EUVIMEDEUVIMED entdecken
Crossref

Rule-Based Protein Classification through Multi-Phase Feature Extraction Technique

Suprativ Saha, Rupak Bhattacharyya, Swarup Kumar Ghosh, Tanmay Bhattacharya

IEEE Transactions on Computational Biology and Bioinformatics · 2026

DOI: 10.1109/tcbbio.2026.3663211 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Computational Biology and Bioinformatics, 2026. Verfasst von Suprativ Saha und 3 weiteren Autor:innen. Hauptthemen laut MEDLINE: Proteins, Sequence Analysis, Protein, Computational Biology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Protein sequence classification is a fundamental step toward functional annotation and biological analysis; however, most of the existing approaches rely on computationally expensive models or flat feature integration with limited interpretability. This paper proposes a multi-phase rule-based protein classification framework that hierarchically integrates biologically meaningful features. An early-exit decision strategy is employed. Feature extraction is performed across four progressive phases comprising chemical properties, hydropathy characteristics, behavioral sequence patterns through n-gram and six-letter exchange encoding, and functional attributes via normalized distance-based encoding. Family-specific knowledge matrices constructed exclusively from training data enable deterministic min-max rule evaluation at each phase for efficient candidate pruning and early termination. Experiments conducted on 8,555 human protein sequences spanning ten families achieve an average classification accuracy of 97.66%. 5-fold, 25-fold, and 45-fold cross-validation statistically confirm performance stability under class-imbalanced conditions. Further cross-species validation on zebrafish and mouse protein datasets yields accuracies of 96.11% and 94.89%, respectively, demonstrating robust generalization across diverse biological distributions. Comparative evaluation against machine-learning-based and transformer-based baselines shows that the proposed framework achieves a superior accuracy-efficiency trade-off while maintaining an overall time complexity of $O(n\log n)$.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsSequence Analysis, ProteinComputational BiologyAnimalsHumansMiceDatabases, ProteinZebrafishClassification AlgorithmsAlgorithmsMachine Learning

Substanzen

Proteins

Zitieren

APA

Saha, S., Bhattacharyya, R., Ghosh, S. K., & Bhattacharya, T. (2026). Rule-Based Protein Classification through Multi-Phase Feature Extraction Technique. IEEE Transactions on Computational Biology and Bioinformatics. https://doi.org/10.1109/tcbbio.2026.3663211

Vancouver

Saha S, Bhattacharyya R, Ghosh SK, Bhattacharya T. Rule-Based Protein Classification through Multi-Phase Feature Extraction Technique. IEEE Transactions on Computational Biology and Bioinformatics. 2026. doi:10.1109/tcbbio.2026.3663211

BibTeX
@article{Saha2026,
  author = {Saha, Suprativ and Bhattacharyya, Rupak and Ghosh, Swarup Kumar and Bhattacharya, Tanmay},
  title = {Rule-Based Protein Classification through Multi-Phase Feature Extraction Technique},
  journal = {IEEE Transactions on Computational Biology and Bioinformatics},
  year = {2026},
  doi = {10.1109/tcbbio.2026.3663211}
}
Kostenlos starten →