PT - JOURNAL ARTICLE AU - Akosua Busia AU - George E. Dahl AU - Clara Fannjiang AU - David H. Alexander AU - Elizabeth Dorfman AU - Ryan Poplin AU - Cory Y. McLean AU - Pi-Chuan Chang AU - Mark DePristo TI - A deep learning approach to pattern recognition for short DNA sequences AID - 10.1101/353474 DP - 2019 Jan 01 TA - bioRxiv PG - 353474 4099 - http://biorxiv.org/content/early/2019/01/28/353474.short 4100 - http://biorxiv.org/content/early/2019/01/28/353474.full AB - Motivation Inferring properties of biological sequences--such as determining the species-of-origin of a DNA sequence or the function of an amino-acid sequence--is a core task in many bioinformatics applications. These tasks are often solved using string-matching to map query sequences to labeled database sequences or via Hidden Markov Model-like pattern matching. In the current work we describe and assess an deep learning approach which trains a deep neural network (DNN) to predict database-derived labels directly from query sequences.Results We demonstrate this DNN performs at state-of-the-art or above levels on a difficult, practically important problem: predicting species-of-origin from short reads of 16S ribosomal DNA. When trained on 16S sequences of over 13,000 distinct species, our DNN achieves read-level species classification accuracy within 2.0% of perfect memorization of training data, and produces more accurate genus-level assignments for reads from held-out species than k-mer, alignment, and taxonomic binning baselines. Moreover, our models exhibit greater robustness than these existing approaches to increasing noise in the query sequences. Finally, we show that these DNNs perform well on experimental 16S mock community dataset. Overall, our results constitute a first step towards our long-term goal of developing a general-purpose deep learning approach to predicting meaningful labels from short biological sequences.Availability TensorFlow training code is available through GitHub (https://github.com/tensorflow/models/tree/master/research). Data in TensorFlow TFRecord format is available on Google Cloud Storage (gs://brain-genomics-public/research/seq2species/).Contact seq2species-interest{at}google.comSupplementary information Supplementary data are available in a separate document.