Improving GO semantic similarity measures by exploring the ontology beneath the terms and modelling uncertainty

Host centric drug repurposing for viral diseases

Computational approaches for drug repurposing for viral diseases have mainly focused on a small number of antivirals that directly target pathogens (virus centric therapies). In this work, we combine ideas from collaborative filtering and network medicine for making predictions on a much larger set of drugs that could be repurposed for host centric therapies, that are aimed at interfering with host cell factors required by a pathogen. Our idea is to create matrices quantifying the perturbation that drugs and viruses induce on human protein interaction networks. Then, we decompose these matrices to learn embeddings of drugs, viruses, and proteins in a low dimensional space. Predictions of host-centric antivirals are obtained by taking the dot product between the corresponding drug and virus representations. Our approach is general and can be applied systematically to any compound with known targets and any virus whose host proteins are known. We show that our predictions have high accuracy and that the embeddings contain meaningful biological information that may provide insights into the underlying biology of viral infections. Our approach can integrate different types of information, does not rely on known drug-virus associations and can be applied to new viral diseases and drugs.

LanDis: the disease landscape explorer

From a network medicine perspective, a disease is the consequence of perturbations on the interactome. These perturbations tend to appear in a specific neighbourhood on the interactome, the disease module, and modules related to phenotypically similar diseases tend to be located in close-by regions. We present LanDis, a freely available web-based interactive tool ( https://paccanarolab.org/landis ) that allows domain experts, medical doctors and the larger scientific community to graphically navigate the interactome distances between the modules of over 44 million pairs of heritable diseases. The map-like interface provides detailed comparisons between pairs of diseases together with supporting evidence. Every disease in LanDis is linked to relevant entries in OMIM and UniProt, providing a starting point for in-depth analysis and an opportunity for novel insight into the aetiology of diseases as well as differential diagnosis.

Identifying Protein Complexes From Protein-Protein Interaction Networks Based on Fuzzy Clustering and GO Semantic Information

Protein complexes are of great significance to provide valuable insights into the mechanisms of biological processes of proteins. A variety of computational algorithms have thus been proposed to identify protein complexes in a protein-protein interaction network. However, few of them can perform their tasks by taking into account both network topology and protein attribute information in a unified fuzzy-based clustering framework. Since proteins in the same complex are similar in terms of their attribute information and the consideration of fuzzy clustering can also make it possible for us to identify overlapping complexes, we target to propose such a novel fuzzy-based clustering framework, namely FCAN-PCI, for an improved identification accuracy. To do so, the semantic similarity between the attribute information of proteins is calculated and we then integrate it into a well-established fuzzy clustering model together with the network topology. After that, a momentum method is adopted to accelerate the clustering procedure. FCAN-PCI finally applies a heuristical search strategy to identify overlapping protein complexes. A series of extensive experiments have been conducted to evaluate the performance of FCAN-PCI by comparing it with state-of-the-art identification algorithms and the results demonstrate the promising performance of FCAN-PCI.

A Novel Graph Topology-Based GO-Similarity Measure for Signature Detection From Multi-Omics Data and its Application to Other Problems

Large scale multi-omics data analysis and signature prediction have been a topic of interest in the last two decades. While various traditional clustering/correlation-based methods have been proposed, but the overall prediction is not always satisfactory. To solve these challenges, in this article, we propose a new approach by leveraging the Gene Ontology (GO)similarity combined with multiomics data. In this article, a new GO similarity measure, ModSchlicker, is proposed and the effectiveness of the proposed measure along with other standardized measures are reviewed while using various graph topology-based Information Content (IC)values of GO-term. The proposed measure is deployed to PPI prediction. Furthermore, by involving GO similarity, we propose a new framework for stronger disease-based gene signature detection from the multi-omics data. For the first objective, we predict interaction from various benchmark PPI datasets of Yeast and Human species. For the latter, the gene expression and methylation profiles are used to identify Differentially Expressed and Methylated (DEM)genes. Thereafter, the GO similarity score along with a statistical method are used to determine the potential gene signature. Interestingly, the proposed method produces a better performance ( 0.9 avg. accuracy and 0.95 AUC)as compared to the other existing related methods during the classification of the participating features (genes)of the signature. Moreover, the proposed method is highly useful in other prediction/classification problems for any kind of large scale omics data.

GoVec: Gene Ontology Representation Learning Using Weighted Heterogeneous Graph and Meta-Path

Biomedical knowledge graphs are crucial to support data-intensive applications in the life sciences and health care. These graphs can be extended by generating a heterogeneous graph that contains both ontology terms and biomedical entities. However, state-of-the-art approaches for Gene Ontology representation learnings are constrained to homogeneous graphs that cannot represent different node types and relations. To address this limitation, we present GoVec to produce representations seamlessly for both ontologies and biological entities by utilizing meta-path-based representation learning in the heterogeneous graph. The resulting vectors can be used in many bioinformatics applications, particularly for calculating semantic similarity and extracting relations among biological entities. We verify the approach's usefulness by comparing the resulting semantic similarities with the manually produced similarities by the experts. Furthermore, the superiority of the GoVec is shown by an extensive set of quantitative and qualitative evaluations. Two downstream tasks, including protein-protein interaction and protein family similarity, are evaluated in comparison with many state-of-the-art approaches. Finally, as a qualitative visual representation, the separability of various protein families is examined and visually separable groups of proteins are generated, which shows the capability of GoVec representations to embed functional semantics into the vectors.

Network-based methods for gene function prediction

The rapid development of high-throughput technology has generated a large number of biological networks. Network-based methods are able to provide rich information for inferring gene function. This is composed of analyzing the topological characteristics of genes in related networks, integrating biological information, and considering data from different data sources. To promote network biology and related biotechnology research, this article provides a survey for the state of the art of advanced methods of network-based gene function prediction and discusses the potential challenges.

NMFGO: Gene Function Prediction via Nonnegative Matrix Factorization with Gene Ontology

Gene Ontology (GO) is a controlled vocabulary of terms that describe molecule function, biological roles, and cellular locations of gene products (i.e., proteins and RNAs), it hierarchically organizes more than 43,000 GO terms via the direct acyclic graph. A gene is generally annotated with several of these GO terms. Therefore, accurately predicting the association between genes and massive terms is a difficult challenge. To combat with this challenge, we propose an matrix factorization based approach called NMFGO. NMFGO stores the available GO annotations of genes in a gene-term association matrix and adopts an ontological structure based taxonomic similarity measure to capture the GO hierarchy. Next, it factorizes the association matrix into two low-rank matrices via nonnegative matrix factorization regularized with the GO hierarchy. After that, it employs a semantic similarity based k nearest neighbor classifier in the low-rank matrices approximated subspace to predict gene functions. Empirical study on three model species (S. cerevisiae, H. sapiens, and A. thaliana) shows that NMFGO is robust to the input parameters and achieves significantly better prediction performance than GIC, TO, dRW- kNN, and NtN, which were re-implemented based on the instructions of the original papers. The supplementary file and demo codes of NMFGO are available at http://mlda.swu.edu.cn/codes.php?name=NMFGO.

