Predictive models for tyrosinase inhibitors: Challenges from heterogeneous activity data determined by different experimental protocols. (April 2018)

• Record Type: Journal Article
• Authors: Tang, Haifeng; Cui, Fengchao; Liu, Lunyang; Li, Yunqi
• Is Part Of: Computational biology and chemistry. Volume 73(2018)
• Page Start: 79
• Page End: 84
• Publication Date: 2018-04
• Subjects: Tyrosinase -- Ligand-based descriptors -- Structure-based descriptors -- Heterogeneous data -- Random Forest algorithm -- QSAR; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2018.02.007
• Languages: English
• ISSNs: 1476-9271

Abstract

Graphical abstract: Highlights: Proposed a filtering method to identify and remove outliers with larger systematic errors arising from heterogeneous data. Constructed a reasonable QSAR model with Q 2 of 0.80 withstructure- and ligand-based descriptors. The correlation between structures and activities for tyrosinase inhibitors is far from simple linear. Abstract: Quantitative Structure-Activity Relationship (QSAR) models of tyrosinase inhibitors were built using Random Forest (RF) algorithm and evaluated by the out-of-bag estimation (R 2 OOB ) and 10-fold cross validation (Q 2 CV ). We found that the performances of QSAR models were closely correlated with the systematic errors of inhibitory activities of tyrosinase inhibitors arising from the different measuring protocols. By defining ERRsys, outliers with larger errors can be efficiently identified and removed from heterogeneous activity data. A reasonable QSAR model (R 2 OOB of 0.74 and Q 2 CV of 0.80) was obtained by the exclusion of 13 outliers with larger systematic errors. It is a clear example of the challenge for QSAR model that can overwhelm heterogeneous data from different experimental protocols.