify similar folds, based on sequence similarity and sequence-structure compatibility. Although these methods are complementary, their integration has not been thoroughly exploited. Statistical machine learning methods provide tools for integrating multiple features, but so far these methods have been used primarily for protein and fold classification, rather than addressing the retrieval problem of fold recognition-finding a proper template for a given query protein. RESULTS: Here we present a two-stage machine learning, information retrieval, approach to fold recognition. First, we use alignment methods to derive pairwise similarity features for query-template protein pairs. We also use global profile-profile alignments in combination with predicted secondary structure, relative solvent accessibility, contact map and beta-strand pairing to extract pairwise structural compatibility features. Second, we apply support vector machines to these features to predict the structural relevance (i.e. in the same fold or not) of the query-template pairs. For each query, the continuous relevance scores are used to rank the templates. The FOLDpro approach is modular, scalable and effective. Compared with 11 other fold recognition methods, FOLDpro yields the best results in almost all standard categories on a comprehensive benchmark dataset. Using predictions of the top-ranked template, the sensitivity is approximately 85, 56, and 27% at the family, superfamily and fold levels respectively. Using the 5 top-ranked templates, the sensitivity increases to 90, 70, and 48%.     

The MASH pipeline for protein function prediction and an algorithm for the geometric refinement of 3D motifs.

The development of new and effective drugs is strongly affected by the need to identify drug targets and to reduce side effects. Resolving these issues depends partially on a thorough understanding of the biological function of proteins. Unfortunately, the experimental determination of protein function is expensive and time consuming. To support and accelerate the determination of protein functions, algorithms for function prediction are designed to gather evidence indicating functional similarity with well studied proteins. One such approach is the MASH pipeline, described in the first half of this paper. MASH identifies matches of geometric and chemical similarity between motifs, representing known functional sites, and substructures of functionally uncharacterized proteins (targets). Observations from several research groups concur that statistically significant matches can indicate functionally related active sites. One major subproblem is the design of effective motifs, which have many matches to functionally related targets (sensitive motifs), and few matches to functionally unrelated targets (specific motifs). Current techniques select and combine structural, physical, and evolutionary properties to generate motifs that mirror functional characteristics in active sites. This approach ignores incidental similarities that may occur with functionally unrelated proteins. To address this problem, we have developed Geometric Sieving (GS), a parallel distributed algorithm that efficiently refines motifs, designed by existing methods, into optimized motifs with maximal geometric and chemical dissimilarity from all known protein structures. In exhaustive comparison of all possible motifs based on the active sites of 10 well-studied proteins, we observed that optimized motifs were among the most sensitive and specific.     

A Time-Series-Based Feature Extraction Approach for Prediction of Protein Structural Class

This paper presents a novel feature vector based on physicochemical property of amino acids for prediction protein structural classes. The proposed method is divided into three different stages. First, a discrete time series representation to protein sequences using physicochemical scale is provided. Later on, a wavelet-based time-series technique is proposed for extracting features from mapped amino acid sequence and a fixed length feature vector for classification is constructed. The proposed feature space summarizes the variance information of ten different biological properties of amino acids. Finally, an optimized support vector machine model is constructed for prediction of each protein structural class. The proposed approach is evaluated using leave-one-out cross-validation tests on two standard datasets. Comparison of our result with existing approaches shows that overall accuracy achieved by our approach is better than exiting methods.     

Integrating multi-attribute similarity networks for robust representation of the protein space

MOTIVATION: A global view of the protein space is essential for functional and evolutionary analysis of proteins. In order to achieve this, a similarity network can be built using pairwise relationships among proteins. However, existing similarity networks employ a single similarity measure and therefore their utility depends highly on the quality of the selected measure. A more robust representation of the protein space can be realized if multiple sources of information are used. RESULTS: We propose a novel approach for analyzing multi-attribute similarity networks by combining random walks on graphs with Bayesian theory. A multi-attribute network is created by combining sequence and structure based similarity measures. For each attribute of the similarity network, one can compute a measure of affinity from a given protein to every other protein in the network using random walks. This process makes use of the implicit clustering information of the similarity network, and we show that it is superior to naive, local ranking methods. We then combine the computed affinities using a Bayesian framework. In particular, when we train a Bayesian model for automated classification of a novel protein, we achieve high classification accuracy and outperform single attribute networks. In addition, we demonstrate the effectiveness of our technique by comparison with a competing kernel-based information integration approach.     

Metabolic engineering of beta-lactam production

Metabolic engineering has become a rational alternative to classical strain improvement in optimisation of beta-lactam production. In metabolic engineering directed genetic modification are introduced to improve the cellular properties of the production strains. This has resulted in substantial increases in the existing beta-lactam production processes. Furthermore, pathway extension, by heterologous expression of novel genes in well-characterised strains, has led to introduction of new fermentation processes that replace environmentally damaging chemical methods. This minireview discusses the recent developments in metabolic engineering and the applications of this approach for improving beta-lactam production.     

Predicting human disease-associated circRNAs based on locality-constrained linear coding

Circular RNAs (circRNAs) are a new kind of endogenous non-coding RNAs, which have been discovered continuously. More and more studies have shown that circRNAs are related to the occurrence and development of human diseases. Identification of circRNAs associated with diseases can contribute to understand the pathogenesis, diagnosis and treatment of diseases. However, experimental methods of circRNA prediction remain expensive and time-consuming. Therefore, it is urgent to propose novel computational methods for the prediction of circRNA-disease associations. In this study, we develop a computational method called LLCDC that integrates the known circRNA-disease associations, circRNA semantic similarity network, disease semantic similarity network, reconstructed circRNA similarity network, and reconstructed disease similarity network to predict circRNAs related to human diseases. Specifically, the reconstructed similarity networks are obtained by using Locality-Constrained Linear Coding (LLC) on the known association matrix, cosine similarities of circRNAs and diseases. Then, the label propagation method is applied to the similarity networks, and four relevant score matrices are respectively obtained. Finally, we use 5-fold cross validation (5-fold CV) to evaluate the performance of LLCDC, and the AUC value of the method is 0.9177, indicating that our method performs better than the other three methods. In addition, case studies on gastric cancer, breast cancer and papillary thyroid carcinoma further verify the reliability of our method in predicting disease-associated circRNAs.