An automated framework for efficiently designing deep convolutional neural networks in genomics
Preprint
Abstract
Convolutional neural networks (CNNs) have become a standard for analysis of biological sequences. Tuning of network architectures is essential for CNN’s performance, yet it requires substantial knowledge of machine learning and commitment of time and effort. This process thus imposes a major barrier to broad and effective application of modern deep learning in genomics. Here, we present AMBER, a fully automated framework to efficiently design and apply CNNs for genomic sequences. AMBER designs optimal models for user-specified biological questions through the state-of-the-art Neural Architecture Search (NAS). We applied AMBER to the task of modelling genomic regulatory features and demonstrated that the predictions of the AMBER-designed model are significantly more accurate than the equivalent baseline non-NAS models and match or even exceed published expert-designed models. Interpretation of AMBER architecture search revealed its design principles of utilizing the full space of computational operations for accurately modelling genomic sequences. Furthermore, we illustrated the use of AMBER to accurately discover functional genomic variants in allele-specific binding and disease heritability enrichment. AMBER provides an efficient automated method for designing accurate deep learning models in genomics.Keywords
All Related Versions
- Published version: Nature Machine Intelligence, 3 (5), 392.
This publication has 32 references indexed in Scilit:
- Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learningNature Biotechnology, 2015
- A method to predict the impact of regulatory variants from DNA sequenceNature Genetics, 2015
- The Genotype-Tissue Expression (GTEx) projectNature Genetics, 2013
- Adipocyte expression of PU.1 transcription factor causes insulin resistance through upregulation of inflammatory cytokine gene expression and ROS productionAmerican Journal of Physiology-Endocrinology and Metabolism, 2012
- MEME-ChIP: motif analysis of large DNA datasetsBioinformatics, 2011
- Transcription factor PU.1 is expressed in white adipose and inhibits adipocyte differentiationAmerican Journal of Physiology-Cell Physiology, 2008
- JASPAR, the open access database of transcription factor-binding profiles: new content and tools in the 2008 updateNucleic Acids Research, 2007
- PLINK: A Tool Set for Whole-Genome Association and Population-Based Linkage AnalysesThe American Journal of Human Genetics, 2007
- Inactivation of PU.1 in adult mice leads to the development of myeloid leukemiaProceedings of the National Academy of Sciences, 2006
- Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning1992