Classifying bio-concentration factor with random forest algorithm, influence of the bio-accumulative vs. non-bio-accumulative compound ratio to modelling result, and applicability domain for random forest model

Presented at the 16th International Workshop on Quantitative Structure-Activity Relationships in Environmental and Health Sciences (QSAR2014), 16–20 June 2014, Milan, Italy.

Abstract

In environmental risk assessment, the bio-concentration factor (BCF) is a widely used parameter in the estimation of the bio-accumulation potential of chemicals. BCF data often have an uneven distribution of classes (bio-accumulative vs. non-bio-accumulative), which could severely bias the classification results towards the prevailing class. The present study focuses on the influence of uneven distribution of the classes in training phase of Random Forest (RF) classification models. Three different training set designs were used and descriptors selected to the models based on the occurrence frequency in RF trees and considering the mechanistic aspects they reflect. Models were compared and their classification performance was analysed, indicating good predictive characteristics (sensitivity = 0.90 and specificity = 0.83) for the balanced set; also imbalanced sets have their strengths in certain application scenarios. The confidence of classifications was assessed with a new schema for the applicability domain that makes use of the RF proximity matrix by analysing the similarity between the predicted compound and the training set of the model. All developed models were made available in the transparent, accessible and reproducible way in QsarDB repository (http://dx.doi.org/10.15152/QDB.116).

Keywords:

• bio-concentration factor
• random forest
• classification
• applicability domain
• imbalanced data set
• proximity matrix

Notes

Presented at the 16th International Workshop on Quantitative Structure-Activity Relationships in Environmental and Health Sciences (QSAR2014), 16–20 June 2014, Milan, Italy.