Mol2Raman: a graph neural network model for predicting Raman spectra from SMILES representations
Digital Discovery · 2026 · 5 (1) · 161-176
DOI: 10.1039/d5dd00210a ↗Kurz gefasst
Fachartikel in der Zeitschrift Digital Discovery, 2026. Verfasst von Salvatore Sorrentino und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics, Politecnico di Milano Piazza Leonardo da Vinci, 32 20133 Milan Italy salvatore.sorrentino@polimi.it dario.polli@polimi.it. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 3.0). Gefördert von: NCI NIH HHS, NextGenerationEU, National Institutes of Health.
Abstract (Originalsprache)
Mol2Raman is a graph neural network that predicts Raman spectra from molecular SMILES. Trained on >31k DFT-calculated spectra, it localizes peaks within 15 cm −1 with 64% accuracy, outperforming current SOTA deep learning algorithms on Raman spectra.
Autor:innen und Institutionen
- Department of Physics, Politecnico di Milano Piazza Leonardo da Vinci, 32 20133 Milan Italy salvatore.sorrentino@polimi.it dario.polli@polimi.it.
- Laser Biomedical Research Center, G. R. Harrison Spectroscopy Laboratory, Massachusetts Institute of Technology Cambridge MA USA.
- Cutaneous Biology Research Center, Massachusetts General Hospital, Harvard Medical School Boston MA USA.
- Citizen Scientist Italy.
- Department of Industrial Chemistry "Toso Montanari", Universitá degli Studi di Bologna Via Piero Gobetti, 85 I-40129 Bologna Italy.
- Center for Chemical Catalysis - C3, Alma Mater Studiorum University of Bologna via Piero Gobetti 85 40129 Bologna Italy.
ORCID-Profile: Salvatore Sorrentino, Alessandro Gussoni, Francesco Calcagno, Gioele Pasotti, Davide Avagliano, Ivan Rivalta, Marco Garavelli, Dario Polli
Förderung
- NCI NIH HHS
- NextGenerationEU
- National Institutes of Health
- National Cancer Center
- HORIZON EUROPE European Innovation Council
Zitieren
APA
Sorrentino, S., Gussoni, A., Calcagno, F., Pasotti, G., Avagliano, D., Rivalta, I., Garavelli, M., & Polli, D. (2026). Mol2Raman: a graph neural network model for predicting Raman spectra from SMILES representations. Digital Discovery, 5(1), 161-176. https://doi.org/10.1039/d5dd00210a
Vancouver
Sorrentino S, Gussoni A, Calcagno F, Pasotti G, Avagliano D, Rivalta I, et al. Mol2Raman: a graph neural network model for predicting Raman spectra from SMILES representations. Digital Discovery. 2026;5(1):161-176. doi:10.1039/d5dd00210a
BibTeX
@article{Sorrentino2026,
author = {Sorrentino, Salvatore and Gussoni, Alessandro and Calcagno, Francesco and Pasotti, Gioele and Avagliano, Davide and Rivalta, Ivan and Garavelli, Marco and Polli, Dario},
title = {Mol2Raman: a graph neural network model for predicting Raman spectra from SMILES representations},
journal = {Digital Discovery},
year = {2026},
volume = {5},
number = {1},
pages = {161--176},
doi = {10.1039/d5dd00210a}
}
EUVIMED