Nonlinear prediction of quantitative structure-activity relationships

Peter Tiño; Ian T. Nabney; Bruce S. Williams; Jens Lösel; Yi Sun

doi:10.1021/ci034255i

Nonlinear prediction of quantitative structure-activity relationships

Peter Tiño, Ian T. Nabney, Bruce S. Williams, Jens Lösel, Yi Sun

Research output: Contribution to journal › Article (Academic Journal) › peer-review

21 Citations (Scopus)

Abstract

Predicting the log of the partition coefficient P is a long-standing benchmark problem in Quantitative Structure-Activity Relationships (QSAR). In this paper we show that a relatively simple molecular representation (using 14 variables) can be combined with leading edge machine learning algorithms to predict logP on new compounds more accurately than existing benchmark algorithms which use complex molecular representations.

Original language	English
Pages (from-to)	1647-1653
Number of pages	7
Journal	Journal of Chemical Information and Computer Sciences
Volume	44
Issue number	5
DOIs	https://doi.org/10.1021/ci034255i
Publication status	Published - 1 Sept 2004

Access to Document

10.1021/ci034255i

Handle.net

Persistent link

Cite this

@article{914fe4925f854438ad857f6593cea64c,

title = "Nonlinear prediction of quantitative structure-activity relationships",

abstract = "Predicting the log of the partition coefficient P is a long-standing benchmark problem in Quantitative Structure-Activity Relationships (QSAR). In this paper we show that a relatively simple molecular representation (using 14 variables) can be combined with leading edge machine learning algorithms to predict logP on new compounds more accurately than existing benchmark algorithms which use complex molecular representations.",

author = "Peter Ti{\~n}o and Nabney, \{Ian T.\} and Williams, \{Bruce S.\} and Jens L{\"o}sel and Yi Sun",

year = "2004",

month = sep,

day = "1",

doi = "10.1021/ci034255i",

language = "English",

volume = "44",

pages = "1647--1653",

journal = "Journal of Chemical Information and Computer Sciences",

issn = "0095-2338",

publisher = "American Chemical Society",

number = "5",

}

TY - JOUR

T1 - Nonlinear prediction of quantitative structure-activity relationships

AU - Tiño, Peter

AU - Nabney, Ian T.

AU - Williams, Bruce S.

AU - Lösel, Jens

AU - Sun, Yi

PY - 2004/9/1

Y1 - 2004/9/1

N2 - Predicting the log of the partition coefficient P is a long-standing benchmark problem in Quantitative Structure-Activity Relationships (QSAR). In this paper we show that a relatively simple molecular representation (using 14 variables) can be combined with leading edge machine learning algorithms to predict logP on new compounds more accurately than existing benchmark algorithms which use complex molecular representations.

AB - Predicting the log of the partition coefficient P is a long-standing benchmark problem in Quantitative Structure-Activity Relationships (QSAR). In this paper we show that a relatively simple molecular representation (using 14 variables) can be combined with leading edge machine learning algorithms to predict logP on new compounds more accurately than existing benchmark algorithms which use complex molecular representations.

U2 - 10.1021/ci034255i

DO - 10.1021/ci034255i

M3 - Article (Academic Journal)

SN - 0095-2338

VL - 44

SP - 1647

EP - 1653

JO - Journal of Chemical Information and Computer Sciences

JF - Journal of Chemical Information and Computer Sciences

IS - 5

ER -

Nonlinear prediction of quantitative structure-activity relationships

Abstract

Access to Document

Handle.net

Fingerprint

Cite this