Genetic Programming in Data Mining for Drug
Discovery
W. Langdon, and S. Barrett. Evolutionary Computing in Data Mining, volume 163 of Studies in Fuzziness and Soft Computing, chapter 10, Springer, (2004)
Abstract
Genetic programming (GP) is used to extract from rat
oral bioavailability (OB) measurements simple,
interpretable and predictive QSAR models which both
generalise to rats and to marketed drugs in humans.
Receiver Operating Characteristics (ROC) curves for the
binary classifier produced by machine learning show no
statistical difference between rats (albeit without
known clearance differences) and man. Thus evolutionary
computing offers the prospect of in silico ADME
screening e.g. for virtual chemicals, for
pharmaceutical drug discovery.
%0 Book Section
%1 langdon:2004:ECDM
%A Langdon, W. B.
%A Barrett, S. J.
%B Evolutionary Computing in Data Mining
%D 2004
%E Ghosh, Ashish
%E Jain, Lakhmi C.
%I Springer
%K ADMET ROC algorithms, discovery, drug fitness, genetic programming,
%P 211--235
%T Genetic Programming in Data Mining for Drug
Discovery
%U http://www.springeronline.com/sgw/cda/frontpage/0,11855,5-175-22-33980376-0,00.html
%V 163
%X Genetic programming (GP) is used to extract from rat
oral bioavailability (OB) measurements simple,
interpretable and predictive QSAR models which both
generalise to rats and to marketed drugs in humans.
Receiver Operating Characteristics (ROC) curves for the
binary classifier produced by machine learning show no
statistical difference between rats (albeit without
known clearance differences) and man. Thus evolutionary
computing offers the prospect of in silico ADME
screening e.g. for virtual chemicals, for
pharmaceutical drug discovery.
%& 10
%@ 3-540-22370-3
@incollection{langdon:2004:ECDM,
abstract = {Genetic programming (GP) is used to extract from rat
oral bioavailability (OB) measurements simple,
interpretable and predictive QSAR models which both
generalise to rats and to marketed drugs in humans.
Receiver Operating Characteristics (ROC) curves for the
binary classifier produced by machine learning show no
statistical difference between rats (albeit without
known clearance differences) and man. Thus evolutionary
computing offers the prospect of in silico ADME
screening e.g. for virtual chemicals, for
pharmaceutical drug discovery.},
added-at = {2008-06-19T17:35:00.000+0200},
author = {Langdon, W. B. and Barrett, S. J.},
biburl = {https://www.bibsonomy.org/bibtex/20cd893e4c28137895654ed04f0693172/brazovayeye},
booktitle = {Evolutionary Computing in Data Mining},
chapter = 10,
editor = {Ghosh, Ashish and Jain, Lakhmi C.},
interhash = {bb8885aea177cd6a00833010b133dbcc},
intrahash = {0cd893e4c28137895654ed04f0693172},
isbn = {3-540-22370-3},
keywords = {ADMET ROC algorithms, discovery, drug fitness, genetic programming,},
notes = {wbl_bioavail postscript and PDF page numbering and
figures NOT identical to published book},
pages = {211--235},
publisher = {Springer},
series = {Studies in Fuzziness and Soft Computing},
size = {25 pages},
timestamp = {2008-06-19T17:45:02.000+0200},
title = {Genetic Programming in Data Mining for Drug
Discovery},
url = {http://www.springeronline.com/sgw/cda/frontpage/0,11855,5-175-22-33980376-0,00.html},
volume = 163,
year = 2004
}