Improved prediction of critical residues for protein function based on network and phylogenetic analyses

Background  

Phylogenetic approaches are commonly used to predict which amino acid residues are critical to the function of a given protein. However, such approaches display inherent limitations, such as the requirement for identification of multiple homologues of the protein under consideration. Therefore, complementary or alternative approaches for the prediction of critical residues would be desirable. Network analyses have been used in the modelling of many complex biological systems, but only very recently have they been used to predict critical residues from a protein's three-dimensional structure. Here we compare a couple of phylogenetic approaches to several different network-based methods for the prediction of critical residues, and show that a combination of one phylogenetic method and one network-based method is superior to other methods previously employed.     

Enhanced membrane protein topology prediction using a hierarchical classification method and a new scoring function

The prediction of transmembrane (TM) helix and topology provides important information about the structure and function of a membrane protein. Due to the experimental difficulties in obtaining a high-resolution model, computational methods are highly desirable. In this paper, we present a hierarchical classification method using support vector machines (SVMs) that integrates selected features by capturing the sequence-to-structure relationship and developing a new scoring function based on membrane protein folding. The proposed approach is evaluated on low- and high-resolution data sets with cross-validation, and the topology (sidedness) prediction accuracy reaches as high as 90%. Our method is also found to correctly predict both the location of TM helices and the topology for 69% of the low-resolution benchmark set. We also test our method for discrimination between soluble and membrane proteins and achieve very low overall false positive (0.5%) and false negative rates (0 to approximately 1.2%). Lastly, the analysis of the scoring function suggests that the topogeneses of single-spanning and multispanning TM proteins have different levels of complexity, and the consideration of interloop topogenic interactions for the latter is the key to achieving better predictions. This method can facilitate the annotation of membrane proteomes to extract useful structural and functional information. It is publicly available at http://bio-cluster.iis.sinica.edu.tw/~bioapp/SVMtop.     

A hierarchical approach to all-atom protein loop prediction

The application of all-atom force fields (and explicit or implicit solvent models) to protein homology-modeling tasks such as side-chain and loop prediction remains challenging both because of the expense of the individual energy calculations and because of the difficulty of sampling the rugged all-atom energy surface. Here we address this challenge for the problem of loop prediction through the development of numerous new algorithms, with an emphasis on multiscale and hierarchical techniques. As a first step in evaluating the performance of our loop prediction algorithm, we have applied it to the problem of reconstructing loops in native structures; we also explicitly include crystal packing to provide a fair comparison with crystal structures. In brief, large numbers of loops are generated by using a dihedral angle-based buildup procedure followed by iterative cycles of clustering, side-chain optimization, and complete energy minimization of selected loop structures. We evaluate this method by using the largest test set yet used for validation of a loop prediction method, with a total of 833 loops ranging from 4 to 12 residues in length. Average/median backbone root-mean-square deviations (RMSDs) to the native structures (superimposing the body of the protein, not the loop itself) are 0.42/0.24 A for 5 residue loops, 1.00/0.44 A for 8 residue loops, and 2.47/1.83 A for 11 residue loops. Median RMSDs are substantially lower than the averages because of a small number of outliers; the causes of these failures are examined in some detail, and many can be attributed to errors in assignment of protonation states of titratable residues, omission of ligands from the simulation, and, in a few cases, probable errors in the experimentally determined structures. When these obvious problems in the data sets are filtered out, average RMSDs to the native structures improve to 0.43 A for 5 residue loops, 0.84 A for 8 residue loops, and 1.63 A for 11 residue loops. In the vast majority of cases, the method locates energy minima that are lower than or equal to that of the minimized native loop, thus indicating that sampling rarely limits prediction accuracy. The overall results are, to our knowledge, the best reported to date, and we attribute this success to the combination of an accurate all-atom energy function, efficient methods for loop buildup and side-chain optimization, and, especially for the longer loops, the hierarchical refinement protocol.     

