DeepSelectNet: Deep Neural Network Based Selective Sequencing for Oxford Nanopore Sequencing

Curated dataset for the manuscript named "DeepSelectNet: Deep Neural Network Based Selective Sequencing for Oxford Nanopore Sequencing". Five publicly available datasets sequenced on ONT MinION/GridION were used for the experiments (see below for original sources). These datasets contained raw signal data in single-FAST5 format (one file per each read), which were converted to BLOW5 format using slow5tools to enable convenient and efficient file manipulation. Then, 40,000 reads containing at least 4500 signal samples were extracted from each dataset. From each dataset, 20,000 reads are for training (<species>/train-<species>.blow5) and the rest for testing (<species>/test-<species>.blow5). Basecalled reads for the dataset used for testing are also available (test-<species>.fastq). Guppy version 6.1.3 under dna_r9.4.1_450bps_hac mode was used. The reference genomes are also given (<species>/<species>-ref.fasta) Original datasets are from the following sources: SARS-CoV-2: https://community.artic.network/t/links-to-raw-fast5-fastq-data-for-artic-protocol/17 Zymo Metagenome: https://github.com/LomanLab/mockcommunity Chlamydomonas: https://sra-download.ncbi.nlm.nih.gov/traces/era20/ERZ/003237/ERR3237140/Chlamydomonas_0.tar.gz Saccharomyces cerevisiae: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA510813