MOTIVATION: Supervised deep learning is used to model the complex relationship between genomic sequence and regulatory function. Understanding how these models make predictions can provide biological insight into regulatory functions. Given the complexity of the sequence to regulatory function mapping (the cis-regulatory code), it has been suggested that the genome contains insufficient sequence variation to train models with suitable complexity. Data augmentation is a widely used approach to increase the data variation available for model training, however current data augmentation methods for genomic sequence data are limited. RESULTS: Inspired by the success of comparative genomics, we show that augmenting genomic sequences with evolutionarily related sequences from other species, which we term phylogenetic augmentation, improves the performance of deep learning models trained on regulatory genomic sequences to predict high-throughput functional assay measurements. Additionally, we show that phylogenetic augmentation can rescue model performance when the training set is down-sampled and permits deep learning on a real-world small dataset, demonstrating that this approach improves data efficiency. Overall, this data augmentation method represents a solution for improving model performance that is applicable to many supervised deep-learning problems in genomics. AVAILABILITY AND IMPLEMENTATION: The open-source GitHub repository agduncan94/phylogenetic_augmentation_paper includes the code for rerunning the analyses here and recreating the figures.

Current technologies for assessing the microbial load in food and water require cellular outgrowth to increase the cell count to a detectable level. This step therefore makes real-time assessment of microbial loads impossible. To circumvent this problem, we have developed a high-sensitivity, multiwavelength fluorescence detector and signal- collection and processing software. This detection system enables one to distinguish between abiotic matter, sporulated bacteria, vegetative bacteria, dead bacteria, and other biomaterials containing aromatic amino acids. Our detection limit is in the 10-100 cell/cm2range (or per cm3if bulk aqueous samples are used), and there is no sample contact. To supplement this detection system, we have developed a variety of ligands, including hemin derivatives, peptides, glycoconjugates, and siderophores, for cell capture to circumvent problems associated with antibodies. These materials are tethered to disposable surfaces (glass, plastics) in arrays for use in capturing biomaterials (e.g., live bacterial cells, dead cells, spores, and toxins); identification is based on which sector of an array it binds to. The detection system can serve as a reader for these coated materials, and variants have been tested for use in scanning food surfaces and food wash water.