Cross-species regulatory sequence activity prediction

PLoS Comput Biol. 2020 Jul 20;16(7):e1008050. doi: 10.1371/journal.pcbi.1008050. eCollection 2020 Jul.


Machine learning algorithms trained to predict the regulatory activity of nucleic acid sequences have revealed principles of gene regulation and guided genetic variation analysis. While the human genome has been extensively annotated and studied, model organisms have been less explored. Model organism genomes offer both additional training sequences and unique annotations describing tissue and cell states unavailable in humans. Here, we develop a strategy to train deep convolutional neural networks simultaneously on multiple genomes and apply it to learn sequence predictors for large compendia of human and mouse data. Training on both genomes improves gene expression prediction accuracy on held out and variant sequences. We further demonstrate a novel and powerful approach to apply mouse regulatory models to analyze human genetic variants associated with molecular phenotypes and disease. Together these techniques unleash thousands of non-human epigenetic and transcriptional profiles toward more effective investigation of how gene regulation affects human disease.

MeSH terms

  • Algorithms
  • Animals
  • Computational Biology
  • Databases, Genetic
  • Epigenomics
  • Gene Expression Regulation*
  • Genetic Variation*
  • Genome, Human
  • Genomics
  • Hepatocytes / metabolism
  • Humans
  • Machine Learning*
  • Mice
  • Models, Genetic
  • Models, Statistical
  • Mutation
  • Neural Networks, Computer
  • Quantitative Trait Loci
  • Sequence Analysis, DNA
  • Software
  • Species Specificity

Grant support

The author received no specific funding for this work.