Rxivist logo

An automated framework for efficiently designing deep convolutional neural networks in genomics

By Zijun Zhang, Christopher Y. Park, Chandra L Theesfeld, Olga G Troyanskaya

Posted 19 Aug 2020
bioRxiv DOI: 10.1101/2020.08.18.251561

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. ### Competing Interest Statement The authors have declared no competing interest.

Download data

  • Downloaded 1,744 times
  • Download rankings, all-time:
    • Site-wide: 12,858
    • In bioinformatics: 1,414
  • Year to date:
    • Site-wide: 31,804
  • Since beginning of last month:
    • Site-wide: 9,121

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide