ANAT 3.0: a framework for elucidating functional protein subnetworks using graph-theoretic and machine learning...

Area of Science:

• Bioinformatics
• Systems Biology
• Computational Biology

Background:

• ANAT is a Cytoscape plugin for inferring functional protein-protein interaction (PPI) networks.
• It serves as a graphical tool for exploring biological pathways in yeast and human.
• Facilitates the elucidation of protein-protein interaction pathways relevant to specific biological processes.

Purpose of the Study:

• To introduce ANAT3.0, an advanced version of the ANAT tool.
• To present updated and expanded protein-protein interaction network databases for human and yeast.
• To incorporate a novel machine-learning layer for enhanced network elucidation.

Main Methods:

• Utilized updated protein-protein interaction network databases containing 544,455 human and 155,504 yeast interactions.
• Integrated a new machine-learning layer into the ANAT framework.
• Employed refined network reconstruction algorithms for improved pathway analysis.

Main Results:

• ANAT3.0 demonstrates a twofold increase in the quality of reconstructing known signaling pathways from KEGG.
• Achieved more comprehensive protein-protein interaction networks compared to previous versions.
• Enhanced network elucidation capabilities through machine learning integration.

Conclusions:

• ANAT3.0 offers improved network reconstruction algorithms and more extensive PPI networks.
• The updated tool enhances the exploration and understanding of biological networks.
• ANAT is accessible via the Cytoscape Appstore and a dedicated website.