Progress on the development of prediction tools for detecting disease causing mutations in proteins

• Published in: Computers in biology and medicine 2025-02, Vol.185, p.109510, Article 109510
• Main Authors: Gromiha, M. Michael, Pandey, Medha, Kulandaisamy, A., Sharma, Divya, Ridha, Fathima
• Format: Article
• Language: English
• Subjects: Algorithms; Binding affinity; Cancer hotspots; Disease-causing mutations; Infectious diseases; Machine-learning; Membrane proteins; Network; Neurodegenerative; Sequence-based features; Stability; Structure
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.109510

Proteins are involved in a variety of functions in living organisms. The mutation of amino acid residues in a protein alters its structure, stability, binding, and function, with some mutations leading to diseases. Understanding the influence of mutations on protein structure and function help to gain deep insights on the molecular mechanism of diseases and devising therapeutic strategies. Hence, several generic and disease-specific methods have been proposed to reveal pathogenic effects on mutations. In this review, we focus on the development of prediction methods for identifying disease causing mutations in proteins. We briefly outline the existing databases for disease-causing mutations, followed by a discussion on sequence- and structure-based features used for prediction. Further, we discuss computational tools based on machine learning, deep learning and large language models for detecting disease-causing mutations. Specifically, we emphasize the advances in predicting hotspots and mutations for targets involved in cancer, neurodegenerative and infectious diseases as well as in membrane proteins. The computational resources including databases and algorithms understanding/predicting the effect of mutations will be listed. Moreover, limitations of existing methods and possible improvements will be discussed. •Mutations in proteins provides insights into disease mechanisms and developing therapeutic strategies.•Databases for studying disease causing and neutral mutations are easily accessible.•Sequence, structure and network-based features are discussed to identify disease-causing mutations.•ML, AI and LLM based methods are explained with applications to cancer, neurodegenerative and infectious diseases.•Disease-causing mutations are relate to stability, binding affinity and interface occurrence.