Functional cohesion of gene sets determined by latent semantic indexing of PubMed abstracts

High-throughput genomic technologies enable researchers to identify genes that are co-regulated with respect to specific experimental conditions. Numerous statistical approaches have been developed to identify differentially expressed genes. Because each approach can produce distinct gene sets, it is difficult for biologists to determine which statistical approach yields biologically relevant gene sets and is appropriate for their study. To address this issue, we implemented Latent Semantic Indexing (LSI) to determine the functional coherence of gene sets. An LSI model was built using over 1 million Medline abstracts for over 20,000 mouse and human genes annotated in Entrez Gene. The gene-to-gene LSI-derived similarities were used to calculate a literature cohesion p-value (LPv) for a given gene set using a Fisher's exact test. We tested this method against genes in more than 6,000 functional pathways annotated in Gene Ontology (GO) and found that approximately 75% of gene sets in GO biological process category and 90% of the gene sets in GO molecular function and cellular component categories were functionally cohesive (LPv<0.05). These results indicate that the LPv methodology is both robust and accurate. Application of this method to previously published microarray datasets demonstrated that LPv can be helpful in selecting the appropriate feature extraction methods. To enable real-time calculation of LPv for mouse or human gene sets, we developed a web tool called Gene-set Cohesion Analysis Tool (GCAT). GCAT can complement other gene set enrichment approaches by determining the overall functional cohesion of data sets, taking into account both explicit and implicit gene interactions reported in the biomedical literature. Availability: GCAT is freely available at http://binf1.memphis.edu/gcat.     

GOing Bayesian: model-based gene set analysis of genome-scale data

The interpretation of data-driven experiments in genomics often involves a search for biological categories that are enriched for the responder genes identified by the experiments. However, knowledge bases such as the Gene Ontology (GO) contain hundreds or thousands of categories with very high overlap between categories. Thus, enrichment analysis performed on one category at a time frequently returns large numbers of correlated categories, leaving the choice of the most relevant ones to the user''s; interpretation.Here we present model-based gene set analysis (MGSA) that analyzes all categories at once by embedding them in a Bayesian network, in which gene response is modeled as a function of the activation of biological categories. Probabilistic inference is used to identify the active categories. The Bayesian modeling approach naturally takes category overlap into account and avoids the need for multiple testing corrections met in single-category enrichment analysis. On simulated data, MGSA identifies active categories with up to 95% precision at a recall of 20% for moderate settings of noise, leading to a 10-fold precision improvement over single-category statistical enrichment analysis. Application to a gene expression data set in yeast demonstrates that the method provides high-level, summarized views of core biological processes and correctly eliminates confounding associations.     

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.     

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.     

Predicting gene function using few positive examples and unlabeled ones

Background

A large amount of functional genomic data have provided enough knowledge in predicting gene function computationally, which uses known functional annotations and relationship between unknown genes and known ones to map unknown genes to GO functional terms. The prediction procedure is usually formulated as binary classification problem. Training binary classifier needs both positive examples and negative ones that have almost the same size. However, from various annotation database, we can only obtain few positive genes annotation for most offunctional terms, that is, there are only few positive examples for training classifier, which makes predicting directly gene function infeasible.

Results

We propose a novel approach SPE_RNE to train classifier for each functional term. Firstly, positive examples set is enlarged by creating synthetic positive examples. Secondly, representative negative examples are selected by training SVM(support vector machine) iteratively to move classification hyperplane to a appropriate place. Lastly, an optimal SVM classifier are trained by using grid search technique. On combined kernel ofYeast protein sequence, microarray expression, protein-protein interaction and GO functional annotation data, we compare SPE_RNE with other three typical methods in three classical performance measures recall R, precise P and their combination F: twoclass considers all unlabeled genes as negative examples, twoclassbal selects randomly same number negative examples from unlabeled gene, PSoL selects a negative examples set that are far from positive examples and far from each other.

Conclusions

In test data and unknown genes data, we compute average and variant of measure F. The experiments showthat our approach has better generalized performance and practical prediction capacity. In addition, our method can also be used for other organisms such as human.

