Graph based method improves identification of transcription factors
GraphTFactor: A graph-based approach for proteins transcription factor prediction
Artificial IntelligenceMachine Learning
Summary
Identifying transcription factors is important because they help control which genes turn on or off. The authors developed GraphTFactor, a tool that turns protein sequences into graphs to better recognize transcription factors. Unlike other methods, this approach works well with sequences of different lengths and keeps the connections between parts of the protein. Tests show it performs better than current tools and also helps explain which parts of the protein influence its predictions. They also provide software and a website so users can try this method on their own protein data.
What this means in practice
- •For bioinformatics engineers: Deploy a flexible tool that predicts transcription factors from protein data without sequence length limits, aiding gene regulation studies.
- •For biotech product developers: Integrate graph-based TF prediction to improve biomarker discovery and therapeutic target identification workflows.
Authors
Domenico Amato, Salvatore Calderaro, Giosuè Lo Bosco, Riccardo Rizzo, Filippo Vella
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.