Abstract
The degree of Allele sharing of the Human Leukocyte Antigen (HLA) genes has been linked with recurrent miscarriage (RM). However, no clear genetic markers of RM have yet been identified, possibly because of the complexity of interactions between paternal and maternal genes during embryo development. We propose a methodology to analyse HLA haplotypes from couples either with histories of successful pregnancies or RM. This article describes a method of RM genetic-risk calculation. The proposed HLA representation techniques allowed us to create an algorithm (IMMATCH) to retrospectively predict RM with an AUC = 0.71 (p = 0.0035) thanks to high-resolution typing and the use of linear algebra on peptide binding affinity data. The algorithm features an adjustable threshold to increase either sensitivity or specificity, allowing a sensitivity of 86%. Combining immunogenetics with artificial intelligence could create personalised tools to better understand the genetic causes of unexplained infertility and a gamete matching platform that could increase pregnancy success rates.
Highlights
Women using assisted reproductive technologies have a significantly higher risk of experiencing miscarriage than those attempting natural pregnancies, even after adjusting for age.[1]
The cause is not identified for about 50% of patients who experience recurrent miscarriage (RM).[2]
There are no methods to accurately assess an individual couple’s genetic risk of RM; such a risk prediction method would likely improve the process of gamete donation
Summary
Women using assisted reproductive technologies have a significantly higher risk of experiencing miscarriage than those attempting natural pregnancies, even after adjusting for age.[1]. The interactions between immunity and pregnancy outcomes have been demonstrated empirically at the population level, with several studies showing consistently that HLA allele sharing correlates with pregnancy outcomes.[12] identifying specific genetic markers, especially for individual couples, remains elusive. The high degree of polymorphism implies that the potential number of combinations of paternal and maternal protein variants is extremely high, which poses serious difficulties for any study design We can illustrate this high variability by examining only the three genes coding for HLA class I proteins: to date there are.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
