Minería de texto para construir la filogenia de los insectos vectores de la enfermedad de Chagas

Abstract

Throughout history, naturists, scientists and biologists have published morphological information of plants and animals in printed media, such as journals and books. However, only a small fraction of that information is available and properly structured to conduct further phylogenetic analyzes. It is necessary to develop software tools to extract, integrate and publish this information.

In this work, a methodology was developed to obtain descriptions of species in separate documents from a book on insect vectors of Chagas disease (Triatominae kissing bugs), and to build the phylogenetic tree of these insects. 131 documents of different species have been obtained, with their characteristics and values. These data obtained were used to infer the phylogeny of this important group of insects.