Large-scale evaluation of molecular descriptors by means of clustering

Matthias Dehmer; Frank Emmert-Streib; Shailesh Tripathi

doi:10.1371/journal.pone.0083956

Large-scale evaluation of molecular descriptors by means of clustering

Matthias Dehmer
, Frank Emmert-Streib
, Shailesh Tripathi

Research output: Contribution to journal › Article › peer-review

16 Citations (Scopus)

Abstract

Molecular descriptors have been explored extensively. From these studies, it is known that a large number of descriptors are strongly correlated and capture similar characteristics of molecules. In this paper, we evaluate 919 Dragon-descriptors of 6 different categories by means of clustering. Also, we analyze these different categories of descriptors also find a subset of descriptors which are least correlated among each other and, hence, characterize molecular graphs distinctively.

Original language	English
Article number	e83956
Pages (from-to)	e83956
Journal	PLoS ONE
Volume	8
Issue number	12
DOIs	https://doi.org/10.1371/journal.pone.0083956
Publication status	Published - 31 Dec 2013
Externally published	Yes

Keywords

Algorithms
Cluster Analysis
Humans
Models, Molecular
Molecular Structure
Quantitative Structure-Activity Relationship
Software

Access to Document

10.1371/journal.pone.0083956

Cite this

@article{f5d285750d2f48788a1b83cba9a971f1,

title = "Large-scale evaluation of molecular descriptors by means of clustering",

abstract = "Molecular descriptors have been explored extensively. From these studies, it is known that a large number of descriptors are strongly correlated and capture similar characteristics of molecules. In this paper, we evaluate 919 Dragon-descriptors of 6 different categories by means of clustering. Also, we analyze these different categories of descriptors also find a subset of descriptors which are least correlated among each other and, hence, characterize molecular graphs distinctively.",

keywords = "Algorithms, Cluster Analysis, Humans, Models, Molecular, Molecular Structure, Quantitative Structure-Activity Relationship, Software",

author = "Matthias Dehmer and Frank Emmert-Streib and Shailesh Tripathi",

year = "2013",

month = dec,

day = "31",

doi = "10.1371/journal.pone.0083956",

language = "English",

volume = "8",

pages = "e83956",

journal = "PLoS ONE",

issn = "1932-6203",

publisher = "Public Library of Science",

number = "12",

}

TY - JOUR

T1 - Large-scale evaluation of molecular descriptors by means of clustering

AU - Dehmer, Matthias

AU - Emmert-Streib, Frank

AU - Tripathi, Shailesh

PY - 2013/12/31

Y1 - 2013/12/31

N2 - Molecular descriptors have been explored extensively. From these studies, it is known that a large number of descriptors are strongly correlated and capture similar characteristics of molecules. In this paper, we evaluate 919 Dragon-descriptors of 6 different categories by means of clustering. Also, we analyze these different categories of descriptors also find a subset of descriptors which are least correlated among each other and, hence, characterize molecular graphs distinctively.

AB - Molecular descriptors have been explored extensively. From these studies, it is known that a large number of descriptors are strongly correlated and capture similar characteristics of molecules. In this paper, we evaluate 919 Dragon-descriptors of 6 different categories by means of clustering. Also, we analyze these different categories of descriptors also find a subset of descriptors which are least correlated among each other and, hence, characterize molecular graphs distinctively.

KW - Algorithms

KW - Cluster Analysis

KW - Humans

KW - Models, Molecular

KW - Molecular Structure

KW - Quantitative Structure-Activity Relationship

KW - Software

UR - https://www.scopus.com/pages/publications/84896716942

U2 - 10.1371/journal.pone.0083956

DO - 10.1371/journal.pone.0083956

M3 - Article

C2 - 24391854

AN - SCOPUS:84896716942

SN - 1932-6203

VL - 8

SP - e83956

JO - PLoS ONE

JF - PLoS ONE

IS - 12

M1 - e83956

ER -

Large-scale evaluation of molecular descriptors by means of clustering

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this