Prediction of drug bioavailability based on molecular structure

Turner, Joseph V.; Glass, B. D.; Agatonović-Kuštrin, Snežana

doi:10.1016/s0003-2670(03)00406-9

Cited by 42 publications

(20 citation statements)

References 211 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In parallel, the authors generated a toxicophore (pharmacophore-based toxicity model) using Catalyst's HypoGen that included hydrogenbonding, hydrophobic, aromatic, and positive ionizable features. Upon analysis of their models, the authors noted There is currently a great deal of models available for predicting absorption, bioavailability, transporter binding, metabolism, volume of distribution, and P450 interactions (Yoshida and Topliss, 2000;de Groot and Ekins, 2002;Ekins et al, 2002a,b;Lewis, 2003;Pintore et al, 2003;Turner et al, 2003;Lombardo et al, 2004). Comprehensive software packages have been developed such as QikProp, which can be used to predict an array of ADMET-related properties such as solubility, membrane permeability, partition coefficients, bloodbrain barrier penetration, plasma protein binding, and the formation of metabolites (Jorgensen and Duffy, 2002).…”

Section: Prediction Of Human Ether-a-go-go Rrelated Gene Bindingmentioning

confidence: 99%

Computational Methods in Drug Discovery

et al. 2013

View full text Add to dashboard Cite

Section: Prediction Of Human Ether-a-go-go Rrelated Gene Bindingmentioning

confidence: 99%

Computational Methods in Drug Discovery

et al. 2013

View full text Add to dashboard Cite

“…if molecular weight >500 Da, sum of OH and NH hydrogen bond donors >5, calculated logP The next important descriptor selected by the C&RT for the partitioning of highly hydrogen bond donor compounds is VAMP HOMO, which is the energy of the highest occupied molecular orbital calculated by AM1 semi empirical method and has been used in previous QSAR models for bioavailability 30 . According to this split, compounds with HOMO energy of <= -9.22 are all poorly-absorbed compounds.…”

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

“…As can be seen were not included all databases/data sets reported, only those with high structural varaibility and oral absorption information. Sietsema (1989) F Oral bioavailability data set Hirono et al (1994) F Oral bioavailability data set Benet et al (1996) F Oral bioavailability data set Bertz and Granneman (1997) F Oral bioavailability data set Yoshida and Topliss (2000) F Oral bioavailability data set Andrews et al (2000) F Oral bioavailability (GlaxoSmithKline, commercial) Veber et al (2002) F (in rats) Oral bioavailability data set Turner et al (2003) F Oral bioavailability data set (Hou et al (2007) F HIA or % oral absorption data set Palm et al (1997) HIA HIA or % oral absorption data set Wessel et al (1998) Although many databases and data sets are reported, only few of them with desirable quality and structural diversity are in public domain. This fact reduces the robustness and predictive capacity of the models obtained (Lombardo et al, 2003;Gola et al, 2006).…”

Section: Experimental Data Setmentioning

confidence: 99%