An efficient network querying method based on conditional random fields

MOTIVATION: A large amount of biomolecular network data for multiple species have been generated by high-throughput experimental techniques, including undirected and directed networks such as protein-protein interaction networks, gene regulatory networks and metabolic networks. There are many conserved functionally similar modules and pathways among multiple biomolecular networks in different species; therefore, it is important to analyze the similarity between the biomolecular networks. Network querying approaches aim at efficiently discovering the similar subnetworks among different species. However, many existing methods only partially solve this problem. RESULTS: In this article, a novel approach for network querying problem based on conditional random fields (CRFs) model is presented, which can handle both undirected and directed networks, acyclic and cyclic networks and any number of insertions/deletions. The CRF method is fast and can query pathways in a large network in seconds using a PC. To evaluate the CRF method, extensive computational experiments are conducted on the simulated and real data, and the results are compared with the existing network querying methods. All results show that the CRF method is very useful and efficient to find the conserved functionally similar modules and pathways in multiple biomolecular networks.     

Protein-protein interaction based on pairwise similarity

Background  

Protein-protein interaction (PPI) is essential to most biological processes. Abnormal interactions may have implications in a number of neurological syndromes. Given that the association and dissociation of protein molecules is crucial, computational tools capable of effectively identifying PPI are desirable. In this paper, we propose a simple yet effective method to detect PPI based on pairwise similarity and using only the primary structure of the protein. The PPI based on Pairwise Similarity (PPI-PS) method consists of a representation of each protein sequence by a vector of pairwise similarities against large subsequences of amino acids created by a shifting window which passes over concatenated protein training sequences. Each coordinate of this vector is typically the E-value of the Smith-Waterman score. These vectors are then used to compute the kernel matrix which will be exploited in conjunction with support vector machines.     

Protein-protein interaction site mapping using NMR-detected mutational scanning

We demonstrate a novel NMR method for the mapping of protein–protein interaction sites. In our approach protein–protein binding sites are mapped by competition binding experiments using indirect NMR reporter technology and Ala positional scanning. The methodology provides high sensitivity, ease of implementation and high-throughput capabilities. The feasibility of the technique is demonstrated with an application to the β-Catenin/Tcf4 complex.     

Protein-protein interaction site predictions with three-dimensional probability distributions of interacting atoms on protein surfaces

Protein-protein interactions are key to many biological processes. Computational methodologies devised to predict protein-protein interaction (PPI) sites on protein surfaces are important tools in providing insights into the biological functions of proteins and in developing therapeutics targeting the protein-protein interaction sites. One of the general features of PPI sites is that the core regions from the two interacting protein surfaces are complementary to each other, similar to the interior of proteins in packing density and in the physicochemical nature of the amino acid composition. In this work, we simulated the physicochemical complementarities by constructing three-dimensional probability density maps of non-covalent interacting atoms on the protein surfaces. The interacting probabilities were derived from the interior of known structures. Machine learning algorithms were applied to learn the characteristic patterns of the probability density maps specific to the PPI sites. The trained predictors for PPI sites were cross-validated with the training cases (consisting of 432 proteins) and were tested on an independent dataset (consisting of 142 proteins). The residue-based Matthews correlation coefficient for the independent test set was 0.423; the accuracy, precision, sensitivity, specificity were 0.753, 0.519, 0.677, and 0.779 respectively. The benchmark results indicate that the optimized machine learning models are among the best predictors in identifying PPI sites on protein surfaces. In particular, the PPI site prediction accuracy increases with increasing size of the PPI site and with increasing hydrophobicity in amino acid composition of the PPI interface; the core interface regions are more likely to be recognized with high prediction confidence. The results indicate that the physicochemical complementarity patterns on protein surfaces are important determinants in PPIs, and a substantial portion of the PPI sites can be predicted correctly with the physicochemical complementarity features based on the non-covalent interaction data derived from protein interiors.     

Accurate prediction of protein dihedral angles through conditional random field

Identifying local conformational changes induced by subtle differences on amino acid sequences is critical in exploring the functional variations of the proteins. In this study, we designed a computational scheme to predict the dihedral angle variations for different amino acid sequences by using conditional random field. This computational tool achieved an accuracy of 87% and 84% in 10-fold cross validation in a large data set for φ and Ψ, respectively. The prediction accuracies of φ and Ψ are positively correlated to each other for most of the 20 types of amino acids. Helical amino acids can achieve higher prediction accuracy in general, while amino acids in beet sheet have higher accuracy at specific angular regions. The prediction accuracy of φ is negatively correlated with amino acid flexibility represented by Vihinen Index. The prediction accuracy of φ can also be negatively correlated with angle distribution dispersion.     

