Search

Droplet microfluidic systems have been widely deployed to interrogate biological and chemical systems. The major limitations of these systems are the relatively high error rates from critical droplet manipulation functions. To address these limitations, we describe the development of FIDELITY (Flotation and Interdigitated electrode forces on Droplets to Enable Lasting system IntegriTY), a highly sensitive and accurate size-based droplet bandpass filter that leverages the natural buoyancy of aqueous droplets and highly localized dielectrophoretic force generated by interdigitated electrode arrays. Droplet manipulation accuracies greater than 99% were achieved at a throughput of up to 100 droplets/s and separation of droplets that differed in diameter by only 6 μm was demonstrated. Last, the utility of FIDELITY was demonstrated in a droplet size quality control application and also in a droplet-based in vitro transcription/translation workflow. We anticipate FIDELITY to be integrated into a broad range of droplet microfluidic configurations to achieve exceptional operational accuracy.

Microbial communities drive diverse processes that impact nearly everything on this planet, from global biogeochemical cycles to human health. Harnessing the power of these microorganisms could provide solutions to many of the challenges that face society. However, naturally occurring microbial communities are not optimized for anthropogenic use. An emerging area of research is focusing on engineering synthetic microbial communities to carry out predefined functions. Microbial community engineers are applying design principles like top-down and bottom-up approaches to create synthetic microbial communities having a myriad of real-life applications in health care, disease prevention, and environmental remediation. Multiple genetic engineering tools and delivery approaches can be used to ‘knock-in' new gene functions into microbial communities. A systematic study of the microbial interactions, community assembling principles, and engineering tools are necessary for us to understand the microbial community and to better utilize them. Continued analysis and effort are required to further the current and potential applications of synthetic microbial communities.

Much work has been done to apply machine learning and deep learning to genomics tasks, but these applications usually require extensive domain knowledge and the resulting models provide very limited interpretability. Here we present the Nucleic Transformer, a conceptually simple but effective and interpretable model architecture that excels in a variety of DNA/RNA tasks. The Nucleic Transformer processes nucleic acid sequences with self-attention and convolutions, two deep learning techniques that have proved dominant in the fields of computer vision and natural language processing. We demonstrate that the Nucleic Transformer can be trained in both supervised and unsupervised fashion without much domain knowledge to achieve high performance with limited amounts of data in Escherichia coli promoter classification, viral genome identification, and degradation properties of COVID-19 mRNA vaccine candidates. Additionally, we showcase extraction of promoter motifs from learned attention and how direct visualization of self-attention maps assists informed decision making using deep learning models.