An Enhancement of Bayesian Inference Network for Ligand-Based Virtual Screening using Features Selection | Science Publications

American Journal of Applied Sciences

Naomie Salim¹  Ammar Abdo¹  Ali Ahmed¹ 

关键词: Features selection;    fingerprint features;    similarity search;    virtual screening;    Drug Data;    Bayesian Inference Network (BIN);    proposed method;    High-Throughput Screening (HTS);    Quantitative Structure-Activity Relationships (QSAR);   

DOI  :  10.3844/ajassp.2011.368.373

学科分类：自然科学（综合）

来源: Science Publications

【 摘 要 】

Problem statement: Similarity based Virtual Screening (VS) deals with a large amount ofdata containing irrelevant and/or redundant fragments or features. Recent use of Bayesian network asan alternative for existing tools for similarity based VS has received noticeable attention of theresearchers in the field of chemoinformatics. Approach: To this end, different models of Bayesiannetwork have been developed. In this study, we enhance the Bayesian Inference Network (BIN) usinga subset of selected molecules features. Results: In this approach, a few features were filtered fromthe molecular fingerprint features based on a features selection approach. Conclusion: Simulatedvirtual screening experiments with MDL Drug Data Report (MDDR) data sets showed that theproposed method provides simple ways of enhancing the cost effectiveness of ligand-based virtualscreening searches, especially for higher diversity data set.

【 授权许可】

Unknown