Learned Feature Generation for Molecules

When classifying molecules for virtual screening, the molecular structure first needs to be converted into meaningful features, before a classifier can be trained. The most common methods use a static algorithm that has been created based on domain knowledge to perform this generation of features. We propose an approach where this conversion is learned by a convolutional neural network finding features that are useful for the task at hand based on the available data. Preliminary results indicate that our current approach can already come up with features that perform similarly well as common methods. Since this approach does not yet use any chemical properties, results could be improved in future versions.