EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PFGPred: a stack ensemble classifier for the identification of fusion genes in plants

Fiza Hamid iD, Kanka Mukherjee, Sakshi Chaudhary, Love Kaushik, Shailesh Kumar iD

DNA Research · 23.06.2026 · 33 (3)

DOI: 10.1093/dnares/dsag005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift DNA Research, online erschienen am 09.06.2026. Verfasst von Fiza Hamid und 4 weiteren Autor:innen. Beteiligte Einrichtung: Bioinformatics Lab, BRIC-National Institute of Plant Genome Research, Aruna Asaf Ali Marg, New Delhi 110067, India. Hauptthemen laut MEDLINE: Gene Fusion, Genes, Plant, Plants. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Biotechnology (DBT), Ministry of Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fusion genes play crucial roles in plant biological processes but remain far less explored than their human counterparts, largely due to limited validated datasets and the absence of plant-specific prediction tools. Existing approaches often produce high false-positive rates, restricting reliable discovery. To address this gap, we developed Plant Fusion Gene Predictor (PFGPred). This ensemble machine learning framework integrates Random Forest, XGBoost, and long short-term memory (LSTM) models into a meta-classifier for accurate identification of true and false fusion genes from RNA sequencing (RNA-Seq) data. PFGPred was trained on a high-confidence dataset of fusion genes validated by both RNA-Seq and whole-genome sequencing from Arabidopsis thaliana, Oryza sativa, Triticum aestivum, and Zea mays, to predict and rank candidate fusion genes for future functional validation. It outperformed individual baseline models, achieving accuracies of 0.97 on training data and 0.77 on independent test data. When evaluated on human datasets, it achieved 0.71 accuracy at the cost of lower sensitivity, reflecting biological differences between plant and human fusion events. Comparative analyses confirmed that PFGPred reliably identifies validated fusions, demonstrating its utility as a cost-effective, plant-specific prediction tool for high-throughput fusion gene screening and functional genomics research. It is freely available as a web server at http://www.nipgr.ac.in/PFGPred.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Gene FusionGenes, PlantPlantsPrediction AlgorithmsBoosting Machine Learning AlgorithmsRandom ForestHumansMachine LearningPredictive Learning ModelsClassification Algorithms

Stichwörter der Autor:innen

fusion transcriptsgene fusionmachine learningplant fusion genewhole-genome sequencing

Autor:innen und Institutionen

  • Bioinformatics Lab, BRIC-National Institute of Plant Genome Research, Aruna Asaf Ali Marg, New Delhi 110067, India.

ORCID-Profile: Fiza Hamid, Shailesh Kumar

Förderung

  • Department of Biotechnology (DBT), Ministry of Science and Technology

Zitieren

APA

Hamid, F., Mukherjee, K., Chaudhary, S., Kaushik, L., & Kumar, S. (2026). PFGPred: a stack ensemble classifier for the identification of fusion genes in plants. DNA Research, 33(3). https://doi.org/10.1093/dnares/dsag005

Vancouver

Hamid F, Mukherjee K, Chaudhary S, Kaushik L, Kumar S. PFGPred: a stack ensemble classifier for the identification of fusion genes in plants. DNA Research. 2026;33(3). doi:10.1093/dnares/dsag005

BibTeX
@article{Hamid2026,
  author = {Hamid, Fiza and Mukherjee, Kanka and Chaudhary, Sakshi and Kaushik, Love and Kumar, Shailesh},
  title = {PFGPred: a stack ensemble classifier for the identification of fusion genes in plants},
  journal = {DNA Research},
  year = {2026},
  volume = {33},
  number = {3},
  doi = {10.1093/dnares/dsag005}
}
Kostenlos starten →