Infrared Spectral Analysis for Prediction of Functional Groups Based on Feature-Aggregated Deep Learning
Journal of Chemical Information and Modeling · 14.08.2023 · 63 (15) · 4615-4622
DOI: 10.1021/acs.jcim.3c00749 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 02.08.2023. Verfasst von Tianyi Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: The State Key Laboratory of Chemical Oncogenomics, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, P. R. China. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: Tsinghua Shenzhen International Graduate School, National Key Research and Development Program of China, Science, Technology and Innovation Commission of Shenzhen Municipality.
Abstract (Originalsprache)
Infrared (IR) spectroscopy is a powerful and versatile tool for analyzing functional groups in organic compounds. A complex and time-consuming interpretation of massive unknown spectra usually requires knowledge of chemistry and spectroscopy. This paper presents a new deep learning method for transforming IR spectral features into intuitive imagelike feature maps and prediction of major functional groups. We obtained 8272 gas-phase IR spectra from the NIST Chemistry WebBook. Feature maps are constructed using the intrinsic correlation of spectral data, and prediction models are developed based on convolutional neural networks. Twenty-one major functional groups for each molecule are successfully identified using binary and multilabel models without expert guidance and feature selection. The multilabel classification model can produce all prediction results simultaneously for rapid characterization. Further analysis of the detailed substructures indicates that our model is capable of obtaining abundant structural information from IR spectra for a comprehensive investigation. The interpretation of our model reveals that the peaks of most interest are similar to those often considered by spectroscopists. In addition to demonstrating great potential for spectral identification, our method may contribute to the development of automated analyses in many fields.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- The State Key Laboratory of Chemical Oncogenomics, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, P. R. China.
- Open FIESTA, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, P. R. China.
- Institute of Biomedical Health Technology and Engineering, Shenzhen Bay Laboratory, Shenzhen 518132, P.R. China.
ORCID-Profile: Tianyi Wang, Ying Tan, Yu Zong Chen, Chunyan Tan
Förderung
- Tsinghua Shenzhen International Graduate School
- National Key Research and Development Program of China
- Science, Technology and Innovation Commission of Shenzhen Municipality
Zitieren
APA
Wang, T., Tan, Y., Chen, Y. Z., & Tan, C. (2023). Infrared Spectral Analysis for Prediction of Functional Groups Based on Feature-Aggregated Deep Learning. Journal of Chemical Information and Modeling, 63(15), 4615-4622. https://doi.org/10.1021/acs.jcim.3c00749
Vancouver
Wang T, Tan Y, Chen YZ, Tan C. Infrared Spectral Analysis for Prediction of Functional Groups Based on Feature-Aggregated Deep Learning. Journal of Chemical Information and Modeling. 2023;63(15):4615-4622. doi:10.1021/acs.jcim.3c00749
BibTeX
@article{Wang2023,
author = {Wang, Tianyi and Tan, Ying and Chen, Yu Zong and Tan, Chunyan},
title = {Infrared Spectral Analysis for Prediction of Functional Groups Based on Feature-Aggregated Deep Learning},
journal = {Journal of Chemical Information and Modeling},
year = {2023},
volume = {63},
number = {15},
pages = {4615--4622},
doi = {10.1021/acs.jcim.3c00749}
}
EUVIMED