Machine Learning-Based Fragment Selection Improves the Performance of Qualitative PRM Assays.

Targeted mass spectrometry-based platforms have become a valuable tool for the sensitive and specific detection of protein biomarkers in clinical and research settings. Traditionally, developing a targeted assay for peptide quantification has involved manually preselecting several fragment ions and establishing a limit of detection (LOD) and a lower limit of quantitation (LLOQ) for confident detection of the target. Established thresholds such as LOD and LLOQ, however, inherently sacrifice sensitivity to afford specificity. Here, we demonstrate that machine learning can be applied to qualitative PRM assays to discriminate positive from negative samples more effectively than a traditional approach utilizing conventional methods. To demonstrate the utility of this method, we trained an ensemble machine learning model using 282 SARS-CoV-2 positive and 994 SARS-CoV-2 negative nasopharyngeal swabs (NP swab) analyzed using a targeted PRM method. This model was then validated using an independent set of 200 positive and 150 negative samples and achieved a sensitivity of 92% relative to results obtained by RT-PCR, which was superior to a traditional approach that resulted in 86.5% sensitivity when analyzing the same data. These results demonstrate that machine learning can be applied to qualitative PRM assays and results in superior performance relative to traditional methods.

CSF free light chain identification of demyelinating disease: comparison with oligoclonal banding and other CSF indexes.

BACKGROUND: Cerebrospinal fluid (CSF) used in immunoglobulin gamma (IgG) index testing and oligoclonal bands (OCBs) are common laboratory tests used in the diagnosis of multiple sclerosis. The measurement of CSF free light chains (FLC) could pose as an alternative to the labor-intensive isoelectric-focusing (IEF) gels used for OCBs. METHODS: A total of 325 residual paired CSF and serum specimens were obtained after physician-ordered OCB IEF testing. CSF kappa (cKFLC) and lambda FLC (cLFLC), albumin and total IgG were measured. Calculations were performed based on combinations of analytes: CSF sum of kappa and lambda ([cKFLC+cLFLC]), kappa-index (K-index) ([cKFLC/sKFLC]/[CSF albumin/serum albumin]), kappa intrathecal fraction (KFLCIF) {([cKFLC/sKFLC]-[0.9358×CSF albumin/serum albumin]^[0.6687×sKFLC]/cKFLC)} and IgG-index ([CSF IgG/CSF albumin]/[serum IgG/serum albumin]). RESULTS: Patients were categorized as: demyelination (n=67), autoimmunity (n=53), non-inflammatory (n=50), inflammation (n=38), degeneration (n=28), peripheral neuropathy (n=24), infection (n=13), cancer (n=11), neuromyelitis optica (n=10) and others (n=31). cKFLC measurement used alone at a cutoff of 0.0611 mg/dL showed >90% agreement to OCBs, similar or better performance than all other calculations, reducing the number of analytes and variables. When cases of demyelinating disease were reviewed, cKFLC measurements showed 86% clinical sensitivity/77% specificity. CONCLUSIONS: cKFLC alone demonstrates comparable performance to OCBs along with increased sensitivity for demyelinating diseases. Replacing OCB with cKFLC would alleviate the need for serum and CSF IgG and albumin and calculated conversions. cKFLC can overcome challenges associated with performance, interpretation, and cost of traditional OCBs, reducing costs and maintaining sensitivity and specificity supporting MS diagnosis.

Screening Method for M-Proteins in Serum Using Nanobody Enrichment Coupled to MALDI-TOF Mass Spectrometry.

BACKGROUND: Current recommendations for screening for monoclonal gammopathies include serum protein electrophoresis (PEL), imunofixation electrophoresis (IFE), and free light chain (FLC) ratios to identify or rule out an M-protein. The aim of this study was to examine the feasibility of an assay based on immunoenrichment and MALDI-TOF-MS (MASS-SCREEN) to qualitatively screen for M-proteins. METHODS: Serum from 556 patients previously screened for M-proteins by PEL and IFE were immunopurified using a κ/λ-specific nanobody bead mixture. Following purification, light chains (LC) were released from their heavy chains by reduction. MALDI-TOF analysis was performed and the mass-to-charge LC distributions were visually examined for the presence of an M-protein by both unblinded and blinded analysts. RESULTS: In unblinded analysis, MASS-SCREEN detected 100% of the PEL-positive samples with an analytical sensitivity and specificity of 96% and 81% using IFE positivity as the standard. In a blinded analysis using 6 different laboratory personnel, consensus was reached in 92% of the samples. Overall analytical sensitivity and specificity were reduced to 92% and 80%, respectively. FLC ratios were found to be abnormal in 28% of MASS-SCREEN-negative samples, suggesting FLC measurements need to be considered in screening. CONCLUSIONS: MASS-SCREEN could replace PEL in a panel that would include FLC measurements. Further studies and method development should be performed to validate the clinical sensitivity and specificity and to determine if this panel will suffice as a general screen for monoclonal proteins.

A mass spectrometry-based targeted assay for detection of SARS-CoV-2 antigen from clinical specimens.

BACKGROUND: The COVID-19 pandemic caused by severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2) has overwhelmed health systems worldwide and highlighted limitations of diagnostic testing. Several types of diagnostic tests including RT-PCR-based assays and antigen detection by lateral flow assays, each with their own strengths and weaknesses, have been developed and deployed in a short time. METHODS: Here, we describe an immunoaffinity purification approach followed a by high resolution mass spectrometry-based targeted qualitative assay capable of detecting SARS-CoV-2 viral antigen from nasopharyngeal swab samples. Based on our discovery experiments using purified virus, recombinant viral protein and nasopharyngeal swab samples from COVID-19 positive patients, nucleocapsid protein was selected as a target antigen. We then developed an automated antibody capture-based workflow coupled to targeted high-field asymmetric waveform ion mobility spectrometry (FAIMS) - parallel reaction monitoring (PRM) assay on an Orbitrap Exploris 480 mass spectrometer. An ensemble machine learning-based model for determining COVID-19 positive samples was developed using fragment ion intensities from the PRM data. FINDINGS: The optimized targeted assay, which was used to analyze 88 positive and 88 negative nasopharyngeal swab samples for validation, resulted in 98% (95% CI = 0.922-0.997) (86/88) sensitivity and 100% (95% CI = 0.958-1.000) (88/88) specificity using RT-PCR-based molecular testing as the reference method. INTERPRETATION: Our results demonstrate that direct detection of infectious agents from clinical samples by tandem mass spectrometry-based assays have potential to be deployed as diagnostic assays in clinical laboratories, which has hitherto been limited to analysis of pure microbial cultures. FUNDING: This study was supported by DBT/Wellcome Trust India Alliance Margdarshi Fellowship grant IA/M/15/1/502023 awarded to AP and the generosity of Eric and Wendy Schmidt.