Novel feature extraction technique for fuzzy relational clustering of a flexible dopamine reuptake inhibitor

Milind Misra, Amit Banerjee, Rajesh N. Davé, Carol A. Venanzi

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

This paper describes a novel clustering methodology for classifying over 700 conformations of a flexible analogue of GBR 12909, a dopamine reuptake inhibitor that has completed phase I clinical trials as a treatment for cocaine abuse. The major aspect of the clustering methodology includes an efficient data-conditioning scheme where a systematic feature extraction procedure based on the structural properties of the molecule was used to reduce the associated feature space. This allowed region-specific clustering that focused on individual pharmacophore elements of the molecule. For clustering of the reduced feature set, the fuzzy clustering partitional method was utilized. Due to the relational nature of the feature data, fuzzy relational clustering was employed, and it successfully detected natural groups defined by rotational minima around N(sp 3)-C(sp 3), O(sp 3)-C(sp 3), and C(sp 3)-C(sp 2) bonds. The proposed clustering methodology also employed several cluster validity measures, which corroborated the partitions produced by the clustering technique and agreed with the results of hierarchical clustering using the XCluster program. Representative structures which exhibited a reasonable spread of energies and showed good spatial coverage of the conformational space were identified for use as putative bioactive conformations in a future Comparative Molecular Field Analysis of GBR 12909 analogues. The clustering methodology developed here is capable of handling other computational chemistry problems, and the feature extraction technique can be easily generalized to other molecules.

Original languageEnglish (US)
Pages (from-to)610-623
Number of pages14
JournalJournal of Chemical Information and Modeling
Volume45
Issue number3
DOIs
StatePublished - May 1 2005

Fingerprint

Dopamine Uptake Inhibitors
Feature extraction
Molecules
Conformations
methodology
Computational chemistry
Fuzzy clustering
Cocaine
Structural properties
conditioning
chemistry
abuse
coverage
energy
Dopamine
vanoxerine
Group

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Chemical Engineering(all)
  • Computer Science Applications
  • Library and Information Sciences

Cite this

@article{1856d908edd54970ba2161fc9c740e37,
title = "Novel feature extraction technique for fuzzy relational clustering of a flexible dopamine reuptake inhibitor",
abstract = "This paper describes a novel clustering methodology for classifying over 700 conformations of a flexible analogue of GBR 12909, a dopamine reuptake inhibitor that has completed phase I clinical trials as a treatment for cocaine abuse. The major aspect of the clustering methodology includes an efficient data-conditioning scheme where a systematic feature extraction procedure based on the structural properties of the molecule was used to reduce the associated feature space. This allowed region-specific clustering that focused on individual pharmacophore elements of the molecule. For clustering of the reduced feature set, the fuzzy clustering partitional method was utilized. Due to the relational nature of the feature data, fuzzy relational clustering was employed, and it successfully detected natural groups defined by rotational minima around N(sp 3)-C(sp 3), O(sp 3)-C(sp 3), and C(sp 3)-C(sp 2) bonds. The proposed clustering methodology also employed several cluster validity measures, which corroborated the partitions produced by the clustering technique and agreed with the results of hierarchical clustering using the XCluster program. Representative structures which exhibited a reasonable spread of energies and showed good spatial coverage of the conformational space were identified for use as putative bioactive conformations in a future Comparative Molecular Field Analysis of GBR 12909 analogues. The clustering methodology developed here is capable of handling other computational chemistry problems, and the feature extraction technique can be easily generalized to other molecules.",
author = "Milind Misra and Amit Banerjee and Dav{\'e}, {Rajesh N.} and Venanzi, {Carol A.}",
year = "2005",
month = "5",
day = "1",
doi = "10.1021/ci049708d",
language = "English (US)",
volume = "45",
pages = "610--623",
journal = "Journal of Chemical Information and Modeling",
issn = "1549-9596",
publisher = "American Chemical Society",
number = "3",

}

Novel feature extraction technique for fuzzy relational clustering of a flexible dopamine reuptake inhibitor. / Misra, Milind; Banerjee, Amit; Davé, Rajesh N.; Venanzi, Carol A.

In: Journal of Chemical Information and Modeling, Vol. 45, No. 3, 01.05.2005, p. 610-623.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Novel feature extraction technique for fuzzy relational clustering of a flexible dopamine reuptake inhibitor

AU - Misra, Milind

AU - Banerjee, Amit

AU - Davé, Rajesh N.

AU - Venanzi, Carol A.

PY - 2005/5/1

Y1 - 2005/5/1

N2 - This paper describes a novel clustering methodology for classifying over 700 conformations of a flexible analogue of GBR 12909, a dopamine reuptake inhibitor that has completed phase I clinical trials as a treatment for cocaine abuse. The major aspect of the clustering methodology includes an efficient data-conditioning scheme where a systematic feature extraction procedure based on the structural properties of the molecule was used to reduce the associated feature space. This allowed region-specific clustering that focused on individual pharmacophore elements of the molecule. For clustering of the reduced feature set, the fuzzy clustering partitional method was utilized. Due to the relational nature of the feature data, fuzzy relational clustering was employed, and it successfully detected natural groups defined by rotational minima around N(sp 3)-C(sp 3), O(sp 3)-C(sp 3), and C(sp 3)-C(sp 2) bonds. The proposed clustering methodology also employed several cluster validity measures, which corroborated the partitions produced by the clustering technique and agreed with the results of hierarchical clustering using the XCluster program. Representative structures which exhibited a reasonable spread of energies and showed good spatial coverage of the conformational space were identified for use as putative bioactive conformations in a future Comparative Molecular Field Analysis of GBR 12909 analogues. The clustering methodology developed here is capable of handling other computational chemistry problems, and the feature extraction technique can be easily generalized to other molecules.

AB - This paper describes a novel clustering methodology for classifying over 700 conformations of a flexible analogue of GBR 12909, a dopamine reuptake inhibitor that has completed phase I clinical trials as a treatment for cocaine abuse. The major aspect of the clustering methodology includes an efficient data-conditioning scheme where a systematic feature extraction procedure based on the structural properties of the molecule was used to reduce the associated feature space. This allowed region-specific clustering that focused on individual pharmacophore elements of the molecule. For clustering of the reduced feature set, the fuzzy clustering partitional method was utilized. Due to the relational nature of the feature data, fuzzy relational clustering was employed, and it successfully detected natural groups defined by rotational minima around N(sp 3)-C(sp 3), O(sp 3)-C(sp 3), and C(sp 3)-C(sp 2) bonds. The proposed clustering methodology also employed several cluster validity measures, which corroborated the partitions produced by the clustering technique and agreed with the results of hierarchical clustering using the XCluster program. Representative structures which exhibited a reasonable spread of energies and showed good spatial coverage of the conformational space were identified for use as putative bioactive conformations in a future Comparative Molecular Field Analysis of GBR 12909 analogues. The clustering methodology developed here is capable of handling other computational chemistry problems, and the feature extraction technique can be easily generalized to other molecules.

UR - http://www.scopus.com/inward/record.url?scp=20444365845&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20444365845&partnerID=8YFLogxK

U2 - 10.1021/ci049708d

DO - 10.1021/ci049708d

M3 - Article

C2 - 15921451

AN - SCOPUS:20444365845

VL - 45

SP - 610

EP - 623

JO - Journal of Chemical Information and Modeling

JF - Journal of Chemical Information and Modeling

SN - 1549-9596

IS - 3

ER -