Multi-label machine learning for protein subcellular localization

• Grant number: 16/25220-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): July 01, 2017
• Effective date (End): November 01, 2018
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Ricardo Cerri
• Grantee: Leonardo Utida Alcântara
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil
• Associated scholarship(s): 17/24807-1 - Active learning for protein subcellular localization, BE.EP.IC

Abstract

Protein subcellular localization is a really important classification task, because the location of proteins inside a cell is directly related to these protein's functions. As there are a lot of proteins that resides at the same time in two or more locations in a cell or move between locations, this can be an arduous task. In Machine Learning, this kind of classification task is named multi-label classification, because each instance (protein) can be classified with two or more labels (locations) at the same time. The main goal of this Scientific Initiation project is to investigate the performance of different methods for predicting the subcellular localization of proteins. Several algorithm dependent and independent methods will be tested and analysed and their results will be compared against the state-of-the-art methods. The tests will use sets of data from virus and plants proteins and will be tested using common evaluation measures for multi-label classification. (AU)