HTW-KI-Werkstatt/RamanSpectraEcoliMetabolitesDig4Bio

--- tags: - raman-spectroscopy - biotechnology - benchtop-spectroscopy - pls-regression - tabular-regression license: cc-by-4.0 language: en pretty_name: Raman Spectra of Bioprocess Analytes Dig4Bio task_categories: - tabular-regression configs: - config_name: default data_files: - split: train path: "train.csv" - split: validation path: "val.csv" - split: test path: "test.csv" size_categories: - n<1K --- ## Dataset Overview This dataset contains Raman spectra of mixtures of glucose, sodium acetate, and magnesium sulfate. The spectra were measured with the system that is presended in the paper "A Setup for Automatic Raman Measurements in High-Throughput Experimentation" (https://doi.org/10.1002/bit.70006). The spectra were used for a Kaggle challenge organized for the EU Project Dig4Bio (https://www.kaggle.com/competitions/dig-4-bio-raman-transfer-learning-challenge/overview/). We gratefully acknowledge the financial support of the EU-HORIZON-project Dig4Bio with the grant number 101159993. ## Target Parameters and Concentration Ranges The dataset contains measured Raman spectra of samples with different parameters from the following substances: * **Glucose** * **Sodium Acetate** * **Magnesium Sulfate** The concentrations were taken according to the volumes that the Tecan Liquid Handling Robot pipetted. ## Data Acquisition Raman spectra were recorded using the follwing settings: * **Instrument:** Metrohm i-Raman Plus * **Laser Wavelength:** 785 nm * **Exposure Time:** 10 s * **Laser Power:** 450 mW * **Scans per Sample:** 2 * **Number of Samples:** 192 ## Citation Please cite our paper, if you use the dataset: (Lange et. al. https://doi.org/10.1002/bit.70006). **BibTeX:** ``` @article{ lange2025setup, title={A Setup for Automatic Raman Measurements in High-Throughput Experimentation}, author={Lange, Christoph and Seidel, Simon and Altmann, Madeline and Stors, Daniel and Kemmer, Annina and Cai, Linda and Born, Stefan and Neubauer, Peter and Bournazou, M Nicolas Cruz}, journal={Biotechnology and Bioengineering}, volume={122}, number={10}, pages={2751--2769}, year={2025}, publisher={Wiley Online Library} }tags: - 拉曼光谱（Raman spectroscopy） - 生物技术（biotechnology） - 台式光谱学（benchtop-spectroscopy） - 偏最小二乘回归（PLS Regression） - 表格回归（tabular-regression） 许可协议: 知识共享署名4.0许可协议（CC BY 4.0） 语言: 英语 数据集展示名称: Dig4Bio项目生物过程分析物拉曼光谱数据集 任务类别: - 表格回归（tabular-regression） 配置项: - 配置名称: 默认 数据文件: - 训练集划分: train.csv - 验证集划分: val.csv - 测试集划分: test.csv 样本量范围: 样本数少于1000 ## 数据集概览 本数据集包含葡萄糖、乙酸钠与硫酸镁混合物的拉曼光谱。所有光谱均采用发表于论文《高通量实验自动拉曼测量装置》（*A Setup for Automatic Raman Measurements in High-Throughput Experimentation*，https://doi.org/10.1002/bit.70006）中提及的测试系统获取。 该光谱数据集曾用于欧盟Dig4Bio项目组织的Kaggle竞赛（https://www.kaggle.com/competitions/dig-4-bio-raman-transfer-learning-challenge/overview/）。本研究衷心感谢欧盟地平线计划（EU-HORIZON）Dig4Bio项目（资助编号101159993）提供的资金支持。 ## 目标参数与浓度范围 本数据集包含以下三种物质不同配比的样品拉曼光谱： * **葡萄糖（Glucose）** * **乙酸钠（Sodium Acetate）** * **硫酸镁（Magnesium Sulfate）** 样品浓度由帝肯（Tecan）液体处理机器人的移液体积计算得到。 ## 数据采集 拉曼光谱采集采用以下参数设置： * **仪器：** 瑞士万通（Metrohm）i-Raman Plus拉曼光谱仪 * **激光波长：** 785 nm * **曝光时长：** 10 s * **激光功率：** 450 mW * **单样品扫描次数：** 2次 * **总样本量：** 192份 ## 引用说明 若使用本数据集，请引用以下论文：（Lange等，https://doi.org/10.1002/bit.70006） **BibTeX引用格式：** bibtex @article{ lange2025setup, title={A Setup for Automatic Raman Measurements in High-Throughput Experimentation}, author={Lange, Christoph and Seidel, Simon and Altmann, Madeline and Stors, Daniel and Kemmer, Annina and Cai, Linda and Born, Stefan and Neubauer, Peter and Bournazou, M Nicolas Cruz}, journal={Biotechnology and Bioengineering}, volume={122}, number={10}, pages={2751--2769}, year={2025}, publisher={Wiley Online Library} }