Greene, W. | Search bioRxiv

bioRxiv2022

STAMP-Based Digital CRISPR-Cas13a (STAMP-dCRISPR) for Amplification-Free Quantification of HIV-1 Plasma Viral Load

The development of new nucleic acid techniques to quantify HIV RNA in plasma is critical for identifying the disease progression and monitoring the effectiveness of antiretroviral therapy. While RT-qPCR has been the gold standard for HIV viral load quantification, digital assays could provide an alternative calibration-free absolute quantification method. Here, we report the development of a self-digitalization through automated membrane-based partitioning (STAMP) technique to digitalize the CRISPR-Cas13 assay (dCRISPR) for amplification-free and absolute quantification of HIV-1 viral RNAs. The analytical performances of STAMP-dCRISPR were evaluated with synthetic HIV-1 RNA, and it was found samples spanning 4 orders of dynamic range between 100 aM to 1 pM can be quantified as fast as 30 min. We also examined the overall assay from RNA extraction to STAMP-dCRISPR quantification with spiked plasma samples. The overall assay showed a resolution of 42 aM at a 90% confidence level. Finally, a total of 20 clinical plasma samples from patients were evaluated with STAMP-dCRISPR. The obtained results agreed well with the RT-qPCR. Our result demonstrates a new type of easy-to-use, scalable, and highly specific digital platform that would offer a simple and accessible platform for amplification-free quantification of viral RNAs, which could be exploited for the quantitative determination of viral load for an array of infectious diseases.

bioengineering↗

bioRxiv2021

Accurate Virus Identification with Interpretable Raman Signatures by Machine Learning

Rapid identification of newly emerging or circulating viruses is an important first step toward managing the public health response to potential outbreaks. A portable virus capture device coupled with label-free Raman Spectroscopy holds the promise of fast detection by rapidly obtaining the Raman signature of a virus followed by a machine learning approach applied to recognize the virus based on its Raman spectrum. In this paper, we present a machine learning analysis on Raman spectra of human and avian viruses. A Convolutional Neural Network (CNN) classifier specifically designed for spectral data achieves very high accuracy for a variety of virus type or subtype identification tasks. In particular, it achieves 99% accuracy for classifying influenza virus type A vs. type B, 96% accuracy for classifying four subtypes of influenza A, 95% accuracy for differentiating enveloped and non-enveloped viruses, and 99% for differentiating avian coronavirus (infectious bronchitis virus, IBV) from other avian viruses. Furthermore, interpretation of neural net responses in the trained CNN model using a full-gradient algorithm highlights Raman spectral ranges that are most important to virus identification. By correlating ML-selected salient Raman ranges with the signature ranges of known biomolecules and chemical functional groups (e.g. amide, amino acid, carboxylic acid) we verify that our ML model effectively recognizes the Raman signatures of proteins, lipids and other vital functional groups present in different viruses and uses a weighted combination of these signatures to identify viruses. The accurate and interpretable machine learning model developed for Raman virus identification presents promising potential in a real-time virus detection system. Significance StatementA portable micro-fluidic platform for virus capture promises rapid enrichment and label-free optical identification of viruses by Raman spectroscopy. A large Raman dataset collected on a variety of viruses enables the training of machine learning (ML) models capable of highly accurate and sensitive virus identification. The trained ML models can then be integrated with the portable device to provide real-time virus detection and identification capability. We validate this conceptual framework by presenting highly accurate virus type and subtype identification results using a convolutional neural network to classify Raman spectra of viruses.

biophysics↗