Comparative analysis of the use of chemoinformatics-based and substructure-based descriptors for quantitative structure-activity relationship (QSAR) modeling

Article type: Research Article

Authors: Karunaratne, Thashmee^{a; *} | Boström, Henrik^a | Norinder, Ulf^{b; c; d}

Affiliations: [a] Department of Computer and Systems Sciences, Stockholm University, Kista, Sweden | [b] AstraZeneca Research and Development, Södertälje, Sweden | [c] Department of Pharmacy, Uppsala University, Uppsala, Sweden | [d] Department of Computational Chemistry, H. Lundbeck A/S, Valby, Denmark

Correspondence: [*] Corresponding author: Thashmee Karunaratne, Department of Computer and Systems Sciences, Stockholm University, Forum 100, SE-164 40 Kista, Sweden. E-mail: [email protected].

Abstract: Quantitative structure-activity relationship (QSAR) models have gained popularity in the pharmaceutical industry due to their potential to substantially decrease drug development costs by reducing expensive laboratory and clinical tests. QSAR modeling consists of two fundamental steps, namely, descriptor discovery and model building. Descriptor discovery methods are either based on chemical domain knowledge or purely data-driven. The former, chemoinformatics-based, and the latter, substructures-based, methods for QSAR modeling, have been developed quite independently. As a consequence, evaluations involving both types of descriptor discovery method are rarely seen. In this study, a comparative analysis of chemoinformatics-based and substructure-based approaches is presented. Two chemoinformatics-based approaches; ECFI and SELMA, are compared to five approaches for substructure discovery; CP, graphSig, MFI, MoFa and SUBDUE, using 18 QSAR datasets. The empirical investigation shows that one of the chemo-informatics-based approaches, ECFI, results in significantly more accurate models compared to all other methods, when used on their own. Results from combining descriptor sets are also presented, showing that the addition of ECFI descriptors to any other descriptor set leads to improved predictive performance for that set, while the use of ECFI descriptors in many cases also can be improved by adding descriptors generated by the other methods.

Keywords: QSAR modeling, chemical descriptors, graph mining

DOI: 10.3233/IDA-130581

Journal: Intelligent Data Analysis, vol. 17, no. 2, pp. 327-341, 2013