GO2Vec: transforming GO terms and proteins to vector representations via graph embeddings

Background

Semantic similarity between Gene Ontology (GO) terms is a fundamental measure for many bioinformatics applications, such as determining functional similarity between genes or proteins. Most previous research exploited information content to estimate the semantic similarity between GO terms; recently some research exploited word embeddings to learn vector representations for GO terms from a large-scale corpus. In this paper, we proposed a novel method, named GO2Vec, that exploits graph embeddings to learn vector representations for GO terms from GO graph. GO2Vec combines the information from both GO graph and GO annotations, and its learned vectors can be applied to a variety of bioinformatics applications, such as calculating functional similarity between proteins and predicting protein-protein interactions.

Results

We conducted two kinds of experiments to evaluate the quality of GO2Vec: (1) functional similarity between proteins on the Collaborative Evaluation of GO-based Semantic Similarity Measures (CESSM) dataset and (2) prediction of protein-protein interactions on the Yeast and Human datasets from the STRING database. Experimental results demonstrate the effectiveness of GO2Vec over the information content-based measures and the word embedding-based measures.

Conclusion

Our experimental results demonstrate the effectiveness of using graph embeddings to learn vector representations from undirected GO and GOA graphs. Our results also demonstrate that GO annotations provide useful information for computing the similarity between GO terms and between proteins.

MiRGOFS: a GO-based functional similarity measurement for miRNAs, with applications to the prediction of miRNA subcellular localization and miRNA-disease association

Motivation

Benefiting from high-throughput experimental technologies, whole-genome analysis of microRNAs (miRNAs) has been more and more common to uncover important regulatory roles of miRNAs and identify miRNA biomarkers for disease diagnosis. As a complementary information to the high-throughput experimental data, domain knowledge like the Gene Ontology and KEGG pathway is usually used to guide gene function analysis. However, functional annotation for miRNAs is scarce in the public databases. Till now, only a few methods have been proposed for measuring the functional similarity between miRNAs based on public annotation data, and these methods cover a very limited number of miRNAs, which are not applicable to large-scale miRNA analysis.

Results

In this paper, we propose a new method to measure the functional similarity for miRNAs, called miRGOFS, which has two notable features: (i) it adopts a new GO semantic similarity metric which considers both common ancestors and descendants of GO terms; (i) it computes similarity between GO sets in an asymmetric manner, and weights each GO term by its statistical significance. The miRGOFS-based predictor achieves an F1 of 61.2% on a benchmark dataset of miRNA localization, and AUC values of 87.7 and 81.1% on two benchmark sets of miRNA-disease association, respectively. Compared with the existing functional similarity measurements of miRNAs, miRGOFS has the advantages of higher accuracy and larger coverage of human miRNAs (over 1000 miRNAs).

Availability and implementation

http://www.csbio.sjtu.edu.cn/bioinf/MiRGOFS/.

Supplementary information

Supplementary data are available at Bioinformatics online.

Advances in the Prediction of Protein Subcellular Locations with Machine Learning

Background:

Revealing the subcellular location of a newly discovered protein can bring insight into their function and guide research at the cellular level. The experimental methods currently used to identify the protein subcellular locations are both time-consuming and expensive. Thus, it is highly desired to develop computational methods for efficiently and effectively identifying the protein subcellular locations. Especially, the rapidly increasing number of protein sequences entering the genome databases has called for the development of automated analysis methods.

Methods:

In this review, we will describe the recent advances in predicting the protein subcellular locations with machine learning from the following aspects: i) Protein subcellular location benchmark dataset construction, ii) Protein feature representation and feature descriptors, iii) Common machine learning algorithms, iv) Cross-validation test methods and assessment metrics, v) Web servers.

Result & Conclusion:

Concomitant with a large number of protein sequences generated by highthroughput technologies, four future directions for predicting protein subcellular locations with machine learning should be paid attention. One direction is the selection of novel and effective features (e.g., statistics, physical-chemical, evolutional) from the sequences and structures of proteins. Another is the feature fusion strategy. The third is the design of a powerful predictor and the fourth one is the protein multiple location sites prediction.

Co-complex protein membership evaluation using Maximum Entropy on GO ontology and InterPro annotation

Motivation

Protein–protein interactions (PPI) play a crucial role in our understanding of protein function and biological processes. The standardization and recording of experimental findings is increasingly stored in ontologies, with the Gene Ontology (GO) being one of the most successful projects. Several PPI evaluation algorithms have been based on the application of probabilistic frameworks or machine learning algorithms to GO properties. Here, we introduce a new training set design and machine learning based approach that combines dependent heterogeneous protein annotations from the entire ontology to evaluate putative co-complex protein interactions determined by empirical studies.

Results

PPI annotations are built combinatorically using corresponding GO terms and InterPro annotation. We use a S.cerevisiae high-confidence complex dataset as a positive training set. A series of classifiers based on Maximum Entropy and support vector machines (SVMs), each with a composite counterpart algorithm, are trained on a series of training sets. These achieve a high performance area under the ROC curve of ≤0.97, outperforming go2ppi—a previously established prediction tool for protein-protein interactions (PPI) based on Gene Ontology (GO) annotations.

Availability and implementation

https://github.com/ima23/maxent-ppi

Supplementary information

Supplementary data are available at Bioinformatics online.

Fusing gene expressions and transitive protein-protein interactions for inference of gene regulatory networks

BACKGROUND

Systematic fusion of multiple data sources for Gene Regulatory Networks (GRN) inference remains a key challenge in systems biology. We incorporate information from protein-protein interaction networks (PPIN) into the process of GRN inference from gene expression (GE) data. However, existing PPIN remain sparse and transitive protein interactions can help predict missing protein interactions. We therefore propose a systematic probabilistic framework on fusing GE data and transitive protein interaction data to coherently build GRN.

RESULTS

We use a Gaussian Mixture Model (GMM) to soft-cluster GE data, allowing overlapping cluster memberships. Next, a heuristic method is proposed to extend sparse PPIN by incorporating transitive linkages. We then propose a novel way to score extended protein interactions by combining topological properties of PPIN and correlations of GE. Following this, GE data and extended PPIN are fused using a Gaussian Hidden Markov Model (GHMM) in order to identify gene regulatory pathways and refine interaction scores that are then used to constrain the GRN structure. We employ a Bayesian Gaussian Mixture (BGM) model to refine the GRN derived from GE data by using the structural priors derived from GHMM. Experiments on real yeast regulatory networks demonstrate both the feasibility of the extended PPIN in predicting transitive protein interactions and its effectiveness on improving the coverage and accuracy the proposed method of fusing PPIN and GE to build GRN.

CONCLUSION

The GE and PPIN fusion model outperforms both the state-of-the-art single data source models (CLR, GENIE3, TIGRESS) as well as existing fusion models under various constraints.

Word and Sentence Embedding Tools to Measure Semantic Similarity of Gene Ontology Terms by Their Definitions

The gene ontology (GO) database contains GO terms that describe biological functions of genes. Previous methods for comparing GO terms have relied on the fact that GO terms are organized into a tree structure. Under this paradigm, the locations of two GO terms in the tree dictate their similarity score. In this article, we introduce two new solutions for this problem by focusing instead on the definitions of the GO terms. We apply neural network-based techniques from the natural language processing (NLP) domain. The first method does not rely on the GO tree, whereas the second indirectly depends on the GO tree. In our first approach, we compare two GO definitions by treating them as two unordered sets of words. The word similarity is estimated by a word embedding model that maps words into an N-dimensional space. In our second approach, we account for the word-ordering within a sentence. We use a sentence encoder to embed GO definitions into vectors and estimate how likely one definition entails another. We validate our methods in two ways. In the first experiment, we test the model's ability to differentiate a true protein-protein network from a randomly generated network. In the second experiment, we test the model in identifying orthologs from randomly matched genes in human, mouse, and fly. In both experiments, a hybrid of NLP and GO tree-based method achieves the best classification accuracy.

Gene Ontology Enrichment Improves Performances of Functional Similarity of Genes

There exists a plethora of measures to evaluate functional similarity (FS) between genes, which is a widely used in many bioinformatics applications including detecting molecular pathways, identifying co-expressed genes, predicting protein-protein interactions, and prioritization of disease genes. Measures of FS between genes are mostly derived from Information Contents (IC) of Gene Ontology (GO) terms annotating the genes. However, existing measures evaluating IC of terms based either on the representations of terms in the annotating corpus or on the knowledge embedded in the GO hierarchy do not consider the enrichment of GO terms by the querying pair of genes. The enrichment of a GO term by a pair of gene is dependent on whether the term is annotated by one gene (i.e., partial annotation) or by both genes (i.e. complete annotation) in the pair. In this paper, we propose a method that incorporate enrichment of GO terms by a gene pair in computing their FS and show that GO enrichment improves the performances of 46 existing FS measures in the prediction of sequence homologies, gene expression correlations, protein-protein interactions, and disease associated genes.

Investigating Correlation between Protein Sequence Similarity and Semantic Similarity Using Gene Ontology Annotations

Sequence similarity is a commonly used measure to compare proteins. With the increasing use of ontologies, semantic (function) similarity is getting importance. The correlation between these measures has been applied in the evaluation of new semantic similarity methods, and in protein function prediction. In this research, we investigate the relationship between the two similarity methods. The results suggest absence of a strong correlation between sequence and semantic similarities. There is a large number of proteins with low sequence similarity and high semantic similarity. We observe that Pearson's correlation coefficient is not sufficient to explain the nature of this relationship. Interestingly, the term semantic similarity values above 0 and below 1 do not seem to play a role in improving the correlation. That is, the correlation coefficient depends only on the number of common GO terms in proteins under comparison, and the semantic similarity measurement method does not influence it. Semantic similarity and sequence similarity have a distinct behavior. These findings are of significant effect for future works on protein comparison, and will help understand the semantic similarity between proteins in a better way.

Improving the measurement of semantic similarity by combining gene ontology and co-functional network: a random walk based approach

BACKGROUND

Gene Ontology (GO) is one of the most popular bioinformatics resources. In the past decade, Gene Ontology-based gene semantic similarity has been effectively used to model gene-to-gene interactions in multiple research areas. However, most existing semantic similarity approaches rely only on GO annotations and structure, or incorporate only local interactions in the co-functional network. This may lead to inaccurate GO-based similarity resulting from the incomplete GO topology structure and gene annotations.

RESULTS

We present NETSIM2, a new network-based method that allows researchers to measure GO-based gene functional similarities by considering the global structure of the co-functional network with a random walk with restart (RWR)-based method, and by selecting the significant term pairs to decrease the noise information. Based on the EC number (Enzyme Commission)-based groups of yeast and Arabidopsis, evaluation test shows that NETSIM2 can enhance the accuracy of Gene Ontology-based gene functional similarity.

CONCLUSIONS

Using NETSIM2 as an example, we found that the accuracy of semantic similarities can be significantly improved after effectively incorporating the global gene-to-gene interactions in the co-functional network, especially on the species that gene annotations in GO are far from complete.

Comparison of different approaches for identifying subnetworks in metabolic networks

A metabolic network model provides a computational framework for studying the metabolism of a cell at the system level. The organization of metabolic networks has been investigated in different studies. One of the organization aspects considered in these studies is the decomposition of a metabolic network. The decompositions produced by different methods are very different and there is no comprehensive evaluation framework to compare the results with each other. In this study, these methods are reviewed and compared in the first place. Then they are applied to six different metabolic network models and the results are evaluated and compared based on two existing and two newly proposed criteria. Results show that no single method can beat others in all criteria but it seems that the methods introduced by Guimera and Amaral and Verwoerd do better on among metabolite-based methods and the method introduced by Sridharan et al. does better among reaction-based ones. Also, the methods are applied to several artificial networks, each constructed from merging a few KEGG pathways. Then, their capability to recover those pathways are compared. Results show that among metabolite-based methods, the method of Guimera and Amaral does better again, however, no notable difference between the performances of reaction-based methods was detected.

Hum-mPLoc 3.0: prediction enhancement of human protein subcellular localization through modeling the hidden correlations of gene ontology and functional domain features

Motivation

Protein subcellular localization prediction has been an important research topic in computational biology over the last decade. Various automatic methods have been proposed to predict locations for large scale protein datasets, where statistical machine learning algorithms are widely used for model construction. A key step in these predictors is encoding the amino acid sequences into feature vectors. Many studies have shown that features extracted from biological domains, such as gene ontology and functional domains, can be very useful for improving the prediction accuracy. However, domain knowledge usually results in redundant features and high-dimensional feature spaces, which may degenerate the performance of machine learning models.

Results

In this paper, we propose a new amino acid sequence-based human protein subcellular location prediction approach Hum-mPLoc 3.0, which covers 12 human subcellular localizations. The sequences are represented by multi-view complementary features, i.e. context vocabulary annotation-based gene ontology (GO) terms, peptide-based functional domains, and residue-based statistical features. To systematically reflect the structural hierarchy of the domain knowledge bases, we propose a novel feature representation protocol denoted as HCM (Hidden Correlation Modeling), which will create more compact and discriminative feature vectors by modeling the hidden correlations between annotation terms. Experimental results on four benchmark datasets show that HCM improves prediction accuracy by 5-11% and F 1 by 8-19% compared with conventional GO-based methods. A large-scale application of Hum-mPLoc 3.0 on the whole human proteome reveals proteins co-localization preferences in the cell.

Availability and Implementation

www.csbio.sjtu.edu.cn/bioinf/Hum-mPLoc3/.

Contacts

hbshen@sjtu.edu.cn.

Supplementary information

Supplementary data are available at Bioinformatics online.

NoGOA: predicting noisy GO annotations using evidences and sparse representation

BACKGROUND

Gene Ontology (GO) is a community effort to represent functional features of gene products. GO annotations (GOA) provide functional associations between GO terms and gene products. Due to resources limitation, only a small portion of annotations are manually checked by curators, and the others are electronically inferred. Although quality control techniques have been applied to ensure the quality of annotations, the community consistently report that there are still considerable noisy (or incorrect) annotations. Given the wide application of annotations, however, how to identify noisy annotations is an important but yet seldom studied open problem.

RESULTS

We introduce a novel approach called NoGOA to predict noisy annotations. NoGOA applies sparse representation on the gene-term association matrix to reduce the impact of noisy annotations, and takes advantage of sparse representation coefficients to measure the semantic similarity between genes. Secondly, it preliminarily predicts noisy annotations of a gene based on aggregated votes from semantic neighborhood genes of that gene. Next, NoGOA estimates the ratio of noisy annotations for each evidence code based on direct annotations in GOA files archived on different periods, and then weights entries of the association matrix via estimated ratios and propagates weights to ancestors of direct annotations using GO hierarchy. Finally, it integrates evidence-weighted association matrix and aggregated votes to predict noisy annotations. Experiments on archived GOA files of six model species (H. sapiens, A. thaliana, S. cerevisiae, G. gallus, B. Taurus and M. musculus) demonstrate that NoGOA achieves significantly better results than other related methods and removing noisy annotations improves the performance of gene function prediction.

CONCLUSIONS

The comparative study justifies the effectiveness of integrating evidence codes with sparse representation for predicting noisy GO annotations. Codes and datasets are available at http://mlda.swu.edu.cn/codes.php?name=NoGOA .

The effects of shared information on semantic calculations in the gene ontology

The structured vocabulary that describes gene function, the gene ontology (GO), serves as a powerful tool in biological research. One application of GO in computational biology calculates semantic similarity between two concepts to make inferences about the functional similarity of genes. A class of term similarity algorithms explicitly calculates the shared information (SI) between concepts then substitutes this calculation into traditional term similarity measures such as Resnik, Lin, and Jiang-Conrath. Alternative SI approaches, when combined with ontology choice and term similarity type, lead to many gene-to-gene similarity measures. No thorough investigation has been made into the behavior, complexity, and performance of semantic methods derived from distinct SI approaches. We apply bootstrapping to compare the generalized performance of 57 gene-to-gene semantic measures across six benchmarks. Considering the number of measures, we additionally evaluate whether these methods can be leveraged through ensemble machine learning to improve prediction performance. Results showed that the choice of ontology type most strongly influenced performance across all evaluations. Combining measures into an ensemble classifier reduces cross-validation error beyond any individual measure for protein interaction prediction. This improvement resulted from information gained through the combination of ontology types as ensemble methods within each GO type offered no improvement. These results demonstrate that multiple SI measures can be leveraged for machine learning tasks such as automated gene function prediction by incorporating methods from across the ontologies. To facilitate future research in this area, we developed the GO Graph Tool Kit (GGTK), an open source C++ library with Python interface (github.com/paulbible/ggtk).

Interspecies gene function prediction using semantic similarity

BACKGROUND

Gene Ontology (GO) is a collaborative project that maintains and develops controlled vocabulary (or terms) to describe the molecular function, biological roles and cellular location of gene products in a hierarchical ontology. GO also provides GO annotations that associate genes with GO terms. GO consortium independently and collaboratively annotate terms to gene products, mainly from model organisms (or species) they are interested in. Due to experiment ethics, research interests of biologists and resources limitations, homologous genes from different species currently are annotated with different terms. These differences can be more attributed to incomplete annotations of genes than to functional difference between them.

RESULTS

Semantic similarity between genes is derived from GO hierarchy and annotations of genes. It is positively correlated with the similarity derived from various types of biological data and has been applied to predict gene function. In this paper, we investigate whether it is possible to replenish annotations of incompletely annotated genes by using semantic similarity between genes from two species with homology. For this investigation, we utilize three representative semantic similarity metrics to compute similarity between genes from two species. Next, we determine the k nearest neighborhood genes from the two species based on the chosen metric and then use terms annotated to k neighbors of a gene to replenish annotations of that gene. We perform experiments on archived (from Jan-2014 to Jan-2016) GO annotations of four species (Human, Mouse, Danio rerio and Arabidopsis thaliana) to assess the contribution of semantic similarity between genes from different species. The experimental results demonstrate that: (1) semantic similarity between genes from homologous species contributes much more on the improved accuracy (by 53.22%) than genes from single species alone, and genes from two species with low homology; (2) GO annotations of genes from homologous species are complementary to each other.

CONCLUSIONS

Our study shows that semantic similarity based interspecies gene function annotation from homologous species is more prominent than traditional intraspecies approaches. This work can promote more research on semantic similarity based function prediction across species.

Detecting Cooperativity between Transcription Factors Based on Functional Coherence and Similarity of Their Target Gene Sets

In eukaryotic cells, transcriptional regulation of gene expression is usually achieved by cooperative transcription factors (TFs). Therefore, knowing cooperative TFs is the first step toward uncovering the molecular mechanisms of gene expression regulation. Many algorithms based on different rationales have been proposed to predict cooperative TF pairs in yeast. Although various types of rationales have been used in the existing algorithms, functional coherence is not yet used. This prompts us to develop a new algorithm based on functional coherence and similarity of the target gene sets to identify cooperative TF pairs in yeast. The proposed algorithm predicted 40 cooperative TF pairs. Among them, three (Pdc2-Thi2, Hot1-Msn1 and Leu3-Met28) are novel predictions, which have not been predicted by any existing algorithms. Strikingly, two (Pdc2-Thi2 and Hot1-Msn1) of the three novel predictions have been experimentally validated, demonstrating the power of the proposed algorithm. Moreover, we show that the predictions of the proposed algorithm are more biologically meaningful than the predictions of 17 existing algorithms under four evaluation indices. In summary, our study suggests that new algorithms based on novel rationales are worthy of developing for detecting previously unidentifiable cooperative TF pairs.

NoisyGOA: Noisy GO annotations prediction using taxonomic and semantic similarity

Gene Ontology (GO) provides GO annotations (GOA) that associate gene products with GO terms that summarize their cellular, molecular and functional aspects in the context of biological pathways. GO Consortium (GOC) resorts to various quality assurances to ensure the correctness of annotations. Due to resources limitations, only a small portion of annotations are manually added/checked by GO curators, and a large portion of available annotations are computationally inferred. While computationally inferred annotations provide greater coverage of known genes, they may also introduce annotation errors (noise) that could mislead the interpretation of the gene functions and their roles in cellular and biological processes. In this paper, we investigate how to identify noisy annotations, a rarely addressed problem, and propose a novel approach called NoisyGOA. NoisyGOA first measures taxonomic similarity between ontological terms using the GO hierarchy and semantic similarity between genes. Next, it leverages the taxonomic similarity and semantic similarity to predict noisy annotations. We compare NoisyGOA with other alternative methods on identifying noisy annotations under different simulated cases of noisy annotations, and on archived GO annotations. NoisyGOA achieved higher accuracy than other alternative methods in comparison. These results demonstrated both taxonomic similarity and semantic similarity contribute to the identification of noisy annotations. Our study shows that annotation errors are predictable and removing noisy annotations improves the performance of gene function prediction. This study can prompt the community to study methods for removing inaccurate annotations, a critical step for annotating gene and pathway functions.

Corpus domain effects on distributional semantic modeling of medical terms

MOTIVATION

Automatically quantifying semantic similarity and relatedness between clinical terms is an important aspect of text mining from electronic health records, which are increasingly recognized as valuable sources of phenotypic information for clinical genomics and bioinformatics research. A key obstacle to development of semantic relatedness measures is the limited availability of large quantities of clinical text to researchers and developers outside of major medical centers. Text from general English and biomedical literature are freely available; however, their validity as a substitute for clinical domain to represent semantics of clinical terms remains to be demonstrated.

RESULTS

We constructed neural network representations of clinical terms found in a publicly available benchmark dataset manually labeled for semantic similarity and relatedness. Similarity and relatedness measures computed from text corpora in three domains (Clinical Notes, PubMed Central articles and Wikipedia) were compared using the benchmark as reference. We found that measures computed from full text of biomedical articles in PubMed Central repository (rho = 0.62 for similarity and 0.58 for relatedness) are on par with measures computed from clinical reports (rho = 0.60 for similarity and 0.57 for relatedness). We also evaluated the use of neural network based relatedness measures for query expansion in a clinical document retrieval task and a biomedical term word sense disambiguation task. We found that, with some limitations, biomedical articles may be used in lieu of clinical reports to represent the semantics of clinical terms and that distributional semantic methods are useful for clinical and biomedical natural language processing applications.

