Predicting protein function from protein/protein interaction data: a probabilistic approach

MOTIVATION:The development of experimental methods for genome scale analysis of molecular interaction networks has made possible new approaches to inferring protein function. This paper describes a method of assigning functions based on a probabilistic analysis of graph neighborhoods in a protein-protein interaction network. The method exploits the fact that graph neighbors are more likely to share functions than nodes which are not neighbors. A binomial model of local neighbor function labeling probability is combined with a Markov random field propagation algorithm to assign function probabilities for proteins in the network. RESULTS: We applied the method to a protein-protein interaction dataset for the yeast Saccharomyces cerevisiae using the Gene Ontology (GO) terms as function labels. The method reconstructed known GO term assignments with high precision, and produced putative GO assignments to 320 proteins that currently lack GO annotation, which represents about 10% of the unlabeled proteins in S. cerevisiae.     

A Factor Graph Approach to Automated GO Annotation

As volume of genomic data grows, computational methods become essential for providing a first glimpse onto gene annotations. Automated Gene Ontology (GO) annotation methods based on hierarchical ensemble classification techniques are particularly interesting when interpretability of annotation results is a main concern. In these methods, raw GO-term predictions computed by base binary classifiers are leveraged by checking the consistency of predefined GO relationships. Both formal leveraging strategies, with main focus on annotation precision, and heuristic alternatives, with main focus on scalability issues, have been described in literature. In this contribution, a factor graph approach to the hierarchical ensemble formulation of the automated GO annotation problem is presented. In this formal framework, a core factor graph is first built based on the GO structure and then enriched to take into account the noisy nature of GO-term predictions. Hence, starting from raw GO-term predictions, an iterative message passing algorithm between nodes of the factor graph is used to compute marginal probabilities of target GO-terms. Evaluations on Saccharomyces cerevisiae, Arabidopsis thaliana and Drosophila melanogaster protein sequences from the GO Molecular Function domain showed significant improvements over competing approaches, even when protein sequences were naively characterized by their physicochemical and secondary structure properties or when loose noisy annotation datasets were considered. Based on these promising results and using Arabidopsis thaliana annotation data, we extend our approach to the identification of most promising molecular function annotations for a set of proteins of unknown function in Solanum lycopersicum.     

Information theory applied to the sparse gene ontology annotation network to predict novel gene function

MOTIVATION: Despite advances in the gene annotation process, the functions of a large portion of gene products remain insufficiently characterized. In addition, the in silico prediction of novel Gene Ontology (GO) annotations for partially characterized gene functions or processes is highly dependent on reverse genetic or functional genomic approaches. To our knowledge, no prediction method has been demonstrated to be highly accurate for sparsely annotated GO terms (those associated to fewer than 10 genes). RESULTS: We propose a novel approach, information theory-based semantic similarity (ITSS), to automatically predict molecular functions of genes based on existing GO annotations. Using a 10-fold cross-validation, we demonstrate that the ITSS algorithm obtains prediction accuracies (precision 97%, recall 77%) comparable to other machine learning algorithms when compared in similar conditions over densely annotated portions of the GO datasets. This method is able to generate highly accurate predictions in sparsely annotated portions of GO, where previous algorithms have failed. As a result, our technique generates an order of magnitude more functional predictions than previous methods. A 10-fold cross validation demonstrated a precision of 90% at a recall of 36% for the algorithm over sparsely annotated networks of the recent GO annotations (about 1400 GO terms and 11,000 genes in Homo sapiens). To our knowledge, this article presents the first historical rollback validation for the predicted GO annotations, which may represent more realistic conditions than more widely used cross-validation approaches. By manually assessing a random sample of 100 predictions conducted in a historical rollback evaluation, we estimate that a minimum precision of 51% (95% confidence interval: 43-58%) can be achieved for the human GO Annotation file dated 2003. AVAILABILITY: The program is available on request. The 97,732 positive predictions of novel gene annotations from the 2005 GO Annotation dataset and other supplementary information is available at http://phenos.bsd.uchicago.edu/ITSS/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.     

Combining Evidence, Specificity, and Proximity towards the Normalization of Gene Ontology Terms in Text

Structured information provided by manual annotation of proteins with Gene Ontology concepts represents a high-quality reliable data source for the research community. However, a limited scope of proteins is annotated due to the amount of human resources required to fully annotate each individual gene product from the literature. We introduce a novel method for automatic identification of GO terms in natural language text. The method takes into consideration several features: (1) the evidence for a GO term given by the words occurring in text, (2) the proximity between the words, and (3) the specificity of the GO terms based on their information content. The method has been evaluated on the BioCreAtIvE corpus and has been compared to current state of the art methods. The precision reached 0.34 at a recall of 0.34 for the identified terms at rank 1. In our analysis, we observe that the identification of GO terms in the _cellular component_ subbranch of GO is more accurate than for terms from the other two subbranches. This observation is explained by the average number of words forming the terminology over the different subbranches.     

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.     

A categorization approach to automated ontological function annotation

Automated function prediction (AFP) methods increasingly use knowledge discovery algorithms to map sequence, structure, literature, and/or pathway information about proteins whose functions are unknown into functional ontologies, typically (a portion of) the Gene Ontology (GO). While there are a growing number of methods within this paradigm, the general problem of assessing the accuracy of such prediction algorithms has not been seriously addressed. We present first an application for function prediction from protein sequences using the POSet Ontology Categorizer (POSOC) to produce new annotations by analyzing collections of GO nodes derived from annotations of protein BLAST neighborhoods. We then also present hierarchical precision and hierarchical recall as new evaluation metrics for assessing the accuracy of any predictions in hierarchical ontologies, and discuss results on a test set of protein sequences. We show that our method provides substantially improved hierarchical precision (measure of predictions made that are correct) when applied to the nearest BLAST neighbors of target proteins, as compared with simply imputing that neighborhood's annotations to the target. Moreover, when our method is applied to a broader BLAST neighborhood, hierarchical precision is enhanced even further. In all cases, such increased hierarchical precision performance is purchased at a modest expense of hierarchical recall (measure of all annotations that get predicted at all).     

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.     

A combined approach for genome wide protein function annotation/prediction

Background

Today large scale genome sequencing technologies are uncovering an increasing amount of new genes and proteins, which remain uncharacterized. Experimental procedures for protein function prediction are low throughput by nature and thus can't be used to keep up with the rate at which new proteins are discovered. On the other hand, proteins are the prominent stakeholders in almost all biological processes, and therefore the need to precisely know their functions for a better understanding of the underlying biological mechanism is inevitable. The challenge of annotating uncharacterized proteins in functional genomics and biology in general motivates the use of computational techniques well orchestrated to accurately predict their functions.

Methods

We propose a computational flow for the functional annotation of a protein able to assign the most probable functions to a protein by aggregating heterogeneous information. Considered information include: protein motifs, protein sequence similarity, and protein homology data gathered from interacting proteins, combined with data from highly similar non-interacting proteins (hereinafter called Similactors). Moreover, to increase the predictive power of our model we also compute and integrate term specific relationships among functional terms based on Gene Ontology (GO).

Results

We tested our method on Saccharomyces Cerevisiae and Homo sapiens species proteins. The aggregation of different structural and functional evidence with GO relationships outperforms, in terms of precision and accuracy of prediction than the other methods reported in literature. The predicted precision and accuracy is 100% for more than half of the input set for both species; overall, we obtained 85.38% precision and 81.95% accuracy for Homo sapiens and 79.73% precision and 80.06% accuracy for Saccharomyces Cerevisiae species proteins.

     

A novel neural response algorithm for protein function prediction

Background

Large amounts of data are being generated by high-throughput genome sequencing methods. But the rate of the experimental functional characterization falls far behind. To fill the gap between the number of sequences and their annotations, fast and accurate automated annotation methods are required. Many methods, such as GOblet, GOFigure, and Gotcha, are designed based on the BLAST search. Unfortunately, the sequence coverage of these methods is low as they cannot detect the remote homologues. Adding to this, the lack of annotation specificity advocates the need to improve automated protein function prediction.

Results

We designed a novel automated protein functional assignment method based on the neural response algorithm, which simulates the neuronal behavior of the visual cortex in the human brain. Firstly, we predict the most similar target protein for a given query protein and thereby assign its GO term to the query sequence. When assessed on test set, our method ranked the actual leaf GO term among the top 5 probable GO terms with accuracy of 86.93%.

Conclusions

The proposed algorithm is the first instance of neural response algorithm being used in the biological domain. The use of HMM profiles along with the secondary structure information to define the neural response gives our method an edge over other available methods on annotation accuracy. Results of the 5-fold cross validation and the comparison with PFP and FFPred servers indicate the prominent performance by our method. The program, the dataset, and help files are available at http://www.jjwanglab.org/NRProF/.

     

Protein classification using probabilistic chain graphs and the Gene Ontology structure

MOTIVATION: Probabilistic graphical models have been developed in the past for the task of protein classification. In many cases, classifications obtained from the Gene Ontology have been used to validate these models. In this work we directly incorporate the structure of the Gene Ontology into the graphical representation for protein classification. We present a method in which each protein is represented by a replicate of the Gene Ontology structure, effectively modeling each protein in its own 'annotation space'. Proteins are also connected to one another according to different measures of functional similarity, after which belief propagation is run to make predictions at all ontology terms. RESULTS: The proposed method was evaluated on a set of 4879 proteins from the Saccharomyces Genome Database whose interactions were also recorded in the GRID project. Results indicate that direct utilization of the Gene Ontology improves predictive ability, outperforming traditional models that do not take advantage of dependencies among functional terms. Average increase in accuracy (precision) of positive and negative term predictions of 27.8% (2.0%) over three different similarity measures and three subontologies was observed. AVAILABILITY: C/C++/Perl implementation is available from authors upon request.     

