GraphTFactor: A graph-based approach for proteins transcription factor prediction

Abstract

Transcription factors (TFs) play an important role in regulating gene expression, making their identification a fundamental task in computational biology. In this work, we propose GraphTFactor, a novel end-to-end framework that models protein sequences as graphs and directly classifies transcription factors. By encoding sequences into graph structures, the proposed approach naturally handles variable-length inputs while preserving relevant relational information, without imposing length constraints. Experimental results show that GraphTFactor outperforms state-of-the-art methods on benchmark datasets, demonstrating the effectiveness of graph-based representations for TF prediction while providing interpretable insights into the sequence regions contributing to the model's predictions. To support reproducibility and practical adoption, we release an open-source software package and an interactive web application that let users easily perform TF prediction on custom sequences.

TransBind2: Improving Transcription Factor-DNA Binding Prediction with Multimodal Data and Bidirectional Cross Attention
S. Basnet, J. Cheng
bioRxiv7 Sep 2026PreprintCC BYFull textBioinformatics & computational biologybioRxiv
Constitutively-active Positive Transcription Factor b (P-TEFb) prevents viral latency.
F. Huang, K. Nishiura, K. Fujinaga
bioRxiv26 Sep 2026PreprintAll rights reservedFull textMicrobiologybioRxiv
Generative design of functional disordered regions in a developmental transcription factor
Lance Denes, Ryan J. Emenecker, Nongyun Wang +5
bioRxiv12 Oct 2026PreprintAll rights reservedFull textSystems & synthetic biologybioRxivPMC
Mechanistic insights into proteolytic activation ofmembrane-bound NAC transcription factor SlNACMTF3 intomato plants under heat stress
P. Kundu, S. Talukdar, S. Roy +3
bioRxiv24 Oct 2026PreprintAll rights reservedFull textPlant biologybioRxiv
Sense-and-response to intracellular signaling via nucleocytoplasmic localization control of a synthetic transcription factor platform
P. Garcia-Diaz, B. Bhatt, M. T. Morgado +3
bioRxiv7 Oct 2026PreprintAll rights reservedFull textSystems & synthetic biologybioRxiv

Cite

BibTeX RIS

BibTeX

@misc{amato2026graphtfactor,
  title = {{GraphTFactor: A graph-based approach for proteins transcription factor prediction}},
  author = {Domenico Amato and Salvatore Calderaro and Giosuè Lo Bosco and Riccardo Rizzo and Filippo Vella},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.40867},
  eprint = {2610.40867},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.40867},
}

RIS

TY  - UNPB
TI  - GraphTFactor: A graph-based approach for proteins transcription factor prediction
AU  - Domenico Amato
AU  - Salvatore Calderaro
AU  - Giosuè Lo Bosco
AU  - Riccardo Rizzo
AU  - Filippo Vella
PY  - 2026
DA  - 2026/10/29
PB  - arXiv
DO  - 10.48550/arxiv.2610.40867
UR  - https://arxiv.org/abs/2610.40867
AB  - Transcription factors (TFs) play an important role in regulating gene expression, making their identification a fundamental task in computational biology. In this work, we propose GraphTFactor, a novel end-to-end framework that models protein sequences as graphs and directly classifies transcription factors. By encoding sequences into graph structures, the proposed approach naturally handles variable-length inputs while preserving relevant relational information, without imposing length constraints. Experimental results show that GraphTFactor outperforms state-of-the-art methods on benchmark datasets, demonstrating the effectiveness of graph-based representations for TF prediction while providing interpretable insights into the sequence regions contributing to the model's predictions. To support reproducibility and practical adoption, we release an open-source software package and an interactive web application that let users easily perform TF prediction on custom sequences.
ER  -

Abstract

Related

Cite