Avaliação de abordagens hierárquicas de aprendizado de máquina aplicadas a bancos de dados biológicos

Abstract

The exponential growth in the generation and availability of biological data in recent decades has increased the importance of databases as a resource to guide innovation and the generation of new biological insights. The broad experimental characterization of these data is, in general, unfeasible, given their complexity and scale, which makes automatic data classification using Machine Learning an essential, faster, and cheaper alternative. Biological datasets are often hierarchical in nature, with varying degrees of complexity, imposing different challenges to train, test, and validate accurate and generalizable classification models. Although 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 datasets, 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.