nam 22 uu 4500 dbt_mods_00066724 10.1021/acs.jcim.5c00513 doi dbt_mods_00066724 ger DE-601 rda eng 540 sdnb bibliography OAI Kamran, Jawad Author aut Institute of Physical Chemistry ,Friedrich Schiller University Jena ,Helmholtzweg 4 ,07743 Jena ,Germany Department of Photonic Data Science ,Leibniz Institute of Photonic Technology ,Albert-Einstein-Straße 9 ,07745 Jena ,Germany (DE-588)1373742720 Transfer-Learning Deep Raman Models Using Semiempirical Quantum Chemistry Kamran, Jawad;Hniopek, Julian;Bocklitz, Thomas 2025-06-18 12 Seiten text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Zweitveröffentlichung Biophotonic technologies such as Raman spectroscopy are powerful tools for obtaining highly specific molecular information. Due to its minimal sample preparation requirements, Raman spectroscopy is widely used across diverse scientific disciplines, often in combination with chemometrics, machine learning (ML), and deep learning (DL). However, Raman spectroscopy lacks large databases of independent Raman spectra for model training, leading to overfitting, overestimation, and limited model generalizability. We address this problem by generating simulated vibrational spectra using semiempirical quantum chemistry methods, enabling the efficient pretraining of deep learning models on large synthetic data sets. These pretrained models are then fine-tuned on a smaller experimental Raman data set of bacterial spectra. Transfer learning significantly reduces the computational cost while maintaining performance comparable to models trained from scratch in this real biophotonic application. The results validate the utility of synthetic data for pretraining deep Raman models and offer a scalable framework for spectral analysis in resource-limited settings. article Hniopek, Julian Author aut Institute of Physical Chemistry ,Friedrich Schiller University Jena ,Helmholtzweg 4 ,07743 Jena ,Germany Department of Photonic Data Science ,Leibniz Institute of Photonic Technology ,Albert-Einstein-Straße 9 ,07745 Jena ,Germany (DE-588)1214890598 Bocklitz, Thomas Author aut Institute of Physical Chemistry ,Friedrich Schiller University Jena ,Helmholtzweg 4 ,07743 Jena ,Germany Department of Photonic Data Science ,Leibniz Institute of Photonic Technology ,Albert-Einstein-Straße 9 ,07745 Jena ,Germany (DE-588)101788207X Friedrich-Schiller-Universität Jena Chemisch-Geowissenschaftliche Fakultät host institution his 65:13<6632 JCIM Journal of Chemical Information and Modeling 1549-9596 1549-960X dbt_mods_00066725 https://www.db-thueringen.de/receive/dbt_mods_00066724 object in context https://www.db-thueringen.de/servlets/MCRFileNodeServlet/dbt_derivate_00068387/ci5c00513.pdf raw object https://www.db-thueringen.de/rsc/thumbnail/dbt_mods_00066724.png preview https://www.db-thueringen.de/receive/dbt_mods_00066724 uri