RESUMEN
Design of structurally-novel drug molecules with deep learning can overcome the technical bottleneck of classical computer-aided drug design. It has become the frontier of new technique research on drug design, and has shown great potential in drug research and development practice. This review starts from the basic principles of deep learning-driven de novo drug design, goes on with the brief introduction to deep molecular generation techniques as well as computational tools and the analysis on representative successful cases, and eventually provides our perspective for future direction and application prospect about this technique. This review will provide ideas on new technique research and references for new drug research and development practice to which this technique is applied.
RESUMEN
Among various technologies used in drug design and discovery, deep learning is still in its infancy. Recently, deep learning approaches have been rapidly developed and applied to address various problems in drug discovery, including generation of virtual compound library, prediction of compound activity, metabolism and toxicity, and prediction of organic synthesis routes. Compared with the traditional machine learning methods, the prediction power of deep learning did not show significant improvement. However, proactively learning and automatically feature extraction bring advantages for deep learning approaches. Compared to first principle-based computational chemistry methods, deep learning can not be generalized because it depends on large-scale and high-quality annotated data sets. But its molecular representation with single-atom atomic environment vectors could be useful for computational chemists. As an emerging technology, deep learning, especially the unsupervised learning method that does not rely on large datasets with labels, is gradually improving. It is expected that someday deep learning method will become practical for drug discovery.