Tree-Based Classification of Functional Groups from IR Spectra: Feature Importance Corroborates Quantum-Chemical Fragment Frequencies
6 affiliations
- 1Department of Chemical and Materials Engineering
- 2Chang Gung University
- 3Department of Pediatrics
- 4Chang Gung Memorial Hospital
- 5Department of Safety, Health and Environment Engineering
- 6Ming-Chi University of Technology
Abstract
Fourier-transform infrared (FTIR) spectroscopy is a widely used analytical technique for identifying functional groups in chemical compounds, but its interpretation remains labor-intensive and reliant on expert knowledge, especially for complex or multicomponent samples. This study presents a tree-based Random Forest (RF) machine-learning framework, successfully developed to predict the presence of specific functional groups (FGs) from an infrared spectra database. Stratification was employed to address positive class imbalance, maintaining the F1-score drop under 12% across models. All models achieved strong overall performance, with accuracy, F1-score, ROC-AUC, and out-of-bag (OOB) scores exceeding 0.8. Of the 46 FGs modeled, 43 demonstrated acceptable performance, while only three underperformed, as categorized by their Matthews correlation coefficient (MCC) and precision-recall area under the curve (PR-AUC) scores. Threshold tuning further improved model performance, yielding up to a 9% increase in MCC score. Finally, feature importance extracted from the trained models exhibited strong interpretability, correlating with theoretically predicted IR spectra and bridging experimental data with theoretical chemical significance. These results establish a robust, interpretable framework with potential for integration into intelligent monitoring and process optimization systems.
Related
- How Molecular Weight Shapes the Relative Importance of Chemical and Structural Descriptors for Aqueous Solubility
- Classification of strongly non-hyperbolic critical points of planar second-order chemical reaction systems
- Representing chemical and enzymatic reactions in fingerprint space for applicability filtering and classification
- ML26: New Ingredients for an Integral-Features Density Functional with Broad Chemical Accuracy
- Uncovering Chemical Degradation Pathways in Amide-Functional Sulfur Polymers for Room-Temperature Na-S Batteries
BibTeX
@misc{secario2026treebased,
title = {{Tree-Based Classification of Functional Groups from IR Spectra: Feature Importance Corroborates Quantum-Chemical Fragment Frequencies}},
author = {Muhammad Khari Secario and Shingjiang Jessie Lue},
howpublished = {ChemRxiv},
year = {2026},
month = sep,
doi = {10.26434/chemrxiv.15008808/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008808/v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Tree-Based Classification of Functional Groups from IR Spectra: Feature Importance Corroborates Quantum-Chemical Fragment Frequencies
AU - Muhammad Khari Secario
AU - Shingjiang Jessie Lue
PY - 2026
DA - 2026/09/14
PB - ChemRxiv
DO - 10.26434/chemrxiv.15008808/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008808/v1
AB - Fourier-transform infrared (FTIR) spectroscopy is a widely used analytical technique for identifying functional groups in chemical compounds, but its interpretation remains labor-intensive and reliant on expert knowledge, especially for complex or multicomponent samples. This study presents a tree-based Random Forest (RF) machine-learning framework, successfully developed to predict the presence of specific functional groups (FGs) from an infrared spectra database. Stratification was employed to address positive class imbalance, maintaining the F1-score drop under 12% across models. All models achieved strong overall performance, with accuracy, F1-score, ROC-AUC, and out-of-bag (OOB) scores exceeding 0.8. Of the 46 FGs modeled, 43 demonstrated acceptable performance, while only three underperformed, as categorized by their Matthews correlation coefficient (MCC) and precision-recall area under the curve (PR-AUC) scores. Threshold tuning further improved model performance, yielding up to a 9% increase in MCC score. Finally, feature importance extracted from the trained models exhibited strong interpretability, correlating with theoretically predicted IR spectra and bridging experimental data with theoretical chemical significance. These results establish a robust, interpretable framework with potential for integration into intelligent monitoring and process optimization systems.
ER -