ChemFluor

We establish a machine learning-based method to predict emission/absorption wavelength and PLQY of organic fluorescent materials.A platform has been establised for experimenters to use, as well as used for potential high-throughput screening.<br>[1]<i>The ChemFluor.zip</i> is the platform based on python, which contain trained models, can be used for the prediction directly.[2]<i>Fingerprints_for_prediction.zip</i> is the fingerprints used in our work.[3]<i>Materials_Real-World_Problem.zip</i> is the molecules collected from recent published work and TD-DFT benchmark studies, which can be seen as real world problem. [4]The molecules are stored in the form of SMILES.<br><i>Alldata_SMILES.xlsx</i> contains all the molecules in our dataset as well as the references. <br>[5]ML-models we used in our paper have been saved and uploaded, as<i> model_in_paper.zip.</i>本研究构建了一种基于机器学习的方法，用于预测有机荧光材料的发射/吸收波长与光致发光量子产率（Photoluminescence Quantum Yield, PLQY）。本研究同时搭建了可供实验人员使用的工具平台，亦可用于潜在的高通量筛选工作。 [1] ChemFluor.zip为基于Python开发的平台，内置训练完成的模型，可直接用于预测任务。[2] Fingerprints_for_prediction.zip包含本研究中使用的分子指纹。[3] Materials_Real-World_Problem.zip收录了从近期已发表文献与含时密度泛函理论（Time-Dependent Density Functional Theory, TD-DFT）基准测试研究中获取的分子，可视为真实应用场景下的测试任务。[4] 所有分子均以简化分子线性输入规范（Simplified Molecular Input Line Entry System, SMILES）格式存储。 Alldata_SMILES.xlsx包含本数据集的全部分子及其相关参考文献信息。 [5] 本论文中使用的机器学习模型已保存并上传至model_in_paper.zip压缩包中。