     

Hierarchical multi-label prediction of gene function

MOTIVATION: Assigning functions for unknown genes based on diverse large-scale data is a key task in functional genomics. Previous work on gene function prediction has addressed this problem using independent classifiers for each function. However, such an approach ignores the structure of functional class taxonomies, such as the Gene Ontology (GO). Over a hierarchy of functional classes, a group of independent classifiers where each one predicts gene membership to a particular class can produce a hierarchically inconsistent set of predictions, where for a given gene a specific class may be predicted positive while its inclusive parent class is predicted negative. Taking the hierarchical structure into account resolves such inconsistencies and provides an opportunity for leveraging all classifiers in the hierarchy to achieve higher specificity of predictions. RESULTS: We developed a Bayesian framework for combining multiple classifiers based on the functional taxonomy constraints. Using a hierarchy of support vector machine (SVM) classifiers trained on multiple data types, we combined predictions in our Bayesian framework to obtain the most probable consistent set of predictions. Experiments show that over a 105-node subhierarchy of the GO, our Bayesian framework improves predictions for 93 nodes. As an additional benefit, our method also provides implicit calibration of SVM margin outputs to probabilities. Using this method, we make function predictions for multiple proteins, and experimentally confirm predictions for proteins involved in mitosis. SUPPLEMENTARY INFORMATION: Results for the 105 selected GO classes and predictions for 1059 unknown genes are available at: http://function.princeton.edu/genesite/ CONTACT: ogt@cs.princeton.edu.     

Gaining confidence in biological interpretation of the microarray data: the functional consistence of the significant GO categories

MOTIVATION: In microarray studies, numerous tools are available for functional enrichment analysis based on GO categories. Most of these tools, due to their requirement of a prior threshold for designating genes as differentially expressed genes (DEGs), are categorized as threshold-dependent methods that often suffer from a major criticism on their changing results with different thresholds. RESULTS: In the present article, by considering the inherent correlation structure of the GO categories, a continuous measure based on semantic similarity of GO categories is proposed to investigate the functional consistence (or stability) of threshold-dependent methods. The results from several datasets show when simply counting overlapping categories between two groups, the significant category groups selected under different DEG thresholds are seemingly very different. However, based on the semantic similarity measure proposed in this article, the results are rather functionally consistent for a wide range of DEG thresholds. Moreover, we find that the functional consistence of gene lists ranked by SAM metric behaves relatively robust against changing DEG thresholds. AVAILABILITY: Source code in R is available on request from the authors.     

Comparison of pathway analysis approaches using lung cancer GWAS data sets

Pathway analysis has been proposed as a complement to single SNP analyses in GWAS. This study compared pathway analysis methods using two lung cancer GWAS data sets based on four studies: one a combined data set from Central Europe and Toronto (CETO); the other a combined data set from Germany and MD Anderson (GRMD). We searched the literature for pathway analysis methods that were widely used, representative of other methods, and had available software for performing analysis. We selected the programs EASE, which uses a modified Fishers Exact calculation to test for pathway associations, GenGen (a version of Gene Set Enrichment Analysis (GSEA)), which uses a Kolmogorov-Smirnov-like running sum statistic as the test statistic, and SLAT, which uses a p-value combination approach. We also included a modified version of the SUMSTAT method (mSUMSTAT), which tests for association by averaging χ² statistics from genotype association tests. There were nearly 18000 genes available for analysis, following mapping of more than 300,000 SNPs from each data set. These were mapped to 421 GO level 4 gene sets for pathway analysis. Among the methods designed to be robust to biases related to gene size and pathway SNP correlation (GenGen, mSUMSTAT and SLAT), the mSUMSTAT approach identified the most significant pathways (8 in CETO and 1 in GRMD). This included a highly plausible association for the acetylcholine receptor activity pathway in both CETO (FDR≤0.001) and GRMD (FDR = 0.009), although two strong association signals at a single gene cluster (CHRNA3-CHRNA5-CHRNB4) drive this result, complicating its interpretation. Few other replicated associations were found using any of these methods. Difficulty in replicating associations hindered our comparison, but results suggest mSUMSTAT has advantages over the other approaches, and may be a useful pathway analysis tool to use alongside other methods such as the commonly used GSEA (GenGen) approach.     

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/.     

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.     

