DEMINERS enables clinical metagenomics and comparative transcriptomic analysis by increasing throughput and accuracy of nanopore direct RNA sequencing
Junwei Song, Li-an Lin, Chao Tang, Chuan Chen, Qingxin Yang, Dan Zhang, Yuancun Zhao, Han-cheng Wei, Kepan Linghu, Zijie Xu, Tingfeng Chen, Zhifeng He, Defu Liu, Yu Zhong, Weizhen Zhu, Wanqin Zeng, Li Chen, Guiqin Song, Mutian Chen, Juan Jiang, Juan Zhou, Jing Wang, Bojiang Chen, Binwu Ying, Yuan Wang, Jia Geng, Jingwen Lin, Lu Chen
Abstract
Nanopore direct RNA sequencing (DRS) is a powerful tool for RNA biology but suffers from low basecalling accuracy, low throughput, and high input requirements. We present DEMINERS, a novel DRS toolkit combining an RNA multiplexing workflow, a Random Forest-based barcode classifier, and an optimized convolutional neural network basecaller with species-specific training. DEMINERS enables accurate demultiplexing of up to 24 samples, reducing RNA input and runtime. Applications include clinical metagenomics, cancer transcriptomics, and parallel transcriptomic comparisons, uncovering microbial diversity in COVID-19 and m6A’s role in malaria and glioma. DEMINERS offers a robust, high-throughput solution for precise transcript and RNA modification analysis.