Importance of the field: The past decade had witnessed remarkable advances in computer science which had given rise to many new possibilities including the ability to simulate and model life's phenomena. Among one of the greatest gifts computer science had contributed to drug discovery is the ability to predict the biological activity of compounds and in doing so drives new prospects and possibilities for the development of novel drugs with robust properties. Areas covered in this review: This review presents an overview of the advances in the computational methods utilized for predicting the biological activity of compounds. What the reader will gain: The reader will gain a conceptual view of the quantitative structure–activity relationship paradigm and the methodological overview of commonly used machine learning algorithms. Take home message: Great advancements in computational methods have now made it possible to model the biological activity of compounds in an accurate manner. To obtain such a feat, it is often necessary to forgo several data pre-processing and post-processing procedures. A wide range of tools are available to perform such tasks; however, the proper selection and piecing together of complementary components in the prediction workflow remains a challenging and highly subjective task that heavily relies on the experience and judgment of the practitioner.