Interpretable machine learning framework for predicting the reactivity of trifluoromethylating reagents
Authors:
- 16 December 2025
- journal article
- research article
- Published by Royal Society of Chemistry (RSC) in Physical Chemistry Chemical Physics
- Vol. 28 (2) , 1864-1876
Abstract
A neural network architecture efficiently predicted TC + DA values using five easily computed and interpretable Mordred-based structural descriptors.Keywords
Funding Information
- Panjab University
This publication has 37 references indexed in Scilit:
- Leveraging graph neural networks to predict Hammett’s constants for benzoic acid derivativesArtificial Intelligence Chemistry, 2024
- Machine learning advancements in organic synthesis: A focused exploration of artificial intelligence applications in chemistryArtificial Intelligence Chemistry, 2024
- A machine learning approach for predicting the reactivity power of hypervalent iodine compoundsArtificial Intelligence Chemistry, 2023
- Machine Learning for Chemistry: Basics and ApplicationsEngineering, 2023
- Predicting the ET(30) parameter of organic solvents via machine learningChemical Physics Letters, 2023
- Navigating with chemometrics and machine learning in chemistryArtificial Intelligence Review, 2023
- Machine learning prediction of empirical polarity using SMILES encoding of organic solventsMolecular Diversity, 2022
- Current Contributions of Organofluorine Compounds to the Agrochemical IndustryiScience, 2020
- Exploration of fluorination reagents starting from FITS reagentsJournal of Fluorine Chemistry, 2014
- Recent Advances in Trifluoromethylation Reactions with Electrophilic Trifluoromethylating ReagentsChemistry – A European Journal, 2014