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.     

Predicting protein functions from PPI networks using functional aggregation

Predicting protein functions computationally from massive protein-protein interaction (PPI) data generated by high-throughput technology is one of the challenges and fundamental problems in the post-genomic era. Although there have been many approaches developed for computationally predicting protein functions, the mutual correlations among proteins in terms of protein functions have not been thoroughly investigated and incorporated into existing prediction methods, especially in voting based prediction methods. In this paper, we propose an innovative method to predict protein functions from PPI data by aggregating the functional correlations among relevant proteins using the Choquet-Integral in fuzzy theory. This functional aggregation measures the real impact of each relevant protein function on the final prediction results, and reduces the impact of repeated functional information on the prediction. Accordingly, a new protein similarity and a new iterative prediction algorithm are proposed in this paper. The experimental evaluations on real PPI datasets demonstrate the effectiveness of our method.     

Bayesian Markov Random Field Analysis for Protein Function Prediction Based on Network Data

Inference of protein functions is one of the most important aims of modern biology. To fully exploit the large volumes of genomic data typically produced in modern-day genomic experiments, automated computational methods for protein function prediction are urgently needed. Established methods use sequence or structure similarity to infer functions but those types of data do not suffice to determine the biological context in which proteins act. Current high-throughput biological experiments produce large amounts of data on the interactions between proteins. Such data can be used to infer interaction networks and to predict the biological process that the protein is involved in. Here, we develop a probabilistic approach for protein function prediction using network data, such as protein-protein interaction measurements. We take a Bayesian approach to an existing Markov Random Field method by performing simultaneous estimation of the model parameters and prediction of protein functions. We use an adaptive Markov Chain Monte Carlo algorithm that leads to more accurate parameter estimates and consequently to improved prediction performance compared to the standard Markov Random Fields method. We tested our method using a high quality S.cereviciae validation network with 1622 proteins against 90 Gene Ontology terms of different levels of abstraction. Compared to three other protein function prediction methods, our approach shows very good prediction performance. Our method can be directly applied to protein-protein interaction or coexpression networks, but also can be extended to use multiple data sources. We apply our method to physical protein interaction data from S. cerevisiae and provide novel predictions, using 340 Gene Ontology terms, for 1170 unannotated proteins and we evaluate the predictions using the available literature.     

Using indirect protein-protein interactions for protein complex prediction

Protein complexes are fundamental for understanding principles of cellular organizations. As the sizes of protein-protein interaction (PPI) networks are increasing, accurate and fast protein complex prediction from these PPI networks can serve as a guide for biological experiments to discover novel protein complexes. However, it is not easy to predict protein complexes from PPI networks, especially in situations where the PPI network is noisy and still incomplete. Here, we study the use of indirect interactions between level-2 neighbors (level-2 interactions) for protein complex prediction. We know from previous work that proteins which do not interact but share interaction partners (level-2 neighbors) often share biological functions. We have proposed a method in which all direct and indirect interactions are first weighted using topological weight (FS-Weight), which estimates the strength of functional association. Interactions with low weight are removed from the network, while level-2 interactions with high weight are introduced into the interaction network. Existing clustering algorithms can then be applied to this modified network. We have also proposed a novel algorithm that searches for cliques in the modified network, and merge cliques to form clusters using a "partial clique merging" method. Experiments show that (1) the use of indirect interactions and topological weight to augment protein-protein interactions can be used to improve the precision of clusters predicted by various existing clustering algorithms; and (2) our complex-finding algorithm performs very well on interaction networks modified in this way. Since no other information except the original PPI network is used, our approach would be very useful for protein complex prediction, especially for prediction of novel protein complexes.     

Prediction of Heterodimeric Protein Complexes from Weighted Protein-Protein Interaction Networks Using Novel Features and Kernel Functions

Since many proteins express their functional activity by interacting with other proteins and forming protein complexes, it is very useful to identify sets of proteins that form complexes. For that purpose, many prediction methods for protein complexes from protein-protein interactions have been developed such as MCL, MCODE, RNSC, PCP, RRW, and NWE. These methods have dealt with only complexes with size of more than three because the methods often are based on some density of subgraphs. However, heterodimeric protein complexes that consist of two distinct proteins occupy a large part according to several comprehensive databases of known complexes. In this paper, we propose several feature space mappings from protein-protein interaction data, in which each interaction is weighted based on reliability. Furthermore, we make use of prior knowledge on protein domains to develop feature space mappings, domain composition kernel and its combination kernel with our proposed features. We perform ten-fold cross-validation computational experiments. These results suggest that our proposed kernel considerably outperforms the naive Bayes-based method, which is the best existing method for predicting heterodimeric protein complexes.     