AVAILABILITY AND IMPLEMENTATION

The software and reference standards used in this study to evaluate semantic similarity and relatedness measures are publicly available as detailed in the article.

CONTACT

pakh0002@umn.eduSupplementary information: Supplementary data are available at Bioinformatics online.

NegGOA: negative GO annotations selection using ontology structure

MOTIVATION

Predicting the biological functions of proteins is one of the key challenges in the post-genomic era. Computational models have demonstrated the utility of applying machine learning methods to predict protein function. Most prediction methods explicitly require a set of negative examples-proteins that are known not carrying out a particular function. However, Gene Ontology (GO) almost always only provides the knowledge that proteins carry out a particular function, and functional annotations of proteins are incomplete. GO structurally organizes more than tens of thousands GO terms and a protein is annotated with several (or dozens) of these terms. For these reasons, the negative examples of a protein can greatly help distinguishing true positive examples of the protein from such a large candidate GO space.

RESULTS

In this paper, we present a novel approach (called NegGOA) to select negative examples. Specifically, NegGOA takes advantage of the ontology structure, available annotations and potentiality of additional annotations of a protein to choose negative examples of the protein. We compare NegGOA with other negative examples selection algorithms and find that NegGOA produces much fewer false negatives than them. We incorporate the selected negative examples into an efficient function prediction model to predict the functions of proteins in Yeast, Human, Mouse and Fly. NegGOA also demonstrates improved accuracy than these comparing algorithms across various evaluation metrics. In addition, NegGOA is less suffered from incomplete annotations of proteins than these comparing methods.

AVAILABILITY AND IMPLEMENTATION

The Matlab and R codes are available at https://sites.google.com/site/guoxian85/neggoa

CONTACT

gxyu@swu.edu.cn

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Exploring information from the topology beneath the Gene Ontology terms to improve semantic similarity measures

Measuring the similarity between pairs of biological entities is important in molecular biology. The introduction of Gene Ontology (GO) provides us with a promising approach to quantifying the semantic similarity between two genes or gene products. This kind of similarity measure is closely associated with the GO terms annotated to biological entities under consideration and the structure of the GO graph. However, previous works in this field mainly focused on the upper part of the graph, and seldom concerned about the lower part. In this study, we aim to explore information from the lower part of the GO graph for better semantic similarity. We proposed a framework to quantify the similarity measure beneath a term pair, which takes into account both the information two ancestral terms share and the probability that they co-occur with their common descendants. The effectiveness of our approach was evaluated against seven typical measurements on public platform CESSM, protein-protein interaction and gene expression datasets. Experimental results consistently show that the similarity derived from the lower part contributes to better semantic similarity measure. The promising features of our approach are the following: (1) it provides a mirror model to characterize the information two ancestral terms share with respect to their common descendant; (2) it quantifies the probability that two terms co-occur with their common descendant in an efficient way; and (3) our framework can effectively capture the similarity measure beneath two terms, which can serve as an add-on to improve traditional semantic similarity measure between two GO terms. The algorithm was implemented in Matlab and is freely available from http://ejl.org.cn/bio/GOBeneath/.

Predicting Protein Function via Semantic Integration of Multiple Networks

Determining the biological functions of proteins is one of the key challenges in the post-genomic era. The rapidly accumulated large volumes of proteomic and genomic data drives to develop computational models for automatically predicting protein function in large scale. Recent approaches focus on integrating multiple heterogeneous data sources and they often get better results than methods that use single data source alone. In this paper, we investigate how to integrate multiple biological data sources with the biological knowledge, i.e., Gene Ontology (GO), for protein function prediction. We propose a method, called SimNet, to Semantically integrate multiple functional association Networks derived from heterogenous data sources. SimNet firstly utilizes GO annotations of proteins to capture the semantic similarity between proteins and introduces a semantic kernel based on the similarity. Next, SimNet constructs a composite network, obtained as a weighted summation of individual networks, and aligns the network with the kernel to get the weights assigned to individual networks. Then, it applies a network-based classifier on the composite network to predict protein function. Experiment results on heterogenous proteomic data sources of Yeast, Human, Mouse, and Fly show that, SimNet not only achieves better (or comparable) results than other related competitive approaches, but also takes much less time. The Matlab codes of SimNet are available at https://sites.google.com/site/guoxian85/simnet.

simDEF: definition-based semantic similarity measure of gene ontology terms for functional similarity analysis of genes

MOTIVATION

Measures of protein functional similarity are essential tools for function prediction, evaluation of protein-protein interactions (PPIs) and other applications. Several existing methods perform comparisons between proteins based on the semantic similarity of their GO terms; however, these measures are highly sensitive to modifications in the topological structure of GO, tend to be focused on specific analytical tasks and concentrate on the GO terms themselves rather than considering their textual definitions.

RESULTS

We introduce simDEF, an efficient method for measuring semantic similarity of GO terms using their GO definitions, which is based on the Gloss Vector measure commonly used in natural language processing. The simDEF approach builds optimized definition vectors for all relevant GO terms, and expresses the similarity of a pair of proteins as the cosine of the angle between their definition vectors. Relative to existing similarity measures, when validated on a yeast reference database, simDEF improves correlation with sequence homology by up to 50%, shows a correlation improvement >4% with gene expression in the biological process hierarchy of GO and increases PPI predictability by > 2.5% in F1 score for molecular function hierarchy.

AVAILABILITY AND IMPLEMENTATION

Datasets, results and source code are available at http://kiwi.cs.dal.ca/Software/simDEF CONTACT: ahmad.pgh@dal.ca or beiko@cs.dal.ca

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

PCTFPeval: a web tool for benchmarking newly developed algorithms for predicting cooperative transcription factor pairs in yeast

Background

Computational identification of cooperative transcription factor (TF) pairs helps understand the combinatorial regulation of gene expression in eukaryotic cells. Many advanced algorithms have been proposed to predict cooperative TF pairs in yeast. However, it is still difficult to conduct a comprehensive and objective performance comparison of different algorithms because of lacking sufficient performance indices and adequate overall performance scores. To solve this problem, in our previous study (published in BMC Systems Biology 2014), we adopted/proposed eight performance indices and designed two overall performance scores to compare the performance of 14 existing algorithms for predicting cooperative TF pairs in yeast. Most importantly, our performance comparison framework can be applied to comprehensively and objectively evaluate the performance of a newly developed algorithm. However, to use our framework, researchers have to put a lot of effort to construct it first. To save researchers time and effort, here we develop a web tool to implement our performance comparison framework, featuring fast data processing, a comprehensive performance comparison and an easy-to-use web interface.

Results

The developed tool is called PCTFPeval (Predicted Cooperative TF Pair evaluator), written in PHP and Python programming languages. The friendly web interface allows users to input a list of predicted cooperative TF pairs from their algorithm and select (i) the compared algorithms among the 15 existing algorithms, (ii) the performance indices among the eight existing indices, and (iii) the overall performance scores from two possible choices. The comprehensive performance comparison results are then generated in tens of seconds and shown as both bar charts and tables. The original comparison results of each compared algorithm and each selected performance index can be downloaded as text files for further analyses.

