CDEF-Tg: Machine Learning-Based Descriptor–Embedding Fusion for Glass Transition Temperature Prediction in a Polyimide-Oriented Polymer Dataset
Polymers · 07.11.2026 · 18 (21) · 2783
DOI: 10.3390/polym18212783 ↗Kurz gefasst
Fachartikel in der Zeitschrift Polymers, online erschienen am 07.11.2026. Verfasst von Mücahit Çalışan und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Faculty of Engineering and Architecture, Bingol University, 12000 Bingol, Türkiye. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Predicting the glass transition temperature (Tg) of polymers from structures remains difficult, and whether descriptors and molecular-language embeddings carry complementary information is unclear. CDEF-Tg (Compact Descriptor–Embedding Fusion for Glass Transition Temperature Prediction) concatenates 205 RDKit descriptors (RDKit205) with a frozen 384-dimensional ChemBERTa embedding (ChemBERTa384) and maps the 589-dimensional vector to Tg with an ExtraTreesRegressor. It was evaluated on 10,065 identity-resolved records of a polyimide-oriented dataset under three leakage-safe protocols: IID Group-Safe (IID, independent and identically distributed), Scaffold OOD (OOD, out-of-distribution), and Similarity OOD (T = 0.90). The model was selected on validation evidence and frozen before the final-test sets were opened. In the locked final test, CDEF-Tg reached a macro mean absolute error (MAE) of 48.84 °C, versus 50.17 °C (RDKit205 alone) and 54.33 °C (ChemBERTa384 alone). Group-aware bootstrap analyses separated CDEF-Tg from RDKit205 alone in MAE only under Similarity OOD and showed no MAE advantage over the comparator RDEF-Tg. Additional validation-only controls showed a lower macro MAE for a Morgan-fingerprint partner than for CDEF-Tg (49.11 versus 53.15 °C), and ChemBERTa384 lowered LightGBM error; the ExtraTrees ordering was stable across random states (split seeds were not varied). The results suggest a modest, protocol-dependent benefit within this dataset; the additional analyses provide descriptive evidence.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Engineering, Faculty of Engineering and Architecture, Bingol University, 12000 Bingol, Türkiye.
- Department of Computer Technologies, Bitlis Eren University, 13000 Bitlis, Türkiye.
ORCID-Profile: Mücahit Çalışan, İbrahim Ayaz
Zitieren
APA
Çalışan, M., & Ayaz, İ. (2026). CDEF-Tg: Machine Learning-Based Descriptor–Embedding Fusion for Glass Transition Temperature Prediction in a Polyimide-Oriented Polymer Dataset. Polymers, 18(21), 2783. https://doi.org/10.3390/polym18212783
Vancouver
Çalışan M, Ayaz İ. CDEF-Tg: Machine Learning-Based Descriptor–Embedding Fusion for Glass Transition Temperature Prediction in a Polyimide-Oriented Polymer Dataset. Polymers. 2026;18(21):2783. doi:10.3390/polym18212783
BibTeX
@article{alan2026,
author = {Çalışan, Mücahit and Ayaz, İbrahim},
title = {CDEF-Tg: Machine Learning-Based Descriptor–Embedding Fusion for Glass Transition Temperature Prediction in a Polyimide-Oriented Polymer Dataset},
journal = {Polymers},
year = {2026},
volume = {18},
number = {21},
pages = {2783},
doi = {10.3390/polym18212783}
}
EUVIMED