Comparing the chemical spaces of metabolites and available chemicals: models of metabolite-likeness

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

The chemical space covered by compounds involved in metabolic reactions was compared with that of a random dataset of purchasable compounds by chemoinformatics techniques. The comparison was based on 3D structure, 2D structure, or descriptors of global properties, by means of self-organizing maps, random forests, and classification trees. The overlap between metabolites and non-metabolites was observed to be the least in the space defined by the global descriptors, the most discriminatory features being the number of OH groups, presence of aromatic systems, and molecular weight. Discrimination between the two datasets was achieved with accuracy up to 97%. Models were built to produce a metabolite-likeness parameter. A relationship between metabolite-likeness and ready biodegradability was observed.
Original languageUnknown
Pages (from-to)23-36
JournalMolecular Diversity
Volume11
Issue number1
DOIs
Publication statusPublished - 1 Jan 2007

Cite this

@article{8d1a9558a97d455a93138d065ff05b4a,
title = "Comparing the chemical spaces of metabolites and available chemicals: models of metabolite-likeness",
abstract = "The chemical space covered by compounds involved in metabolic reactions was compared with that of a random dataset of purchasable compounds by chemoinformatics techniques. The comparison was based on 3D structure, 2D structure, or descriptors of global properties, by means of self-organizing maps, random forests, and classification trees. The overlap between metabolites and non-metabolites was observed to be the least in the space defined by the global descriptors, the most discriminatory features being the number of OH groups, presence of aromatic systems, and molecular weight. Discrimination between the two datasets was achieved with accuracy up to 97{\%}. Models were built to produce a metabolite-likeness parameter. A relationship between metabolite-likeness and ready biodegradability was observed.",
author = "Sousa, {Jo{\~a}o Montargil Aires de}",
year = "2007",
month = "1",
day = "1",
doi = "10.1007/s11030-006-9054-0",
language = "Unknown",
volume = "11",
pages = "23--36",
journal = "Molecular Diversity",
issn = "1381-1991",
publisher = "Springer Science Business Media",
number = "1",

}

Comparing the chemical spaces of metabolites and available chemicals: models of metabolite-likeness. / Sousa, João Montargil Aires de.

In: Molecular Diversity, Vol. 11, No. 1, 01.01.2007, p. 23-36.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Comparing the chemical spaces of metabolites and available chemicals: models of metabolite-likeness

AU - Sousa, João Montargil Aires de

PY - 2007/1/1

Y1 - 2007/1/1

N2 - The chemical space covered by compounds involved in metabolic reactions was compared with that of a random dataset of purchasable compounds by chemoinformatics techniques. The comparison was based on 3D structure, 2D structure, or descriptors of global properties, by means of self-organizing maps, random forests, and classification trees. The overlap between metabolites and non-metabolites was observed to be the least in the space defined by the global descriptors, the most discriminatory features being the number of OH groups, presence of aromatic systems, and molecular weight. Discrimination between the two datasets was achieved with accuracy up to 97%. Models were built to produce a metabolite-likeness parameter. A relationship between metabolite-likeness and ready biodegradability was observed.

AB - The chemical space covered by compounds involved in metabolic reactions was compared with that of a random dataset of purchasable compounds by chemoinformatics techniques. The comparison was based on 3D structure, 2D structure, or descriptors of global properties, by means of self-organizing maps, random forests, and classification trees. The overlap between metabolites and non-metabolites was observed to be the least in the space defined by the global descriptors, the most discriminatory features being the number of OH groups, presence of aromatic systems, and molecular weight. Discrimination between the two datasets was achieved with accuracy up to 97%. Models were built to produce a metabolite-likeness parameter. A relationship between metabolite-likeness and ready biodegradability was observed.

U2 - 10.1007/s11030-006-9054-0

DO - 10.1007/s11030-006-9054-0

M3 - Article

VL - 11

SP - 23

EP - 36

JO - Molecular Diversity

JF - Molecular Diversity

SN - 1381-1991

IS - 1

ER -