SOMP: web server for in silico prediction of sites of metabolism for drug-like compounds.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 25777527.
- Also identified by DOI 10.1093/bioinformatics/btv087.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
A new freely available web server site of metabolism predictor to predict the sites of metabolism (SOM) based on the structural formula of chemicals has been developed. It is based on the analyses of 'structure-SOM' relationships using a Bayesian approach and labelled multilevel neighbourhoods of atoms descriptors to represent the structures of over 1000 metabolized xenobiotics. The server allows predicting SOMs that are catalysed by 1A2, 2C9, 2C19, 2D6 and 3A4 isoforms of cytochrome P450 and enzymes of the UDP-glucuronosyltransferase family. The average invariant accuracy of prediction that was calculated for the training sets (using leave-one-out cross-validation) and evaluation sets is 0.9 and 0.95, respectively. Freely available on the web at http://www.way2drug.com/SOMP.
Medical subject headings
- Algorithms
- Computational Biology
- Cytochrome P-450 Enzyme System
- Metabolic Networks and Pathways
- Pharmaceutical Preparations
- Software
- Xenobiotics