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.
Highlights
The characteristic ionic currents of nucleotide kmers are commonly used in analyzing nanopore sequencing readouts
We show that the framework can generalize the 5-methyl group in thymine to cytosine, thereby accurately predicting the characteristic ionic currents of 5-methylcytosine (5mC)-containing DNA 6mers
Our deep learning framework consists of three groups of layers, including graph convolutional network (GCN) layers, convolutional neural network (CNN) layers, and one fully connected neural network (NN) layer
Summary
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-methylcytosinecontaining DNA 6mers, shedding light on the de novo detection of nucleotide modifications. Our previous hierarchical Dirichlet process approach could be structured to learn associations between kmers with specific shared properties, e.g., by numbers of pyrimidine bases, but could not generally learn relationships between arbitrary chemical similarities[2] Such approaches necessarily represent base modifications as distinct, unrelated characters. We show that the framework can generalize the 5-methyl group in thymine to cytosine, thereby accurately predicting the characteristic ionic currents of 5-methylcytosine (5mC)-containing DNA 6mers Such generalization of chemical information is a reason for optimism about the potential for de novo detection of nucleotide modifications
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.