Conclusions

Allowing users to select eight existing performance indices and 15 existing algorithms for comparison, our web tool benefits researchers who are eager to comprehensively and objectively evaluate the performance of their newly developed algorithm. Thus, our tool greatly expedites the progress in the research of computational identification of cooperative TF pairs.

Properly defining the targets of a transcription factor significantly improves the computational identification of cooperative transcription factor pairs in yeast

Background

Transcriptional regulation of gene expression in eukaryotes is usually accomplished by cooperative transcription factors (TFs). Computational identification of cooperative TF pairs has become a hot research topic and many algorithms have been proposed in the literature. A typical algorithm for predicting cooperative TF pairs has two steps. (Step 1) Define the targets of each TF under study. (Step 2) Design a measure for calculating the cooperativity of a TF pair based on the targets of these two TFs. While different algorithms have distinct sophisticated cooperativity measures, the targets of a TF are usually defined using ChIP-chip data. However, there is an inherent weakness in using ChIP-chip data to define the targets of a TF. ChIP-chip analysis can only identify the binding targets of a TF but it cannot distinguish the true regulatory from the binding but non-regulatory targets of a TF.

Results

This work is the first study which aims to investigate whether the performance of computational identification of cooperative TF pairs could be improved by using a more biologically relevant way to define the targets of a TF. For this purpose, we propose four simple algorithms, all of which consist of two steps. (Step 1) Define the targets of a TF using (i) ChIP-chip data in the first algorithm, (ii) TF binding data in the second algorithm, (iii) TF perturbation data in the third algorithm, and (iv) the intersection of TF binding and TF perturbation data in the fourth algorithm. Compared with the first three algorithms, the fourth algorithm uses a more biologically relevant way to define the targets of a TF. (Step 2) Measure the cooperativity of a TF pair by the statistical significance of the overlap of the targets of these two TFs using the hypergeometric test. By adopting four existing performance indices, we show that the fourth proposed algorithm (PA4) significantly out performs the other three proposed algorithms. This suggests that the computational identification of cooperative TF pairs is indeed improved when using a more biologically relevant way to define the targets of a TF. Strikingly, the prediction results of our simple PA4 are more biologically meaningful than those of the 12 existing sophisticated algorithms in the literature, all of which used ChIP-chip data to define the targets of a TF. This suggests that properly defining the targets of a TF may be more important than designing sophisticated cooperativity measures. In addition, our PA4 has the power to predict several experimentally validated cooperative TF pairs, which have not been successfully predicted by any existing algorithms in the literature.

Conclusions

This study shows that the performance of computational identification of cooperative TF pairs could be improved by using a more biologically relevant way to define the targets of a TF. The main contribution of this study is not to propose another new algorithm but to provide a new thinking for the research of computational identification of cooperative TF pairs. Researchers should put more effort on properly defining the targets of a TF (i.e. Step 1) rather than totally focus on designing sophisticated cooperativity measures (i.e. Step 2). The lists of TF target genes, the Matlab codes and the prediction results of the four proposed algorithms could be downloaded from our companion website http://cosbi3.ee.ncku.edu.tw/TFI/

A network medicine approach to quantify distance between hereditary disease modules on the interactome

We introduce a MeSH-based method that accurately quantifies similarity between heritable diseases at molecular level. This method effectively brings together the existing information about diseases that is scattered across the vast corpus of biomedical literature. We prove that sets of MeSH terms provide a highly descriptive representation of heritable disease and that the structure of MeSH provides a natural way of combining individual MeSH vocabularies. We show that our measure can be used effectively in the prediction of candidate disease genes. We developed a web application to query more than 28.5 million relationships between 7,574 hereditary diseases (96% of OMIM) based on our similarity measure.

Mining protein interactomes to improve their reliability and support the advancement of network medicine

High-throughput detection of protein interactions has had a major impact in our understanding of the intricate molecular machinery underlying the living cell, and has permitted the construction of very large protein interactomes. The protein networks that are currently available are incomplete and a significant percentage of their interactions are false positives. Fortunately, the structural properties observed in good quality social or technological networks are also present in biological systems. This has encouraged the development of tools, to improve the reliability of protein networks and predict new interactions based merely on the topological characteristics of their components. Since diseases are rarely caused by the malfunction of a single protein, having a more complete and reliable interactome is crucial in order to identify groups of inter-related proteins involved in disease etiology. These system components can then be targeted with minimal collateral damage. In this article, an important number of network mining tools is reviewed, together with resources from which reliable protein interactomes can be constructed. In addition to the review, a few representative examples of how molecular and clinical data can be integrated to deepen our understanding of pathogenesis are discussed.

Predicting protein function via downward random walks on a gene ontology

Background

High-throughput bio-techniques accumulate ever-increasing amount of genomic and proteomic data. These data are far from being functionally characterized, despite the advances in gene (or gene’s product proteins) functional annotations. Due to experimental techniques and to the research bias in biology, the regularly updated functional annotation databases, i.e., the Gene Ontology (GO), are far from being complete. Given the importance of protein functions for biological studies and drug design, proteins should be more comprehensively and precisely annotated.

Results

We proposed downward Random Walks (dRW) to predict missing (or new) functions of partially annotated proteins. Particularly, we apply downward random walks with restart on the GO directed acyclic graph, along with the available functions of a protein, to estimate the probability of missing functions. To further boost the prediction accuracy, we extend dRW to dRW-kNN. dRW-kNN computes the semantic similarity between proteins based on the functional annotations of proteins; it then predicts functions based on the functions estimated by dRW, together with the functions associated with the k nearest proteins. Our proposed models can predict two kinds of missing functions: (i) the ones that are missing for a protein but associated with other proteins of interest; (ii) the ones that are not available for any protein of interest, but exist in the GO hierarchy. Experimental results on the proteins of Yeast and Human show that dRW and dRW-kNN can replenish functions more accurately than other related approaches, especially for sparse functions associated with no more than 10 proteins.

Conclusion

The empirical study shows that the semantic similarity between GO terms and the ontology hierarchy play important roles in predicting protein function. The proposed dRW and dRW-kNN can serve as tools for replenishing functions of partially annotated proteins.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-015-0713-y) contains supplementary material, which is available to authorized users.

A Two-Stage Geometric Method for Pruning Unreliable Links in Protein-Protein Networks

Protein-protein interactions (PPIs) play essential roles for determining the outcomes of most of the cellular functions of the cell. Although the experimentally detected high-throughput PPI data promise new opportunities for the study of many biological mechanisms including cellular metabolism and protein functions, experimentally detected PPIs have high levels of false positive rate. Therefore, it is of high practical value to develop novel computational tools for pruning low-confidence PPIs. In this paper, we propose a new geometric approach called Leave-One-Out Logistic Metric Embedding (LOO-LME) for assessing the reliability of interactions. Unlike previous approaches which mainly seek to preserve the noisy topological information of the PPI networks in the embedding space, LOO-LME first transforms the learning task into an equivalent discriminant form, then directly deals with the uncertainty in PPI networks using a leave-one-out-style approach. The experimental results show that LOO-LME substantially outperforms previous methods on PPI assessment problems. LOO-LME could thus facilitate further graph-based studies of PPIs and may help infer their hidden underlying biological knowledge.

