14 Opening the Black Box of Fertility Prediction. (7th May 2021)

• Record Type: Journal Article
• Authors: Kerns, Karl
• Is Part Of: Journal of animal science. Volume 99(2021)Supplement 1
• Page Start: 141
• Page End: 142
• Publication Date: 2021-05-07
• Subjects: boar -- fertility prediction -- machine and deep learning; Livestock -- Periodicals; Livestock; Electronic journals; Periodicals; 636.005
• DOI: 10.1093/jas/skab054.240
• Languages: English
• ISSNs: 0021-8812

Abstract

Abstract: Analysis of the U.S. swine herd shows variation in pregnancy rate is more attributable to male-factor subfertility than the dam. To date, a limited degree of correlations has been observed between conventional semen analysis parameters and actual fertility after standard quality cutoffs are met. Thus, a clear ability to predict male-factor fertility is lacking. Knowledge of what makes fertilization competent spermatozoa has been long sought after for centuries. It was only in the last half-century that we understood spermatozoa undergo a biological process after ejaculation to acquire the capacity to fertilize. Since then, work has been done to elucidate the molecular pathways involved in sperm capacitation. Recent technological advances in flow cytometry, namely image-based flow cytometry, allows for high-throughput, single-cell phenotyping. Single-cell phenotyping with biomarkers reflecting significant sperm capacitation events, mitochondrial status, cell health, and more, allows multi-million bioimage data sets to be easily attained. These datasets can then be analyzed utilizing machine and deep learning analytic methods and correlated with single sire field fertility data to open the black box of boar fertility prediction. Our findings establish a new paradigm in sperm function and pave the way for accurate fertility prediction in future precision agriculture applications. This work was supported by the National Institute of Food and Agriculture (NIFA), U.S. Department of Agriculture (USDA) award number 2019-67012-29714.