Data quality in the human and environmental health sciences: Using statistical confidence scoring to improve QSAR/QSPR modeling

摘要

A greater number of toxicity data are becoming publicly available allowing for in silico modeling. However, questions often arise as how to incorporate data quality and how to deal with contradicting data if more than a single datum point is available for the same compound. In this study, two well-known and studied QSAR/QSPR models for skin permeability and aquatic toxicology have been investigated in the context of statistical data quality. In particular, the potential benefits of the incorporation of the statistical Confidence Scoring (CS) approach within modelling and validation. As a result, robust QSAR/QSPR models for the skin permeability coefficient and the toxicity of nonpolar narcotics to Aliivibrio fischeri assay were created. CSweighted linear regression for training and CS-weighted root mean square error (RMSE) for validation were statistically superior compared to standard linear regression and standard RMSE. Strategies are proposed as to how to interpret data with high and low CS, as well as how to deal with large datasets containing multiple entries.