Highly accurate method for ligand-binding site prediction in unbound state (apo) protein structures

This article describes a new method for predicting ligand-binding sites of proteins. The method involves calculating the van der Waals interaction energy between a protein and probes placed on the protein surface, and then clustering the probes with attractive interaction to find the energetically most favorable locus. In 80% (28/35) of the test cases, the ligand-binding site was successfully predicted on a ligand-bound protein structure, and in 77% (27/35) was successfully predicted on an unbound structure. Our method was used to successfully predict ligand-binding sites unaffected by induced-fit as long as its scales were not very large, and it contributed to a significant improvement in prediction with unbound state protein structures. This represents a significant advance over conventional methods in detecting ligand-binding sites on uncharacterized proteins. Moreover, our method can predict ligand-binding sites with a narrower locus than those achieved using conventional methods.     

Inferring function using patterns of native disorder in proteins

Natively unstructured regions are a common feature of eukaryotic proteomes. Between 30% and 60% of proteins are predicted to contain long stretches of disordered residues, and not only have many of these regions been confirmed experimentally, but they have also been found to be essential for protein function. In this study, we directly address the potential contribution of protein disorder in predicting protein function using standard Gene Ontology (GO) categories. Initially we analyse the occurrence of protein disorder in the human proteome and report ontology categories that are enriched in disordered proteins. Pattern analysis of the distributions of disordered regions in human sequences demonstrated that the functions of intrinsically disordered proteins are both length- and position-dependent. These dependencies were then encoded in feature vectors to quantify the contribution of disorder in human protein function prediction using Support Vector Machine classifiers. The prediction accuracies of 26 GO categories relating to signalling and molecular recognition are improved using the disorder features. The most significant improvements were observed for kinase, phosphorylation, growth factor, and helicase categories. Furthermore, we provide predicted GO term assignments using these classifiers for a set of unannotated and orphan human proteins. In this study, the importance of capturing protein disorder information and its value in function prediction is demonstrated. The GO category classifiers generated can be used to provide more reliable predictions and further insights into the behaviour of orphan and unannotated proteins.     

Widely predicting specific protein functions based on protein-protein interaction data and gene expression profile

GESTs (gene expression similarity and taxonomy similarity), a gene functional prediction approach previously proposed by us, is based on gene expression similarity and concept similarity of functional classes defined in Gene Ontology (GO). In this paper, we extend this method to protein-protein interaction data by introducing several methods to filter the neighbors in protein interaction networks for a protein of unknown function(s). Unlike other conventional methods, the proposed approach automatically selects the most appropriate functional classes as specific as possible during the learning process, and calls on genes annotated to nearby classes to support the predictions to some small-sized specific classes in GO. Based on the yeast protein-protein interaction information from MIPS and a dataset of gene expression profiles, we assess the performances of our approach for predicting protein functions to “biology process” by three measures particularly designed for functional classes organized in GO. Results show that our method is powerful for widely predicting gene functions with very specific functional terms. Based on the GO database published in December 2004, we predict some proteins whose functions were unknown at that time, and some of the predictions have been confirmed by the new SGD annotation data published in April, 2006.     

从氨基酸序列预测蛋白质折叠速率

蛋白质折叠速率预测是当今生物物理学最具挑战性的课题之一．近年来,许多科研工作者开展了大量的研究工作来探索折叠速率的决定因素,许多参数和方法被相继提出．但氨基酸残基间的相互作用、氨基酸的序列顺序等信息对折叠速率的影响从未被提及．采用伪氨基酸组成的方法提取氨基酸的序列顺序信息,利用蒙特卡洛方法选择最佳特征因子,建立线性回归模型进行折叠速率预测．该方法能在不需要任何(显示)结构信息的情况下,直接从蛋白质的氨基酸序列出发对折叠速率进行预测．在Jackknife交互检验方法的验证下,对含有99个蛋白质的数据集,发现折叠速率的预测值与实验值有很好的相关性,相关系数能达到0.81,预测误差仅为2.54．这一精度明显优于其他基于序列的方法,充分说明蛋白质的序列顺序信息是影响蛋白质折叠速率的重要因素．     

Widely predicting specific protein functions based on protein-protein interaction data and gene expression profile

