Formal modeling of Gene Ontology annotation predictions based on factor graphs

20th Argentinean Bioengineering Society Congress

物理学;生物科学

Spetale, Flavio^1,2 ; Murillo, Javier^1,2 ; Tapia, Elizabeth^1,2 ; Arce, Débora^3 ; Ponce, Sergio^3 ; Bulacio, Pilar^1,2

CIFASIS-Conicet, 27 de Febrero 210 bis, Rosario

S2000EZP, Argentina^1

Facultad de Ciencias Exactas, Ingenieria y Agrimensura, Universidad Nacional de Rosario, Riobamba 245 bis, Rosario

S2000EZP, Argentina^2

Facultad Regional San Nicolás, Universidad Tecnológica Nacional, San Nicolás

332, Argentina^3

关键词: Cellular components;    Classification methods;    Gene ontology annotations;    Heuristic solutions;    Machine learning classification;    Ontology model;    Predicate logic;    Prediction of Protein Function;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/705/1/012001/pdf
DOI  :  10.1088/1742-6596/705/1/012001

学科分类：生物科学（综合）

来源: IOP

【 摘 要 】

Gene Ontology (GO) is a hierarchical vocabulary for gene product annotation. Its synergy with machine learning classification methods has been widely used for the prediction of protein functions. Current classification methods rely on heuristic solutions to check the consistency with some aspects of the underlying GO structure. In this work we formalize the GO is-a relationship through predicate logic. Moreover, an ontology model based on Forney Factor Graph (FFG) is shown on a general fragment of Cellular Component GO.