Applications of machine learning tools for ultra-sensitive detection of lipoarabinomannan with plasmonic grating biosensors in clinical samples of tuberculosis.

BACKGROUND: Tuberculosis is one of the top ten causes of death globally and the leading cause of death from a single infectious agent. Eradicating the Tuberculosis epidemic by 2030 is one of the top United Nations Sustainable Development Goals. Early diagnosis is essential to achieving this goal because it improves individual prognosis and reduces transmission rates of asymptomatic infected. We aim to support this goal by developing rapid and sensitive diagnostics using machine learning algorithms to minimize the need for expert intervention. METHODS AND FINDINGS: A single molecule fluorescence immunosorbent assay was used to detect Tuberculosis biomarker lipoarabinomannan from a set of twenty clinical patient samples and a control set of spiked human urine. Tuberculosis status was separately confirmed by GeneXpert MTB/RIF and cell culture. Two machine learning algorithms, an automatic and a semiautomatic model, were developed and trained by the calibrated lipoarabinomannan titration assay data and then tested against the ground truth patient data. The semiautomatic model differed from the automatic model by an expert review step in the former, which calibrated the lower threshold to determine single molecules from background noise. The semiautomatic model was found to provide 88.89% clinical sensitivity, while the automatic model resulted in 77.78% clinical sensitivity. CONCLUSIONS: The semiautomatic model outperformed the automatic model in clinical sensitivity as a result of the expert intervention applied during calibration and both models vastly outperformed manual expert counting in terms of time-to-detection and completion of analysis. Meanwhile, the clinical sensitivity of the automatic model could be improved significantly with a larger training dataset. In short, semiautomatic, and automatic Gaussian Mixture Models have a place in supporting rapid detection of Tuberculosis in resource-limited settings without sacrificing clinical sensitivity.

Sensitivity and performance of three novel quantitative assays of SARS-CoV-2 nucleoprotein in blood.

To assess if SARS-CoV-2 (COVID-19) systemic disease can be determined by available nucleoprotein assays, we compared the performance of three commercial SARS-CoV-2 nucleoprotein (N) assays in plasma. A total of 272 plasma samples collected in the period November-December 2021 were analyzed by the methods Simoa SARS CoV-2 N Protein Advantage Kit [Quanterix Simoa], Solsten SARS-CoV-2 Antigen enzyme immunosorbent assay (ELISA) [Solsten ELISA], and Elecsys SARS-CoV-2 Antigen electrochemiluminescence immunoassay [Elecsys ECLIA]. Additionally, a dilution series of inactivated virus culture was analyzed by the three assays. The SARS CoV-2 PCR-status was not known for the patients. Linear correlation in the pairwise correlation between assays as well as linearity of dilution series of inactivated virus culture was estimated by Spearman score. Sensitivity and specificity were estimated by pairwise comparison. The three assays showed poor agreement on patient samples with regards to concentration. Performance on virus culture was excellent but with different level of detection (LOD). Positive vs negative results show comparable sensitivity and specificity of Quanterix Simoa and Solsten ELISA, with a higher LOD in Elecsys ECLIA and thus lower sensitivity and high specificity. N by all tested assays can be used as a marker for systemic COVID-19 disease.

FLU-LISA (fluorescence-linked immunosorbent assay): high-throughput antibody profiling using antigen microarrays.

Vaccination and natural infection both elicit potent humoral responses that provide protection from subsequent infections. The immune history of an individual following such exposures is in part encoded by antibodies. While there are multiple immunoassays for measuring antibody responses, the majority of these methods measure responses to a single antigen. A commonly used method for measuring antibody responses is ELISA-a semiquantitative assay that is simple to perform in research and clinical settings. Here, we present FLU-LISA (fluorescence-linked immunosorbent assay)-a novel antigen microarray-based assay for rapid high-throughput antibody profiling. The assay can be used for profiling immunoglobulin (Ig) G, IgA and IgM responses to multiple antigens simultaneously, requiring minimal amounts of sample and antigens. Using several influenza and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) antigen microarrays, we demonstrated the specificity and sensitivity of our novel assay and compared it with the traditional ELISA, using samples from mice, chickens and humans. We also showed that our assay can be readily used with dried blood spots, which can be collected from humans and wild birds. FLU-LISA can be readily used to profile hundreds of samples against dozens of antigens in a single day, and therefore offers an attractive alternative to the traditional ELISA.

Digital and Analog Detection of SARS-CoV-2 Nucleocapsid Protein via an Upconversion-Linked Immunosorbent Assay.

The COVID-19 crisis requires fast and highly sensitive tests for the early stage detection of the SARS-CoV-2 virus. For detecting the nucleocapsid protein (N protein), the most abundant viral antigen, we have employed upconversion nanoparticles that emit short-wavelength light under near-infrared excitation (976 nm). The anti-Stokes emission avoids autofluorescence and light scattering and thus enables measurements without optical background interference. The sandwich upconversion-linked immunosorbent assay (ULISA) can be operated both in a conventional analog mode and in a digital mode based on counting individual immune complexes. We have investigated how different antibody combinations affect the detection of the wildtype N protein and the detection of SARS-CoV-2 (alpha variant) in lysed culture fluid via the N protein. The ULISA yielded a limit of detection (LOD) of 1.3 pg/mL (27 fM) for N protein detection independent of the analog or digital readout, which is approximately 3 orders of magnitude more sensitive than conventional enzyme-linked immunosorbent assays or commercial lateral flow assays for home testing. In the case of SARS-CoV-2, the digital ULISA additionally improved the LOD by a factor of 10 compared to the analog readout.

Organic Light-Emitting Diode Based Fluorescence-Linked Immunosorbent Assay for SARS-CoV-2 Antibody Detection.

Immunodiagnostics have been widely used in the detection of disease biomarkers. The conventional immunological tests in central laboratories require expensive equipment and, for non-specialists, the tests are technically demanding and time-consuming, which has prevented their use by the public. Thus, point-of-care tests (POCT), such as lateral flow immunoassays, are being, or have been, developed as more convenient and low-cost methods for immunodiagnostics. However, the sensitivity of such tests is often a concern. Here, a fluorescence-linked immunosorbent assay (FLISA) using organic light-emitting diodes (OLEDs) as excitation light sources was investigated as a way forward for the development of compact and sensitive POCTs. Phycoerythrin (PE) was selected as the fluorescent dye, and OLEDs were designed with different emission spectra. The leakage light of different OLEDs for exciting PE was then investigated to reduce the background noise and improve the sensitivity of the system. Finally, as proof-of-principle that OLED-based technology can be successfully further developed for POCT, antibodies to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in human serum was detected by OLED-FLISA.