Human intestinal transporter database: QSAR modeling and virtual profiling of drug uptake, efflux and interactions

Abstract

Purpose: Membrane transporters mediate many biological effects of chemicals and play a major role in pharmacokinetics and drug resistance. The selection of viable drug candidates among biologically active compounds requires the assessment of their transporter interaction profiles.

Methods: Using public sources, we have assembled and curated the largest, to our knowledge, human intestinal transporter database (>5,000 interaction entries for >3,700 molecules). This data was used to develop thoroughly validated classification Quantitative Structure-Activity Relationship (QSAR) models of transport and/or inhibition of several major transporters including MDR1, BCRP, MRP1-4, PEPT1, ASBT, OATP2B1, OCT1, and MCT1.

Results: QSAR models have been developed with advanced machine learning techniques such as Support Vector Machines, Random Forest, and k Nearest Neighbors using Dragon and MOE chemical descriptors. These models afforded high external prediction accuracies of 71-100% estimated by 5-fold external validation, and showed hit retrieval rates with up to 20-fold enrichment in the virtual screening of DrugBank compounds.

Conclusions: The compendium of predictive QSAR models developed in this study can be used for virtual profiling of drug candidates and/or environmental agents with the optimal transporter profiles.

Figure 1

Localization of major intestinal transporters on enterocytes. Rectangles with arrows represent efflux (black) and influx (white) transporters.

Figure 2

Relative data content by database entries per transporter (a) and chemical classes in the database (b).

Figure 3

Overlap in known substrates (a) and inhibitors (b) of efflux transporters on the apical side.

Figure 4

Structural profiles of intestinal transporters for substrate (a) and inhibition (b) datasets. Green color represents descriptors with higher values in the active class, red – in the inactive class. Two datasets, MCT1 (in a) and MRP3 (in b), have too few compounds (31 and 36, respectively) and were not used for modeling.

Figure 5

Cumulative (a) and early (b) enrichment of hits in the virtual screening of DrugBank compounds, green curve represents retrieval of substrate hits, magenta–inhibitor hits, gray – expected performance by random guess.