Dataset Information

High-precision high-coverage functional inference from integrated data sources.

ABSTRACT:

Background

Information obtained from diverse data sources can be combined in a principled manner using various machine learning methods to increase the reliability and range of knowledge about protein function. The result is a weighted functional linkage network (FLN) in which linked neighbors share at least one function with high probability. Precision is, however, low. Aiming to provide precise functional annotation for as many proteins as possible, we explore and propose a two-step framework for functional annotation (1) construction of a high-coverage and reliable FLN via machine learning techniques (2) development of a decision rule for the constructed FLN to optimize functional annotation.

Results

We first apply this framework to Saccharomyces cerevisiae. In the first step, we demonstrate that four commonly used machine learning methods, Linear SVM, Linear Discriminant Analysis, Naïve Bayes, and Neural Network, all combine heterogeneous data to produce reliable and high-coverage FLNs, in which the linkage weight more accurately estimates functional coupling of linked proteins than use individual data sources alone. In the second step, empirical tuning of an adjustable decision rule on the constructed FLN reveals that basing annotation on maximum edge weight results in the most precise annotation at high coverages. In particular at low coverage all rules evaluated perform comparably. At coverage above approximately 50%, however, they diverge rapidly. At full coverage, the maximum weight decision rule still has a precision of approximately 70%, whereas for other methods, precision ranges from a high of slightly more than 30%, down to 3%. In addition, a scoring scheme to estimate the precisions of individual predictions is also provided. Finally, tests of the robustness of the framework indicate that our framework can be successfully applied to less studied organisms.

Conclusion

We provide a general two-step function-annotation framework, and show that high coverage, high precision annotations can be achieved by constructing a high-coverage and reliable FLN via data integration followed by applying a maximum weight decision rule.

SUBMITTER: Linghu B

PROVIDER: S-EPMC2292694 | biostudies-literature | 2008 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

High-precision high-coverage functional inference from integrated data sources.

Linghu Bolan B Snitkin Evan S ES Holloway Dustin T DT Gustafson Adam M AM Xia Yu Y DeLisi Charles C

BMC bioinformatics 20080225

<h4>Background</h4>Information obtained from diverse data sources can be combined in a principled manner using various machine learning methods to increase the reliability and range of knowledge about protein function. The result is a weighted functional linkage network (FLN) in which linked neighbors share at least one function with high probability. Precision is, however, low. Aiming to provide precise functional annotation for as many proteins as possible, we explore and propose a two-step fr ...[more]

PMID: 18298847

Similar Datasets

Project description:An important problem in molecular biology is to build a complete understanding of transcriptional regulatory processes in the cell. We have developed a flexible, probabilistic framework to predict TF binding from multiple data sources that differs from the standard hypothesis testing (scanning) methods in several ways. Our probabilistic modeling framework estimates the probability of binding and, thus, naturally reflects our degree of belief in binding. Probabilistic modeling also allows for easy and systematic integration of our binding predictions into other probabilistic modeling methods, such as expression-based gene network inference. The method answers the question of whether the whole analyzed promoter has a binding site, but can also be extended to estimate the binding probability at each nucleotide position. Further, we introduce an extension to model combinatorial regulation by several TFs. Most importantly, the proposed methods can make principled probabilistic inference from multiple evidence sources, such as, multiple statistical models (motifs) of the TFs, evolutionary conservation, regulatory potential, CpG islands, nucleosome positioning, DNase hypersensitive sites, ChIP-chip binding segments and other (prior) sequence-based biological knowledge. We developed both a likelihood and a Bayesian method, where the latter is implemented with a Markov chain Monte Carlo algorithm. Results on a carefully constructed test set from the mouse genome demonstrate that principled data fusion can significantly improve the performance of TF binding prediction methods. We also applied the probabilistic modeling framework to all promoters in the mouse genome and the results indicate a sparse connectivity between transcriptional regulators and their target promoters. To facilitate analysis of other sequences and additional data, we have developed an on-line web tool, ProbTF, which implements our probabilistic TF binding prediction method using multiple data sources. Test data set, a web tool, source codes and supplementary data are available at: http://www.probtf.org.

Project description:Immunization through vaccines among children has contributed to improved childhood survival and health outcomes globally. However, vaccine coverage among children is unevenly distributed across settings and populations. The measurement of inequalities is essential for understanding gaps in vaccine coverage affecting certain sub-populations and monitoring progress towards achieving equity. Our study aimed to characterize the methods of reporting inequalities in childhood vaccine coverage, inclusive of the settings, data source types, analytical methods, and reporting modalities used to quantify and communicate inequality. We conducted a scoping review of publications in academic journals which included analyses of inequalities in vaccination among children. Literature searches were conducted in PubMed and Web of Science and included relevant articles published between 8 December 2013 and 7 December 2023. Overall, 242 publications were identified, including 204 assessing inequalities in a single country and 38 assessing inequalities across more than one country. We observed that analyses on inequalities in childhood vaccine coverage rely heavily on Demographic Health Survey (DHS) or Multiple Indicator Cluster Surveys (MICS) data (39.3%), and papers leveraging these data had increased in the last decade. Additionally, about half of the single-country studies were conducted in low- and middle-income countries. We found that few studies analyzed and reported inequalities using summary measures of health inequality and largely used the odds ratio resulting from logistic regression models for analyses. The most analyzed dimensions of inequality were economic status and maternal education, and the most common vaccine outcome indicator was full vaccination with the recommended vaccine schedule. However, the definition and construction of both dimensions of inequality and vaccine coverage measures varied across studies, and a variety of approaches were used to study inequalities in vaccine coverage across contexts. Overall, harmonizing methods for selecting and categorizing dimensions of inequalities as well as methods for analyzing and reporting inequalities can improve our ability to assess the magnitude and patterns of inequality in vaccine coverage and compare those inequalities across settings and time.

Dataset Information

High-precision high-coverage functional inference from integrated data sources.

Background

Results

Conclusion

Publications

High-precision high-coverage functional inference from integrated data sources.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets