A rule-based expert system for chemical prioritization using effects-based chemical categories.
SAR QSAR Environ Res
; 25(4): 253-87, 2014.
Article
em En
| MEDLINE
| ID: mdl-24779615
ABSTRACT
A rule-based expert system (ES) was developed to predict chemical binding to the estrogen receptor (ER) patterned on the research approaches championed by Gilman Veith to whom this article and journal issue are dedicated. The ERES was built to be mechanistically transparent and meet the needs of a specific application, i.e. predict for all chemicals within two well-defined inventories (industrial chemicals used as pesticide inerts and antimicrobial pesticides). These chemicals all lack structural features associated with high affinity binders and thus any binding should be low affinity. Similar to the high-quality fathead minnow database upon which Veith QSARs were built, the ERES was derived from what has been termed gold standard data, systematically collected in assays optimized to detect even low affinity binding and maximizing confidence in the negatives determinations. The resultant logic-based decision tree ERES, determined to be a robust model, contains seven major nodes with multiple effects-based chemicals categories within each. Predicted results are presented in the context of empirical data within local chemical structural groups facilitating informed decision-making. Even using optimized detection assays, the ERES applied to two inventories of >600 chemicals resulted in only ~5% of the chemicals predicted to bind ER.
Palavras-chave
Texto completo:
1
Bases de dados:
MEDLINE
Assunto principal:
Sistemas Inteligentes
/
Substâncias Perigosas
/
Relação Quantitativa Estrutura-Atividade
Tipo de estudo:
Prognostic_studies
/
Risk_factors_studies
Idioma:
En
Revista:
SAR QSAR Environ Res
Assunto da revista:
SAUDE AMBIENTAL
Ano de publicação:
2014
Tipo de documento:
Article
País de afiliação:
Estados Unidos