iPHLoc-ES: Identification of bacteriophage protein locations using evolutionary and structural features

Area of Science:

• Bacteriophage biology
• Bioinformatics
• Computational biology

Background:

• Bacteriophage proteins are crucial for bacterial function and phage-based therapy.
• Understanding bacteriophage protein subcellular localization is key to elucidating their mechanisms of action within host cells.
• Accurate localization prediction is essential for developing effective phage therapies.

Purpose of the Study:

• To develop iPHLoc-ES, a computational method for predicting the subcellular localization of bacteriophage proteins.
• To differentiate between phage proteins located within the host cell and those outside.
• To distinguish between membrane- and cytoplasm-located proteins within the host cell.

Main Methods:

• Extraction of evolutionary and structural features from bacteriophage proteins.
• Utilizing Support Vector Machine (SVM) as the primary classification algorithm.
• Employing Recursive Feature Elimination (RFE) for feature selection and dimensionality reduction.

Main Results:

• iPHLoc-ES demonstrates superior performance compared to existing state-of-the-art prediction methods.
• The method effectively discriminates between host- and non-host-located phage proteins.
• Accurate classification of host-located proteins into membrane or cytoplasm is achieved.

Conclusions:

• iPHLoc-ES provides a significant advancement in predicting bacteriophage protein subcellular localization.
• The tool aids in understanding bacteriophage-host interactions and advancing phage-based therapeutic strategies.
• iPHLoc-ES is available as a standalone tool and web application for broader accessibility.