ADME Evaluation in Drug Discovery. 7. Prediction of Oral Absorption by Correlation and Classification

Abstract

A critically evaluated database of human intestinal absorption for 648 chemical compounds is reported in this study, among which 579 are believed to be transported by passive diffusion. The correlation analysis between the intestinal absorption and several important molecular properties demonstrated that no single molecular property could be used as a good discriminator to efficiently distinguish the poorly absorbed compounds from those that are well absorbed. The theoretical correlation models for a training set of 455 compounds were proposed by using the genetic function approximation technique. The best prediction model contains four molecular descriptors: topological polar surface area, the predicted distribution coefficient at pH ) 6.5, the number of violations of the Lipinski's rule-of-five, and the square of the number of hydrogenbond donors. The model was able to predict the fractional absorption with an r ) 0.84 and a prediction error (absolute mean error) of 11.2% for the training set. Moreover, it achieves an r ) 0.90 and a prediction error of 7.8% for a 98-compound test set. The recursive partitioning technique was applied to find the simple hierarchical rules to classify the compounds into poor (%FA e 30%) and good (%FA > 30%) intestinal absorption classes. The high quality of the classification model was validated by the satisfactory predictions on the training set (correctly identifying 95.9% of the compounds in the poor-absorption class and 96.1% of the compounds in the good-absorption class) and on the test set (correctly identifying 100% of the compounds in the poor-absorption class and 96.8% of the compounds in the good-absorption class). We expect that, in the future, the rules for the prediction of carrier-mediated transporting and first pass metabolism can be integrated into the current hierarchical rules, and the classification model may become more powerful in the prediction of intestinal absorption or even human bioavailability. The databases of human intestinal absorption reported here are available for download from the supporting Web site: http:// modem.ucsd.edu/adme.

Coping with Unbalanced Class Data Sets in Oral Absorption Models

“…Table 5 gives a summary of all the molecular descriptors used in the selected models of 9, 10, 16 and 17. The most common molecular descriptors used in the best models were descriptors of hydrogen bonding (such as SHHBd, SHBint2), log D at various pH values which is related to lipophilicity and acid/base property, ACD_Density which is related to the number of heteroatoms in the molecules, and polar surface area (PSA) which has been cited as a molecular descriptor relating to polarity and size 20,63 . Other important molecular attributes are size related parameters.…”

“…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 main dataset used for this work consisted of %HIA data of 645 drugs and drug-like compounds 20 . As stated previously this dataset is biased towards the number of highlyabsorbed compounds.…”

Drug Absorption Modeling as a Tool to Define the Strategy in Clinical Formulation Development

“…Such a profiling is nowadays not only conducted by means of in vitro experiments, but also by computational methods (4,5). The well known Lipinski rules (6) can help in anticipating drug absorption hurdles and more recently, some quantitative structure bioavailability relationships (QSBR) were proposed leading to a more refined estimate of the drug absorption (7)(8)(9)(10)(11)(12)(13)(14)(15). An alternative to the QSBR approach is the concept of the absorption potential (16) or the estimation of a maximal absorbable dose (17).…”

Hit to Lead Generation for Oncology Targets

“…Early assessment of ADME (Absorption, Distribution, Metabolism and Elimination) profi le and safety profi le is critical to improve drug like properties and to avoid scaff old based liabilities in the later stage of the drug development process (9). While complete ADME and safety assessment cannot be carried out with a large number of synthetic targets generated at this phase of the project it is helpful to track some of the high/medium-throughput in-vitro ADME assays like CaCO-2 (absorption/effl ux) and microsomal stability (metabolism).…”