RNAdegformer: accurate prediction of mRNA degradation at nucleotide resolution with deep learning.

Messenger RNA-based therapeutics have shown tremendous potential, as demonstrated by the rapid development of messenger RNA based vaccines for COVID-19. Nevertheless, distribution of mRNA vaccines worldwide has been hampered by mRNA's inherent thermal instability due to in-line hydrolysis, a chemical degradation reaction. Therefore, predicting and understanding RNA degradation is a crucial and urgent task. Here we present RNAdegformer, an effective and interpretable model architecture that excels in predicting RNA degradation. RNAdegformer processes RNA sequences with self-attention and convolutions, two deep learning techniques that have proved dominant in the fields of computer vision and natural language processing, while utilizing biophysical features of RNA. We demonstrate that RNAdegformer outperforms previous best methods at predicting degradation properties at nucleotide resolution for COVID-19 mRNA vaccines. RNAdegformer predictions also exhibit improved correlation with RNA in vitro half-life compared with previous best methods. Additionally, we showcase how direct visualization of self-attention maps assists informed decision-making. Further, our model reveals important features in determining mRNA degradation rates via leave-one-feature-out analysis.

A peek in the micro-sized world: a review of design principles, engineering tools, and applications of engineered microbial community.

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.

Nucleic Transformer: Classifying DNA Sequences with Self-Attention and Convolutions.

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 the classification of DNA sequences. The Nucleic Transformer employs self-attention and convolutions on nucleic acid sequences, leveraging two prominent deep learning strategies commonly used in computer vision and natural language analysis. We demonstrate that the Nucleic Transformer can be trained without much domain knowledge to achieve high performance in Escherichia coli promoter classification, viral genome identification, enhancer classification, and chromatin profile predictions.

FIDELITY: A quality control system for droplet microfluidics.

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.