In Silico Prediction of Caco‐2 Cell Permeability by a Classification QSAR Approach

Abstract

In the present study, 21 validated QSAR models that discriminate compounds with high Caco-2 permeability (Papp ≥8×10(-6) cm/s) from those with moderate-poor permeability (Papp <8×10(-6) cm/s) were developed on a novel large dataset of 674 compounds. 20 DRAGON descriptor families were used. The global accuracies of obtained models were ranking between 78-82 %. A general model combining all types of molecular descriptors was developed and it classified correctly 81.56 % and 83.94 % for training and test sets, respectively. An external set of 10 compounds was predicted and 80 % was correctly assessed by in vitro Caco-2 assays. The potential use of the final model was evaluated by a virtual screening of a human intestinal absorption database of 269 compounds. The model predicted 121 compounds with high Caco-2 permeability and the 90 % of them had high values of human intestinal absorption (HIA≥80). This study provides the most comprehensive database of Caco-2 permeability and evidenced the utility of the combined methodology (in silico+in vitro) in the prediction of Caco-2 permeability. It suggests that the present methodology can be used in the design of large libraries of compounds with appropriate values of permeability and to perform virtual screening in the early stages of drug development.

Towards Better BBB Passage Prediction Using an Extensive and Curated Data Set

“…It is worthwhile point out that previous derived models have proven that DELS is as ignificant descriptor for modeling drug transport properties such as human intestinal permeation. [79] 3.3 Quantitative Approach Using MLR MLR-GA analysis was used to select the best subset of descriptors and to develop the linear models on the training set. It is noteworthy that some compounds were identified as outliers because of their particular structural features poorly represented in the training set, which could affect the variable selection for ab etter modeling of those compounds (X outliers) or the experimental uncertainties (Y outliers).…”

Selective Hypoxia‐Cytotoxin 7‐Fluoro‐2‐Aminophenazine 5,10‐Dioxide: Toward “Candidate‐to‐Drug” Stage in the Drug‐Development Pipeline

“…If the compound has the HIA% more than 30%, it is labeled as (+); [b] Caco‐2 permeability. If the compound has the Caco‐2 permeability value ≥ 8×10‐6 cm/s, it is labeled as high Caco‐2 permeability (+); [c] P‐glycoprotein inhibition or substrate . Non‐inhibition or ability to be substrate is labeled as (‐); [d] Renal organic cation transporter (OCT2) inhibition .…”

“…On the other hand, we predicted the aqueous solubility (LogS) due to the solubility problems observed previously with this kind of compounds (Table ) . Concerning to the absorption and distribution aspects, the predicted parameters, i. e. HIA and Caco‐2 permeability, indicated that 1 could be orally administered (Table ). On the other hand, a relevant bio‐system in the absorption processes is the P‐gp, a member of the ATP‐binding cassette family extensively distributed and expressed in many human organs with secretory or barrier functions, i. e. intestinal epithelium, hepatocytes, renal proximal tubular cells, adrenal gland and endothelial capillaries of the brain comprising the blood‐brain barrier, consequently playing relevant role in drug bioavailability, metabolism and toxicity.…”

ChemSAR: an online pipelining platform for molecular SAR modeling

“…The latest report was in 2013 [76], the authors built a model using DT method with 1289 compounds which could accurately predict 78.4/76.1/79.1% of H/M/L compounds on the training set and 78.6/71.1/77.6% on the test set. In 2011 [77], Pham et al built a model using linear discriminant analysis (LDA) method with 674 molecules which reported results: MCC = 0.62, Accuracy = 81.56% (training set), Accuracy = 83.94% (test set). Compared with the two models above, our model has an almost comparative or better performance.…”