Associations of Nelore microbiome with host metadata using machine learning and convolutional networks

• Grant number: 19/15557-7
• Support Opportunities: Scholarships abroad - Research Internship - Post-doctor
• Effective date (Start): October 28, 2019
• Effective date (End): September 27, 2020
• Field of knowledge: Agronomical Sciences - Animal Husbandry - Genetics and Improvement of Domestic Animals
• Principal Investigator: Luciana Correia de Almeida Regitano
• Grantee: Bruno Gabriel Nascimento Andrade
• Supervisor: Paul Walsh
• Host Institution: Embrapa Pecuária Sudeste. Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA). Ministério da Agricultura, Pecuária e Abastecimento (Brasil). São Carlos , SP, Brazil
• Research place: Cork Institute of Technology (CIT), Ireland
• Associated to the scholarship: 17/12642-8 - Microbiome diversity of Nelore steers compared to different diets and its influence in production characteristics and methane emission, BP.PD

Abstract

The success of different ruminant species in the colonization of different environments is due to their ability to digest complex polysaccharides (cellulose and others), which is found abundantly in the form of leaves and grasses. This ability is possible thanks to the association of a complex microbial community to different segments of the gastrointestinal, known as the microbiota. Advances in sequencing technology are now allowing us to explore the diversity of non-cultivable microorganisms. This method, with which we can explore their taxonomic diversity, is known as metagenomics and can be applied either to the gene pool or to ribosomal RNA coding gene amplicons (16 or 18s). Previous analyses indicated that some phenotypes were influenced by diet, like methane emission; therefore, this research aims to apply machine learning and convolutional networks approaches to explore the association between the taxonomic diversity of both rumen and gut microbiomes of 52 animals under two different diets and host phenotypes/environmental traits, such as methane production, feed efficiency and metabolite concentration. (AU)