Protein-protein interaction in transport

The transport of histidine in the gram negative bacterium S. typhimurium has been studied over a number of years and found to occur through five transport systems (Ames, 1972). Of these, the one with the highest affinity has been studied in detail from the genetic, physiological and biochemical point of view. This system, known as the high-affinity histidine permease, is composed of two subsystems, the J-P and K-P systems, which have a component in common, the P protein, presumed to be membrane-bound. The J-P system, moreover, is known to require the presence of a periplasmic histidine-binding protein, the J protein. The J protein is coded for by the hisJ gene and the P protein is coded for by the hisP gene. Both of these genes have been mapped at 75 min on the Salmonella chromosomal map. Adjacent to them is a regulatory gene, the dhuA gene. The periplasmic histidine-binding protein J has been shown to interact directly with the second component of transport, the P protein (Ames and Spudich, 1976). In accordance with this, histidine-binding protein J has been shown to contain, besides the histidine-binding site, a second site, essential for function, the interaction site (Kustu and Ames, 1974). We have recently shown that a mutant J protein with a defective interaction site but an intact histidine-binding site cannot function in histidine transport, unless an appropriate compensating mutation is introduced in the P protein. The interaction between the J and P proteins is an obligatory step in transport. The mutation in the interaction site of the J protein has been shown to map in the hisJ gene, and the compensating supressor mutation in the P protein has been shown to map in the hisP gene. Our contention that the J and P proteins engage in a functional interaction assumes further strength from other studies on protein-protein interaction in bacteriophage development and in ribosomal structure. Among the possible functions of the J-P interaction in histidine transport, a likely one is the transmission of information to the P protein, concerning whether or not the histidine-binding site on the J protein is occupied. Appropriate conformational changes then can occur in either the J or the P protein, or both, such that the histidine is released in the correct location and direction on the inside of the cell. This could occur either by a pore-formation mechanism or by binding-site translocation. Another alternative is that the P protein is part of an energy transducing mechanism in which energy is transmitted to the J protein, through the interaction site, as a prerequisite for the J protein participation in translocation. Among the interesting findings coming out of this work, is also the fact that the P protein performs a central function in transport being involved in the permeation of other substrates besides histidine. It is likely that other binding proteins besides the J protein require the P protein. Thus an interesting question which we are trying to answer at present is whether the P protein has separate interaction sites for each of these other binding proteins requiring its function, or whether they all interact at one common site.     

Identifying gene and protein mentions in text using conditional random fields

BACKGROUND: We present a model for tagging gene and protein mentions from text using the probabilistic sequence tagging framework of conditional random fields (CRFs). Conditional random fields model the probability P(t/o) of a tag sequence given an observation sequence directly, and have previously been employed successfully for other tagging tasks. The mechanics of CRFs and their relationship to maximum entropy are discussed in detail. RESULTS: We employ a diverse feature set containing standard orthographic features combined with expert features in the form of gene and biological term lexicons to achieve a precision of 86.4% and recall of 78.7%. An analysis of the contribution of the various features of the model is provided.     

Extraction of semantic biomedical relations from text using conditional random fields

Background  

The increasing amount of published literature in biomedicine represents an immense source of knowledge, which can only efficiently be accessed by a new generation of automated information extraction tools. Named entity recognition of well-defined objects, such as genes or proteins, has achieved a sufficient level of maturity such that it can form the basis for the next step: the extraction of relations that exist between the recognized entities. Whereas most early work focused on the mere detection of relations, the classification of the type of relation is also of great importance and this is the focus of this work. In this paper we describe an approach that extracts both the existence of a relation and its type. Our work is based on Conditional Random Fields, which have been applied with much success to the task of named entity recognition.     

Protein fold recognition using segmentation conditional random fields (SCRFs).

