Bi-stream CNN Down Syndrome screening model based on genotyping array

Abstract

BackgroundHuman Down syndrome (DS) is usually caused by genomic micro-duplications and dosage imbalances of human chromosome 21. It is associated with many genomic and phenotype abnormalities. Even though human DS occurs about 1 per 1,000 births worldwide, which is a very high rate, researchers haven’t found any effective method to cure DS. Currently, the most efficient ways of human DS prevention are screening and early detection.MethodsIn this study, we used deep learning techniques and analyzed a set of Illumina genotyping array data. We built a bi-stream convolutional neural networks model to screen/predict the occurrence of DS. Firstly, we built image input data by converting the intensities of each SNP site into chromosome SNP maps. Next, we proposed a bi-stream convolutional neural network (CNN) architecture with nine layers and two branch models. We further merged two CNN branch models into one model in the fourth convolutional layer, and output the prediction in the last layer.ResultsOur bi-stream CNN model achieved 99.3% average accuracies, and very low false-positive and false-negative rates, which was necessary for further applications in disease prediction and medical practice. We further visualized the feature maps and learned filters from intermediate convolutional layers, which showed the genomic patterns and correlated SNPs variations in human DS genomes. We also compared our methods with other CNN and traditional machine learning models. We further analyzed and discussed the characteristics and strengths of our bi-stream CNN model.ConclusionsOur bi-stream model used two branch CNN models to learn the local genome features and regional patterns among adjacent genes and SNP sites from two chromosomes simultaneously. It achieved the best performance in all evaluating metrics when compared with two single-stream CNN models and three traditional machine-learning algorithms. The visualized feature maps also provided opportunities to study the genomic markers and pathway components associated with Human DS, which provided insights for gene therapy and genomic medicine developments.

Deep Learning for Rare Disease: A Scoping Review

“…CNNs were used with other data types by utilizing CNN’s capacity to learn patterns in data such as genomic data[54, 55], EMG signals[56], electroencephalography[57], protein-protein molecular dynamics[35], and published rare disease literature[58]. For example, [54] applied CNN to SNP maps to predict occurrences of Down syndrome. [56] converted EMG signals to 2-dimensional time-frequency representation and applied CNN to classify amyotrophic lateral sclerosis.…”

Bringing machine learning to research on intellectual and developmental disabilities: taking inspiration from neurological diseases

“…Their proposed model did not need priori knowledge and could apply to long non-coding RNAs which implicated the etiology of ASD as well. Feng et al converted the genotype intensity information into chromosome SNP maps and then applied 10-layer CNN to classify Down syndrome (DS) samples (63 DS, 315 control) [ 126 ]. They achieved a very high classification accuracy of 99.3%.…”

Discrimination of alcohol dependence based on the convolutional neural network

“…The detection of SNP was completed by Shanghai Tianhao Biotechnology Co., Ltd., using the GoldMag® nanoparticle method (Gold Magnet Co., Ltd., Xi’an, China) to extract genomic DNA samples from blood, using Nano drop 2000C (Thermo Scientific, Walther, Massachusetts, USA) to determine DNA concentration, use Sequenom MassARRAY Assay Design 3.0 software (San Diego, California, USA) to design multiple SNP MassEXTEND analysis, use Sequenom MassARRAY RS1000 to genotype SNP (San Diego, California, USA), and use Sequenom Typer 4.0 software (San Diego, California, USA) for data management and analysis. After encoding the detected SNP genotype data and interpolating the missing values [ 50 ], in order not to introduce artificial bias, we ensured that the interpolation probability meets the Hardy-Weinberg equilibrium law (HWE) [ 51 ].…”