Method predicts miscarriage risk due to egg aneuploidy

"The goal of our project was to understand the genetic cause of female infertility and develop a method to improve clinical prognosis of patients' aneuploidy risk," says Jinchuan Xing. (Credit: Getty Images)

Specialized genome analysis can predict the risk of having one of the most common types of miscarriage, researchers report.

In the journal Human Genetics, researchers describe a technique combining genomic sequencing with machine-learning methods to predict the possibility someone will experience a miscarriage because of egg aneuploidy, a human egg with an abnormal number of chromosomes.

Infertility is a major reproductive health issue that affects about 12% of women of reproductive age in the United States. Aneuploidy in human eggs accounts for a significant proportion of infertility, causing early miscarriage and in vitro fertilization (IVF) failure.

Recent studies have shown that genes predispose certain women to aneuploidy, but the exact genetic causes of aneuploid egg production have remained unclear. The new study is the first to evaluate how well individual genetic variants in the genome can predict a someone’s risk of infertility.

“The goal of our project was to understand the genetic cause of female infertility and develop a method to improve clinical prognosis of patients’ aneuploidy risk,” says Jinchuan Xing, an author of the study and an associate professor in the genetics department at Rutgers University. “Based on our work, we showed that the risk of embryonic aneuploidy in female IVF patients can be predicted with high accuracy with the patients’ genomic data. We also have identified several potential aneuploidy risk genes.”

Working with Reproduction Medicine Associates of New Jersey, an IVF clinic in Basking Ridge, New Jersey, the scientists were able to examine genetic samples of patients using a technique called “whole exome sequencing,” which allows researchers to home in on the protein coding sections of the vast human genome.

Then they created software using machine learning, an aspect of artificial intelligence in which programs can learn and make predictions without following specific instructions. To do so, the researchers developed algorithms and statistical models that analyzed and drew inferences from patterns in the genetic data.

As a result, the scientists were able to create a specific risk score based on a woman’s genome. The scientists also identified three genes—MCM5, FGGY, and DDX60L—that, when mutated, are highly associated with a risk of producing eggs with aneuploidy.

While age is a predictive factor for aneuploidy, it is not a highly accurate gauge because aneuploidy rates within individuals of the same age can vary dramatically. Identifying genetic variations with more predictive power arms patients and their treating clinicians with better information, Xing says.

“I like to think of the coming era of genetic medicine when a woman can enter a doctor’s office or, in this case, perhaps, a fertility clinic with her genomic information, and have a better sense of how to approach treatment,” Xing says. “Our work will enable such a future.”

Source: Rutgers University