Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/120986
Title: Predicción de actividad inhibitoria de moléculas pequeñas sobre el receptor serotoninérgico 5 HT2 A mediante modelos de machine learning
Author: Rojas Mena, Aramis Adriana
Tutor: Sanchez-Martinez, Melchor  
Others: Maceira, Marc  
Canovas Izquierdo, Javier Luis  
Abstract: The present work is included within the field of computer science and its application in the health sciences, specifically the development of machine learning models that allow predicting the activity of small molecules on the serotonergic receptor 5- HT2A. This receptor is associated with already known psychiatric pathologies, for which there is treatment with small molecules that inhibit it, but with frequent adverse effects. Both classification and regression algorithms are tested to see which ones could have a better predictive capacity on the inhibition constant, Ki, and be able to perform computational screening on groups of small molecules that could be a therapeutic alternative. The findings suggest that, based on a balanced and screened data set, the classification algorithms generally have a very good ability to predict the activity (active or inactive) of small molecules on this 5-HT2A receptor. The best algorithm is SVM, with an accuracy and precision of over 93%. Regression algorithms are not helpful in predicting activity. For both cases, it will be necessary to reproduce similar studies on this receptor, with different sources of data and other algorithms or different configuration of its hyperparameters, in order to infer more robust knowledge.
Keywords: serotoninergic receptors
ki
prediction
Document type: info:eu-repo/semantics/masterThesis
Issue Date: Jun-2020
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
arrojasTFM0620Memoria.pdfMemoria del TFM1,88 MBAdobe PDFThumbnail
View/Open