Please use this identifier to cite or link to this item:
https://www.arca.fiocruz.br/handle/icict/53979
EVALUATING HIERARCHICAL MACHINE LEARNING APPROACHES TO CLASSIFY BIOLOGICAL DATABASES.
class hierarchy
hierarchical classification
protein function prediction
protein structural classification
Author
Affilliation
Universidade Federal de Minas Gerais. Belo Horizonte, MG, Brasil/Fundação Oswaldo Cruz. Instituto René Rachou. Belo Horizonte, MG, Brasil/Stilingue Inteligência Artificial. Ouro Preto, MG, Brasil
Universidade Federal de Minas Gerais. Belo Horizonte, MG, Brasil/Fundação Oswaldo Cruz. Instituto René Rachou. Belo Horizonte, MG, Brasil/Universidade Federal dos Vales do Jequitinhonha e Mucuri. Instituto de Ciências Agrícolas. Diamantina, MG, Brasil
School of Chemistry and Molecular Biosciences. University of Queensland. Queensland, Australia/Systems and Computational Biology, Bio 21 Institute, University of Melbourne. Melbourne, Victoria, Australia/Computational Biology and Clinical Informatics, Baker Heart and Diabetes Institute. Melbourne, Victoria, Australia
Fundação Oswaldo Cruz. Instituto René Rachou. Belo Horizonte, MG, Brasil
Systems and Computational Biology. Bio 21 Institute. University of Melbourne. Melbourne, Victoria, Australia/Computational Biology and Clinical Informatics. Baker Heart and Diabetes Institute. Melbourne, Victoria, Australia/School of Computing and Information Systems. University of Melbourne. Melbourne, Victoria, Australia
Universidade Federal de Minas Gerais. Belo Horizonte, MG, Brasil/Fundação Oswaldo Cruz. Instituto René Rachou. Belo Horizonte, MG, Brasil/Universidade Federal dos Vales do Jequitinhonha e Mucuri. Instituto de Ciências Agrícolas. Diamantina, MG, Brasil
School of Chemistry and Molecular Biosciences. University of Queensland. Queensland, Australia/Systems and Computational Biology, Bio 21 Institute, University of Melbourne. Melbourne, Victoria, Australia/Computational Biology and Clinical Informatics, Baker Heart and Diabetes Institute. Melbourne, Victoria, Australia
Fundação Oswaldo Cruz. Instituto René Rachou. Belo Horizonte, MG, Brasil
Systems and Computational Biology. Bio 21 Institute. University of Melbourne. Melbourne, Victoria, Australia/Computational Biology and Clinical Informatics. Baker Heart and Diabetes Institute. Melbourne, Victoria, Australia/School of Computing and Information Systems. University of Melbourne. Melbourne, Victoria, Australia
Abstract
The rate of biological data generation has increased dramatically in recent years, which has driven the importance of databases as a resource to guide innovation and the generation of biological insights. Given the complexity and scale of these databases, automatic data classification is often required. Biological data sets are often hierarchical in nature, with varying degrees of complexity, imposing different challenges to train, test and validate accurate and generalizable classification models. While some approaches to classify hierarchical data have been proposed, no guidelines regarding their utility, applicability and limitations have been explored or implemented. These include 'Local' approaches considering the hierarchy, building models per level or node, and 'Global' hierarchical classification, using a flat classification approach. To fill this gap, here we have systematically contrasted the performance of 'Local per Level' and 'Local per Node' approaches with a 'Global' approach applied to two different hierarchical datasets: BioLip and CATH. The results show how different components of hierarchical data sets, such as variation coefficient and prediction by depth, can guide the choice of appropriate classification schemes. Finally, we provide guidelines to support this process when embarking on a hierarchical classification task, which will help optimize computational resources and predictive performance.
Keywords
biological databaseclass hierarchy
hierarchical classification
protein function prediction
protein structural classification
Share