Welcome to SMART Documentation
SMART (Small Molecule Accurate Recognition Technology) is the next generation of NMR analysis.
SMART is a user-friendly, AI-based dereplication and analysis tool that uses 2D NMR data to rapidly associate newly isolated NPs with their known analogues. SMART has been designed to mimic the normal path of experiential learning in that additional 2D NMR spectral inputs can be used to enrich its database and improve its performance. In short, SMART aims to become an experienced associate to natural products researchers as well as other classes of organic chemists.
Frequently asked Questions
Q: Is the data I upload to analyze publicly visible?
A: Data you upload to analyze at SMART will remain private unless you explicitly make it public. The way to make your data public are to add individual annotated HSQC data to SMART database (Moliverse). See also the tab 'Contributing to SMART'.
Q: Will HSQC data that I create be public by default?
A: Yes, when you add your annotated HSQC data to the Moliverse it will be visible for other users when they explore 'Into the Moliverse'. In that way your compounds can gain more attention and you likely get more citations for your paper. As training a dCNN takes some time, we will include your spectrum in new releases of SMART.
Q: Can I select more than one file at a time for each group in molecular networking?
A: Yes, you can drag&drop up to 8 CSV files in the analysis window. The analyses will run iteratively.
NMR spectrometer Types (Bruker, JEOL, Varian...)
Q: Does SMART support data from different NMR vendors?
A: Yes, the only input you need for SMART analysis is the NMR table of 1H and 13C chemical shifts. These are vendor and processing software independent.
We officially test on the latest Chrome browser. Other browsers, e.g. Firefox, Internet Explorer, Opera, Edge, are not officially supported but likely will not have any issues with SMART 2.0.
We acknowledge the use of Advanced Chemistry Development, Inc. for use of their HSQC predictor for calculating data in the SMART tool.
We thank Dr. Kikuko Hayamizu for her efforts to create the free open CH-NMR-NP database distributed by JEOL, which was used to train the SMART 2.0.
We sincerely thank the following people who have done great work to make the idea of web-based SMART become true. You guys are awesome. Names appear in alphabetic order.