D3GRN: a data driven dynamic network construction method to infer gene regulatory networks.

Area of Science:

• Systems Biology
• Bioinformatics
• Computational Biology

Background:

• Inferring gene regulatory networks (GRNs) from gene expression data is a fundamental challenge in systems biology.
• Existing algorithms often frame GRN inference as a regression problem, utilizing ensemble strategies.
• Recent advancements in data-driven dynamic network construction offer new approaches to this regression problem.

Purpose of the Study:

• To propose a novel data-driven dynamic network construction method for inferring gene regulatory networks.
• To address limitations in existing network inference algorithms by incorporating a functional decomposition approach.

Main Methods:

• The proposed method, D3GRN, transforms gene regulatory relationships into functional decomposition problems.
• Each subproblem is solved using the Algorithm for Revealing Network Interactions (ARNI).
• A bootstrapping and area-based scoring strategy is employed to refine network inference and overcome unit-level limitations of ARNI.

Main Results:

• D3GRN demonstrates competitive performance against state-of-the-art algorithms on benchmark datasets (DREAM4 and DREAM5).
• Performance is evaluated using the Area Under the Precision-Recall curve (AUPR) metric.
• The method effectively infers gene regulatory networks from gene-expression data.

Conclusions:

• A novel data-driven dynamic network construction method (D3GRN) has been developed.
• D3GRN integrates ARNI with bootstrapping and area-based scoring for robust GRN inference.
• The method shows strong performance on benchmark datasets, offering a competitive new perspective for GRN inference.