Dataset Information

Improving the calling of non-invasive prenatal testing on 13-/18-/21-trisomy by support vector machine discrimination.

ABSTRACT: With the advance of next-generation sequencing (NGS) technologies, non-invasive prenatal testing (NIPT) has been developed and employed in fetal aneuploidy screening on 13-/18-/21-trisomies through detecting cell-free fetal DNA (cffDNA) in maternal blood. Although Z-test is widely used in NIPT NGS data analysis, there is still necessity to improve its accuracy for reducing a) false negatives and false positives, and b) the ratio of unclassified data, so as to lower the potential harm to patients as well as the induced cost of retests. Combining the multiple Z-tests with indexes of clinical signs and quality control, features were collected from the known samples and scaled for model training using support vector machine (SVM). We trained SVM models from the qualified NIPT NGS data that Z-test can discriminate and tested the performance on the data that Z-test cannot discriminate. On screenings of 13-/18-/21-trisomies, the trained SVM models achieved 100% accuracies in both internal validations and unknown sample predictions. It is shown that other machine learning (ML) models can also achieve similar high accuracy, and SVM model is most robust in this study. Moreover, four false positives and four false negatives caused by Z-test were corrected by using the SVM models. To our knowledge, this is one of the earliest studies to employ SVM in NIPT NGS data analysis. It is expected to replace Z-test in clinical practice.

SUBMITTER: Yang J

PROVIDER: S-EPMC6281214 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Improving the calling of non-invasive prenatal testing on 13-/18-/21-trisomy by support vector machine discrimination.

Yang Jianfeng J Ding Xiaofan X Zhu Weidong W

PloS one 20181205 12

With the advance of next-generation sequencing (NGS) technologies, non-invasive prenatal testing (NIPT) has been developed and employed in fetal aneuploidy screening on 13-/18-/21-trisomies through detecting cell-free fetal DNA (cffDNA) in maternal blood. Although Z-test is widely used in NIPT NGS data analysis, there is still necessity to improve its accuracy for reducing a) false negatives and false positives, and b) the ratio of unclassified data, so as to lower the potential harm to patients ...[more]

PMID: 30517156

Similar Datasets

Project description:Background: Among full autosomal trisomies, only trisomies of chromosome 21 (Down syndrome, DS), 18 (Edward syndrome, ES) and 13 (Patau syndrome, PS) are compatible with postnatal survival. But the mechanisms, how a supernumerary chromosome disrupts the normal development and causes specific phenotypes, are still not fully explained. As an alternative to gene dosage effects due to the trisomic chromosome, a genome-wide transcriptional dysregulation has been postulated. The aim of this study was to define the transcriptional changes in trisomy 13, 18, and 21 during early fetal development in order to define whether (1) overexpression of genes of the trisomic chromosome contributes solely to the phenotype, if (2) all genes of the trisomic chromosome are upregulated similarly and whether the ratio of gene expression is in agreement with the gene dosis, (3) whether the different trisomies behave similarly in the characteristics of transcriptional dysregulation, and (4) whether transcriptional pattern can be potentially used in prenatal diagnosis. Methods: Using oligonucleotide microarrays (Affymetrix, U133 Plus 2.0), we analyzed whole genome expression profiles representing 54.000 probe sets in cultured amniocytes (AC) and chorion villus cells (CV) from pregnancies with a normal karyotype and with trisomies of human chromosomes 21, 18 and 13. Findings: We observed a low to moderate up-regulation for a subset of genes of the trisomic chromosomes. Transcriptional level of approximately 12-13 % of the supernumerary chromosome appeared similar to the respective chromosome pair in normal karyotypes. Expression values as well as the expression patterns of genes from the trisomic chromosome can distinguish the respective trisomic samples from euploid controls. A subset of chromosome 21-genes including the DSCR1-gene involved in fetal heart development was consistently up-regulated in different tissues (AC, CV) of trisomy 21 fetuses whereas only minor changes were found for genes of all other chromosomes. In contrast, in trisomy 13 and trisomy 18 vigorous downstream transcriptional changes were found. Interpretation: Global transcriptome analysis for autosomal trisomies 13, 18, and 21 supported a combination of the two major hypotheses. As several transcriptional pathways are altered, complex regulatory mechanisms are involved in the pathogenesis of autosomal trisomies. A genome-wide transcriptional dysregulation was predominantly observed in trisomies 13 and 18, whereas a more to chromosome 21 restricted expression alteration was found in trisomy 21. Experiment Overall Design: The study included the following samples: Three samples with normal chromosomes in Amniocytes (AC) and chorion villus cells (CV) each, three samples with trisomy 13 in AC, three samples with trisomy 18 in CV, and three samples with trisomy 21 in AC and CV each.

Dataset Information

Improving the calling of non-invasive prenatal testing on 13-/18-/21-trisomy by support vector machine discrimination.

Publications

Improving the calling of non-invasive prenatal testing on 13-/18-/21-trisomy by support vector machine discrimination.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure