Abstract
AbstractThe accuracy of in silico models can be inhomogeneous: models can show excellent performance on some chemical subspaces but have low accuracy on others. We show that applicability domain (AD) approaches can differentiate reliable and non‐reliable predictions and identify those with experimental accuracy for both regression and classification models. For reliably predicted molecules, the predicted values can be used instead of experimental measurements. This can halve time and costs of experimental measurements. The developed classification models for AMES mutagenicity test and CYP450 inhibition, which are important drug discovery properties, are publicly available at the online chemical database and modeling environment (OCHEM) site http://qspr.eu Copyright © 2010 John Wiley & Sons, Ltd.
References
28
Referenced
89
10.1016/j.patrec.2005.10.010
- BiJK BenettK.Regression Error Characteristic Curves.
10.1016/j.drudis.2006.06.013
10.1002/jps.21494
10.1002/(SICI)1099-128X(199609)10:5/6<687::AID-CEM469>3.0.CO;2-O
10.1002/(SICI)1099-128X(199701)11:1<39::AID-CEM433>3.0.CO;2-S
10.1002/(SICI)1099-128X(199705)11:3<181::AID-CEM459>3.0.CO;2-7
10.1002/(SICI)1099-128X(199807/08)12:4<295::AID-CEM510>3.0.CO;2-T
10.1016/S0166-445X(00)00158-2
10.1021/ci800151m
10.1177/026119290503300209
{'key': 'e_1_2_1_13_2', 'first-page': '185', 'article-title': 'Associative neural network', 'volume': '458', 'author': 'Tetko IV', 'year': '2008', 'journal-title': 'Methods Mol. Biol.'}
/ Methods Mol. Biol. / Associative neural network by Tetko IV (2008)10.1021/ci010379o
10.1021/ci025515j
10.1021/ci00027a006
10.1021/ci700443v
10.1007/BF00058655
10.1021/ci0202741
{'key': 'e_1_2_1_20_2', 'first-page': '80', 'volume-title': 'Applicability Domain for Classification problems', 'author': 'Sushko I', 'year': '2009'}
/ Applicability Domain for Classification problems by Sushko I (2009)10.1021/tx049666n
10.1016/S0166-1280(02)00618-8
10.1080/10629360412331297344
10.1002/qsar.200960003
10.1002/cbdv.200900075
10.1016/S0027-5107(00)00064-6
10.1021/ci900161g
10.1007/978-3-642-48736-1_5
10.1080/15287398809531194
Dates
Type | When |
---|---|
Created | 15 years, 4 months ago (April 8, 2010, 3:38 a.m.) |
Deposited | 1 year, 11 months ago (Aug. 31, 2023, 12:52 a.m.) |
Indexed | 3 weeks ago (Aug. 2, 2025, 12:16 a.m.) |
Issued | 15 years, 5 months ago (March 1, 2010) |
Published | 15 years, 5 months ago (March 1, 2010) |
Published Online | 15 years, 4 months ago (April 8, 2010) |
Published Print | 15 years, 5 months ago (March 1, 2010) |
@article{Sushko_2010, title={Applicability domain for in silico models to achieve accuracy of experimental measurements}, volume={24}, ISSN={1099-128X}, url={http://dx.doi.org/10.1002/cem.1296}, DOI={10.1002/cem.1296}, number={3–4}, journal={Journal of Chemometrics}, publisher={Wiley}, author={Sushko, Iurii and Novotarskyi, Sergii and Körner, Robert and Pandey, Anil Kumar and Kovalishyn, Vasily V. and Prokopenko, Volodymyr V. and Tetko, Igor V.}, year={2010}, month=mar, pages={202–208} }