A statistical framework for genomic data fusion

Lanckriet, Gert R. G.; Bie, Tijl De; Cristianini, Nello; Jordan, Michael I.; Noble, William Stafford

doi:10.1093/bioinformatics/bth294

Cited by 589 publications

(456 citation statements)

References 24 publications

Supporting

Mentioning

433

Contrasting

Order By: Relevance

“…This reveals a considerable complementarity between the different methods: if methods are applied individually, some gene functions may be predicted highly accurately while the others not at all. A combination of genome sequence-based predictors is able to reach across many different GO functions, consistent with the success of past approaches that integrate across large-scale experimental data sources (Troyanskaya et al, 2003;Lee et al, 2004;Lanckriet et al, 2004;von Mering et al, 2005;Hu et al, 2009;Lee et al, 2010).…”

Section: Extensive Complementarity Between Afp Methodssupporting

confidence: 73%

“…S1a; Pellegrini et al, 1999;Kensche et al, 2008;de Vienne and Azé, 2012) or by machine learning (Tian et al, 2008;Škunca et al, 2013). Second, biophysical and protein sequence properties (BPS) method includes 1,170 features representing amino acid composition, particular motifs or periodicities (King et al, 2001;Jensen et al, 2003;Lanckriet et al, 2004;Minneci et al, 2013) and various sequence statistics (summary in Sec. S1).…”

Section: Representing Gene Families Using Diverse Sets Of Genomic Feamentioning

confidence: 99%

“…We employ the empirical kernel map (EKM) (Tsuda, 1999;Lanckriet et al, 2004;Sokolov and Ben-Hur, 2010) approach, wherein sequence similarity between pairs of OGs is considered by performing searches towards a reference set of genomes, in our case encompassing six genomes (Sec. S1) and 8,447 OGs therein.…”

Section: Representing Gene Families Using Diverse Sets Of Genomic Feamentioning

confidence: 99%

“…Such rules may, however, also extend to the deeper, more informative levels of the GO. A known example is the contrast between ribosomal proteins and membrane proteins in yeast, where the former are predictable from gene coexpression, while in the latter case, protein compositional features are more relevant (Lanckriet et al, 2004). More generally, assigning function-specific weights to integrated gene networks inferred from biological experiments improves AFP accuracy (Myers and Troyanskaya, 2007;Mostafavi and Morris, 2010).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Extensive complementarity between gene function prediction methods

2016

View full text Add to dashboard Cite

Motivation: The number of sequenced genomes rises steadily, but we still lack the knowledge about the biological roles of many genes. Automatic function prediction (AFP) is thus a necessity. We hypothesize that AFP approaches which draw on distinct genome features may be useful for predicting different types of gene functions, motivating a systematic analysis of the benefits gained by obtaining and integrating such predictions. Results: Our pipeline amalgamates 5,133,543 genes from 2,071 genomes in a single massive analysis that evaluates five established genomic AFP methodologies. While 1,227 Gene Ontology terms yielded reliable predictions, the majority of these functions were accessible to only one or two of the methods. Moreover, different methods tend to assign a GO term to non-overlapping sets of genes. Thus, inferences made by diverse AFP methods display a striking complementary, both gene-wise and function-wise. Because of this, a viable integration strategy is to simply rely on a single mostconfident prediction per gene/function, instead of enforcing agreement across multiple AFP methods. Using an information-theoretic approach, we estimate that current databases contain 29.2 bits/gene of known E. coli gene functions. This can be increased by up to 5.5 bits/gene using individual AFP methods, or by 11 additional bits/gene upon integration, thereby providing a highly-ranking predictor on the CAFA2 community benchmark. Availability of more sequenced genomes boosts the predictive accuracy of AFP approaches and also the benefit from integrating them.

show abstract

Section: Extensive Complementarity Between Afp Methodssupporting

confidence: 73%

Section: Representing Gene Families Using Diverse Sets Of Genomic Feamentioning

confidence: 99%

Section: Representing Gene Families Using Diverse Sets Of Genomic Feamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Extensive complementarity between gene function prediction methods

2016

View full text Add to dashboard Cite

show abstract

“…Data fusion at results level has also been proposed, based on formal probabilistic approaches, capable of integrating heterogeneous outputs from different resources [53]. Computational implementations can include the representation of each input data set as a separate kernel and the weighted optimized combination of these kernels to reconstruct co-expression patterns [54], as well as Bayesian network-based functions [55], decision trees [56] and weighted rank aggregation [57]. In particular, we tested the RankAggreg R package [58], which exploits the rank aggregation method.…”

Section: Comparative Meta-analysis Of Results From Different Platformsmentioning

confidence: 99%

Gene co-expression analyses: an overview from microarray collections inArabidopsis thaliana

et al. 2016

View full text Add to dashboard Cite

Bioinformatics web-based resources and databases are precious references for most biological laboratories worldwide. However, the quality and reliability of the information they provide depends on them being used in an appropriate way that takes into account their specific features. Huge collections of gene expression data are currently publicly available, ready to support the understanding of gene and genome functionalities. In this context, tools and resources for gene co-expression analyses have flourished to exploit the 'guilty by association' principle, which assumes that genes with correlated expression profiles are functionally related. In the case of Arabidopsis thaliana, the reference species in plant biology, the resources available mainly consist of microarray results. After a general overview of such resources, we tested and compared the results they offer for gene co-expression analysis. We also discuss the effect on the results when using different data sets, as well as different data normalization approaches and parameter settings, which often consider different metrics for establishing co-expression. A dedicated example analysis of different gene pools, implemented by including/excluding mutant samples in a reference data set, showed significant variation of gene co-expression occurrence, magnitude and direction. We conclude that, as the heterogeneity of the resources and methods may produce different results for the same query genes, the exploration of more than one of the available resources is strongly recommended. The aim of this article is to show how best to integrate data sources and/or merge outputs to achieve robust analyses and reliable interpretations, thereby making use of diverse data resources an opportunity for added value.

show abstract

Kernels for Remote Sensing Image Classification

Izquierdo‐Verdiguier

Gómez-Chova

Camps‐Valls

2015

Wiley Encyclopedia of Electrical and Electronics Engineering

View full text Add to dashboard Cite

Classification of images acquired by airborne and satellite sensors is a very challenging problem. These remotely sensed images usually acquire information from the scene at different wavelengths or spectral channels. The main problems involved are related to the high dimensionality of the data to be classified and the very few existing labeled samples, the diverse noise sources involved in the acquisition process, the intrinsic nonlinearity and non‐Gaussianity of the data distribution in feature spaces, and the high computational cost involved to process big data cubes in near real time. The framework of statistical learning in general, and of kernel methods in particular, has gained popularity in the last decade. New methods have been presented to address all these problem specificities. We will review the main existing algorithmic proposals to cope with the spatial homogeneity of images, to take advantage of the manifold structure with semisupervised learning, to encode invariances, and to deal with one‐class and multitemporal problems. The design of a suitable regularized functional has led to the successful solution of many remote sensing image classification problems. This article reviews the main advances for remote sensing image supervised classification with kernels through illustrative examples.

show abstract

A statistical framework for genomic data fusion

Abstract: Supplementary data at http://noble.gs.washington.edu/proj/sdp-svm

Cited by 589 publications

References 24 publications

Extensive complementarity between gene function prediction methods

Extensive complementarity between gene function prediction methods

Gene co-expression analyses: an overview from microarray collections inArabidopsis thaliana

Kernels for Remote Sensing Image Classification

Contact Info

Product

Resources

About