GESTs (gene expression similarity and taxonomy similarity), a gene functional prediction approach previously proposed by us, is based on gene expression similarity and concept similarity of functional classes defined in Gene Ontology (GO). In this paper, we extend this method to protein-protein interac-tion data by introducing several methods to filter the neighbors in protein interaction networks for a protein of unknown function(s). Unlike other conventional methods, the proposed approach automati-cally selects the most appropriate functional classes as specific as possible during the learning proc-ess, and calls on genes annotated to nearby classes to support the predictions to some small-sized specific classes in GO. Based on the yeast protein-protein interaction information from MIPS and a dataset of gene expression profiles, we assess the performances of our approach for predicting protein functions to “biology process” by three measures particularly designed for functional classes organ-ized in GO. Results show that our method is powerful for widely predicting gene functions with very specific functional terms. Based on the GO database published in December 2004, we predict some proteins whose functions were unknown at that time, and some of the predictions have been confirmed by the new SGD annotation data published in April, 2006.     

Identify submitochondria and subchloroplast locations with pseudo amino acid composition: Approach from the strategy of discrete wavelet transform feature extraction

It is very challenging and complicated to predict protein locations at the sub-subcellular level. The key to enhancing the prediction quality for protein sub-subcellular locations is to grasp the core features of a protein that can discriminate among proteins with different subcompartment locations. In this study, a different formulation of pseudoamino acid composition by the approach of discrete wavelet transform feature extraction was developed to predict submitochondria and subchloroplast locations. As a result of jackknife cross-validation, with our method, it can efficiently distinguish mitochondrial proteins from chloroplast proteins with total accuracy of 98.8% and obtained a promising total accuracy of 93.38% for predicting submitochondria locations. Especially the predictive accuracy for mitochondrial outer membrane and chloroplast thylakoid lumen were 82.93% and 82.22%, respectively, showing an improvement of 4.88% and 27.22% when other existing methods were compared. The results indicated that the proposed method might be employed as a useful assistant technique for identifying sub-subcellular locations. We have implemented our algorithm as an online service called SubIdent (http://bioinfo.ncu.edu.cn/services.aspx).     

Accuracy improvement in protein complex prediction from protein interaction networks by refining cluster overlaps

Background

Recent computational techniques have facilitated analyzing genome-wide protein-protein interaction data for several model organisms. Various graph-clustering algorithms have been applied to protein interaction networks on the genomic scale for predicting the entire set of potential protein complexes. In particular, the density-based clustering algorithms which are able to generate overlapping clusters, i.e. the clusters sharing a set of nodes, are well-suited to protein complex detection because each protein could be a member of multiple complexes. However, their accuracy is still limited because of complex overlap patterns of their output clusters.

Results

We present a systematic approach of refining the overlapping clusters identified from protein interaction networks. We have designed novel metrics to assess cluster overlaps: overlap coverage and overlapping consistency. We then propose an overlap refinement algorithm. It takes as input the clusters produced by existing density-based graph-clustering methods and generates a set of refined clusters by parameterizing the metrics. To evaluate protein complex prediction accuracy, we used the f-measure by comparing each refined cluster to known protein complexes. The experimental results with the yeast protein-protein interaction data sets from BioGRID and DIP demonstrate that accuracy on protein complex prediction has increased significantly after refining cluster overlaps.

Conclusions

The effectiveness of the proposed cluster overlap refinement approach for protein complex detection has been validated in this study. Analyzing overlaps of the clusters from protein interaction networks is a crucial task for understanding of functional roles of proteins and topological characteristics of the functional systems.

     

Predicting Human Protein Subcellular Locations by the Ensemble of Multiple Predictors via Protein-Protein Interaction Network with Edge Clustering Coefficients

One of the fundamental tasks in biology is to identify the functions of all proteins to reveal the primary machinery of a cell. Knowledge of the subcellular locations of proteins will provide key hints to reveal their functions and to understand the intricate pathways that regulate biological processes at the cellular level. Protein subcellular location prediction has been extensively studied in the past two decades. A lot of methods have been developed based on protein primary sequences as well as protein-protein interaction network. In this paper, we propose to use the protein-protein interaction network as an infrastructure to integrate existing sequence based predictors. When predicting the subcellular locations of a given protein, not only the protein itself, but also all its interacting partners were considered. Unlike existing methods, our method requires neither the comprehensive knowledge of the protein-protein interaction network nor the experimentally annotated subcellular locations of most proteins in the protein-protein interaction network. Besides, our method can be used as a framework to integrate multiple predictors. Our method achieved 56% on human proteome in absolute-true rate, which is higher than the state-of-the-art methods.     