Protein fold recognition is an important step towards understanding protein three-dimensional structures and their functions. A conditional graphical model, i.e., segmentation conditional random fields (SCRFs), is proposed as an effective solution to this problem. In contrast to traditional graphical models, such as the hidden Markov model (HMM), SCRFs follow a discriminative approach. Therefore, it is flexible to include any features in the model, such as overlapping or long-range interaction features over the whole sequence. The model also employs a convex optimization function, which results in globally optimal solutions to the model parameters. On the other hand, the segmentation setting in SCRFs makes their graphical structures intuitively similar to the protein 3-D structures and more importantly provides a framework to model the long-range interactions between secondary structures directly. Our model is applied to predict the parallel beta-helix fold, an important fold in bacterial pathogenesis and carbohydrate binding/cleavage. The cross-family validation shows that SCRFs not only can score all known beta-helices higher than non-beta-helices in the Protein Data Bank (PDB), but also accurately locates rungs in known beta-helix proteins. Our method outperforms BetaWrap, a state-of-the-art algorithm for predicting beta-helix folds, and HMMER, a general motif detection algorithm based on HMM, and has the additional advantage of general application to other protein folds. Applying our prediction model to the Uniprot Database, we identify previously unknown potential beta-helices.     

Protein 8-class secondary structure prediction using conditional neural fields

Compared with the protein 3-class secondary structure (SS) prediction, the 8-class prediction gains less attention and is also much more challenging, especially for proteins with few sequence homologs. This paper presents a new probabilistic method for 8-class SS prediction using conditional neural fields (CNFs), a recently invented probabilistic graphical model. This CNF method not only models the complex relationship between sequence features and SS, but also exploits the interdependency among SS types of adjacent residues. In addition to sequence profiles, our method also makes use of non-evolutionary information for SS prediction. Tested on the CB513 and RS126 data sets, our method achieves Q8 accuracy of 64.9 and 64.7%, respectively, which are much better than the SSpro8 web server (51.0 and 48.0%, respectively). Our method can also be used to predict other structure properties (e.g. solvent accessibility) of a protein or the SS of RNA.     

Recognition of bacteria named entity using conditional random fields in Spark

Background

Microbe plays a crucial role in the functional mechanism of an ecosystem. Identification of the interactions among microbes is an important step towards understand the structure and function of microbial communities, as well as of the impact of microbes on human health and disease. Despite the importance of it, there is not a gold-standard dataset of microbial interactions currently. Traditional approaches such as growth and co-culture analysis need to be performed in the laboratory, which are time-consuming and costly. By providing predicted candidate interactions to experimental verification, computational methods are able to alleviate this problem. Mining microbial interactions from mass medical texts is one type of computational methods. Identification of the named entity of bacteria and related entities from the text is the basis for microbial relation extraction. In the previous work, a system of bacteria named entities recognition based on the dictionary and conditional random field was proposed. However, it is inefficient when dealing with large-scale text.

Results

We implemented bacteria named entity recognition on Spark platform and designed experiments for comparison to verify the correctness and validity of the proposed system. The experimental results show that it can achieve higher F-Measure on the comparison of correctness. Moreover, the predicting speed is much faster than the previous version in large-scale biomedical datasets, and the computational efficiency is improved remarkably by about 3.1 to 6.7 times.

Conclusions

The system for bacteria named entity recognition solves the inefficiency of the previous proposed system on large-scale datasets. The proposed system has good performance in accuracy and scalability.

     

Improving conditional random field model for prediction of protein-RNA residue-base contacts

Background: For understanding biological cellular systems, it is important to analyze interactions between protein residues and RNA bases. A method based on conditional random fields (CRFs) was developed for predicting contacts between residues and bases, which receives multiple sequence alignments for given protein and RNA sequences, respectively, and learns the model with many parameters involved in relationships between neighboring residue-base pairs by maximizing the pseudo likelihood function. Methods: In this paper, we proposed a novel CRF-based model with more complicated dependency relationships between random variables than the previous model, but which takes less parameters for the sake of avoidance of overfitting to training data. Results: We performed cross-validation experiments for evaluating the proposed model, and took the average of AUC (area under receiver operating characteristic curve) scores. The result suggests that the proposed CRF-based model without using L₁-norm regularization (lasso) outperforms the existing model with and without the lasso under several input observations to CRFs. Conclusions: We proposed a novel stochastic model for predicting protein-RNA residue-base contacts, and improved the prediction accuracy in terms of the AUC score. It implies that more dependency relationships in a CRF could be controlled by less parameters.     

Protein-protein interaction through beta-strand addition

Protein-protein interactions have essential roles at almost every level of organization and communication in living cells. During complex formation, proteins can interact via covalent, surface-surface or peptide-surface contacts. Many protein complexes are now known to involve the binding of linear motifs in one of the binding partners. An emerging mechanism of such non-covalent peptide-surface interaction involves the donation or addition of a beta strand in the ligand to a beta sheet or a beta strand in the receptor. Such 'beta-strand addition' contacts can dictate or modulate binding specificity and affinity, or can be used in more promiscuous protein-protein contacts. Three main classes of beta-strand addition can be distinguished: beta-sheet augmentation; beta-strand insertion and fold complementation; and beta-strand zippering. A survey of protein-protein complexes in the protein data bank identifies beta-strand additions in many important metabolic pathways. Targeting these interactions might, thus, provide novel routes for rational drug design.     

