2014
DOI: 10.1186/1758-2946-6-29
|View full text |Cite
|
Sign up to set email alerts
|

Cytochrome P450 site of metabolism prediction from 2D topological fingerprints using GPU accelerated probabilistic classifiers

Abstract: BackgroundThe prediction of sites and products of metabolism in xenobiotic compounds is key to the development of new chemical entities, where screening potential metabolites for toxicity or unwanted side-effects is of crucial importance. In this work 2D topological fingerprints are used to encode atomic sites and three probabilistic machine learning methods are applied: Parzen-Rosenblatt Window (PRW), Naive Bayesian (NB) and a novel approach called RASCAL (Random Attribute Subsampling Classification ALgorithm… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

2
34
0

Year Published

2014
2014
2023
2023

Publication Types

Select...
6
3

Relationship

1
8

Authors

Journals

citations
Cited by 29 publications
(36 citation statements)
references
References 40 publications
2
34
0
Order By: Relevance
“…A method using the decision trees on the activation energies and solvent accessible surface area calculated from MOE [3235] has been developed. Recently, the PASS algorithm using some 2D fingerprint descriptors [36] or the RASCAL (Random Attribute Subsampling Classification) algorithm [37] using some circular fingerprints has been employed to predict SOM by CYP450 enzymes [38, 39]. …”
Section: Introductionmentioning
confidence: 99%
“…A method using the decision trees on the activation energies and solvent accessible surface area calculated from MOE [3235] has been developed. Recently, the PASS algorithm using some 2D fingerprint descriptors [36] or the RASCAL (Random Attribute Subsampling Classification) algorithm [37] using some circular fingerprints has been employed to predict SOM by CYP450 enzymes [38, 39]. …”
Section: Introductionmentioning
confidence: 99%
“…For example, a cheminformatian might be interested in knowing whether: a particular small compound (ligand) is capable of inducing a desirable biological effect on a specific target protein [1, 2]; an enzyme catalyses a certain chemical reaction, or a catalytic mechanism of an enzyme is appropriate for a chemical reaction [3]; a substructure of a substrate is a site of metabolism [4]; a ligand is structurally similar to a reference set of ligands known to possess desirable physical, chemical and biological properties [2, 5, 6]; a protein is a potential target for a given ligand [2, 7]; etc.…”
Section: Introductionmentioning
confidence: 99%
“…O-and N-dealkylations suitable for VOC generation are found to yield reaction intermediates of relative high stability [41]. Additionally, we discarded predicted SOMs expected to be too buried for CYP-catalyzed oxidation [40,47,49]. For the 32 analyzed substrates of oxidative degradation the SOMs for dealkylation could be covered in 27 cases.…”
Section: Som Predictionmentioning
confidence: 99%
“…Positions where H·-abstraction resulted in an energy difference dE < 30 kcal mol −1 were considered as potential SOMs. As CYP-catalyzed oxidation reactions require accessibility of the SOM [47][48][49], we implemented a second selection criterion in our SOM prediction. Based on the energy-minimized structure from H·-abstraction calculations, we calculated solvent accessible surface areas (SASAs) for all hydrogens using MOE [31].…”
Section: Prediction Of Site Of Metabolismmentioning
confidence: 99%