RELATING CHEMICAL ACTIVITY TO STRUCTURE - AN EXAMINATION OF ILP SUCCESSES

被引:49
作者
KING, RD [1 ]
STERNBERG, MJE [1 ]
SRINIVASAN, A [1 ]
机构
[1] UNIV OXFORD,COMP LAB,OXFORD OX1 3QD,ENGLAND
关键词
ILP; INDUCTIVE; CHEMISTRY; COMPARISON; REGRESSION; DECISION-TREE;
D O I
10.1007/BF03037232
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Problems concerned with learning the relationships between molecular structure and activity have been important test-beds for Inductive Logic programming (ILP) systems, In this paper we examine these applications and empirically evaluate the extent to which a first-order representation was required. We compared ILP theories with those constructed using standard linear regression and a decision-tree learner on a series of progressively more difficult problems. When a propositional encoding is feasible for the feature-based algorithms, we show that such algorithms are capable of matching the predictive accuracies of an ILP theory. However, as the complexity of the compounds considered increased, propositional encodings becomes intractable. In such cases, our results show that ILP programs can still continue to construct accurate, understandable theories. Based on this evidence, we propose future work to realise fully the potential of ILP in structure-activity problem.
引用
收藏
页码:411 / 433
页数:23
相关论文
共 13 条
[1]  
[Anonymous], NEW GENERATION COMPU
[2]  
BAHLER D, 1993, 26TH P HAW INT C SYS
[3]  
Brieman L., 1984, CLASSIFICATION REGRE
[4]   STRUCTURE ACTIVITY RELATIONSHIP OF MUTAGENIC AROMATIC AND HETEROAROMATIC NITRO-COMPOUNDS - CORRELATION WITH MOLECULAR-ORBITAL ENERGIES AND HYDROPHOBICITY [J].
DEBNATH, AK ;
DECOMPADRE, RLL ;
DEBNATH, G ;
SHUSTERMAN, AJ ;
HANSCH, C .
JOURNAL OF MEDICINAL CHEMISTRY, 1991, 34 (02) :786-797
[5]   CORRELATION OF BIOLOGICAL ACTIVITY OF PHENOXYACETIC ACIDS WITH HAMMETT SUBSTITUENT CONSTANTS AND PARTITION COEFFICIENTS [J].
HANSCH, C ;
MALONEY, PP ;
FUJITA, T .
NATURE, 1962, 194 (4824) :178-&
[6]   QUANTITATIVE STRUCTURE-ACTIVITY-RELATIONSHIPS BY NEURAL NETWORKS AND INDUCTIVE LOGIC PROGRAMMING .2. THE INHIBITION OF DIHYDROFOLATE-REDUCTASE BY TRIAZINES [J].
HIRST, JD ;
KING, RD ;
STERNBERG, MJE .
JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN, 1994, 8 (04) :421-432
[7]   DRUG DESIGN BY MACHINE LEARNING - THE USE OF INDUCTIVE LOGIC PROGRAMMING TO MODEL THE STRUCTURE-ACTIVITY-RELATIONSHIPS OF TRIMETHOPRIM ANALOGS BINDING TO DIHYDROFOLATE-REDUCTASE [J].
KING, RD ;
MUGGLETON, S ;
LEWIS, RA ;
STERNBERG, MJE .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 1992, 89 (23) :11322-11326
[8]  
KING RD, 1993, 26TH P HAW INT C SYS
[9]  
MARSH P, 1989, NEW SCI 1118
[10]  
MARTIN YC, 1978, QUANTITATIVE DRUG DE