NPClassifier: A Deep Neural Network-Based Structural Classification Tool for Natural Products

31 August 2020, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


Computational approaches such as genome and metabolome mining are becoming essential to natural products (NP) research. Consequently, demands for automated NP classification system for massive data are increasing. The semantic ontology of NPs classifies molecules based on the taxonomy of the producing organism, the nature of the biosynthetic pathway, their biological properties, as well as the presence of chemical substructures. Thus, a holistic and automatic NP classification framework could have considerable value to comprehensively navigate the relatedness of NPs. Here, we introduce NPClassifier, the first deep-learning tool for the automated structural classification of NPs. We expect that NPClassifier will accelerate NP discovery by facilitating and enabling large-scale genome and metabolome mining efforts and linking of NP structures to their underlying bioactivity.


Natural products
Deep Learning
Natural Product Classification
Morgan Fingerprints


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.