Data Set Modelability by QSAR

被引:107
作者
Golbraikh, Alexander [1 ]
Muratov, Eugene [1 ,2 ]
Fourches, Denis [1 ]
Tropsha, Alexander [1 ]
机构
[1] Univ N Carolina, Lab Mol Modeling, Div Chem Biol & Med Chem, UNC Eshelman Sch Pharm, Chapel Hill, NC 27599 USA
[2] AV Bogatsky Phys Chem Inst NAS Ukraine, Dept Mol Struct & Cheminformat, UA-65080 Odessa, Ukraine
关键词
ACTIVITY CLIFFS;
D O I
10.1021/ci400572x
中图分类号
R914 [药物化学];
学科分类号
100701 ;
摘要
We introduce a simple MODelability Index (MODI) that estimates the feasibility of obtaining predictive QSAR models (correct classification rate above 0.7) for a binary data set of bioactive compounds. MODI is defined as an activity class-weighted ratio of the number of nearest-neighbor pairs of compounds with the same activity class versus the total number of pairs. The MODI values were calculated for more than 100 data sets, and the threshold of 0.65 was found to separate the nonmodelable and modelable data sets.
引用
收藏
页码:1 / 4
页数:4
相关论文
共 18 条
[1]   A high-throughput method for assessing chemical toxicity using a Caenorhabditis elegans reproduction assay [J].
Boyd, Windy A. ;
McBride, Sandra J. ;
Rice, Julie R. ;
Snyder, Daniel W. ;
Freedman, Jonathan H. .
TOXICOLOGY AND APPLIED PHARMACOLOGY, 2010, 245 (02) :153-+
[2]   Using Graph Indices for the Analysis and Comparison of Chemical Datasets [J].
Fourches, Denis ;
Tropsha, Alexander .
MOLECULAR INFORMATICS, 2013, 32 (9-10) :827-842
[3]   Trust, But Verify: On the Importance of Chemical Structure Curation in Cheminformatics and QSAR Modeling Research [J].
Fourches, Denis ;
Muratov, Eugene ;
Tropsha, Alexander .
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2010, 50 (07) :1189-1204
[4]   Structure-activity landscape index: Identifying and quantifying activity cliffs [J].
Guha, Rajarshi ;
Van Drie, John H. .
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2008, 48 (03) :646-658
[5]   AN INTEGRATED APPROACH TO 3-DIMENSIONAL INFORMATION MANAGEMENT WITH MACCS-3D [J].
GUNER, OF ;
HUGHES, DW ;
DUMONT, LM .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1991, 31 (03) :408-414
[6]   Hierarchical QSAR technology based on the Simplex representation of molecular structure [J].
Kuz'min, V. E. ;
Artemenko, A. G. ;
Muratov, E. N. .
JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN, 2008, 22 (6-7) :403-421
[7]   Combinatorial QSAR modeling of P-glycoprotein substrates [J].
Lima, Patricia de Cerqueira ;
Golbraikh, Alexander ;
Oloff, Scott ;
Xiao, Yunde ;
Tropsha, Alexander .
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2006, 46 (03) :1245-1254
[8]   On outliers and activity cliffs - Why QSAR often disappoints [J].
Maggiora, Gerald M. .
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2006, 46 (04) :1535-1535
[9]   Human Intestinal Transporter Database: QSAR Modeling and Virtual Profiling of Drug Uptake, Efflux and Interactions [J].
Sedykh, Alexander ;
Fourches, Denis ;
Duan, Jianmin ;
Hucke, Oliver ;
Garneau, Michel ;
Zhu, Hao ;
Bonneau, Pierre ;
Tropsha, Alexander .
PHARMACEUTICAL RESEARCH, 2013, 30 (04) :996-1007
[10]   From Activity Cliffs to Target-Specific Scoring Models and Pharmacophore Hypotheses [J].
Seebeck, Birte ;
Wagener, Markus ;
Rarey, Matthias .
CHEMMEDCHEM, 2011, 6 (09) :1630-1639