The human ATP-binding cassette (ABC) transporter ABCG2 (BCRP/MXR1/ABCP) plays a critical role in cellular protection against xenobiotics as well as pharmacokinetics of drugs in our body. In the present study, we aimed to analyze the quantitative structure-activity relationship (QSAR) latently residing in ABCG2-drug interactions. We first established standard methods for expression of human ABCG2 in insect cells, quality control of plasma membrane samples by using electron microscopy techniques, and high-speed screening of ABCG2 inhibition with test compounds. Plasma membrane vesicles prepared from ABCG2-expressing Sf9 cells were used as a model system to measure the ATP-dependent transport of [3H]methotrexate (MTX). Forty-nine different therapeutic drugs and natural compounds were tested for their ability to inhibit ABCG2-mediated MTX transport. Based on their inhibition profiles, we performed QSAR analysis using chemical fragmentation codes deduced from the structures of test compounds. Multiple linear regression analysis delineated a relationship between the structural components and the extent of ABCG2 inhibition, allowing us to identify one set of structure-specific chemical fragmentation codes that are closely correlated with the inhibition of ABCG2 transport activity. Based on the QSAR analysis data, we predicted the potency of gefitinib to inhibit ABCG2. The validity of our QSAR-based prediction for gefitinib was examined by actual experiments. Our kinetic analysis experiments suggest that the ABCG2-ATP complex binds gefitinib. The present study provides a new strategy for analyzing ABCG2-drug interactions. This strategy is considered to be practical and useful for the molecular designing of new ABCG2 modulators.