Dataset Information

Information-based methods for predicting gene function from systematic gene knock-downs.

ABSTRACT:

Background

The rapid annotation of genes on a genome-wide scale is now possible for several organisms using high-throughput RNA interference assays to knock down the expression of a specific gene. To date, dozens of RNA interference phenotypes have been recorded for the nematode Caenorhabditis elegans. Although previous studies have demonstrated the merit of using knock-down phenotypes to predict gene function, it is unclear how the data can be used most effectively. An open question is how to optimally make use of phenotypic observations, possibly in combination with other functional genomics datasets, to identify genes that share a common role.

Results

We compared several methods for detecting gene-gene functional similarity from phenotypic knock-down profiles. We found that information-based measures, which explicitly incorporate a phenotype's genomic frequency when calculating gene-gene similarity, outperform non-information-based methods. We report the presence of newly predicted modules identified from an integrated functional network containing phenotypic congruency links derived from an information-based measure. One such module is a set of genes predicted to play a role in regulating body morphology based on their multiply-supported interactions with members of the TGF-beta signaling pathway.

Conclusion

Information-based metrics significantly improve the comparison of phenotypic knock-down profiles, based upon their ability to enhance gene function prediction and identify novel functional modules.

SUBMITTER: Weirauch MT

PROVIDER: S-EPMC2596148 | biostudies-literature | 2008 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Information-based methods for predicting gene function from systematic gene knock-downs.

Weirauch Matthew T MT Wong Christopher K CK Byrne Alexandra B AB Stuart Joshua M JM

BMC bioinformatics 20081029

<h4>Background</h4>The rapid annotation of genes on a genome-wide scale is now possible for several organisms using high-throughput RNA interference assays to knock down the expression of a specific gene. To date, dozens of RNA interference phenotypes have been recorded for the nematode Caenorhabditis elegans. Although previous studies have demonstrated the merit of using knock-down phenotypes to predict gene function, it is unclear how the data can be used most effectively. An open question is ...[more]

PMID: 18959798

Similar Datasets

Project description:IntroductionBacteremia is a common but life-threatening infectious disease. However, a well-defined rule to assess patient risk of bacteremia and the urgency of blood culture is lacking. The aim of this study is to establish a predictive model for bacteremia in septic patients using available big data in the emergency department (ED) through logistic regression and other machine learning (ML) methods.Material and methodsWe conducted a retrospective cohort study at the ED of National Cheng Kung University Hospital in Taiwan from January 2015 to December 2019. ED adults (≥18 years old) with systemic inflammatory response syndrome and receiving blood cultures during the ED stay were included. Models I and II were established based on logistic regression, both of which were derived from support vector machine (SVM) and random forest (RF). Net reclassification index was used to determine which model was superior.ResultsDuring the study period, 437,969 patients visited the study ED, and 40,395 patients were enrolled. Patients diagnosed with bacteremia accounted for 7.7% of the cohort. The area under the receiver operating curve (AUROC) in models I and II was 0.729 (95% CI, 0.718-0.740) and 0.731 (95% CI, 0.721-0.742), with Akaike information criterion (AIC) of 16,840 and 16,803, respectively. The performance of model II was superior to that of model I. The AUROC values of models III and IV in the validation dataset were 0.730 (95% CI, 0.713-0.747) and 0.705 (0.688-0.722), respectively. There is no statistical evidence to support that the performance of the model created with logistic regression is superior to those created by SVM and RF.DiscussionThe advantage of the SVM or RF model is that the prediction model is more elastic and not limited to a linear relationship. The advantage of the LR model is that it is easy to explain the influence of the independent variable on the response variable. These models could help medical staff identify high-risk patients and prevent unnecessary antibiotic use. The performance of SVM and RF was not inferior to that of logistic regression.ConclusionsWe established models that provide discrimination in predicting bacteremia among patients with sepsis. The reported results could inspire researchers to adopt ML in their development of prediction algorithms.

Dataset Information

Information-based methods for predicting gene function from systematic gene knock-downs.

Background

Results

Conclusion

Publications

Information-based methods for predicting gene function from systematic gene knock-downs.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets