Related Experiment Video
Updated: Sep 28, 2025
09:03
Semiconductor Sequencing for Preimplantation Genetic Testing for Aneuploidy
Published on: August 25, 2019
9.5K
Predicting embryonic aneuploidy rate in IVF patients using whole-exome sequencing
Siqi Sun1, Maximilian Miller2, Yanran Wang2
1Department of Genetics, Rutgers, The State University of New Jersey, Piscataway, NJ, 08854, USA.
Human Genetics
|March 29, 2022
Summary
Machine learning models predict egg aneuploidy risk in women undergoing in vitro fertilization (IVF) using whole-exome sequencing data. This approach identifies potential genetic risk factors, improving infertility diagnosis and future research.
Area of Science:
- Reproductive Biology
- Genetics
- Bioinformatics
Background:
- Infertility affects 12% of US women of reproductive age.
- Egg aneuploidy contributes to miscarriage and IVF failure.
- Genetic causes of aneuploid egg production are not fully understood.
Purpose of the Study:
- Evaluate machine learning classifiers for predicting embryonic aneuploidy risk in female IVF patients.
- Utilize whole-exome sequencing data for risk prediction.
- Identify novel genetic risk factors for aneuploidy.
Main Methods:
- Applied machine learning classifiers to whole-exome sequencing data from two patient cohorts.
- Assessed classifier performance using area under the receiver operating curve (AUC).
- Identified key genes contributing to predictive power.
Main Results:
- Achieved AUC of 0.77 and 0.68 in the two datasets.
- Demonstrated trade-off between precision and specificity for risk classification.
- Identified MCM5, FGGY, and DDX60L as potential aneuploidy risk genes.
- Found candidate genes enriched in meiotic pathways.
Conclusions:
- Whole-exome sequencing data can be mined to predict aneuploidy risk.
- Machine learning improves clinical diagnosis of infertility.
- Identified candidate genes and pathways warrant further investigation for aneuploidy.