NetTurnP--neural network prediction of beta-turns by use of evolutionary information and predicted protein sequence features

β-turns are the most common type of non-repetitive structures, and constitute on average 25% of the amino acids in proteins. The formation of β-turns plays an important role in protein folding, protein stability and molecular recognition processes. In this work we present the neural network method NetTurnP, for prediction of two-class β-turns and prediction of the individual β-turn types, by use of evolutionary information and predicted protein sequence features. It has been evaluated against a commonly used dataset BT426, and achieves a Matthews correlation coefficient of 0.50, which is the highest reported performance on a two-class prediction of β-turn and not-β-turn. Furthermore NetTurnP shows improved performance on some of the specific β-turn types. In the present work, neural network methods have been trained to predict β-turn or not and individual β-turn types from the primary amino acid sequence. The individual β-turn types I, I', II, II', VIII, VIa1, VIa2, VIba and IV have been predicted based on classifications by PROMOTIF, and the two-class prediction of β-turn or not is a superset comprised of all β-turn types. The performance is evaluated using a golden set of non-homologous sequences known as BT426. Our two-class prediction method achieves a performance of: MCC=0.50, Qtotal=82.1%, sensitivity=75.6%, PPV=68.8% and AUC=0.864. We have compared our performance to eleven other prediction methods that obtain Matthews correlation coefficients in the range of 0.17-0.47. For the type specific β-turn predictions, only type I and II can be predicted with reasonable Matthews correlation coefficients, where we obtain performance values of 0.36 and 0.31, respectively. CONCLUSION: The NetTurnP method has been implemented as a webserver, which is freely available at http://www.cbs.dtu.dk/services/NetTurnP/. NetTurnP is the only available webserver that allows submission of multiple sequences.     

Network-based auto-probit modeling for protein function prediction

Predicting the functional roles of proteins based on various genome-wide data, such as protein-protein association networks, has become a canonical problem in computational biology. Approaching this task as a binary classification problem, we develop a network-based extension of the spatial auto-probit model. In particular, we develop a hierarchical Bayesian probit-based framework for modeling binary network-indexed processes, with a latent multivariate conditional autoregressive Gaussian process. The latter allows for the easy incorporation of protein-protein association network topologies-either binary or weighted-in modeling protein functional similarity. We use this framework to predict protein functions, for functions defined as terms in the Gene Ontology (GO) database, a popular rigorous vocabulary for biological functionality. Furthermore, we show how a natural extension of this framework can be used to model and correct for the high percentage of false negative labels in training data derived from GO, a serious shortcoming endemic to biological databases of this type. Our method performance is evaluated and compared with standard algorithms on weighted yeast protein-protein association networks, extracted from a recently developed integrative database called Search Tool for the Retrieval of INteracting Genes/proteins (STRING). Results show that our basic method is competitive with these other methods, and that the extended method-incorporating the uncertainty in negative labels among the training data-can yield nontrivial improvements in predictive accuracy.     

Consistent probabilistic outputs for protein function prediction

Background:

The wide availability of genome-scale data for several organisms has stimulated interest in computational approaches to gene function prediction. Diverse machine learning methods have been applied to unicellular organisms with some success, but few have been extensively tested on higher level, multicellular organisms. A recent mouse function prediction project (MouseFunc) brought together nine bioinformatics teams applying a diverse array of methodologies to mount the first large-scale effort to predict gene function in the laboratory mouse.

Results:

In this paper, we describe our contribution to this project, an ensemble framework based on the support vector machine that integrates diverse datasets in the context of the Gene Ontology hierarchy. We carry out a detailed analysis of the performance of our ensemble and provide insights into which methods work best under a variety of prediction scenarios. In addition, we applied our method to Saccharomyces cerevisiae and have experimentally confirmed functions for a novel mitochondrial protein.

Conclusion:

Our method consistently performs among the top methods in the MouseFunc evaluation. Furthermore, it exhibits good classification performance across a variety of cellular processes and functions in both a multicellular organism and a unicellular organism, indicating its ability to discover novel biology in diverse settings.

     

Machine learning techniques for protein function prediction

Proteins play important roles in living organisms, and their function is directly linked with their structure. Due to the growing gap between the number of proteins being discovered and their functional characterization (in particular as a result of experimental limitations), reliable prediction of protein function through computational means has become crucial. This paper reviews the machine learning techniques used in the literature, following their evolution from simple algorithms such as logistic regression to more advanced methods like support vector machines and modern deep neural networks. Hyperparameter optimization methods adopted to boost prediction performance are presented. In parallel, the metamorphosis in the features used by these algorithms from classical physicochemical properties and amino acid composition, up to text-derived features from biomedical literature and learned feature representations using autoencoders, together with feature selection and dimensionality reduction techniques, are also reviewed. The success stories in the application of these techniques to both general and specific protein function prediction are discussed.     

