Machine Learning Techniques to Determine Mutation Impact in Proteins Associated to Neurofibromatosis

Nowadays, computational intelligence has been employed to predict aspects related to detect diseases, which has become an essential practice in health around the world. Specifically, this work used the application of support vector machines, artificial neural networks, and random forest models extracted from machine learning approaches for finding relevant mutations associated to Neurofibromatosis. Information from the protein composition based on amino acids was employed to train the models and determine the mutation impact for genetic diseases as Neurofibromatosis one and two. A cross-validation method was implemented to analyze the generalization of the mentioned models. Results show that artificial neural networks hold the best performance to determine if the mutation can impact the protein structure. Finally, the aim of this study is to contribute to the understanding of the mutation effect in biomolecules based on computational models based on information extracted from protein sequence data.