Development of a Method for Evaluating Drug-Likeness and Ease of Synthesis Using a Data Set in Which Compounds Are Assigned Scores Based on Chemists' Intuition

Abstract

The concept of drug-likeness, an important characteristic for any compound in a screening library, is nevertheless difficult to pin down. Based on our belief that this concept is implicit within the collective experience of working chemists, we devised a data set to capture an intuitive human understanding of both this characteristic and ease of synthesis, a second key characteristic. Five chemists assigned a pair of scores to each of 3980 diverse compounds, with the component scores of each pair corresponding to drug-likeness and ease of synthesis, respectively. Using this data set, we devised binary classifiers with an artificial neural network and a support vector machine. These models were found to efficiently eliminate compounds that are not drug-like and/or hard-to-synthesize derivatives, demonstrating the suitability of these models for use as compound acquisition filters.

Effect of Molecular Descriptor Feature Selection in Support Vector Machine Classification of Pharmacokinetic and Toxicological Properties of Chemical Agents

“…[1][2][3][4][5][6][7] These descriptors were initially developed for the construction of quantitative structure-activity relationship (QSAR) and quantitative structure-property relationship (QSPR) of structurally related compounds. 8 They have been extensively used for the statistical-learning-based prediction of pharmacodynamic, pharmacokinetic, and toxicological properties of chemical agents including drug-likeness, [9][10][11] blood-brain barrier penetration, 12,13 human intestinal absorption, 4 drug-receptor binding, [14][15][16] drug metabolism, 17 cellular membrane partitioning, 18 chemical space navigation, 19 and antibacterial activity. 20,21 Some of these molecular descriptors are developed for the study of a particular type of properties of a group of structurally related chemical agents.…”

Drug-like properties: guiding principles for design – or chemical prejudice?

“…In addition, traditionally less tractable targets, such as protein-protein interactions, might require diverse, new chemistry. The opinions of medicinal chemists as to what molecules constitute worthwhile additions to a compound collection, or valuable HTS hits, are not consistent [40,41]. Medicinal chemical opinion is a consequence of experience, knowledge, intuition and prejudice, which will continue to be key drivers for compound selection and design strategies.…”

“…These judgements are often reliable, but are inevitably subjective [40]. An interesting recent study [41] highlights notable variation in rejection rates between chemists reviewing compounds for purchase (a useful surrogate for screen hit lists) that were first ''spiked'' with some 250 particularly unpalatable structures.…”

Properties Guiding Drug‐ and Lead‐Likeness

“…Many of these unwanted functionalities have been collected based on chemists feedback from hit identifi cation and lead optimization projects, and by looking at compounds not considered good starting points for optimization by medicinal chemistry or diffi cult to synthesize [35] . However, one could say that " beauty is in the eye of the beholder " and selecting attractive chemical starting points depends upon the experience and prejudice of individual chemists.…”