Consistent probabilistic outputs for protein function prediction

In predicting hierarchical protein function annotations, such as terms in the Gene Ontology (GO), the simplest approach makes predictions for each term independently. However, this approach has the unfortunate consequence that the predictor may assign to a single protein a set of terms that are inconsistent with one another; for example, the predictor may assign a specific GO term to a given protein ('purine nucleotide binding') but not assign the parent term ('nucleotide binding'). Such predictions are difficult to interpret. In this work, we focus on methods for calibrating and combining independent predictions to obtain a set of probabilistic predictions that are consistent with the topology of the ontology. We call this procedure 'reconciliation'. We begin with a baseline method for predicting GO terms from a collection of data types using an ensemble of discriminative classifiers. We apply the method to a previously described benchmark data set, and we demonstrate that the resulting predictions are frequently inconsistent with the topology of the GO. We then consider 11 distinct reconciliation methods: three heuristic methods; four variants of a Bayesian network; an extension of logistic regression to the structured case; and three novel projection methods - isotonic regression and two variants of a Kullback-Leibler projection method. We evaluate each method in three different modes - per term, per protein and joint - corresponding to three types of prediction tasks. Although the principal goal of reconciliation is interpretability, it is important to assess whether interpretability comes at a cost in terms of precision and recall. Indeed, we find that many apparently reasonable reconciliation methods yield reconciled probabilities with significantly lower precision than the original, unreconciled estimates. On the other hand, we find that isotonic regression usually performs better than the underlying, unreconciled method, and almost never performs worse; isotonic regression appears to be able to use the constraints from the GO network to its advantage. An exception to this rule is the high precision regime for joint evaluation, where Kullback-Leibler projection yields the best performance.     

Combining evolutionary and structural information for local protein structure prediction

We study the effects of various factors in representing and combining evolutionary and structural information for local protein structural prediction based on fragment selection. We prepare databases of fragments from a set of non-redundant protein domains. For each fragment, evolutionary information is derived from homologous sequences and represented as estimated effective counts and frequencies of amino acids (evolutionary frequencies) at each position. Position-specific amino acid preferences called structural frequencies are derived from statistical analysis of discrete local structural environments in database structures. Our method for local structure prediction is based on ranking and selecting database fragments that are most similar to a target fragment. Using secondary structure type as a local structural property, we test our method in a number of settings. The major findings are: (1) the COMPASS-type scoring function for fragment similarity comparison gives better prediction accuracy than three other tested scoring functions for profile-profile comparison. We show that the COMPASS-type scoring function can be derived both in the probabilistic framework and in the framework of statistical potentials. (2) Using the evolutionary frequencies of database fragments gives better prediction accuracy than using structural frequencies. (3) Finer definition of local environments, such as including more side-chain solvent accessibility classes and considering the backbone conformations of neighboring residues, gives increasingly better prediction accuracy using structural frequencies. (4) Combining evolutionary and structural frequencies of database fragments, either in a linear fashion or using a pseudocount mixture formula, results in improvement of prediction accuracy. Combination at the log-odds score level is not as effective as combination at the frequency level. This suggests that there might be better ways of combining sequence and structural information than the commonly used linear combination of log-odds scores. Our method of fragment selection and frequency combination gives reasonable results of secondary structure prediction tested on 56 CASP5 targets (average SOV score 0.77), suggesting that it is a valid method for local protein structure prediction. Mixture of predicted structural frequencies and evolutionary frequencies improve the quality of local profile-to-profile alignment by COMPASS.     

