What is it about?
Deep learning is a form of artificial neural network with multiple layers. This form of machine learning algorithm has been applied widely outside of pharmaceutical research. It has seen some applications in bioinformatics and sparsely in cheminformatics compared with SVM or Bayesian methods.
Featured Image
Why is it important?
This perspective is timely as there has been use of the approach but few if any prospective predictions. Everything has been using leave out groups or retrospective analysis. While some have shown improvements using deep learning over other methods, it is time to really exhaustively access the utility of this method.
Perspectives
Deep learning has really exploded outside of the pharmaceutical industry with various open source tool kits, but there are few ready to use tools for use in cheminformatics for non experts etc. By providing an accessible analysis of the work published to date it may get others interested in the need to develop software and also apply to different datasets.
Dr Sean Ekins
Collaborations in Chemistry
Read the Original
This page is a summary of: The Next Era: Deep Learning in Pharmaceutical Research, Pharmaceutical Research, September 2016, Springer Science + Business Media,
DOI: 10.1007/s11095-016-2029-7.
You can read the full text:
Contributors
The following have contributed to this page
