Dataset Information

Investigating the predictability of essential genes across distantly related organisms using an integrative approach.

ABSTRACT: Rapid and accurate identification of new essential genes in under-studied microorganisms will significantly improve our understanding of how a cell works and the ability to re-engineer microorganisms. However, predicting essential genes across distantly related organisms remains a challenge. Here, we present a machine learning-based integrative approach that reliably transfers essential gene annotations between distantly related bacteria. We focused on four bacterial species that have well-characterized essential genes, and tested the transferability between three pairs among them. For each pair, we trained our classifier to learn traits associated with essential genes in one organism, and applied it to make predictions in the other. The predictions were then evaluated by examining the agreements with the known essential genes in the target organism. Ten-fold cross-validation in the same organism yielded AUC scores between 0.86 and 0.93. Cross-organism predictions yielded AUC scores between 0.69 and 0.89. The transferability is likely affected by growth conditions, quality of the training data set and the evolutionary distance. We are thus the first to report that gene essentiality can be reliably predicted using features trained and tested in a distantly related organism. Our approach proves more robust and portable than existing approaches, significantly extending our ability to predict essential genes beyond orthologs.

SUBMITTER: Deng J

PROVIDER: S-EPMC3035443 | biostudies-literature | 2011 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Investigating the predictability of essential genes across distantly related organisms using an integrative approach.

Deng Jingyuan J Deng Lei L Su Shengchang S Zhang Minlu M Lin Xiaodong X Wei Lan L Minai Ali A AA Hassett Daniel J DJ Lu Long J LJ

Nucleic acids research 20100924 3

Rapid and accurate identification of new essential genes in under-studied microorganisms will significantly improve our understanding of how a cell works and the ability to re-engineer microorganisms. However, predicting essential genes across distantly related organisms remains a challenge. Here, we present a machine learning-based integrative approach that reliably transfers essential gene annotations between distantly related bacteria. We focused on four bacterial species that have well-chara ...[more]

PMID: 20870748

Similar Datasets

Project description:Obesity is a multi-factorial health problem in which genetic factors play an important role. Limited results have been obtained in single-gene studies using either genomic or transcriptomic data. RNA sequencing technology has shown its potential in gaining accurate knowledge about the transcriptome, and may reveal novel genes affecting complex diseases. Integration of genomic and transcriptomic variation (expression quantitative trait loci [eQTL] mapping) has identified causal variants that affect complex diseases. We integrated transcriptomic data from adipose tissue and genomic data from a porcine model to investigate the mechanisms involved in obesity using a systems genetics approach.Using a selective gene expression profiling approach, we selected 36 animals based on a previously created genomic Obesity Index for RNA sequencing of subcutaneous adipose tissue. Differential expression analysis was performed using the Obesity Index as a continuous variable in a linear model. eQTL mapping was then performed to integrate 60 K porcine SNP chip data with the RNA sequencing data. Results were restricted based on genome-wide significant single nucleotide polymorphisms, detected differentially expressed genes, and previously detected co-expressed gene modules. Further data integration was performed by detecting co-expression patterns among eQTLs and integration with protein data.Differential expression analysis of RNA sequencing data revealed 458 differentially expressed genes. The eQTL mapping resulted in 987 cis-eQTLs and 73 trans-eQTLs (false discovery rate?<?0.05), of which the cis-eQTLs were associated with metabolic pathways. We reduced the eQTL search space by focusing on differentially expressed and co-expressed genes and disease-associated single nucleotide polymorphisms to detect obesity-related genes and pathways. Building a co-expression network using eQTLs resulted in the detection of a module strongly associated with lipid pathways. Furthermore, we detected several obesity candidate genes, for example, ENPP1, CTSL, and ABHD12B.To our knowledge, this is the first study to perform an integrated genomics and transcriptomics (eQTL) study using, and modeling, genomic and subcutaneous adipose tissue RNA sequencing data on obesity in a porcine model. We detected several pathways and potential causal genes for obesity. Further validation and investigation may reveal their exact function and association with obesity.

Project description:Machine learning approaches to predict essential genes have gained a lot of traction in recent years. These approaches predominantly make use of sequence and network-based features to predict essential genes. However, the scope of network-based features used by the existing approaches is very narrow. Further, many of these studies focus on predicting essential genes within the same organism, which cannot be readily used to predict essential genes across organisms. Therefore, there is clearly a need for a method that is able to predict essential genes across organisms, by leveraging network-based features. In this study, we extract several sets of network-based features from protein-protein association networks available from the STRING database. Our network features include some common measures of centrality, and also some novel recursive measures recently proposed in social network literature. We extract hundreds of network-based features from networks of 27 diverse organisms to predict the essentiality of 87000+ genes. Our results show that network-based features are statistically significantly better at classifying essential genes across diverse bacterial species, compared to the current state-of-the-art methods, which use mostly sequence and a few 'conventional' network-based features. Our diverse set of network properties gave an AUROC of 0.847 and a precision of 0.320 across 27 organisms. When we augmented the complete set of network features with sequence-derived features, we achieved an improved AUROC of 0.857 and a precision of 0.335. We also constructed a reduced set of 100 sequence and network features, which gave a comparable performance. Further, we show that our features are useful for predicting essential genes in new organisms by using leave-one-species-out validation. Our network features capture the local, global and neighbourhood properties of the network and are hence effective for prediction of essential genes across diverse organisms, even in the absence of other complex biological knowledge. Our approach can be readily exploited to predict essentiality for organisms in interactome databases such as the STRING, where both network and sequence are readily available. All codes are available at https://github.com/RamanLab/nbfpeg.

Dataset Information

Investigating the predictability of essential genes across distantly related organisms using an integrative approach.

Publications

Investigating the predictability of essential genes across distantly related organisms using an integrative approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets