Integrated smart analytics of nucleic acid amplification tests via paper microfluidics and deep learning in cloud computing

Pandemics such as COVID-19 have exposed global inequalities in essential health care. Here, we proposed a novel analytics of nucleic acid amplification tests (NAATs) by combining paper microfluidics with deep learning and cloud computing. Real-time amplifications of synthesized SARS-CoV-2 RNA templates were performed in paper devices. Information pertained to on-chip reactions in time-series format were transmitted to cloud server on which deep learning (DL) models were preloaded for data analysis. DL models enable prediction of NAAT results using partly gathered real-time fluorescence data. Using information provided by the G-channel, accurate prediction can be made as early as 9 min, a 78% reduction from the conventional 40 min mark. Reaction dynamics hidden in amplification curves were effectively leveraged. Positive and negative samples can be unbiasedly and automatically distinguished. Practical utility of the approach was validated by cross-platform study using clinical datasets. Predicted clinical accuracy, sensitivity and specificity were 98.6%, 97.6% and 99.1%. Not only the approach reduced the need for the use of bulky apparatus, but also provided intelligent, distributable and robotic insights for NAAT analysis. It set a novel paradigm for analyzing NAATs, and can be combined with the most cutting-edge technologies in fields of biosensor, artificial intelligence and cloud computing to facilitate fundamental and clinical research.Copyright © 2023 Elsevier Ltd

Paper microfluidics with deep learning for portable intelligent nucleic acid amplification tests.

During global outbreaks such as COVID-19, regular nucleic acid amplification tests (NAATs) have posed unprecedented burden on hospital resources. Data of traditional NAATs are manually analyzed post assay. Integration of artificial intelligence (AI) with on-chip assays give rise to novel analytical platforms via data-driven models. Here, we combined paper microfluidics, portable optoelectronic system with deep learning for SARS-CoV-2 detection. The system was quite streamlined with low power dissipation. Pixel by pixel signals reflecting amplification of synthesized SARS-CoV-2 templates (containing ORF1ab, N and E genes) can be real-time processed. Then, the data were synchronously fed to the neural networks for early prediction analysis. Instead of the quantification cycle (Cq) based analytics, reaction dynamics hidden at the early stage of amplification curve were utilized by neural networks for predicting subsequent data. Qualitative and quantitative analysis of the 40-cycle NAATs can be achieved at the end of 22nd cycle, reducing time cost by 45%. In particular, the attention mechanism based deep learning model trained by microfluidics-generated data can be seamlessly adapted to multiple clinical datasets including readouts of SARS-CoV-2 detection. Accuracy, sensitivity and specificity of the prediction can reach up to 98.1%, 97.6% and 98.6%, respectively. The approach can be compatible with the most advanced sensing technologies and AI algorithms to inspire ample innovations in fields of fundamental research and clinical settings.

ADAPTABLE ENGINEERING OF CELLULOSE-BASED VERTICAL FLOW ASSAYS FOR RAPID DIAGNOSTICS - THE CASE OF COVID-19

Paper microfluidics has had a rich history in medical diagnostics owing to their portability, low-cost and capacity for mass manufacture. While nitrocellulose has widespread use in commercial paper-based assays, shortages can become a bottleneck for deployment. Here, we seek to overcome this limitation by enabling swift and efficient production of cellulose-based paper assays with minimal substrate processing via protein engineering. We demonstrate good clinical and lab-based performance for both serological and antigen rapid tests and their compatibility with roll-to-roll mass manufacturing, which validates our proposed workflow for commercialization. © 2021 MicroTAS 2021 - 25th International Conference on Miniaturized Systems for Chemistry and Life Sciences. All rights reserved.

Recombinase polymerase amplification integrated with microfluidics for nucleic acid testing at point of care.

Nucleic acid testing (NAT) implemented on a portable, miniaturized, and integrated device with rapid and sensitive results readout is highly demanded for pathogen detection or genetic screening at resource-limited settings, especially after the outbreak of coronavirus disease 2019 (COVID-19). The integration of recombinase polymerase amplification (RPA) with emerging microfluidics, classified by paper-based microfluidics and chip-based microfluidics, shows great potential to perform laboratory independent NAT assays at point of care with minimal labor, time and energy consumption. This review summarizes the state-of-the-art of RPA integrated with paper-based microfluidics and chip-based microfluidics, and discusses their pros and cons. Finally, existing challenges and possible ways for optimization of microfluidics-based RPA are proposed.

Direct capture and smartphone quantification of airborne SARS-CoV-2 on a paper microfluidic chip.

SARS, a new type of respiratory disease caused by SARS-CoV, was identified in 2003 with significant levels of morbidity and mortality. The recent pandemic of COVID-19, caused by SARS-CoV-2, has generated even greater extents of morbidity and mortality across the entire world. Both SARS-CoV and SARS-CoV-2 spreads through the air in the form of droplets and potentially smaller droplets (aerosols) via exhaling, coughing, and sneezing. Direct detection from such airborne droplets would be ideal for protecting general public from potential exposure before they infect individuals. However, the number of viruses in such droplets and aerosols is too low to be detected directly. A separate air sampler and enough collection time (several hours) are necessary to capture a sufficient number of viruses. In this work, we have demonstrated the direct capture of the airborne droplets on the paper microfluidic chip without the need for any other equipment. 10% human saliva samples were spiked with the known concentration of SARS-CoV-2 and sprayed to generate liquid droplets and aerosols into the air. Antibody-conjugated submicron particle suspension is then added to the paper channel, and a smartphone-based fluorescence microscope isolated and counted the immunoagglutinated particles on the paper chip. The total capture-to-assay time was <30 min, compared to several hours with the other methods. In this manner, SARS-CoV-2 could be detected directly from the air in a handheld and low-cost manner, contributing to slowing the spread of SARS-CoV-2. We can presumably adapt this technology to a wide range of other respiratory viruses.

Point-of-Care Toolkit for Multiplex Molecular Diagnosis of SARS-CoV-2 and Influenza A and B Viruses.

Severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2) is still spreading around the globe causing immense public health and socioeconomic problems. As the infection can progress with mild symptoms that can be misinterpreted as the flu, self-testing methods that can positively identify SARS-CoV-2 are needed to effectively track and prevent the transmission of the virus. In this work, we report a point-of-care toolkit for multiplex molecular diagnosis of SARS-CoV-2 and influenza A and B viruses in saliva samples. Our assay is physically programmed to run a sequence of chemical reactions on a paper substrate and internally generate heat to drive these reactions for an autonomous extraction, purification, and amplification of the viral RNA. Using our assay, we could reliably detect SARS-CoV-2 and influenza viruses at concentrations as low as 50 copies/µL visually from a colorimetric analysis. The capability to autonomously perform a traditionally labor-intensive genetic assay on a disposable platform will enable frequent, on-demand self-testing, a critical need to track and contain this and future outbreaks.