Multilabel classification machine learning method for predicting long non coding RNA-associated diseases

• Grant number: 22/14762-9
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2023
• End date: February 28, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Ricardo Cerri
• Grantee: Lívia Umberto Bertoni
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil
• Associated scholarship(s): 24/05438-9 - Deep tree-ensembles for predicting lncRNA-associated diseases, BE.EP.IC

Abstract

Long non-coding RNAs (lncRNAs) are RNAs longer than 200 nucleotides that are not translated into functional proteins. They play an important role in various life processes. In parallel, an increasing number of studies have revealed associations between abnormal expressions of these RNAs and human diseases. Many biotechnological approaches have been used to identify and detect these lncRNAs. However, there are some complications in these processes, associated with cost, operational procedure and experimental process. Therefore, it is preferable to build AI-based models for disease prediction from lncRNA data, which will be useful for diagnosis and disease therapy. The main objective of this project is the implementation of a lncRNA-associated disease prediction method, being a case of multilabel classification, since a single lncRNA can be associated with more than one disease. Different methods - dependent or independent of the algorithm - will be analyzed and tested, and their results will be compared to state-of-art methods. The results will be evaluated using a collection of data from lncRNAs sequences using measures from specific evaluation for multilabel classification problems.