A sensitive method for computing GO-based functional similarities among genes with 'shallow annotation'

Methods for computing similarities among genes have attracted increasing attention for their applications in gene clustering, gene expression data analysis, protein interaction prediction and evaluation. To address the need for automatically computing functional similarities of genes, an important class of methods that computes functional similarities by comparing Gene Ontology (GO) annotations of genes has been developed. However, all of the currently available methods have some drawbacks; for example, they either ignore the specificity of the GO terms or do not consider the information contained within the GO structure. As a result, the existing methods perform weakly when the genes are annotated with 'shallow annotations'. Here, we propose a new method to compute functional similarities among genes based on their GO annotations and compare it with the widely-used G-SESAME method. The results show that the new method reliably distinguishes functional similarities among genes and demonstrate that the method is especially sensitive to genes with 'shallow annotations'. Moreover, our method has high correlations with sequence and EC similarities.     

Methodology for the inference of gene function from phenotype data

Background

Biomedical ontologies are increasingly instrumental in the advancement of biological research primarily through their use to efficiently consolidate large amounts of data into structured, accessible sets. However, ontology development and usage can be hampered by the segregation of knowledge by domain that occurs due to independent development and use of the ontologies. The ability to infer data associated with one ontology to data associated with another ontology would prove useful in expanding information content and scope. We here focus on relating two ontologies: the Gene Ontology (GO), which encodes canonical gene function, and the Mammalian Phenotype Ontology (MP), which describes non-canonical phenotypes, using statistical methods to suggest GO functional annotations from existing MP phenotype annotations. This work is in contrast to previous studies that have focused on inferring gene function from phenotype primarily through lexical or semantic similarity measures.

Results

We have designed and tested a set of algorithms that represents a novel methodology to define rules for predicting gene function by examining the emergent structure and relationships between the gene functions and phenotypes rather than inspecting the terms semantically. The algorithms inspect relationships among multiple phenotype terms to deduce if there are cases where they all arise from a single gene function.We apply this methodology to data about genes in the laboratory mouse that are formally represented in the Mouse Genome Informatics (MGI) resource. From the data, 7444 rule instances were generated from five generalized rules, resulting in 4818 unique GO functional predictions for 1796 genes.

Conclusions

We show that our method is capable of inferring high-quality functional annotations from curated phenotype data. As well as creating inferred annotations, our method has the potential to allow for the elucidation of unforeseen, biologically significant associations between gene function and phenotypes that would be overlooked by a semantics-based approach. Future work will include the implementation of the described algorithms for a variety of other model organism databases, taking full advantage of the abundance of available high quality curated data.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-014-0405-z) contains supplementary material, which is available to authorized users.     

Supervised principal component analysis for gene set enrichment of microarray data with continuous or survival outcomes

MOTIVATION: Gene set analysis allows formal testing of subtle but coordinated changes in a group of genes, such as those defined by Gene Ontology (GO) or KEGG Pathway databases. We propose a new method for gene set analysis that is based on principal component analysis (PCA) of genes expression values in the gene set. PCA is an effective method for reducing high dimensionality and capture variations in gene expression values. However, one limitation with PCA is that the latent variable identified by the first PC may be unrelated to outcome. RESULTS: In the proposed supervised PCA (SPCA) model for gene set analysis, the PCs are estimated from a selected subset of genes that are associated with outcome. As outcome information is used in the gene selection step, this method is supervised, thus called the Supervised PCA model. Because of the gene selection step, test statistic in SPCA model can no longer be approximated well using t-distribution. We propose a two-component mixture distribution based on Gumbel exteme value distributions to account for the gene selection step. We show the proposed method compares favorably to currently available gene set analysis methods using simulated and real microarray data. SOFTWARE: The R code for the analysis used in this article are available upon request, we are currently working on implementing the proposed method in an R package.     

CLENCH: a program for calculating Cluster ENriCHment using the Gene Ontology

SUMMARY: Analysis of microarray data most often produces lists of genes with similar expression patterns, which are then subdivided into functional categories for biological interpretation. Such functional categorization is most commonly accomplished using Gene Ontology (GO) categories. Although there are several programs that identify and analyze functional categories for human, mouse and yeast genes, none of them accept Arabidopsis thaliana data. In order to address this need for A.thaliana community, we have developed a program that retrieves GO annotations for A.thaliana genes and performs functional category analysis for lists of genes selected by the user. AVAILABILITY: http://www.personal.psu.edu/nhs109/Clench     

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.