首页|Searching for Target-Selective Compounds Using Different Combinations of Multiclass Support Vector Machine Ranking Methods, Kernel Functions, and Fingerprint Descriptors
Searching for Target-Selective Compounds Using Different Combinations of Multiclass Support Vector Machine Ranking Methods, Kernel Functions, and Fingerprint Descriptors
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NSTL
Amer Chemical Soc
The identification of small chemical compounds that are selective for a target protein over one or more closely related members of the same family is of high relevance for applications in chemical biology. Conventional 2D similarity searching using known selective molecules as templates has recently been found to preferentially detect selective over non-selective and inactive database compounds. To improve the initially observed search performance, we have attempted to use 2D fingerprints as descriptors for support vector machine (SVM)-based selectivity searching. Different from typically applied binary SVM compound classification, SVM analysis has been adapted here for multiclass predictions and compound ranking to distinguish between selective, active but non-selective, and inactive compounds. In systematic database search calculations, we tested combinations of four alternative SVM ranking schemes, four different kernel functions, and four fingerprints and were able to further improve selectivity search performance by effectively removing non-selective molecules from high ranking positions while retaining high recall of selective compounds.
AIDED CHEMICAL BIOLOGYDRUG DISCOVERYMOLECULAR SIMILARITY2D FINGERPRINTSDESIGNCHEMOGENOMICS
Wassermann, AM、Geppert, H、Bajorath, J
展开 >
Rhein Freidrich Wilhelms Univ Bonn, LIMES Program Unit Chem Biol & Med Chem, B IT, Dept Life Sci Informat, D-53113 Bonn, Germany.
NSTL
Amer Chemical Soc
