- author = "W. B. Langdon and S. J. Barrett and B. F. Buxton",
- title = "Predicting Biochemical Interactions -- Human P450 2D6 Enzyme Inhibition",
- booktitle = "Proceedings of the 2003 Congress on Evolutionary Computation CEC2003",
- editor = "Ruhul Sarker and Robert Reynolds and Hussein Abbass and Kay Chen Tan and Bob McKay and Daryl Essam and Tom Gedeon",
- pages = "807--814",
- year = "2003",
- publisher = "IEEE Press",
- address = "Canberra",
- publisher_address = "445 Hoes Lane, P.O. Box 1331, Piscataway, NJ 08855-1331, USA",
- month = "8-12 " # dec,
- organisation = "IEEE Neural Network Council (NNC), Engineers Australia (IEAust), Evolutionary Programming Society (EPS), Institution of Electrical Engineers (IEE)",
- keywords = "genetic algorithms, genetic programming, QSAR, drug, P450, Pareto multi-objective fitnessBiochemistry, Chemicals, Drugs, Humans, Lead time reduction, Learning systems, Libraries, Pharmaceuticals, Predictive models, biochemistry, chemistry computing, drugs, enzymes, generalisation (artificial intelligence), learning (artificial intelligence), medical computing, regression analysis, search problems, GP, Glaxo Welcome molecules, SmithKline Beecham compounds, biochemical interactions prediction, chemical libraries, chemical space, cheminformatics models, drug discovery, human P450 2D6 enzyme inhibition, intelligent pharmaceutical QSAR modelling techniques, machine learning knowledge, medicine optimisation, regression analysis, silico screening",
- ISBN = "0-7803-7804-0",
-
URL = "
http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/wbl_cec2003.pdf",
-
URL = "
http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/wbl_cec2003.ps.gz",
-
DOI = "
doi:10.1109/CEC.2003.1299750",
- size = "8 pages",
-
abstract = "In silico screening of chemical libraries or virtual
chemicals may reduce drug discovery and medicine
optimisation lead times and increase the probability of
success by directing search through chemical space.
About a dozen intelligent pharmaceutical QSAR modelling
techniques were used to predict IC50 concentration
(three classes) of drug interaction with a cell wall
enzyme (P450 CYC2D6). Genetic programming gave
comprehensible cheminformatics models which generalised
best. This was shown by a blind test on GlaxoWelcome
molecules of machine learning knowledge nuggets mined
from SmithKline Beecham compounds. Performance on
similar chemicals (interpolation) and diverse chemicals
(extrapolation) suggest generalisation is more
difficult than avoiding over fitting.
Two GP approaches, classification via regression using a multi-objective fitness measure and a direct winner takes all (WTA) or one versus all (OVA) classification, are described. Predictive rules were compressed by separate follow up GP runs seeded with the best program.",
- notes = "CEC 2003 - A joint meeting of the IEEE, the IEAust, the EPS, and the IEE.",
