Evaluating and elucidating the reactivity of OH radicals with atmospheric organic pollutants: Reaction kinetics and mechanisms by machine learning

Combined DFT and Machine Learning Study of the Dissociation and Migration of H in Pyrrole Derivatives

“…41,42 The molecular structure descriptors include the chemical bond length and the number of different types of atoms in substituent groups. 43 A total of 25 descriptors shown in Table S3 are selected as the initial descriptors. We used the one-hot encoding method for discrete descriptions.…”

“…In this work, two types of molecular descriptors, quantum chemical descriptors, and molecular structure descriptors are considered for the model. The quantum chemical descriptors include the dipole moment (DM), the lowest unoccupied molecular orbital (LUMO), and the highest occupied molecular orbital (HOMO), etc. , The molecular structure descriptors include the chemical bond length and the number of different types of atoms in substituent groups . A total of 25 descriptors shown in Table S3 are selected as the initial descriptors.…”

Structure-Based Reaction Descriptors for Predicting Rate Constants by Machine Learning: Application to Hydrogen Abstraction from Alkanes by CH3/H/O Radicals

“…Zhong et al combined a convolutional neural network with molecular image to model radical rate constants of water contaminants, whose predictive performance was comparable to the molecular fingerprint-deep neural network model developed by the same group. ,− Greaves et al predicted rate constants for organic processes in mixtures containing ionic liquids by applying multiple linear regression and artificial neural networks with descriptors taken mostly from the Dragon descriptor database . To make the established machine learning models broadly available, Sanches-Neto et al developed a web application “pySiRC” that predicts reaction rate constants of radical-based oxidation processes of aqueous organic contaminants by combining three machine learning algorithms with molecular fingerprints. , …”

“…Zhong 27 To make the established machine learning models broadly available, Sanches-Neto et al developed a web application "pySiRC" that predicts reaction rate constants of radical-based oxidation processes of aqueous organic contaminants by combining three machine learning algorithms with molecular fingerprints. 28,29 Alkane (C n H 2n+2 ) is an important component of various fuels, such as natural gas (mainly composed of methane), lighter fuel (e.g., n-butane), motor gasoline (consisting of various compounds of alkane and aliphatic hydrocarbon), and aviation fuel. In the case of aviation fuel, the combustion largely occurs by abstracting hydrogen atoms from different sites of alkanes by free radicals such as O, H, OH, HO 2 , CH 3 , and so on.…”

SpectraFP: a new spectra-based descriptor to aid in cheminformatics, molecular characterization and search algorithm applications

“…These are commonly used in the structure–activity relationship (SAR) and/or quantitative property/activity (QSPR/QSAR) approaches for the prediction of biological activities, chemical reactivity and physicochemical properties. 15,16 Therefore, the use of the chemical shift as an input parameter to encode the structural characteristics of molecules becomes important to provide chemically relevant information for the prediction of essential properties in several areas of science.…”