DDTRN: predicting bacterial transcriptional regulatory networks based on gene sequences using dual descriptor.

DDTRN predicts bacterial transcriptional regulatory networks with high accuracy, achieving an average AUC of 0.869 and PR AUC of 0.868 across diverse species.

• Why it matters: Accurate reconstruction of bacterial TRNs is crucial for understanding gene regulation, especially in non-model organisms lacking extensive transcriptomic data, creating a significant knowledge gap.
• What they did: They developed DDTRN, a sequence-based binary classification framework using a Dual Descriptor model that encodes regulator-target gene pairs with Composition Weight Map and Position Weight Function, evaluated on eight bacterial datasets.
• The result: DDTRN outperforms traditional methods, demonstrates robustness with limited data, and offers interpretable insights into regulatory features, enabling scalable TRN inference where expression data are scarce.