Protein sub-cellular localization prediction for special compartments via optimized time series distances

Area of Science:

• Bioinformatics
• Computational Biology
• Molecular Biology

Background:

• Protein sub-cellular localization is crucial for understanding protein function.
• Existing prediction tools often struggle with specialized compartments and conserved targeting signals.
• Apicoplast localization in apicomplexan parasites presents a significant prediction challenge.

Purpose of the Study:

• To develop an alternative method for predicting protein sub-cellular localization.
• To address limitations of standard tools in predicting localization to special compartments.
• To improve prediction accuracy for proteins with scarce training data or poorly conserved targeting signals.

Main Methods:

• A targeted protein sequence model was developed.
• Weighted measures for time series comparison were incorporated.
• The method was tested on predicting localization in special compartments across three species.

Main Results:

• The proposed method demonstrated reliable predictions for difficult sub-cellular localization cases.
• Performance was validated experimentally, particularly where existing methods yielded sub-optimal results.
• The approach proved effective even with limited training data and non-conserved targeting signals.

Conclusions:

• The novel method complements existing bioinformatics tools for protein localization prediction.
• It offers a viable solution for predicting localization in challenging scenarios, including specialized organelles.
• This work advances the capability to accurately determine protein destinations within the cell.