Informed Chemical Classification of Organophosphorus Compounds via Unsupervised Machine Learning of X-ray Absorption Spectroscopy and X-ray Emission Spectroscopy
Informed Chemical Classification of Organophosphorus Compounds via Unsupervised Machine Learning of X-ray Absorption Spectroscopy and X-ray Emission Spectroscopy
复制标题
DOI：
10.1021/acs.jpca.2c03635
复制
发表时间：
2022-07-15
影响因子：
2.9
通讯作者：
Seidler, Gerald T.
中科院分区：
文献类型：
--
作者：
Tetef, Samantha;Kashyap, Vikram;Seidler, Gerald T.
我们分析了有机磷化合物的系综，以形成其X射线吸收近边结构（XANES）和价核X射线发射光谱（VtC-XES）中编码的信息的无偏表征。通过无监督机器学习，特别是均匀流形近似和投影（UMAP）嵌入中的聚类分析，数据驱动的化学类别的出现，发现了对配位，氧化，芳香性，分子内氢键和配体身份的光谱敏感性。随后，我们通过高斯过程分类器实现监督机器学习，以确定与我们对聚类的初始定性评估相匹配的预测的置信度。这些结果进一步支持了利用无监督机器学习作为有监督机器学习的先驱的好处，我们称之为无监督类验证（UVC），这一结果超出了目前X射线光谱的情况。
We analyze an ensemble of organophosphorus compounds to form an unbiased characterization of the information encoded in their X-ray absorption near-edge structure (XANES) and valence-to-core X-ray emission spectra (VtC-XES). Data-driven emergence of chemical classes via unsupervised machine learning, specifically cluster analysis in the Uniform Manifold Approximation and Projection (UMAP) embedding, finds spectral sensitivity to coordination, oxidation, aromaticity, intramolecular hydrogen bonding, and ligand identity. Subsequently, we implement supervised machine learning via Gaussian process classifiers to identify confidence in predictions that match our initial qualitative assessments of clustering. The results further support the benefit of utilizing unsupervised machine learning as a precursor to supervised machine learning, which we term Unsupervised Validation of Classes (UVC), a result that goes beyond the present case of X-ray spectroscopies.