Open AccessDeep neural networks identify sequence context features predictive of transcription factor binding
Author(s) -
An Zheng,
Michael Lamkin,
Hanqing Zhao,
Cynthia Wu,
Hao Su,
Melissa Gymrek
Publication year - 2021
Publication title -
nature machine intelligence
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 4.894
H-Index - 16
ISSN - 2522-5839
DOI - 10.1038/s42256-020-00282-y
Subject(s) - transcription factor , computational biology , sequence motif , dna binding site , convolutional neural network , chromatin , dna sequencing , transcription (linguistics) , biology , genetics , dna , motif (music) , computer science , artificial intelligence , gene , promoter , gene expression , linguistics , philosophy , physics , acoustics
Transcription factors (TFs) bind DNA by recognizing specific sequence motifs, typically of length 6-12bp. A motif can occur many thousands of times in the human genome, but only a subset of those sites are actually bound. Here we present a machine learning framework leveraging existing convolutional neural network architectures and model interpretation techniques to identify and interpret sequence context features most important for predicting whether a particular motif instance will be bound. We apply our framework to predict binding at motifs for 38 TFs in a lymphoblastoid cell line, score the importance of context sequences at base-pair resolution, and characterize context features most predictive of binding. We find that the choice of training data heavily influences classification accuracy and the relative importance of features such as open chromatin. Overall, our framework enables novel insights into features predictive of TF binding and is likely to inform future deep learning applications to interpret non-coding genetic variants.