Learning, visualizing and exploring 16S rRNA structure using an attention-based deep neural network

摘要

Recurrent neural networks with memory and attention mechanisms are widely used in natu ral language processing because they can capture short and long term sequential information for diverse tasks. We propose an integrated deep learning model for microbial DNAsequence data, which exploits convolutional neural networks, recurrent neural networks,and attention mechanisms to predict taxonomic classifications and sample-associated attributes, such as the relationship between the microbiome and host phenotype, on the read/sequence level. In this paper, we develop this novel deep learning approach and evaluateits application to amplicon sequences. We apply our approach to short DNA reads and fullsequences of 16S ribosomal RNA (rRNA) marker genes, which identify the heterogeneity ofa microbial community sample. We demonstrate that our implementation of a novel attention-based deep network architecture, Read2Pheno, achieves read-level phenotypicprediction. Training Read2Pheno models will encode sequences (reads) into dense, meaningful representations: learned embedded vectors output from the intermediate layer of thenetwork model, which can provide biological insight when visualized. The attention layer ofRead2Pheno models can also automatically identify nucleotide regions in reads/sequenceswhich are particularly informative for classification. As such, this novel approach can avoidpre/post-processing and manual interpretation required with conventional approaches tomicrobiome sequence classification. We further show, as proof-of-concept, that aggregatingread-level information can robustly predict microbial community properties, host phenotype,and taxonomic classification, with performance at least comparable to conventionalapproaches. An implementation of the attention-based deep learning network is available athttps://github.com/EESI/sequence_attention (a python package) and https://github.com/EESI/seq2att (a command line tool).