Search

Characterizing differences in biological sequences between two conditions using high-throughput sequencing data is a prevalent problem wherein we seek to (i) quantify how sequence abundances change between conditions, and (ii) build predictive models to estimate such differences for unobserved sequences. A key shortcoming of current approaches is their extremely limited ability to share information across related but non-identical reads. Consequently, they cannot make effective use of sequencing data, nor can they be directly applied in many settings of interest. We introducemodel-based enrichment(MBE) to overcome this shortcoming. MBE is based on sound theoretical principles, is easy to implement, and can trivially make use of advances in modernday machine learning classification architectures or related innovations. We extensively evaluate MBE empirically, both in simulation and on real data. Overall, we find that our new approach improves accuracy compared to current ways of performing such differential analyses.

Adeno-associated viruses (AAVs) hold tremendous promise as delivery vectors for clinical gene therapy, but they need improvement. AAVs with enhanced properties, such as more efficient and/or cell-type specific infection, can be engineered by creating a large, diverse starting library and screening for desired phenotypes, in some cases iteratively. Although this approach has succeeded in numerous specific cases, such as infecting cell types from the brain to the lung, the starting libraries often contain a high proportion of variants unable to assemble or package their genomes, a general prerequisite for engineering any gene delivery goal. Herein, we develop and showcase a machine learning (ML)-based method for systematically designing more effective starting libraries — ones that have broadly good packaging capabilities while being as diverse as possible. Such carefully designed but general libraries stand to significantly increase the chance of success in engineering any property of interest. Furthermore, we use this approach to design a clinically-relevant AAV peptide insertion library that achieves 5-fold higher packaging fitness than the state-of-the-art library, with negligible reduction in diversity. We demonstrate the general utility of this designed library on a downstream task to which our approach was agnostic: infection of primary human brain tissue. The ML-designed library had approximately 10-fold more successful variants than the current state-of-the-art library. Not only should our new library serve useful for any number of other engineering goals, but our library design approach itself can also be applied to other types of libraries for AAV and beyond.

MotivationInferring 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.ResultsWe 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 thank-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.AvailabilityTensorFlow 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/).Contactseq2species-interest@google.comSupplementary informationSupplementary data are available in a separate document.