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

Convolutional neural networks (CNNs) have become a standard for analysis of biological sequences. Tuning of network architectures is essential for a 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 Automated Modelling for Biological Evidence-based Research (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. At present, deep learning models in genomics are manually tuned through trial and error, which is time consuming and imposes a barrier for biomedical researchers not trained in machine learning. The authors develop an automated framework to design and apply convolutional neural networks for genomic sequences.