Performance Analysis of Computational Methods for Predicting Protein Function in Rare Diseases

Authors

Aichetou Mohamed Sidiya, Effat UniversityFollow
Hanin Alzaher, Effat UniversityFollow
Razan Almahdi, Effat UniversityFollow
Tayeb Brahimi, Effat UniversityFollow

Abstract

Protein function prediction is crucial for understanding the underlying mechanisms of rare diseases. With the increasing availability of computational methods including machine learning-based approaches, network-based methods, and sequence-based methods, predicting protein functions has become more accessible. However, it is not clear which of these methods performs better or how they compare to each other in terms of accuracy, efficiency, and scalability. In this study, we evaluate several computational methods for predicting protein functions in rare diseases using key performance indicators (KPIs). We analyze the strengths and weaknesses of each method and provide recommendations for researchers and clinicians interested in using these methods for rare disease research. The present analysis highlights mi-SVM and RWRKNN as top performers in terms of accuracy, with DeepWalk leading in efficiency. RoF outperforms SVM in speed and accuracy, emphasizing the need for careful model choice based on dataset size and resource availability. Results demonstrate the importance of carefully selecting computational methods for protein function prediction in rare diseases and highlight the need for more research in this area.

Recommended Citation

Sidiya, Aichetou Mohamed; Alzaher, Hanin; Almahdi, Razan; and Brahimi, Tayeb (2023) "Performance Analysis of Computational Methods for Predicting Protein Function in Rare Diseases," Effat Undergraduate Research Journal: Vol. 4: Iss. 1, Article 9.
Available at: https://digitalcommons.aaru.edu.jo/eurj/vol4/iss1/9