Structural interpretation of protein-protein interaction network

Background

Currently a huge amount of protein-protein interaction data is available from high throughput experimental methods. In a large network of protein-protein interactions, groups of proteins can be identified as functional clusters having related functions where a single protein can occur in multiple clusters. However experimental methods are error-prone and thus the interactions in a functional cluster may include false positives or there may be unreported interactions. Therefore correctly identifying a functional cluster of proteins requires the knowledge of whether any two proteins in a cluster interact, whether an interaction can exclude other interactions, or how strong the affinity between two interacting proteins is.

Methods

In the present work the yeast protein-protein interaction network is clustered using a spectral clustering method proposed by us in 2006 and the individual clusters are investigated for functional relationships among the member proteins. 3D structural models of the proteins in one cluster have been built – the protein structures are retrieved from the Protein Data Bank or predicted using a comparative modeling approach. A rigid body protein docking method (Cluspro) is used to predict the protein-protein interaction complexes. Binding sites of the docked complexes are characterized by their buried surface areas in the docked complexes, as a measure of the strength of an interaction.

Results

The clustering method yields functionally coherent clusters. Some of the interactions in a cluster exclude other interactions because of shared binding sites. New interactions among the interacting proteins are uncovered, and thus higher order protein complexes in the cluster are proposed. Also the relative stability of each of the protein complexes in the cluster is reported.

Conclusions

Although the methods used are computationally expensive and require human intervention and judgment, they can identify the interactions that could occur together or ones that are mutually exclusive. In addition indirect interactions through another intermediate protein can be identified. These theoretical predictions might be useful for crystallographers to select targets for the X-ray crystallographic determination of protein complexes.

     

Globally predicting protein functions based on co-expressed protein-protein interaction networks and ontology taxonomy similarities

Determining protein functions is an important task in the post-genomic era. Most of the current methods work on some large-sized functional classes selected from functional categorization systems prior to the prediction processes. GESTs, a prediction approach previously proposed by us, is based on gene expression similarity and taxonomy similarity of the functional classes. Unlike many conventional methods, it does not require pre-selecting the functional classes and can predict specific functions for genes according to the functional annotations of their co-expressed genes. In this paper, we extend this method for analyzing protein-protein interaction data. We introduce gene expression data to filter the interacting neighbors of a protein in order to enhance the degree of functional consensus among the neighbors. Using the taxonomy similarity of protein functional classes, the proposed approach can call on the interacting neighbor proteins annotated to nearby classes to support the predictions for an uncharacterized protein, and automatically select the most appropriate small-sized specific functional classes in Gene Ontology (GO) during the learning process. By three measures particularly designed for the functional classes organized in GO, we evaluate the effects of using different taxonomy similarity scores on the prediction performance. Based on the yeast protein-protein interaction data from MIPS and a dataset of gene expression profiles, we show that this method is powerful for predicting protein function to very specific terms. Compared with the other two taxonomy similarity measures used in this study, if we want to achieve higher prediction accuracy with an acceptable specific level (predicted depth), SB-TS measure proposed by us is a reasonable choice for ontology-based functional predictions.     

A computational model for predicting protein interactions based on multidomain collaboration

Recently, several domain-based computational models for predicting protein-protein interactions (PPIs) have been proposed. The conventional methods usually infer domain or domain combination (DC) interactions from already known interacting sets of proteins, and then predict PPIs using the information. However, the majority of these models often have limitations in providing detailed information on which domain pair (single domain interaction) or DC pair (multidomain interaction) will actually interact for the predicted protein interaction. Therefore, a more comprehensive and concrete computational model for the prediction of PPIs is needed. We developed a computational model to predict PPIs using the information of intraprotein domain cohesion and interprotein DC coupling interaction. A method of identifying the primary interacting DC pair was also incorporated into the model in order to infer actual participants in a predicted interaction. Our method made an apparent improvement in the PPI prediction accuracy, and the primary interacting DC pair identification was valid specifically in predicting multidomain protein interactions. In this paper, we demonstrate that 1) the intraprotein domain cohesion is meaningful in improving the accuracy of domain-based PPI prediction, 2) a prediction model incorporating the intradomain cohesion enables us to identify the primary interacting DC pair, and 3) a hybrid approach using the intra/interdomain interaction information can lead to a more accurate prediction.     

