HTW-KI-Werkstatt/RamanSpectraRalstoniaFermentations

--- tags: - raman-spectroscopy - bioprocess-monitoring - polyhydroxyalkanoates - ralstonia-eutropha - regression license: cc-by-4.0 language: en pretty_name: R. eutropha PHA Copolymer Raman Dataset task_categories: - tabular-regression configs: - config_name: default data_files: - split: train path: "train.parquet" - split: validation path: "val.parquet" - split: test path: "test.parquet" size_categories: - n<1K --- ## Dataset Overview This dataset contains **Raman spectra** (both real and synthetic) recorded during the batch cultivation of *Ralstonia eutropha*. The primary focus is the monitoring of the biodegradable copolymer **poly(hydroxybutyrate-co-hydroxyhexanoate) [P(HB-co-HHx)]**. ## Target Parameters and Composition The dataset tracks the synthesis of the P(HB-co-HHx) copolymer and the metabolic state of the cultivation, focusing on the following key metrics: * **Cell Dry Weight [g/L]**: Total biomass concentration consisting of both the polymer and the active cell mass. * **Fructose HPLC [g/L]**: Residual concentration of the fructose substrate, which leads primarily to the incorporation of HB monomers. * **Hhx [g/L]**: Concentration of the polyhydroxyhexanoate monomer within the copolymer. * **HB [g/L]**: Concentration of the polyhydroxybutyrate monomer within the copolymer. * **Residual CDW [g/L]**: The non-polymer cell mass (calculated as total CDW minus total PHA), representing the catalytic capacity of the culture. * **Urea kit [g/L]**: Concentration of the nitrogen source, critical for identifying the nutrient limitation that triggers PHA accumulation. ## Data Acquisition & Generation The dataset utilizes a combination of experimental observations and high-fidelity synthetic data to represent the cultivation dynamics of *R. eutropha*. * **Organism:**: *Ralstonia eutropha* * **Cultivation Mode:**: Batch fermentation. * **Instrument**: Tec5 Multi-Spec Raman 785 nm * **Exposure Time**: 10s ## Citation If you use this dataset in your research, please cite the following paper: ```bibtex @article{lange_data_2024, title = {Data Augmentation Scheme for Raman Spectra with Highly Correlated Annotations}, editor = {Flavio Manenti and Gintaras V. Reklaitis}, series = {Computer Aided Chemical Engineering}, publisher = {Elsevier}, volume = {53}, pages = {3055-3060}, year = {2024}, booktitle = {34th European Symposium on Computer Aided Process Engineering / 15th International Symposium on Process Systems Engineering}, issn = {1570-7946}, doi = {https://doi.org/10.1016/B978-0-443-28824-1.50510-X}, url = {https://www.sciencedirect.com/science/article/pii/B978044328824150510X}, author = {Christoph Lange and Isabel Thiele and Lara Santolin and Sebastian L. Riedel and Maxim Borisyak and Peter Neubauer and Mariano Nicolas Cruz-Bournazou}, keywords = {Raman Spectroscopy, Convolutional Neural Network, Data Augmentation}, } ```