NLP-BCH-Ens: NLP-based intelligent computational model for discrimination of malaria parasite

Area of Science:

• Computational biology
• Infectious disease research
• Bioinformatics

Background:

• Malaria, caused by Plasmodium falciparum, is a fatal disease.
• Microscopic diagnosis of malaria is time-consuming and prone to errors.
• Accurate parasite detection is vital for developing effective malaria treatments.

Purpose of the Study:

• To develop an automated, accurate method for predicting malaria parasites.
• To discriminate between secretory and non-secretory proteins of Plasmodium falciparum.

Main Methods:

• Protein sequences were transformed into numerical descriptors using discrete, biochemical, physiochemical, and NLP techniques.
• Four classification algorithms were fused into an ensemble model using majority voting and genetic algorithms.
• BCH error correction code was integrated with a support vector machine.

Main Results:

• The proposed ensemble model demonstrated significant improvements over previous methods.
• The model achieved remarkable success in discriminating secretory and non-secretory proteins.
• Simulated results confirm the model's effectiveness and accuracy.

Conclusions:

• The developed model offers an effective tool for malaria parasite detection.
• Automated protein sequence analysis can enhance diagnostic accuracy for infectious diseases.
• This approach aids in the development of targeted malaria therapies.