Cell-free DNA: Comparison of Technologies

Cell-free fetal DNA screening for Down syndrome has gained rapid acceptance over the past few years with increasing market penetration. Three main laboratory methodologies are currently used: a massive parallel shotgun sequencing (MPSS), a targeted massive parallel sequencing (t-MPS) and a single nucleotide polymorphism (SNP) based approach. Although each of these technologies has its own advantages and disadvantages, the performance of all was shown to be comparable and superior to that of traditional first-trimester screening for the detection of trisomy 21 in a routine prenatal population. Differences in performance were predominantly shown for chromosomal anomalies other than trisomy 21. Understanding the limitations and benefits of each technology is essential for proper counseling to patients. These technologies, as well as few investigational technologies described in this review, carry a great potential beyond screening for the common aneuploidies.

DeepSelectNet: deep neural network based selective sequencing for oxford nanopore sequencing

BACKGROUND

Nanopore sequencing allows selective sequencing, the ability to programmatically reject unwanted reads in a sample. Selective sequencing has many present and future applications in genomics research and the classification of species from a pool of species is an example. Existing methods for selective sequencing for species classification are still immature and the accuracy highly varies depending on the datasets. For the five datasets we tested, the accuracy of existing methods varied in the range of [Formula: see text] 77 to 97% (average accuracy < 89%). Here we present DeepSelectNet, an accurate deep-learning-based method that can directly classify nanopore current signals belonging to a particular species. DeepSelectNet utilizes novel data preprocessing techniques and improved neural network architecture for regularization.

RESULTS

For the five datasets tested, DeepSelectNet's accuracy varied between [Formula: see text] 91 and 99% (average accuracy [Formula: see text] 95%). At its best performance, DeepSelectNet achieved a nearly 12% accuracy increase compared to its deep learning-based predecessor SquiggleNet. Furthermore, precision and recall evaluated for DeepSelectNet on average were always > 89% (average [Formula: see text] 95%). In terms of execution performance, DeepSelectNet outperformed SquiggleNet by [Formula: see text] 13% on average. Thus, DeepSelectNet is a practically viable method to improve the effectiveness of selective sequencing.

CONCLUSIONS

Compared to base alignment and deep learning predecessors, DeepSelectNet can significantly improve the accuracy to enable real-time species classification using selective sequencing. The source code of DeepSelectNet is available at https://github.com/AnjanaSenanayake/DeepSelectNet .