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