Biochemical-free enrichment or depletion of RNA classes in real-time during direct RNA sequencing with RISER (cell lines). Biochemical-free enrichment or depletion of RNA classes in real-time during direct RNA sequencing with RISER (cell lines)

The heterogeneous composition of cellular transcriptomes poses a major challenge for detecting weakly expressed RNA classes, as they can be obscured by abundant RNAs. Although biochemical protocols can enrich or deplete specified RNAs, they are time-consuming, expensive and can compromise RNA integrity. Here we introduce RISER, a biochemical-free technology for the real-time enrichment or depletion of RNA classes. RISER performs selective rejection of molecules during direct RNA sequencing by identifying RNA classes directly from nanopore signals with deep learning and communicating with the sequencing hardware in real time. By targeting the dominant messenger and mitochondrial RNA classes for depletion, RISER reduced their respective read counts by more than 85%, resulting in an increase in sequencing depth of up to 93% for long non-coding RNAs. We also applied RISER for the depletion of globin mRNA in whole blood, achieving a decrease in globin reads by more than 90% as well as a significant increase in non-globin reads. Furthermore, using a GPU or a CPU, RISER is faster than GPU-accelerated basecalling and mapping. RISER’s modular and retrainable software and intuitive command-line interface allow easy adaptation to other RNA classes. RISER is available at https://github.com/comprna/riser. Overall design: Nanopore direct RNA sequencing was performed using 2 blood samples from human donors for training RISER, and 1 blood sample from another human donor for testing RISER during live MinION sequencing.

细胞转录组的异质性组成，为弱表达RNA类别的检测带来了重大挑战——这类RNA极易被高丰度RNA所遮蔽。
尽管现有生化实验方案可实现特定RNA的富集或去除，但此类方法耗时久、成本高昂，且会损害RNA的完整性。
在此我们介绍RISER——一种无需生化处理的技术，可实时完成RNA类别的富集或去除。
RISER可在直接RNA测序（direct RNA sequencing）过程中实现目标分子的选择性排除：其通过深度学习（deep learning）直接从纳米孔信号（nanopore signals）中识别RNA类别，并与测序硬件实现实时通信。
通过靶向去除占主导地位的信使RNA（messenger RNA，mRNA）与线粒体RNA（mitochondrial RNA），RISER可将二者各自的测序读段数降低85%以上，进而使长链非编码RNA（long non-coding RNAs）的测序深度最高提升93%。
我们还将RISER应用于全血样本中珠蛋白mRNA（globin mRNA）的去除，实现了珠蛋白读段减少90%以上，同时非珠蛋白读段数量显著提升。
此外，无论是使用图形处理器（Graphics Processing Unit，GPU）还是中央处理器（Central Processing Unit，CPU），RISER的运行速度均快于经GPU加速的碱基识别（basecalling）与序列比对（mapping）流程。
RISER采用模块化且可重新训练的软件架构，搭配直观的命令行界面，可轻松适配其他RNA类别的分选需求。
RISER的开源代码可在https://github.com/comprna/riser获取。
整体实验设计：使用来自2名人类供体的血液样本训练RISER，随后在实时MinION测序过程中，使用来自另1名人类供体的血液样本测试RISER的性能。