Machine learning‐enhanced noninvasive prenatal testing of monogenic disorders
Prenatal Diagnosis · 2024-08 · 44 (9) · 1024-1032
DOI: 10.1002/pd.6570 ↗Kurz gefasst
Fachartikel in der Zeitschrift Prenatal Diagnosis, online erschienen am 30.04.2024. Verfasst von Noa Liscovitch-Brauer und 9 weiteren Autor:innen. Beteiligte Einrichtung: Identifai-Genetics Ltd., Tel Aviv, Israel. Hauptthemen laut MEDLINE: Machine Learning, Noninvasive Prenatal Testing. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 26 Literaturangaben. Gefördert von: Israeli Innovation Authority.
Abstract (Originalsprache)
Objective
Single‐nucleotide variants (SNVs) are of great significance in prenatal diagnosis as they are the leading cause of inherited single‐gene disorders (SGDs). Identifying SNVs in a non‐invasive prenatal screening (NIPS) scenario is particularly challenging for maternally inherited SNVs. We present an improved method to predict inherited SNVs from maternal or paternal origin in a genome‐wide manner.
Methods
We performed SNV‐NIPS based on the combination of fragments of cell free DNA (cfDNA) features, Bayesian inference and a machine‐learning (ML) prediction refinement step using random forest (RF) classifiers trained on millions of non‐pathogenic variants. We next evaluate the real‐world performance of our refined method in a clinical setting by testing our models on 16 families with singleton pregnancies and varying fetal fraction (FF) levels, and validate the results over millions of inherited variants in each fetus.
Results
The average area under the ROC curve (AUC) values are 0.996 over all families for paternally inherited variants, 0.81 for the challenging maternally inherited variants, 0.86 for homozygous biallelic variants and 0.95 for compound heterozygous variants. Discriminative AUCs were achieved even in families with a low FF. We further investigate the performance of our method in correctly predicting SNVs in coding regions of clinically relevant genes and demonstrate significantly improved AUCs in these regions. Finally, we focus on the pathogenic variants in our cohort and show that our method correctly predicts if the fetus is unaffected or affected in all (10/10, 100%) of the families containing a pathogenic SNV.
Conclusions
Overall, we demonstrate our ability to perform genome‐wide NIPS for maternal and homozygous biallelic variants and showcase the utility of our method in a clinical setting.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Identifai-Genetics Ltd., Tel Aviv, Israel.
- Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
- Edmond J Safra Center for Bioinformatics, Tel Aviv University, Tel Aviv, Israel.
- Raphael Recanati Genetic Institute, Rabin Medical Center, Beilinson Hospital, Petah Tikva, Israel.
- Felsenstein Medical Research Center, Tel-Aviv University, Tel-Aviv, Israel.
ORCID-Profile: Noa Liscovitch-Brauer
Förderung
- Israeli Innovation Authority
Zitieren
APA
Liscovitch-Brauer, N., Mesika, R., Rabinowitz, T., Volkov, H., Grad, M., Matar, R. T., Basel-Salmon, L., Tadmor, O., Beker, A., & Shomron, N. (2024). Machine learning‐enhanced noninvasive prenatal testing of monogenic disorders. Prenatal Diagnosis, 44(9), 1024-1032. https://doi.org/10.1002/pd.6570
Vancouver
Liscovitch-Brauer N, Mesika R, Rabinowitz T, Volkov H, Grad M, Matar RT, et al. Machine learning‐enhanced noninvasive prenatal testing of monogenic disorders. Prenatal Diagnosis. 2024;44(9):1024-1032. doi:10.1002/pd.6570
BibTeX
@article{LiscovitchBrauer2024,
author = {Liscovitch-Brauer, Noa and Mesika, Ravit and Rabinowitz, Tom and Volkov, Hadas and Grad, Meitar and Matar, Reut Tomashov and Basel-Salmon, Lina and Tadmor, Oren and Beker, Amir and Shomron, Noam},
title = {Machine learning‐enhanced noninvasive prenatal testing of monogenic disorders},
journal = {Prenatal Diagnosis},
year = {2024},
volume = {44},
number = {9},
pages = {1024--1032},
doi = {10.1002/pd.6570}
}
EUVIMED