TY - JOUR
T1 - DeepSAT
T2 - Learning Molecular Structures from Nuclear Magnetic Resonance Data
AU - Kim, Hyun Woo
AU - Zhang, Chen
AU - Reher, Raphael
AU - Wang, Mingxun
AU - Alexander, Kelsey L.
AU - Nothias, Louis Félix
AU - Han, Yoo Kyong
AU - Shin, Hyeji
AU - Lee, Ki Yong
AU - Lee, Kyu Hyeong
AU - Kim, Myeong Ji
AU - Dorrestein, Pieter C.
AU - Gerwick, William H.
AU - Cottrell, Garrison W.
N1 - Publisher Copyright:
© 2023, Springer Nature Switzerland AG.
PY - 2023/12
Y1 - 2023/12
N2 - The identification of molecular structure is essential for understanding chemical diversity and for developing drug leads from small molecules. Nevertheless, the structure elucidation of small molecules by Nuclear Magnetic Resonance (NMR) experiments is often a long and non-trivial process that relies on years of training. To achieve this process efficiently, several spectral databases have been established to retrieve reference NMR spectra. However, the number of reference NMR spectra available is limited and has mostly facilitated annotation of commercially available derivatives. Here, we introduce DeepSAT, a neural network-based structure annotation and scaffold prediction system that directly extracts the chemical features associated with molecular structures from their NMR spectra. Using only the 1H-13C HSQC spectrum, DeepSAT identifies related known compounds and thus efficiently assists in the identification of molecular structures. DeepSAT is expected to accelerate chemical and biomedical research by accelerating the identification of molecular structures.
AB - The identification of molecular structure is essential for understanding chemical diversity and for developing drug leads from small molecules. Nevertheless, the structure elucidation of small molecules by Nuclear Magnetic Resonance (NMR) experiments is often a long and non-trivial process that relies on years of training. To achieve this process efficiently, several spectral databases have been established to retrieve reference NMR spectra. However, the number of reference NMR spectra available is limited and has mostly facilitated annotation of commercially available derivatives. Here, we introduce DeepSAT, a neural network-based structure annotation and scaffold prediction system that directly extracts the chemical features associated with molecular structures from their NMR spectra. Using only the 1H-13C HSQC spectrum, DeepSAT identifies related known compounds and thus efficiently assists in the identification of molecular structures. DeepSAT is expected to accelerate chemical and biomedical research by accelerating the identification of molecular structures.
KW - Convolutional neural network
KW - Nuclear magnetic resonance
KW - Structure prediction
UR - http://www.scopus.com/inward/record.url?scp=85167507081&partnerID=8YFLogxK
U2 - 10.1186/s13321-023-00738-4
DO - 10.1186/s13321-023-00738-4
M3 - Article
AN - SCOPUS:85167507081
SN - 1758-2946
VL - 15
JO - Journal of Cheminformatics
JF - Journal of Cheminformatics
IS - 1
M1 - 71
ER -