Predicting Disease-Causing Mutations: A Bioinformatics and Machine Learning Approach
Proteins are vital for numerous biological processes, with their functions determined by their unique three-dimensional structure, which depends on their amino acid sequence. Even minor mutations can disrupt protein folding, stability, and interactions, potentially leading to various diseases [1]. Using bioinformatics tools and molecular dynamics simulations, we predict how specific genetic mutations disrupt protein structure and function. This lets us better understand genetic diseases and may provide insights into developing targeted therapies [2].
We will focus on understanding how specific mutations alter protein function, and potentially lead to misfolding or activity loss. By integrating data from genomic databases and leveraging machine learning techniques, we aim to predict which mutations are most likely to cause disease. This streamlined approach could provide a foundation for personalized medicine, with treatments tailored based on specific mutations present in a patient's genome, ultimately contributing to more effective disease management.
Sources: [1] A. L. M. Li, L. A. Thomas, and J. M. Griffith, "Predicting the effect of missense mutations on protein structure and function: the PolyPhen-2 and SIFT algorithms," Nucleic Acids Research, vol. 39, no. 17, pp. e118, Sep. 2011. [Online]. Available: https://academic.oup.com/nar/article/39/17/e118/2411278?login=false [Accessed: Aug. 29, 2024]. [2] B. Alberts, A. Johnson, J. Lewis, M. Raff, K. Roberts, and P. Walter, Molecular Biology of the Cell, 6th ed. New York: Garland Science, 2014. [Online]. Available: https://www.ncbi.nlm.nih.gov/books/NBK26830/ [Accessed: Aug. 29, 2024].