An unsupervised conditional random fields approach for clustering gene expression time series

MOTIVATION: There is a growing interest in extracting statistical patterns from gene expression time-series data, in which a key challenge is the development of stable and accurate probabilistic models. Currently popular models, however, would be computationally prohibitive unless some independence assumptions are made to describe large-scale data. We propose an unsupervised conditional random fields (CRF) model to overcome this problem by progressively infusing information into the labelling process through a small variable voting pool. RESULTS: An unsupervised CRF model is proposed for efficient analysis of gene expression time series and is successfully applied to gene class discovery and class prediction. The proposed model treats each time series as a random field and assigns an optimal cluster label to each time series, so as to partition the time series into clusters without a priori knowledge about the number of clusters and the initial centroids. Another advantage of the proposed method is the relaxation of independence assumptions.     

Drug-target interaction prediction by random walk on the heterogeneous network

Predicting potential drug-target interactions from heterogeneous biological data is critical not only for better understanding of the various interactions and biological processes, but also for the development of novel drugs and the improvement of human medicines. In this paper, the method of Network-based Random Walk with Restart on the Heterogeneous network (NRWRH) is developed to predict potential drug-target interactions on a large scale under the hypothesis that similar drugs often target similar target proteins and the framework of Random Walk. Compared with traditional supervised or semi-supervised methods, NRWRH makes full use of the tool of the network for data integration to predict drug-target associations. It integrates three different networks (protein-protein similarity network, drug-drug similarity network, and known drug-target interaction networks) into a heterogeneous network by known drug-target interactions and implements the random walk on this heterogeneous network. When applied to four classes of important drug-target interactions including enzymes, ion channels, GPCRs and nuclear receptors, NRWRH significantly improves previous methods in terms of cross-validation and potential drug-target interaction prediction. Excellent performance enables us to suggest a number of new potential drug-target interactions for drug development.     

Protein-protein interaction and quaternary structure

Protein-protein recognition plays an essential role in structure and function. Specific non-covalent interactions stabilize the structure of macromolecular assemblies, exemplified in this review by oligomeric proteins and the capsids of icosahedral viruses. They also allow proteins to form complexes that have a very wide range of stability and lifetimes and are involved in all cellular processes. We present some of the structure-based computational methods that have been developed to characterize the quaternary structure of oligomeric proteins and other molecular assemblies and analyze the properties of the interfaces between the subunits. We compare the size, the chemical and amino acid compositions and the atomic packing of the subunit interfaces of protein-protein complexes, oligomeric proteins, viral capsids and protein-nucleic acid complexes. These biologically significant interfaces are generally close-packed, whereas the non-specific interfaces between molecules in protein crystals are loosely packed, an observation that gives a structural basis to specific recognition. A distinction is made within each interface between a core that contains buried atoms and a solvent accessible rim. The core and the rim differ in their amino acid composition and their conservation in evolution, and the distinction helps correlating the structural data with the results of site-directed mutagenesis and in vitro studies of self-assembly.     

A conditional random fields method for RNA sequence-structure relationship modeling and conformation sampling

Accurate tertiary structures are very important for the functional study of non-coding RNA molecules. However, predicting RNA tertiary structures is extremely challenging, because of a large conformation space to be explored and lack of an accurate scoring function differentiating the native structure from decoys. The fragment-based conformation sampling method (e.g. FARNA) bears shortcomings that the limited size of a fragment library makes it infeasible to represent all possible conformations well. A recent dynamic Bayesian network method, BARNACLE, overcomes the issue of fragment assembly. In addition, neither of these methods makes use of sequence information in sampling conformations. Here, we present a new probabilistic graphical model, conditional random fields (CRFs), to model RNA sequence-structure relationship, which enables us to accurately estimate the probability of an RNA conformation from sequence. Coupled with a novel tree-guided sampling scheme, our CRF model is then applied to RNA conformation sampling. Experimental results show that our CRF method can model RNA sequence-structure relationship well and sequence information is important for conformation sampling. Our method, named as TreeFolder, generates a much higher percentage of native-like decoys than FARNA and BARNACLE, although we use the same simple energy function as BARNACLE. CONTACT: zywang@ttic.edu; j3xu@ttic.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.