Coping with Unbalanced Class Data Sets in Oral Absorption Models

Abstract

Class imbalance occurs frequently in drug discovery datasets. In oral absorption datasets, in the literature, there are considerably more of highly-absorbed compounds compared with poorly-absorbed compounds. This produces models that are biased towards highly-absorbed compounds which lack generalization to industry settings where more early stage drug candidates are poorly-absorbed. This paper presents two strategies to cope with unbalanced class datasets: Under-sampling the majority high absorption class and misclassification costs using classification decision trees. The published dataset by Hou et al (2007), which contained percentage human intestinal absorption of 645 drug and drug-like compounds, was used for the development and validation of classification trees using C&RT analysis. The results indicate that under-sampling the majority class, highly-absorbed compounds, leads to a balanced distribution (50:50) training set which can achieve better accuracies for poorlyabsorbed compounds, whereas the biased training set achieved higher accuracies for highlyabsorbed compounds. The use of misclassification costs resulted in improved class predictions, when applied to reduce false positives or false negatives. Moreover, it was shown that the classical overall accuracy measure used in many publications is particularly misleading in the case of unbalanced datasets and more appropriate measures presented here may be used for a more realistic assessment of the classification models' performance. Thus, these strategies offer improvements to cope with unbalanced class datasets to obtain classification models applicable in industry.

Estimation of Biliary Excretion of Foreign Compounds Using Properties of Molecular Structure

“…It is a well-established fact that compounds with higher logP have poor aqueous solubility and are more likely to pass through lipid bilayer of biological membranes (34). The general trend in the literature with regards to the role of lipophilicity in pharmacokinetic processes indicates that more lipophilic compounds have higher oral absorption, plasma protein binding, and volume of distribution (35)(36)(37) and are more prone to P450 metabolism (30,35). This may lead to the reduced chance of excretion through bile as the intact drug.…”

QSAR Modeling of Imbalanced High-Throughput Screening Data in PubChem

“…For instance, Chen et al 16 used the under-sampling method for toxicity modeling of Tetrahymena pyriformi s. Sun et al applied the same method to the prediction of cytochrome P450 profiles of environmental chemicals. Newby et al 17 modeled imbalanced oral absorption data sets. Chen et al compared the over-sampling approach with under-sampling and showed that the under-sampling method performed more consistently.…”

A rule of unity for human intestinal absorption 3: Application to pharmaceuticals

“…The median Π values and the corresponding mean FA values have a similar trend as one moves from the negative region to the positive region. Interestingly, it is evident from Figure 5 and Table 1 (Newby, Freitas, & Ghafourian, 2013); it may be due to a reluctance of scientists, companies and journals to publish negative results.…”

“…There is limited information available on the pharmaceutical formulation factors like hydration and different polymorphs of the drug employed in the clinical trials. In the literature, there is a relatively low number of reported poorly absorbed compounds (Newby, Freitas, & Ghafourian, ); it may be due to a reluctance of scientists, companies and journals to publish negative results.…”