Dataset Information

Transcript features alone enable accurate prediction and understanding of gene expression in S. cerevisiae.

ABSTRACT:

Background

Gene expression is a central process in all living organisms. Central questions in the field are related to the way the expression levels of genes are encoded in the transcripts and affect their evolution, and the potential to predict expression levels solely by transcript features. In this study we analyze S. cerevisiae, a model organism with the most abundant relevant cellular and genomic measurements, to evaluate the accuracy in which expression levels can be predicted by different parts of the transcript. To this end, we perform various types of regression analyses based on a total of 5323 features of the transcript. The main advantage of the proposed predictors over previous ones is related to the accurate and comprehensive definitions of the relevant transcript features, which are based on biophysical knowledge of the gene transcription and translation processes, their modeling and evolution.

Results

Cross validation analyses of our predictors demonstrate that they achieve a correlation of 0.68/0.68/0.70/0.61/0.81 with mRNA levels, ribosomal density, protein levels, proteins per mRNA molecule (PPR), and ribosomal load (RL) respectively (all p-values <10(-140)). When we consider predictors that are based exclusively on the features related to different parts of the transcript (5'UTR, ORF, 3'UTR), the correlations with protein levels were 0.27/0.71/0.25 (all p-values <10(-5)), suggesting that the information in the UTRs is redundant, and features of the ORF alone yield similar predictions to the ones obtained based on the entire transcript.

Conclusions

The reported results demonstrate that in the analyzed model organism the expression levels of a gene are encoded in the transcript. Specifically, the prediction of a large fraction of the variance of the different gene expression steps based on transcript features alone is feasible in S. cerevisiae. We report dozens of novel transcript features related to expression levels predictions, demonstrating how such analyses can aid in understanding the gene expression process and its evolution, and how such predictors can be designed for other organisms in the future.

SUBMITTER: Zur H

PROVIDER: S-EPMC3852043 | biostudies-literature | 2013

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Transcript features alone enable accurate prediction and understanding of gene expression in S. cerevisiae.

Zur Hadas H Tuller Tamir T

BMC bioinformatics 20131015

<h4>Background</h4>Gene expression is a central process in all living organisms. Central questions in the field are related to the way the expression levels of genes are encoded in the transcripts and affect their evolution, and the potential to predict expression levels solely by transcript features. In this study we analyze S. cerevisiae, a model organism with the most abundant relevant cellular and genomic measurements, to evaluate the accuracy in which expression levels can be predicted by d ...[more]

PMID: 24564391

Similar Datasets

Project description:BackgroundHistone Mark Modifications (HMs) are crucial actors in gene regulation, as they actively remodel chromatin to modulate transcriptional activity: aberrant combinatorial patterns of HMs have been connected with several diseases, including cancer. HMs are, however, reversible modifications: understanding their role in disease would allow the design of 'epigenetic drugs' for specific, non-invasive treatments. Standard statistical techniques were not entirely successful in extracting representative features from raw HM signals over gene locations. On the other hand, deep learning approaches allow for effective automatic feature extraction, but at the expense of model interpretation.ResultsHere, we propose ShallowChrome, a novel computational pipeline to model transcriptional regulation via HMs in both an accurate and interpretable way. We attain state-of-the-art results on the binary classification of gene transcriptional states over 56 cell-types from the REMC database, largely outperforming recent deep learning approaches. We interpret our models by extracting insightful gene-specific regulative patterns, and we analyse them for the specific case of the PAX5 gene over three differentiated blood cell lines. Finally, we compare the patterns we obtained with the characteristic emission patterns of ChromHMM, and show that ShallowChrome is able to coherently rank groups of chromatin states w.r.t. their transcriptional activity.ConclusionsIn this work we demonstrate that it is possible to model HM-modulated gene expression regulation in a highly accurate, yet interpretable way. Our feature extraction algorithm leverages on data downstream the identification of enriched regions to retrieve gene-wise, statistically significant and dynamically located features for each HM. These features are highly predictive of gene transcriptional state, and allow for accurate modeling by computationally efficient logistic regression models. These models allow a direct inspection and a rigorous interpretation, helping to formulate quantifiable hypotheses.

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

Transcript features alone enable accurate prediction and understanding of gene expression in S. cerevisiae.

Background

Results

Conclusions

Publications

Transcript features alone enable accurate prediction and understanding of gene expression in S. cerevisiae.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets