Extensive complementarity between gene function prediction methods

Vidulin, Vedrana; Šmuc, Tomislav; Supek, Fran (2016) Extensive complementarity between gene function prediction methods. Bioinformatics, 32 (23). pp. 3645-3653. ISSN 1367-4803

Preview

PDF - Accepted Version - article
Download (987kB) | Preview

Official URL: https://academic.oup.com/bioinformatics/article/32...

Abstract

Motivation: The number of sequenced genomes rises steadily, but we still lack the knowledge about the biological roles of many genes. Automated 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 rely on a single most- confident 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.

Item Type:

Article

Additional Information:

This is a pre-copyedited, author-produced version of an article accepted for publication in Bioinformatics following peer review. The version of record Biomater. Sci., 2016,4, 1412-1416 is available online at: http://pubs.rsc.org/en/Content/ArticleLanding/2016/BM/C6BM00287K#!divAbstract; DOI: 10.1093/bioinformatics/btw532.

Uncontrolled Keywords:

gene function prediction; comparative genomics; gene ontology; random forest

Subjects:

NATURAL SCIENCES > Biology
NATURAL SCIENCES > Biology > Genetics, Evolution and Phylogenetics
TECHNICAL SCIENCES > Computing > Data Processing
BIOTECHNICAL SCIENCES > Biotechnology > Bioinformatics

Divisions:

Division of Electronics

Projects:

Project title	Project leader	Project code	Project type
Postupci strojnog učenja za dubinsku analizu složenih struktura podataka-DescriptiveInduction	Dragan Gamberger	IP-2013-11-9623	HRZZ
Mulitidisciplinarni pristup otkriću lijekova s ciljanim djelovanjem na matične stanice tumora – uloga transporta kalija-MultiCaST	Marijeta Kralj	IP-2013-11-5660	HRZZ
Foundational Research on MULTIlevel comPLEX networks and systems-MULTIPLEX	UNSPECIFIED	317532	EK
Enhancement of the Innovation Potential in SEE through new Molecular Solutions in Research and Development-INNOMOL	UNSPECIFIED	316289	EK
Learning from Massive, Incompletely annotated, and Structured Data-MAESTRA	UNSPECIFIED	612944	EK