Machine learning analysis to identify endometrial transcriptomic biomarkers predictive of pregnancy success following artificial insemination in dairy cows

The objective of this research was to identify a set of genes whose transcript abundance is predictive of a cow's ability to become pregnant following artificial insemination (AI). Endometrial epithelial cells from the uterine body were collected for RNA sequencing using the cytobrush method from 193 first-service Holstein cows at estrus prior to AI (day 0). A group of 253 first-service cows not used for cytobrush collection were controls. There was no effect of cytobrush collection on pregnancy outcomes at day 30 or 70, or on pregnancy loss between day 30 and 70. There were 2 upregulated and 214 downregulated genes (FDR < 0.05, absolute fold change > 2-fold) for cows pregnant at day 30 versus those that were not pregnant. Functional terms overrepresented in the downregulated genes included those related to immune and inflammatory responses. Machine learning for fertility biomarkers with the R package BORUTA resulted in identification of 57 biomarkers that predicted pregnancy outcome at day 30 with an average accuracy of 77%. Thus, machine learning can identify predictive biomarkers of pregnancy in endometrium with high accuracy. Moreover, sampling of endometrial epithelium using the cytobrush can help understand functional characteristics of the endometrium at AI without compromising cow fertility. Overall design: 193 lactating dairy cows underwent cytobrush collection of the uterine body directly before artificial insemination. RNA was extracted from the endometrial cells and subsequently underwent machine learning to predict biomarkers of pregnancy success.