A protocol for computer-based protein structure and function prediction

Genome sequencing projects have ciphered millions of protein sequence, which require knowledge of their structure and function to improve the understanding of their biological role. Although experimental methods can provide detailed information for a small fraction of these proteins, computational modeling is needed for the majority of protein molecules which are experimentally uncharacterized. The I-TASSER server is an on-line workbench for high-resolution modeling of protein structure and function. Given a protein sequence, a typical output from the I-TASSER server includes secondary structure prediction, predicted solvent accessibility of each residue, homologous template proteins detected by threading and structure alignments, up to five full-length tertiary structural models, and structure-based functional annotations for enzyme classification, Gene Ontology terms and protein-ligand binding sites. All the predictions are tagged with a confidence score which tells how accurate the predictions are without knowing the experimental data. To facilitate the special requests of end users, the server provides channels to accept user-specified inter-residue distance and contact maps to interactively change the I-TASSER modeling; it also allows users to specify any proteins as template, or to exclude any template proteins during the structure assembly simulations. The structural information could be collected by the users based on experimental evidences or biological insights with the purpose of improving the quality of I-TASSER predictions. The server was evaluated as the best programs for protein structure and function predictions in the recent community-wide CASP experiments. There are currently >20,000 registered scientists from over 100 countries who are using the on-line I-TASSER server.     

Using search engine technology for protein function prediction

Prediction of protein function is one of the most challenging problems in the post-genomic era. In this paper, we propose a novel algorithm Improved ProteinRank (IPR) for protein function prediction, which is based on the search engine technology and the preferential attachment criteria. In addition, an improved algorithm IPRW is developed from IPR to be used in the weighted protein?protein interaction (PPI) network. The proposed algorithms IPR and IPRW are applied to the PPI network of S.cerevisiae. The experimental results show that both IPR and IPRW outweigh the previous methods for the prediction of protein functions.     

A partially function-to-topic model for protein function prediction

Background

Proteins are a kind of macromolecules and the main component of a cell, and thus it is the most essential and versatile material of life. The research of protein functions is of great significance in decoding the secret of life. In recent years, researchers have introduced multi-label supervised topic model such as Labeled Latent Dirichlet Allocation (Labeled-LDA) into protein function prediction, which can obtain more accurate and explanatory prediction. However, the topic-label corresponding way of Labeled-LDA is associating each label (GO term) with a corresponding topic directly, which makes the latent topics to be completely degenerated, and ignores the differences between labels and latent topics.

Result

To achieve more accurate probabilistic modeling of function label, we propose a Partially Function-to-Topic Prediction (PFTP) model for introducing the local topics subset corresponding to each function label. Meanwhile, PFTP not only supports latent topics subset within a given function label but also a background topic corresponding to a ‘fake’ function label, which represents common semantic of protein function. Related definitions and the topic modeling process of PFTP are described in this paper. In a 5-fold cross validation experiment on yeast and human datasets, PFTP significantly outperforms five widely adopted methods for protein function prediction. Meanwhile, the impact of model parameters on prediction performance and the latent topics discovered by PFTP are also discussed in this paper.

Conclusion

All of the experimental results provide evidence that PFTP is effective and have potential value for predicting protein function. Based on its ability of discovering more-refined latent sub-structure of function label, we can anticipate that PFTP is a potential method to reveal a deeper biological explanation for protein functions.

     

Scoring function accuracy for membrane protein structure prediction

We perform a systematic examination of the ability of several different high-resolution, atomic-detail scoring functions to discriminate native conformations of loops in membrane proteins from non-native but physically reasonable, or "decoy," conformations. Decoys constructed from changing a loop conformation while keeping the remainder of the protein fixed are a challenging test of energy function accuracy. Nevertheless, the best of the energy functions we examined recognized the native structure as lowest in energy around half the time, and consistently chose it as a low-energy structure. This suggests that the best of present energy functions, even without a representation of the lipid bilayer, are of sufficient accuracy to give reasonable confidence in predictions of membrane protein structure. We also constructed homology models for each structure, using other known structures in the same protein family as templates. Homology models were constructed using several scoring functions and modeling programs, but with a comparable sampling effort for each procedure. Our results indicate that the quality of sequence alignment is probably the most important factor in model accuracy for sequence identity from 20-40%; one can expect a reasonably accurate model for membrane proteins when sequence identity is greater than 30%, in agreement with previous studies. Most errors are localized in loop regions, which tend to be found outside the lipid bilayer. For the most discriminative energy functions, it appears that errors are most likely due to lack of sufficient sampling, although it should be stressed that present energy functions are still far from perfectly reliable.     

