Computational characterization and identification of human polycystic ovary syndrome genes.
Sci Rep
; 8(1): 12949, 2018 08 28.
Article
en En
| MEDLINE
| ID: mdl-30154492
ABSTRACT
Human polycystic ovary syndrome (PCOS) is a highly heritable disease regulated by genetic and environmental factors. Identifying PCOS genes is time consuming and costly in wet-lab. Developing an algorithm to predict PCOS candidates will be helpful. In this study, for the first time, we systematically analyzed properties of human PCOS genes. Compared with genes not yet known to be involved in PCOS regulation, known PCOS genes display distinguishing characteristics (i) they tend to be located at network center; (ii) they tend to interact with each other; (iii) they tend to enrich in certain biological processes. Based on these features, we developed a machine-learning algorithm to predict new PCOS genes. 233 PCOS candidates were predicted with a posterior probability >0.9. Evidence supporting 7 of the top 10 predictions has been found.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Síndrome del Ovario Poliquístico
/
Bases de Datos de Ácidos Nucleicos
/
Redes Reguladoras de Genes
/
Aprendizaje Automático
Tipo de estudio:
Diagnostic_studies
/
Prognostic_studies
Límite:
Female
/
Humans
Idioma:
En
Revista:
Sci Rep
Año:
2018
Tipo del documento:
Article
País de afiliación:
China
Pais de publicación:
ENGLAND
/
ESCOCIA
/
GB
/
GREAT BRITAIN
/
INGLATERRA
/
REINO UNIDO
/
SCOTLAND
/
UK
/
UNITED KINGDOM