Optical spectroscopy raman associated with artificial intelligence algorithms to predict gestational status in bovine females

• Grant number: 25/13722-1
• Support Opportunities: Scholarships in Brazil - Master
• Start date: September 01, 2025
• End date: May 31, 2027
• Field of knowledge: Agronomical Sciences - Veterinary Medicine - Animal Reproduction
• Principal Investigator: Luciano Andrade Silva
• Grantee: Mariane Aparecida de Andrade Belezone
• Host Institution: Faculdade de Zootecnia e Engenharia de Alimentos (FZEA). Universidade de São Paulo (USP). Pirassununga , SP, Brazil
• Associated research grant: 24/16812-9 - OPTICAL SPECTROSCOPY RAMAN ASSOCIATED WITH ARTIFICIAL INTELLIGENCE ALGORITHMS TO PREDICT CONCEPTION AND GESTATIONAL STATUS IN BOVINE FEMALES, AP.R

Abstract

The global demand for food has grown in parallel with population growth. This fact encourages the development of technologies to improve productivity. In beef cattle farming, specifically in the area of reproduction, technologies applied in recent decades to multiply genetic material and produce calves have been essential for the growth of this sector. However, the efficiency of many of these technologies can be improved. Early identification and selective use of females with greater conception potential and gestational diagnosis as early as possible are examples of actions that could substantially contribute to improved production efficiency. Techniques for highly accurate, rapid, and field-based clinical reproductive diagnostics can be valuable for decision-making. With the rapid evolution of computer processing systems, artificial intelligence and machine learning are tools that allow the analysis of complex, large-volume data for diagnostic purposes. In this project, two studies will aim to develop methodologies for ultra-early pregnancy diagnosis. Spectral data will be obtained by optical Raman spectroscopy in blood serum and cervicovaginal mucus collected from female cattle subjected to the IATF technique. Changes in the composition of metabolites in these biological samples may be associated with different homeostatic statuses, mainly dependent on the modulation of metabolism by reproductive hormones. After obtaining the spectral data, their dimensionality will be reduced and adjusted by principal component analysis and then subjected to analysis with machine learning algorithms for diagnostic determination. The aim of this research project is to identify and describe patterns of spectral signatures ("fingerprints") that allow for the rapid, accurate and low-cost diagnosis of early pregnancy. The results of this project may, in a second step, direct the use of other analytical metabolomics techniques to identify the components that are distinct between pregnant and non-pregnant females, and subsequently allow the development of low-cost rapid tests for use in the field or for the development of clinical and nutritional treatments that can increase reproductive efficiency.