Year: 2021
Type: article
Abstract: The characteristic ionic currents of nucleotide kmers are commonly used in analyzing nanopore sequencing readouts. We present a graph convolutional network-based deep learning framework for predicting kmer characteristic ionic currents from corresponding chemical structures. We show such a framework can generalize the chemical information of the 5-methyl group from thymine to cytosine by correctly predicting 5-methylcytosine-containing DNA 6mers, thus shedding light on the de novo detection of nucleotide modifications.
Source: Nature Communications
Authors: Hongxu Ding, Ioannis Anastopoulos, Andrew D. Bailey, Joshua Stuart, Benedict Paten
Institution: University of California, Santa Cruz
Language: English
Subfield: Biomedical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $5,560
Awards: G1901922422, G2346335489, G2444277551, G2549908489, G2630888106, Enabling Comparative Pangenomics, G3980831455, Unbiased analysis of genomic correlates of gene expression in health and disease, G5524504805, UC Santa Cruz Training Program In Genomic Sciences, A Unified Nanopore Platform for Direct Sequencing of Individual Full Length RNA Strands Bearing Modified Nucleotides, GENCODE: comprehensive genome annotation for human and mouse, Comprehensive, flexible and FAIR Tools for the HuBMAP HIVE, Center for Big Data in Translational Genomics, The construction and utility of reference pan-genome graphs, GENCODE: comprehensive gene annotation for human and mouse, The Human Pangenome Reference Consortium Coordination Center
OpenAlex ID: W3213894656