Theoretically-derived molecular descriptors important in human intestinal absorption

Agatonović-Kuštrin, Snežana; Beresford, Rosemary; Yusof, A. P. M.

doi:10.1016/s0731-7085(00)00492-1

Cited by 62 publications

(41 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The high HOMO energy group (Node 7) on the other hand, consists mainly of compounds of moderate absorption level (HIA of 40-60%) and, although marked as highly-absorbed, contains more of the poorly-absorbed compounds to be classified at the next level. These compounds are also of polar nature with many hydrogen bonding groups, but they also have planar areas in the molecule resulting from aromatic groups or other conjugated double bonds (hence high HOMO energy) 31 . High HOMO energy compounds at Node 7 will have high absorption provided that they have dipole moment > 6.63.…”

Section: Interpretation Of the Selected Models Based On Ts1mentioning

confidence: 99%

Coping with Unbalanced Class Data Sets in Oral Absorption Models

Newby

Freitas

Ghafourian

2013

J. Chem. Inf. Model.

View full text Add to dashboard Cite

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.

show abstract

Section: Interpretation Of the Selected Models Based On Ts1mentioning

confidence: 99%

Coping with Unbalanced Class Data Sets in Oral Absorption Models

Newby

Freitas

Ghafourian

2013

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Examples include a quantitative structure-gradient elution retention relationship of phenylthiocarbamyl amino acid derivatives encoded with 36 calculated molecular descriptors [29], and a quantitative structure-human intestinal absorption relationship of 86 drug molecules encoded with 57 constitutional, topological, chemical, geometrical, and quantum chemical descriptors [30]. The results of these studies helped to highlight important factors in the determination of these important properties.…”

Section: Resultsmentioning

confidence: 99%

Genetic Neural Networks for Functional Approximation

Chiu

2003

QSAR Comb. Sci.

View full text Add to dashboard Cite

Quantitative structure-activity relationship (QSAR) analysis is a commonly used ligand-based molecular design method for the lead optimization process in the pharmaceutical industry. Typically, development of a QSAR model goes through the following stages: descriptor generation, function approximation (including feature selection and model construction), and model validation. This article highlights a promising genetic neural network (GNN) method for function approximation in QSAR and reviews its underlying theoretical concepts, techniques, and recent applications.

show abstract

“…24,25 These models are constructed based on different types of descriptors, such as physicochemical descriptors, 12,[26][27][28][29] topological descriptors and so on. [30][31][32][33] With regards to computational techniques, the most common mathematical methods include articial neural networks 27,28,33 and multiple linear regression. 30 Furthermore, support vector machine (SVM), 29,34 multivariate adaptive regression splines 24 and stepwise regression 25 have also been applied.…”

Section: 11mentioning

confidence: 99%

“…We collected their HIA values from 13 HIA studies. 1,3,13,20,24,26,27,32,[37][38][39][40][41] To improve the quality and reliability of the dataset, we dealt with it as follows. When there were two or more entries for one molecule, if these values did not differ a lot (<20%), the arithmetic mean value was adopted to reduce the random error; otherwise, the corresponding HIA value will be reconrmed again.…”

Section: Data Collectionmentioning

confidence: 99%

Predicting human intestinal absorption with modified random forest approach: a comprehensive evaluation of molecular representation, unbalanced data, and applicability domain issues

et al. 2017

View full text Add to dashboard Cite

With the increase of complexity and risk in drug discovery processes, human intestinal absorption (HIA) prediction has become more and more important. Up to now, some predictive models have been constructed to estimate HIA of new drug-like compounds with acceptable accuracies, but there are still some issues to be explored including the limited and unbalanced HIA data, the performance of different types of descriptors and the application domain issues of published models. To address these problems, in this study, we collected a relatively large dataset consisting of 970 compounds, and 9 different types of descriptors were calculated for further modeling. For all the modeling processes, a parameter named samplesize in the random forest (RF) method was applied to balance the dataset. And then, classification models were established based on different training sets and different combinations of descriptors. published models, our model exhibits some advantages in data size, model accuracy and model practicability to some extent. This structure-activity relationship model is necessary and useful for HIA prediction and it could be a convenient tool for virtual screening in the early stage of drug development.

show abstract

Theoretically-derived molecular descriptors important in human intestinal absorption

Cited by 62 publications

References 19 publications

Coping with Unbalanced Class Data Sets in Oral Absorption Models

Coping with Unbalanced Class Data Sets in Oral Absorption Models

Genetic Neural Networks for Functional Approximation

Predicting human intestinal absorption with modified random forest approach: a comprehensive evaluation of molecular representation, unbalanced data, and applicability domain issues

Contact Info

Product

Resources

About