Emerging chemical patterns: A new methodology for molecular classification and compound selection

被引:35
作者
Auer, Jens [1 ]
Bajorath, Juergen [1 ]
机构
[1] Univ Bonn, Dept Life Sci Informat, B IT, D-53113 Bonn, Germany
关键词
PREDICTION; DISCOVERY; DESIGN;
D O I
10.1021/ci600301t
中图分类号
R914 [药物化学];
学科分类号
100701 ;
摘要
A concept termed Emerging Chemical Patterns (ECPs) is introduced as a novel approach to molecular classification. The methodology makes it possible to extract key molecular features from very few known active compounds and classify molecules according to different potency levels. The approach was developed in light of the situation often faced during the early stages of lead optimization efforts: too few active reference molecules are available to build computational models for the prediction of potent compounds. The ECP method generates high-resolution signatures of active compounds. Predictive ECP models can be built based on the information provided by sets of only three molecules with potency in the nanomolar and micromolar range. In addition to individual compound predictions, an iterative ECP scheme has been designed. When applied to different sets of active molecules, iterative ECP classification produced compound selection sets with increases in average potency of up to 3 orders of magnitude.
引用
收藏
页码:2502 / 2514
页数:13
相关论文
共 28 条
[1]  
[Anonymous], 2002, Biopolymers
[2]  
[Anonymous], MOE
[3]  
[Anonymous], 1993, Multi-Interval Discretization of Continuous-ValuedAttributes for Classification Learning
[4]  
BAILEY J, 3 IEEE INT C DAT MIN, P485
[5]  
Dong G., 1999, P 5 ACM SIGKDD INT C, P43, DOI [10.1145/312129.312191, 10.1145/312129., DOI 10.1145/312129]
[6]  
Dong GZ, 1999, LECT NOTES ARTIF INT, V1721, P30
[7]  
Esposito Emilio Xavier, 2004, Methods Mol Biol, V275, P131
[8]   Fuzzy clustering as a means of selecting representative conformers and molecular alignments [J].
Feher, M ;
Schmidt, JM .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2003, 43 (03) :810-818
[9]   Prediction of biological activity for high-throughput screening using binary kernel discrimination [J].
Harper, G ;
Bradshaw, J ;
Gittins, JC ;
Green, DVS ;
Leach, AR .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2001, 41 (05) :1295-1300
[10]   ZINC - A free database of commercially available compounds for virtual screening [J].
Irwin, JJ ;
Shoichet, BK .
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2005, 45 (01) :177-182