Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.21256/zhaw-27328| Publikationstyp: | Konferenz: Poster |
| Art der Begutachtung: | Peer review (Abstract) |
| Titel: | A deep ensemble learning method for automatic classification of multiplets in 1D NMR spectra |
| Autor/-in: | Fischetti, Giulia Schmid, Nicolas Bruderer, Simon Paruzzo, Federico Toscano, Giuseppe Graf, Dominik Fey, Michael Henrici, Andreas Scarso, Alessandro Caldarelli, Guido Heitmann, Björn Wilhelm, Dirk |
| et. al: | No |
| DOI: | 10.21256/zhaw-27328 |
| Tagungsband: | EUROMAR 2022 Abstractbook |
| Herausgeber/-in des übergeordneten Werkes: | Prisner, Thomas |
| Seite(n): | 236 |
| Angaben zur Konferenz: | European Conference on Magnetic Resonance (EUROMAR), Utrecht, The Netherlands, 10-14 July 2022 |
| Erscheinungsdatum: | 14-Jul-2022 |
| Verlag / Hrsg. Institution: | ZHAW Zürcher Hochschule für Angewandte Wissenschaften |
| Sprache: | Englisch |
| Schlagwörter: | Nuclear Magnetic Resonance; Automatic signal classification; Deep learning; 1H spectra; Multiplet assignment |
| Fachgebiet (DDC): | 006: Spezielle Computerverfahren 530: Physik |
| Zusammenfassung: | The identification and characterization of signal peaks in NMR spectra is a crucial yet time-consuming and error-prone stage in the determination of complex chemical compounds. The introduction of automation in the NMR analysis can ease the workflow while increasing the robustness and reproducibility of the results. Here, we present a novel supervised deep learning method to perform automatic detection and classification of multiplets in one dimensional proton NMR spectra. The method consists of a probabilistic deep learning approach based on an ensemble of deep convolutional neural networks. The training set is composed of a large number of synthetic spectra containing classes of basic nonoverlapping multiplets only. All networks in the ensemble produce the same prediction for basic multiplets, while resonances not represented in the training set cause arbitrary errors that differ across the networks. Therefore, high output variance in the ensemble is an indicator of the presence of overlapping multiplets. Being able to distinguish between basic and overlapping multiplets is a decisive stage. Together with classification within different resonance categories, it helps to perform automated peak picking and coupling constants extraction. We show that our model can discriminate signal regions effectively and minimize classification errors between different categories of resonances. Most importantly, we demonstrate that the network generalizes remarkably well on real experimental proton NMR spectra. The evaluation is carried out through the implementation of a specific statistical procedure for quantitatively testing the ensemble prediction against experts’ annotations. |
| URI: | https://euromar2022.org/wp-content/uploads/2022/07/Euromar-AbstractBook_2022-A4_22jul_new.pdf https://digitalcollection.zhaw.ch/handle/11475/27328 |
| Volltext Version: | Publizierte Version |
| Lizenz (gemäss Verlagsvertrag): | Lizenz gemäss Verlagsvertrag |
| Departement: | School of Engineering |
| Organisationseinheit: | Institut für Angewandte Mathematik und Physik (IAMP) |
| Publiziert im Rahmen des ZHAW-Projekts: | Maschinelles Lernen für NMR-Spektroskopie |
| Enthalten in den Sammlungen: | Publikationen School of Engineering |
Dateien zu dieser Ressource:
| Datei | Beschreibung | Größe | Format | |
|---|---|---|---|---|
| 2022_Fischetti-etal_Deep-Ensemble-learning-multiplet-classification_EUROMAR-Poster.pdf | 605.98 kB | Adobe PDF |  Öffnen/Anzeigen |
Zur Langanzeige
Fischetti, G., Schmid, N., Bruderer, S., Paruzzo, F., Toscano, G., Graf, D., Fey, M., Henrici, A., Scarso, A., Caldarelli, G., Heitmann, B., & Wilhelm, D. (2022). A deep ensemble learning method for automatic classification of multiplets in 1D NMR spectra [Conference poster]. In T. Prisner (Ed.), EUROMAR 2022 Abstractbook (p. 236). ZHAW Zürcher Hochschule für Angewandte Wissenschaften. https://doi.org/10.21256/zhaw-27328
Fischetti, G. et al. (2022) ‘A deep ensemble learning method for automatic classification of multiplets in 1D NMR spectra’, in T. Prisner (ed.) EUROMAR 2022 Abstractbook. ZHAW Zürcher Hochschule für Angewandte Wissenschaften, p. 236. Available at: https://doi.org/10.21256/zhaw-27328.
G. Fischetti et al., “A deep ensemble learning method for automatic classification of multiplets in 1D NMR spectra,” in EUROMAR 2022 Abstractbook, Jul. 2022, p. 236. doi: 10.21256/zhaw-27328.
FISCHETTI, Giulia, Nicolas SCHMID, Simon BRUDERER, Federico PARUZZO, Giuseppe TOSCANO, Dominik GRAF, Michael FEY, Andreas HENRICI, Alessandro SCARSO, Guido CALDARELLI, Björn HEITMANN und Dirk WILHELM, 2022. A deep ensemble learning method for automatic classification of multiplets in 1D NMR spectra. In: Thomas PRISNER (Hrsg.), EUROMAR 2022 Abstractbook [online]. Conference poster. ZHAW Zürcher Hochschule für Angewandte Wissenschaften. 14 Juli 2022. S. 236. Verfügbar unter: https://euromar2022.org/wp-content/uploads/2022/07/Euromar-AbstractBook_2022-A4_22jul_new.pdf
Fischetti, Giulia, Nicolas Schmid, Simon Bruderer, Federico Paruzzo, Giuseppe Toscano, Dominik Graf, Michael Fey, et al. 2022. “A Deep Ensemble Learning Method for Automatic Classification of Multiplets in 1D NMR Spectra.” Conference poster. In EUROMAR 2022 Abstractbook, edited by Thomas Prisner, 236. ZHAW Zürcher Hochschule für Angewandte Wissenschaften. https://doi.org/10.21256/zhaw-27328.
Fischetti, Giulia, et al. “A Deep Ensemble Learning Method for Automatic Classification of Multiplets in 1D NMR Spectra.” EUROMAR 2022 Abstractbook, edited by Thomas Prisner, ZHAW Zürcher Hochschule für Angewandte Wissenschaften, 2022, p. 236, https://doi.org/10.21256/zhaw-27328.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.