In Silico ADME Modeling 3: Computational Models to Predict Human Intestinal Absorption Using Sphere Exclusion and kNN QSAR Methods

Abstract

Modeling of human intestinal absorption (HIA) data of 175 diverse drugs and 336 calculated descriptors is performed to develop global predictive models that are applicable to the whole medicinal chemistry space. With this aim, we employed two automated procedures, (a) Sphere Exclusion Algorithm (SEA) to select members of the training and test sets based on structural dissimilarity and (b) k-Nearest Neighbors (kNN) method along with Genetic Algorithms (kNN-QSAR-GA) to select significant and independent descriptors. This methodology helped us to derive optimal Quantitative Structure -Property Relationship (QSPR) models based on three and four descriptors. The best three descriptor model is based on Delta Chi Index of order 3 (Cluster), Hydrogen type E-State index ShsOH, AlogP99 (q ext statistics with reported models using other approaches, it is shown that: (a) the models have high stability and are robust and (b) for the first time in HIA modeling, the combination of an automated training set selection (SEA) followed by variable selection (kNN-QSAR_GA) is shown to be a promising methodology to build multiple stable models that are useful in consensus prediction. From the analysis of the physical meaning of the selected descriptors, it is inferred that the HIA of small organic compounds can be accurately predicted using calculated descriptors that code for the following fundamental properties: (1) lipophilicity, (2) hydrogen bonding capacity, (3) size, and (4) shape and further, the role of new calculated descriptors on the HIA profile of small organic compounds is uncovered. Finally, as the models reported herein are based on computed properties, they appear to be a valuable tool in virtual screening, where selection and prioritization of candidates is required.

Trend Analysis of a Database of Intravenous Pharmacokinetic Parameters in Humans for 670 Drug Compounds

“…Previous reports have focused on prediction methods that utilize animal pharmacokinetic data (Caldwell et al, 2004;Ward and Smith, 2004a,b;Jolivette and Ward, 2005;Evans et al, 2006;Mahmood et al, 2006;Martinez et al, 2006;Tang and Mayersohn, 2006;Fagerholm, 2007;McGinnity et al, 2007) and in vitro data (Obach et al, 1997;Lombardo et al, 2002Lombardo et al, , 2004Nestorov et al, 2002;Riley et al, 2005;Grime and Riley, 2006). Recently, the availability of computational chemistry methodologies has increased, and these have been applied to the prediction of human pharmacokinetics and/or general absorption-distribution-metabolism-excretion-toxicology properties (Cruciani et al, 2005;Ghafourian et al, 2006;Gleeson et al, 2006;Lombardo et al, 2006;Gleeson, 2007;Gunturi and Narayanan, 2007;Norinder and Bergstroem, 2007). The construction of effective models not only requires sound computational tools but, very importantly, databases that have been carefully assembled.…”

Correlation of blood-brain penetration and human serum albumin binding with theoretical descriptors

“…2. The descriptor ranges for D7-D11 are [4,41], [0, 0.352], [5.582, 24.48], [-0.195, 0.065] and [-0.188, -0.099], respectively. The same analyses for Eq.…”

“…To enhance the efficiency and costeffectiveness of the pharmaceutical industry, in recent years, numerous in vitro ADME-Tox assays [1][2][3] and in silico prediction methods [4][5] have been developed, improved and integrated into early-stage pharmaceutical research and development. Since the experimental methods for determing and evaluating ADME-Tox properties are often time-consuming and expensive, in silico predictive models are becoming increasingly important tools as relatively cheap alternatives for initial screening.…”

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

“…The decline in the productivity of the pharmaceutical industry is mostly due to the poor ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties. [2][3][4][5][6][7][8][9] Nowadays, oral administration has become the route favored by patients because of its ease and patient compliance. For a new oral drug, bioavailability is one of the most desirable attributes, whereas the determination of oral bioavailability is very challenging due to the fact that bioavailability is a complex function of many biologic and physicochemical factors.…”