Reference : Unification of functional annotation descriptions using text mining

	Document type :	Scientific journals : Article
	Discipline(s) :	Life sciences : Biochemistry, biophysics & molecular biology
	Focus Areas :	Systems Biomedicine
	To cite this reference:	http://hdl.handle.net/10993/47454

Title :	Unification of functional annotation descriptions using text mining
Language :	English
Author, co-author :	Teixeira Queiros, Pedro [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Systems Ecology >]
	Novikova, Polina [University of Luxembourg > CRC > Communication department (Communication Department) > ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)]
	Wilmes, Paul [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Systems Ecology]
	May, Patrick [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Bioinformatics Core]
Publication date :	13-May-2021
Journal title :	Biological Chemistry
Publisher :	Walter de Gruyter
Peer reviewed :	Yes (verified by ORBilu)
Audience :	International
ISSN :	1431-6730
e-ISSN :	1437-4315
City :	Berlin
Country :	Germany
Keywords :	[en] Protein annotation ; Functional annotation ; Text mining ; Natural language processing
Abstract :	[en] A common approach to genome annotation involves the use of homology-based tools for the prediction of the functional role of proteins. The quality of functional annotations is dependent on the reference data used, as such, choosing the appropriate sources is crucial. Unfortunately, no single reference data source can be universally considered the gold standard, thus using multiple references could potentially increase annotation quality and coverage. However, this comes with challenges, particularly due to the introduction of redundant and exclusive annotations. Through text mining it is possible to identify highly similar functional descriptions, thus strengthening the confidence of the final protein functional annotation and providing a redundancy-free output. Here we present UniFunc, a text mining approach that is able to detect similar functional descriptions with high precision. UniFunc was built as a small module and can be independently used or integrated into protein function annotation pipelines. By removing the need to individually analyse and compare annotation results, UniFunc streamlines the complementary use of multiple reference datasets.
Research centres :	Luxembourg Centre for Systems Biomedicine (LCSB): Bioinformatics Core (R. Schneider Group) ; Luxembourg Centre for Systems Biomedicine (LCSB): Eco-Systems Biology (Wilmes Group)
Funders :	FNR PRIDE17/11823097
Permalink :	http://hdl.handle.net/10993/47454
DOI :	10.1515/hsz-2021-0125
Other URL :	https://doi.org/10.1515/hsz-2021-0125
FnR project :	FnR ; FNR11823097 > Paul Wilmes > MICROH-DTU > Microbiomes In One Health > 01/09/2018 > 28/02/2025 > 2017

	File(s) associated to this reference
	Fulltext file(s): File Commentary Version Size Access Open access 10.1515_hsz-2021-0125.pdf Publisher postprint 736.56 kB View/Open

All documents in ORBi^lu are protected by a user license.

 

University of Luxembourg Library |  Feedback |  Legal notices Site Map