NMR-AI: An Open Platform for NMR-Enhanced Molecular Representations and Physicochemical Property Prediction
Open Access
- 16 July 2026
- journal article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (14) , 8318-8324
Abstract
Accurate prediction of physicochemical properties is increasingly limited by an information ceiling of structure-only molecular descriptors. Here, predicted 1H|13C NMR chemical shifts are transformed into fixed-length NMR vectors and concatenated with ECFP4 to form the hybrid spectral–structural representation SpectraPRINTS, enabling direct evaluation of representational complementarity across logP, logS, and logD (pH 2.6, 7.4, and 10.5), as well as the most acidic and most basic pKas. With a fixed learning protocol, SpectraPRINT reduces error for lipophilicity- and solubility-related end points (up to 39% lower RMSE vs ECFP4), while no systematic gain is observed for the most acidic and most basic macroscopic pKa end points. The workflow is released as NMR-AI, a freely accessible web platform integrating NMR spectra prediction, descriptor construction, and property prediction, enabling interactive use and independent validation. The NMR-AI platform is accessible at https://cheminformaticsportal.if-pan.krakow.pl/.Keywords
This publication has 36 references indexed in Scilit:
- Developing a Hybrid Molecular Representation Combining Chemical Structure and MIR Spectral Data: A LogP Prediction Case StudyJournal of Chemical Information and Modeling, 2025
- From NMR to AI: Fusing 1H and 13C Representations for Enhanced QSPR ModelingJournal of Chemical Information and Modeling, 2025
- From NMR to AI: Do We Need 1H NMR Experimental Spectra to Obtain High-Quality logD Prediction Models?Journal of Chemical Information and Modeling, 2025
- Pharmaceutical approaches for enhancing solubility and oral bioavailability of poorly soluble drugsEuropean Journal of Pharmaceutics and Biopharmaceutics, 2024
- ROBERT: Bridging the Gap Between Machine Learning and ChemistryWIREs Computational Molecular Science, 2024
- From NMR to AI: Designing a Novel Chemical Representation to Enhance Machine Learning Predictions of Physicochemical PropertiesJournal of Chemical Information and Modeling, 2024
- Exposing the Limitations of Molecular Machine Learning with Activity CliffsJournal of Chemical Information and Modeling, 2022
- A review of molecular representation in the age of machine learningWIREs Computational Molecular Science, 2022
- A review on machine learning approaches and trends in drug discoveryComputational and Structural Biotechnology Journal, 2021
- Toward the Complete Prediction of the 1H and 13C NMR Spectra of Complex Organic Molecules by DFT Methods: Application to Natural SubstancesChemistry – A European Journal, 2006