FF‐QuantSC: accurate quantification of fetal fraction by a neural network model

Abstract

Abstract Background Noninvasive prenatal testing (NIPT) is one of the most commonly employed clinical measures for screening of fetal aneuploidy. Fetal Fraction (ff) has been demonstrated to be one of the key factors affecting the performance of NIPT. Accurate quantification of ff plays vital role in NIPT. Methods In this study, we present a new approach, the accurate Quantification of Fetal Fraction with Shallow‐Coverage sequencing of maternal plasma DNA (FF‐QuantSC), for the estimation of ff in NIPT. The method employs neural network model and utilizes differential genomic patterns between fetal and maternal genomes to quantify ff. Results Our results show that the predicted ff by FF‐QuantSC exhibit high correlation with the Y chromosome–based method on male pregnancies, and achieves the highest accuracy compared with other ff estimation approaches. We also demonstrate that the model generates statistically similar results on both male and female pregnancies. Conclusion FF‐QuantSC achieves high accuracy in ff quantification. The method is suitable for application in both male and female pregnancies. Since the method does not require additional information upon NIPT routines, it can be easily incorporated into current NIPT settings without causing extra costs. We believe that FF‐QuantSC shall provide valuable additions to NIPT.

Keywords

• female pregnancy
• fetal fraction
• FF‐QuantSC
• neural network
• NIPT
• shallow‐coverage sequencing