Molecular barcoding of native RNAs using nanopore sequencing and deep learning
)
Nanopore sequencing has enabled high-throughput sequencing of native RNA molecules without conversion to cDNA. However errors introduced by base calling raw nanopore signal complicates sequence-based analytics including barcode demultiplexing. Currently there is no formal barcoding protocol for native RNA sequencing, limiting the applicability to scenarios where the amount of RNA available is low, such as in the case of patient-derived RNA samples.
We describe a novel strategy to barcode and demultiplex direct RNA sequencing, involving custom DNA oligonucleotides ligated to RNA transcripts during library preparation. The raw signal associated with the DNA barcode is extracted, transformed into an array of pixels, and demultiplexed using a deep convolutional neural network classifier. Our method, DeePlexiCon, implements a 20-layer residual neural network model that can demultiplex 84% of reads with 99% specificity.