MarVis: a tool for clustering and visualization of metabolic biomarkers

Background

Gene set analysis based on Gene Ontology (GO) can be a promising method for the analysis of differential expression patterns. However, current studies that focus on individual GO terms have limited analytical power, because the complex structure of GO introduces strong dependencies among the terms, and some genes that are annotated to a GO term cannot be found by statistically significant enrichment.

Results

We proposed a method for enriching clustered GO terms based on semantic similarity, namely cluster enrichment analysis based on GO (CeaGO), to extend the individual term analysis method. Using an Affymetrix HGU95aV2 chip dataset with simulated gene sets, we illustrated that CeaGO was sensitive enough to detect moderate expression changes. When compared to parent-based individual term analysis methods, the results showed that CeaGO may provide more accurate differentiation of gene expression results. When used with two acute leukemia (ALL and ALL/AML) microarray expression datasets, CeaGO correctly identified specifically enriched GO groups that were overlooked by other individual test methods.

Conclusion

By applying CeaGO to both simulated and real microarray data, we showed that this approach could enhance the interpretation of microarray experiments. CeaGO is currently available at http://chgc.sh.cn/en/software/CeaGO/.     

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.     

Novel search method for the discovery of functional relationships

MOTIVATION: Numerous annotations are available that functionally characterize genes and proteins with regard to molecular process, cellular localization, tissue expression, protein domain composition, protein interaction, disease association and other properties. Searching this steadily growing amount of information can lead to the discovery of new biological relationships between genes and proteins. To facilitate the searches, methods are required that measure the annotation similarity of genes and proteins. However, most current similarity methods are focused only on annotations from the Gene Ontology (GO) and do not take other annotation sources into account. RESULTS: We introduce the new method BioSim that incorporates multiple sources of annotations to quantify the functional similarity of genes and proteins. We compared the performance of our method with four other well-known methods adapted to use multiple annotation sources. We evaluated the methods by searching for known functional relationships using annotations based only on GO or on our large data warehouse BioMyn. This warehouse integrates many diverse annotation sources of human genes and proteins. We observed that the search performance improved substantially for almost all methods when multiple annotation sources were included. In particular, our method outperformed the other methods in terms of recall and average precision.     

Prediction of protein subcellular localization by weighted gene ontology terms

We develop a new weighting approach of gene ontology (GO) terms for predicting protein subcellular localization. The weights of individual GO terms, corresponding to their contribution to the prediction algorithm, are determined by the term-weighting methods used in text categorization. We evaluate several term-weighting methods, which are based on inverse document frequency, information gain, gain ratio, odds ratio, and chi-square and its variants. Additionally, we propose a new term-weighting method based on the logarithmic transformation of chi-square. The proposed term-weighting method performs better than other term-weighting methods, and also outperforms state-of-the-art subcellular prediction methods. Our proposed method achieves 98.1%, 99.3%, 98.1%, 98.1%, and 95.9% overall accuracies for the animal BaCelLo independent dataset (IDS), fungal BaCelLo IDS, animal Höglund IDS, fungal Höglund IDS, and PLOC dataset, respectively. Furthermore, the close correlation between high-weighted GO terms and subcellular localizations suggests that our proposed method appropriately weights GO terms according to their relevance to the localizations.     

PFP: Automated prediction of gene ontology functional annotations with confidence scores using protein sequence data

Protein function prediction is a central problem in bioinformatics, increasing in importance recently due to the rapid accumulation of biological data awaiting interpretation. Sequence data represents the bulk of this new stock and is the obvious target for consideration as input, as newly sequenced organisms often lack any other type of biological characterization. We have previously introduced PFP (Protein Function Prediction) as our sequence-based predictor of Gene Ontology (GO) functional terms. PFP interprets the results of a PSI-BLAST search by extracting and scoring individual functional attributes, searching a wide range of E-value sequence matches, and utilizing conventional data mining techniques to fill in missing information. We have shown it to be effective in predicting both specific and low-resolution functional attributes when sufficient data is unavailable. Here we describe (1) significant improvements to the PFP infrastructure, including the addition of prediction significance and confidence scores, (2) a thorough benchmark of performance and comparisons to other related prediction methods, and (3) applications of PFP predictions to genome-scale data. We applied PFP predictions to uncharacterized protein sequences from 15 organisms. Among these sequences, 60-90% could be annotated with a GO molecular function term at high confidence (>or=80%). We also applied our predictions to the protein-protein interaction network of the Malaria plasmodium (Plasmodium falciparum). High confidence GO biological process predictions (>or=90%) from PFP increased the number of fully enriched interactions in this dataset from 23% of interactions to 94%. Our benchmark comparison shows significant performance improvement of PFP relative to GOtcha, InterProScan, and PSI-BLAST predictions. This is consistent with the performance of PFP as the overall best predictor in both the AFP-SIG '05 and CASP7 function (FN) assessments. PFP is available as a web service at http://dragon.bio.purdue.edu/pfp/.