面向蛋白质功能位点识别的机器学习平台构建

有关蛋白质功能的研究是解析生命奥秘的基础,机器学习技术在该领域已有广泛应用。利用支持向量机(support vectormachine,SVM)方法,构建一个预测蛋白质功能位点的通用平台。该平台先提取非同源蛋白质序列,再对这些序列进行特征编码(包括序列的基本信息、物化特征、结构信息及序列保守性特征等),以编码好的样本作为训练数据,利用SVM进行训练,得到敏感性、特异性、Matthew相关系数、准确率及ROC曲线等评价指标,反复测试,得到评价指标最优的SVM模型后,便可以用来预测蛋白质序列上的功能位点。该平台除了应用在预测蛋白质功能位点之外,还可以应用于疾病相关单核苷酸多态性(SNP)预测分析、预测蛋白质结构域分析、生物分子间的相互作用等。     

A deep dense inception network for protein beta-turn prediction

Beta-turn prediction is useful in protein function studies and experimental design. Although recent approaches using machine-learning techniques such as support vector machine (SVM), neural networks, and K nearest neighbor have achieved good results for beta-turn prediction, there is still significant room for improvement. As previous predictors utilized features in a sliding window of 4-20 residues to capture interactions among sequentially neighboring residues, such feature engineering may result in incomplete or biased features and neglect interactions among long-range residues. Deep neural networks provide a new opportunity to address these issues. Here, we proposed a deep dense inception network (DeepDIN) for beta-turn prediction, which takes advantage of the state-of-the-art deep neural network design of dense networks and inception networks. A test on a recent BT6376 benchmark data set shows that DeepDIN outperformed the previous best tool BetaTPred3 significantly in both the overall prediction accuracy and the nine-type beta-turn classification accuracy. A tool, called MUFold-BetaTurn, was developed, which is the first beta-turn prediction tool utilizing deep neural networks. The tool can be downloaded at http://dslsrv8.cs.missouri.edu/~cf797/MUFoldBetaTurn/download.html .     

ncRNA-disease association prediction based on sequence information and tripartite network

Background

Current technology has demonstrated that mutation and deregulation of non-coding RNAs (ncRNAs) are associated with diverse human diseases and important biological processes. Therefore, developing a novel computational method for predicting potential ncRNA-disease associations could benefit pathologists in understanding the correlation between ncRNAs and disease diagnosis, treatment, and prevention. However, only a few studies have investigated these associations in pathogenesis.

Results

This study utilizes a disease-target-ncRNA tripartite network, and computes prediction scores between each disease-ncRNA pair by integrating biological information derived from pairwise similarity based upon sequence expressions with weights obtained from a multi-layer resource allocation technique. Our proposed algorithm was evaluated based on a 5-fold-cross-validation with optimal kernel parameter tuning. In addition, we achieved an average AUC that varies from 0.75 without link cut to 0.57 with link cut methods, which outperforms a previous method using the same evaluation methodology. Furthermore, the algorithm predicted 23 ncRNA-disease associations supported by other independent biological experimental studies.

Conclusions

Taken together, these results demonstrate the capability and accuracy of predicting further biological significant associations between ncRNAs and diseases and highlight the importance of adding biological sequence information to enhance predictions.

     

Diffusion kernel-based logistic regression models for protein function prediction

Assigning functions to unknown proteins is one of the most important problems in proteomics. Several approaches have used protein-protein interaction data to predict protein functions. We previously developed a Markov random field (MRF) based method to infer a protein's functions using protein-protein interaction data and the functional annotations of its protein interaction partners. In the original model, only direct interactions were considered and each function was considered separately. In this study, we develop a new model which extends direct interactions to all neighboring proteins, and one function to multiple functions. The goal is to understand a protein's function based on information on all the neighboring proteins in the interaction network. We first developed a novel kernel logistic regression (KLR) method based on diffusion kernels for protein interaction networks. The diffusion kernels provide means to incorporate all neighbors of proteins in the network. Second, we identified a set of functions that are highly correlated with the function of interest, referred to as the correlated functions, using the chi-square test. Third, the correlated functions were incorporated into our new KLR model. Fourth, we extended our model by incorporating multiple biological data sources such as protein domains, protein complexes, and gene expressions by converting them into networks. We showed that the KLR approach of incorporating all protein neighbors significantly improved the accuracy of protein function predictions over the MRF model. The incorporation of multiple data sets also improved prediction accuracy. The prediction accuracy is comparable to another protein function classifier based on the support vector machine (SVM), using a diffusion kernel. The advantages of the KLR model include its simplicity as well as its ability to explore the contribution of neighbors to the functions of proteins of interest.