Expression signature as a biomarker for prenatal diagnosis of trisomy 21

Abstract

A universal biomarker panel with the potential to predict high-risk pregnancies or adverse pregnancy outcome does not exist. Transcriptome analysis is a powerful tool to capture differentially expressed genes (DEG), which can be used as biomarker-diagnostic-predictive tool for various conditions in prenatal setting. In search of biomarker set for predicting high-risk pregnancies, we performed global expression profiling to find DEG in Ts21. Subsequently, we performed targeted validation and diagnostic performance evaluation on a larger group of case and control samples. Initially, transcriptomic profiles of 10 cultivated amniocyte samples with Ts21 and 9 with normal euploid constitution were determined using expression microarrays. Datasets from Ts21 transcriptomic studies from GEO repository were incorporated. DEG were discovered using linear regression modelling and validated using RT-PCR quantification on an independent sample of 16 cases with Ts21 and 32 controls. The classification performance of Ts21 status based on expression profiling was performed using supervised machine learning algorithm and evaluated using a leave-one-out cross validation approach. Global gene expression profiling has revealed significant expression changes between normal and Ts21 samples, which in combination with data from previously performed Ts21 transcriptomic studies, were used to generate a multi-gene biomarker for Ts21, comprising of 9 gene expression profiles. In addition to biomarker's high performance in discriminating samples from global expression profiling, we were also able to show its discriminatory performance on a larger sample set 2, validated using RT-PCR experiment (AUC=0.97), while its performance on data from previously published studies reached discriminatory AUC values of 1.00. Our results show that transcriptomic changes might potentially be used to discriminate trisomy of chromosome 21 in the prenatal setting. As expressional alterations reflect both, causal and reactive cellular mechanisms, transcriptomic changes may thus have future potential in the diagnosis of a wide array of heterogeneous diseases that result from genetic disturbances.

Figure 1. The directionality of HSA21 differentially expressed genes in comparison to non-HSA21.

A pattern of upregulation is present in differentially expressed HSA21 genes, while non-HSA21 genes tended to be slightly down-regulated.

Figure 2. Differential expression of genes in the validation core set, where light blue bars represent average expression in euploid samples and dark blue in samples with trisomy 21.

Confidence intervals of 95% for the expression mean based t-ditribution are also presented.

Figure 3. Random operator curve analyses, based on data from the RP-PCR validation stage.

Figure 4. Validation of results, based on data from studies by Altug-Teber et al [3] and Chou et al [13]

In the upper part of the figure, the per-sample predictions based on the expression profiles of 9 gene biomarker are displayed, with predicted probability of positive Ts21 status presented on y axis. The color of the dots represent the actual karyotyping diagnostic result. Below, heatmap representing gene expression level for each sample (heatmap rows) and for each gene (heatmap columns) is presented. The expression of 8 genes tends to be comparatively increased in samples with true trisomy 21 status, while expression of LAMB3 is directed oppositely, towards down-regulation in Ts21 samples. In the heatmap yellow color represents higher expression and red color lower expression level, where values have been scaled separately per each row. Middle part of the figure represents principal component analysis of 9-gene expression for samples expression profiles published in [3,13]. In the bottom part, plots representing ROC-based classification performance of 9-gene expression biomarker may be observed.