Integrating multiple networks for protein function prediction

Background

High throughput techniques produce multiple functional association networks. Integrating these networks can enhance the accuracy of protein function prediction. Many algorithms have been introduced to generate a composite network, which is obtained as a weighted sum of individual networks. The weight assigned to an individual network reflects its benefit towards the protein functional annotation inference. A classifier is then trained on the composite network for predicting protein functions. However, since these techniques model the optimization of the composite network and the prediction tasks as separate objectives, the resulting composite network is not necessarily optimal for the follow-up protein function prediction.

Results

We address this issue by modeling the optimization of the composite network and the prediction problems within a unified objective function. In particular, we use a kernel target alignment technique and the loss function of a network based classifier to jointly adjust the weights assigned to the individual networks. We show that the proposed method, called MNet, can achieve a performance that is superior (with respect to different evaluation criteria) to related techniques using the multiple networks of four example species (yeast, human, mouse, and fly) annotated with thousands (or hundreds) of GO terms.

Conclusion

MNet can effectively integrate multiple networks for protein function prediction and is robust to the input parameters. Supplementary data is available at https://sites.google.com/site/guoxian85/home/mnet. The Matlab code of MNet is available upon request.

Identifying cooperative transcription factors in yeast using multiple data sources

BACKGROUND

Transcriptional regulation of gene expression is usually accomplished by multiple interactive transcription factors (TFs). Therefore, it is crucial to understand the precise cooperative interactions among TFs. Various kinds of experimental data including ChIP-chip, TF binding site (TFBS), gene expression, TF knockout and protein-protein interaction data have been used to identify cooperative TF pairs in existing methods. The nucleosome occupancy data is not yet used for this research topic despite that several researches have revealed the association between nucleosomes and TFBSs.

RESULTS

In this study, we developed a novel method to infer the cooperativity between two TFs by integrating the TF-gene documented regulation, TFBS and nucleosome occupancy data. TF-gene documented regulation and TFBS data were used to determine the target genes of a TF, and the genome-wide nucleosome occupancy data was used to assess the nucleosome occupancy on TFBSs. Our method identifies cooperative TF pairs based on two biologically plausible assumptions. If two TFs cooperate, then (i) they should have a significantly higher number of common target genes than random expectation and (ii) their binding sites (in the promoters of their common target genes) should tend to be co-depleted of nucleosomes in order to make these binding sites simultaneously accessible to TF binding. Each TF pair is given a cooperativity score by our method. The higher the score is, the more likely a TF pair has cooperativity. Finally, a list of 27 cooperative TF pairs has been predicted by our method. Among these 27 TF pairs, 19 pairs are also predicted by existing methods. The other 8 pairs are novel cooperative TF pairs predicted by our method. The biological relevance of these 8 novel cooperative TF pairs is justified by the existence of protein-protein interactions and co-annotation in the same MIPS functional categories. Moreover, we adopted three performance indices to compare our predictions with 11 existing methods' predictions. We show that our method performs better than these 11 existing methods in identifying cooperative TF pairs in yeast. Finally, the cooperative TF network constructed from the 27 predicted cooperative TF pairs shows that our method has the power to find cooperative TF pairs of different biological processes.

CONCLUSION

Our method is effective in identifying cooperative TF pairs in yeast. Many of our predictions are validated by the literature, and our method outperforms 11 existing methods. We believe that our study will help biologists to understand the mechanisms of transcriptional regulation in eukaryotic cells.

An integrative approach for measuring semantic similarities using gene ontology

Background

Gene Ontology (GO) provides rich information and a convenient way to study gene functional similarity, which has been successfully used in various applications. However, the existing GO based similarity measurements have limited functions for only a subset of GO information is considered in each measure. An appropriate integration of the existing measures to take into account more information in GO is demanding.

Results

We propose a novel integrative measure called InteGO2 to automatically select appropriate seed measures and then to integrate them using a metaheuristic search method. The experiment results show that InteGO2 significantly improves the performance of gene similarity in human, Arabidopsis and yeast on both molecular function and biological process GO categories.

Conclusions

InteGO2 computes gene-to-gene similarities more accurately than tested existing measures and has high robustness. The supplementary document and software are available at http://mlg.hit.edu.cn:8082/.

A comprehensive performance evaluation on the prediction results of existing cooperative transcription factors identification algorithms

Background

Eukaryotic transcriptional regulation is known to be highly connected through the networks of cooperative transcription factors (TFs). Measuring the cooperativity of TFs is helpful for understanding the biological relevance of these TFs in regulating genes. The recent advances in computational techniques led to various predictions of cooperative TF pairs in yeast. As each algorithm integrated different data resources and was developed based on different rationales, it possessed its own merit and claimed outperforming others. However, the claim was prone to subjectivity because each algorithm compared with only a few other algorithms and only used a small set of performance indices for comparison. This motivated us to propose a series of indices to objectively evaluate the prediction performance of existing algorithms. And based on the proposed performance indices, we conducted a comprehensive performance evaluation.

Results

We collected 14 sets of predicted cooperative TF pairs (PCTFPs) in yeast from 14 existing algorithms in the literature. Using the eight performance indices we adopted/proposed, the cooperativity of each PCTFP was measured and a ranking score according to the mean cooperativity of the set was given to each set of PCTFPs under evaluation for each performance index. It was seen that the ranking scores of a set of PCTFPs vary with different performance indices, implying that an algorithm used in predicting cooperative TF pairs is of strength somewhere but may be of weakness elsewhere. We finally made a comprehensive ranking for these 14 sets. The results showed that Wang J's study obtained the best performance evaluation on the prediction of cooperative TF pairs in yeast.

Conclusions

In this study, we adopted/proposed eight performance indices to make a comprehensive performance evaluation on the prediction results of 14 existing cooperative TFs identification algorithms. Most importantly, these proposed indices can be easily applied to measure the performance of new algorithms developed in the future, thus expedite progress in this research field.

Information content-based Gene Ontology functional similarity measures: which one to use for a given biological data type?

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

Spotlite: web application and augmented algorithms for predicting co-complexed proteins from affinity purification--mass spectrometry data

Protein-protein interactions defined by affinity purification and mass spectrometry (APMS) suffer from high false discovery rates. Consequently, lists of potential interactions must be pruned of contaminants before network construction and interpretation, historically an expensive, time-intensive, and error-prone task. In recent years, numerous computational methods were developed to identify genuine interactions from the hundreds of candidates. Here, comparative analysis of three popular algorithms, HGSCore, CompPASS, and SAINT, revealed complementarity in their classification accuracies, which is supported by their divergent scoring strategies. We improved each algorithm by an average area under a receiver operating characteristics curve increase of 16% by integrating a variety of indirect data known to correlate with established protein-protein interactions, including mRNA coexpression, gene ontologies, domain-domain binding affinities, and homologous protein interactions. Each APMS scoring approach was incorporated into a separate logistic regression model along with the indirect features; the resulting three classifiers demonstrate improved performance on five diverse APMS data sets. To facilitate APMS data scoring within the scientific community, we created Spotlite, a user-friendly and fast web application. Within Spotlite, data can be scored with the augmented classifiers, annotated, and visualized ( http://cancer.unc.edu/majorlab/software.php ). The utility of the Spotlite platform to reveal physical, functional, and disease-relevant characteristics within APMS data is established through a focused analysis of the KEAP1 E3 ubiquitin ligase.

An extensive analysis of disease-gene associations using network integration and fast kernel-based gene prioritization methods

OBJECTIVE

In the context of "network medicine", gene prioritization methods represent one of the main tools to discover candidate disease genes by exploiting the large amount of data covering different types of functional relationships between genes. Several works proposed to integrate multiple sources of data to improve disease gene prioritization, but to our knowledge no systematic studies focused on the quantitative evaluation of the impact of network integration on gene prioritization. In this paper, we aim at providing an extensive analysis of gene-disease associations not limited to genetic disorders, and a systematic comparison of different network integration methods for gene prioritization.

MATERIALS AND METHODS

We collected nine different functional networks representing different functional relationships between genes, and we combined them through both unweighted and weighted network integration methods. We then prioritized genes with respect to each of the considered 708 medical subject headings (MeSH) diseases by applying classical guilt-by-association, random walk and random walk with restart algorithms, and the recently proposed kernelized score functions.

RESULTS

The results obtained with classical random walk algorithms and the best single network achieved an average area under the curve (AUC) across the 708 MeSH diseases of about 0.82, while kernelized score functions and network integration boosted the average AUC to about 0.89. Weighted integration, by exploiting the different "informativeness" embedded in different functional networks, outperforms unweighted integration at 0.01 significance level, according to the Wilcoxon signed rank sum test. For each MeSH disease we provide the top-ranked unannotated candidate genes, available for further bio-medical investigation.

CONCLUSIONS

Network integration is necessary to boost the performances of gene prioritization methods. Moreover the methods based on kernelized score functions can further enhance disease gene ranking results, by adopting both local and global learning strategies, able to exploit the overall topology of the network.

Hierarchical ensemble methods for protein function prediction

Protein function prediction is a complex multiclass multilabel classification problem, characterized by multiple issues such as the incompleteness of the available annotations, the integration of multiple sources of high dimensional biomolecular data, the unbalance of several functional classes, and the difficulty of univocally determining negative examples. Moreover, the hierarchical relationships between functional classes that characterize both the Gene Ontology and FunCat taxonomies motivate the development of hierarchy-aware prediction methods that showed significantly better performances than hierarchical-unaware "flat" prediction methods. In this paper, we provide a comprehensive review of hierarchical methods for protein function prediction based on ensembles of learning machines. According to this general approach, a separate learning machine is trained to learn a specific functional term and then the resulting predictions are assembled in a "consensus" ensemble decision, taking into account the hierarchical relationships between classes. The main hierarchical ensemble methods proposed in the literature are discussed in the context of existing computational methods for protein function prediction, highlighting their characteristics, advantages, and limitations. Open problems of this exciting research area of computational biology are finally considered, outlining novel perspectives for future research.

Measure the Semantic Similarity of GO Terms Using Aggregate Information Content

The rapid development of gene ontology (GO) and huge amount of biomedical data annotated by GO terms necessitate computation of semantic similarity of GO terms and, in turn, measurement of functional similarity of genes based on their annotations. In this paper we propose a novel and efficient method to measure the semantic similarity of GO terms. The proposed method addresses the limitations in existing GO term similarity measurement techniques; it computes the semantic content of a GO term by considering the information content of all of its ancestor terms in the graph. The aggregate information content (AIC) of all ancestor terms of a GO term implicitly reflects the GO term's location in the GO graph and also represents how human beings use this GO term and all its ancestor terms to annotate genes. We show that semantic similarity of GO terms obtained by our method closely matches the human perception. Extensive experimental studies show that this novel method also outperforms all existing methods in terms of the correlation with gene expression data. We have developed web services for measuring semantic similarity of GO terms and functional similarity of genes using the proposed AIC method and other popular methods. These web services are available at http://bioinformatics.clemson.edu/G-SESAME.

GOssTo: a stand-alone application and a web tool for calculating semantic similarities on the Gene Ontology

Summary: We present GOssTo, the Gene Ontology semantic similarity Tool, a user-friendly software system for calculating semantic similarities between gene products according to the Gene Ontology. GOssTo is bundled with six semantic similarity measures, including both term- and graph-based measures, and has extension capabilities to allow the user to add new similarities. Importantly, for any measure, GOssTo can also calculate the Random Walk Contribution that has been shown to greatly improve the accuracy of similarity measures. GOssTo is very fast, easy to use, and it allows the calculation of similarities on a genomic scale in a few minutes on a regular desktop machine.

Contact: alberto@cs.rhul.ac.uk

Availability: GOssTo is available both as a stand-alone application running on GNU/Linux, Windows and MacOS from www.paccanarolab.org/gossto and as a web application from www.paccanarolab.org/gosstoweb. The stand-alone application features a simple and concise command line interface for easy integration into high-throughput data processing pipelines.

Heterodimeric protein complex identification by naïve Bayes classifiers

Background

Protein complexes are basic cellular entities that carry out the functions of their components. It can be found that in databases of protein complexes of yeast like CYC2008, the major type of known protein complexes is heterodimeric complexes. Although a number of methods for trying to predict sets of proteins that form arbitrary types of protein complexes simultaneously have been proposed, it can be found that they often fail to predict heterodimeric complexes.

Results

In this paper, we have designed several features characterizing heterodimeric protein complexes based on genomic data sets, and proposed a supervised-learning method for the prediction of heterodimeric protein complexes. This method learns the parameters of the features, which are embedded in the naïve Bayes classifier. The log-likelihood ratio derived from the naïve Bayes classifier with the parameter values obtained by maximum likelihood estimation gives the score of a given pair of proteins to predict whether the pair is a heterodimeric complex or not. A five-fold cross-validation shows good performance on yeast. The trained classifiers also show higher predictability than various existing algorithms on yeast data sets with approximate and exact matching criteria.

Conclusions

Heterodimeric protein complex prediction is a rather harder problem than heteromeric protein complex prediction because heterodimeric protein complex is topologically simpler. However, it turns out that by designing features specialized for heterodimeric protein complexes, predictability of them can be improved. Thus, the design of more sophisticate features for heterodimeric protein complexes as well as the accumulation of more accurate and useful genome-wide data sets will lead to higher predictability of heterodimeric protein complexes. Our tool can be downloaded from http://imi.kyushu-u.ac.jp/~om/.

A framework for unifying ontology-based semantic similarity measures: a study in the biomedical domain

Ontologies are widely adopted in the biomedical domain to characterize various resources (e.g. diseases, drugs, scientific publications) with non-ambiguous meanings. By exploiting the structured knowledge that ontologies provide, a plethora of ad hoc and domain-specific semantic similarity measures have been defined over the last years. Nevertheless, some critical questions remain: which measure should be defined/chosen for a concrete application? Are some of the, a priori different, measures indeed equivalent? In order to bring some light to these questions, we perform an in-depth analysis of existing ontology-based measures to identify the core elements of semantic similarity assessment. As a result, this paper presents a unifying framework that aims to improve the understanding of semantic measures, to highlight their equivalences and to propose bridges between their theoretical bases. By demonstrating that groups of measures are just particular instantiations of parameterized functions, we unify a large number of state-of-the-art semantic similarity measures through common expressions. The application of the proposed framework and its practical usefulness is underlined by an empirical analysis of hundreds of semantic measures in a biomedical context.