Prediction of subcellular location apoptosis proteins with ensemble classifier and feature selection

Apoptosis proteins have a central role in the development and the homeostasis of an organism. These proteins are very important for understanding the mechanism of programmed cell death. The function of an apoptosis protein is closely related to its subcellular location. It is crucial to develop powerful tools to predict apoptosis protein locations for rapidly increasing gap between the number of known structural proteins and the number of known sequences in protein databank. In this study, amino acids pair compositions with different spaces are used to construct feature sets for representing sample of protein feature selection approach based on binary particle swarm optimization, which is applied to extract effective feature. Ensemble classifier is used as prediction engine, of which the basic classifier is the fuzzy K-nearest neighbor. Each basic classifier is trained with different feature sets. Two datasets often used in prior works are selected to validate the performance of proposed approach. The results obtained by jackknife test are quite encouraging, indicating that the proposed method might become a potentially useful tool for subcellular location of apoptosis protein, or at least can play a complimentary role to the existing methods in the relevant areas. The supplement information and software written in Matlab are available by contacting the corresponding author.     

基于深度学习与多层次信息融合的药物靶标亲和力预测*

药物研发是非常重要但也十分耗费人力物力的过程。利用计算机辅助预测药物与蛋白质亲和力的方法可以极大地加快药物研发过程。药物靶标亲和力预测的关键在于对药物和蛋白质进行准确详细地信息表征。提出一种基于深度学习与多层次信息融合的药物靶标亲和力的预测模型,试图通过综合药物与蛋白质的多层次信息,来获得更好的预测表现。首先将药物表述成分子图和扩展连接指纹两种形式,分别利用图卷积神经网络模块和全连接层进行学习;其次将蛋白质序列和蛋白质K-mer特征分别输入卷积神经网络模块和全连接层来学习蛋白质潜在特征;随后将4个通道学习到的特征进行融合,再利用全连接层进行预测。在两个基准药物靶标亲和力数据集上验证了所提方法的有效性,并与其他已有模型作对比研究。结果说明提出的模型相比基准模型能得到更好的预测性能,表明提出的综合药物与蛋白质多层次信息的药物靶标亲和力预测策略是有效的。     

mPLR-Loc: An adaptive decision multi-label classifier based on penalized logistic regression for protein subcellular localization prediction

Proteins located in appropriate cellular compartments are of paramount importance to exert their biological functions. Prediction of protein subcellular localization by computational methods is required in the post-genomic era. Recent studies have been focusing on predicting not only single-location proteins but also multi-location proteins. However, most of the existing predictors are far from effective for tackling the challenges of multi-label proteins. This article proposes an efficient multi-label predictor, namely mPLR-Loc, based on penalized logistic regression and adaptive decisions for predicting both single- and multi-location proteins. Specifically, for each query protein, mPLR-Loc exploits the information from the Gene Ontology (GO) database by using its accession number (AC) or the ACs of its homologs obtained via BLAST. The frequencies of GO occurrences are used to construct feature vectors, which are then classified by an adaptive decision-based multi-label penalized logistic regression classifier. Experimental results based on two recent stringent benchmark datasets (virus and plant) show that mPLR-Loc remarkably outperforms existing state-of-the-art multi-label predictors. In addition to being able to rapidly and accurately predict subcellular localization of single- and multi-label proteins, mPLR-Loc can also provide probabilistic confidence scores for the prediction decisions. For readers’ convenience, the mPLR-Loc server is available online (http://bioinfo.eie.polyu.edu.hk/mPLRLocServer).     

Enhancing interacting residue prediction with integrated contact matrix prediction in protein-protein interaction

Identifying the residues in a protein that are involved in protein-protein interaction and identifying the contact matrix for a pair of interacting proteins are two computational tasks at different levels of an in-depth analysis of protein-protein interaction. Various methods for solving these two problems have been reported in the literature. However, the interacting residue prediction and contact matrix prediction were handled by and large independently in those existing methods, though intuitively good prediction of interacting residues will help with predicting the contact matrix. In this work, we developed a novel protein interacting residue prediction system, contact matrix-interaction profile hidden Markov model (CM-ipHMM), with the integration of contact matrix prediction and the ipHMM interaction residue prediction. We propose to leverage what is learned from the contact matrix prediction and utilize the predicted contact matrix as “feedback” to enhance the interaction residue prediction. The CM-ipHMM model showed significant improvement over the previous method that uses the ipHMM for predicting interaction residues only. It indicates that the downstream contact matrix prediction could help the interaction site prediction.