Machine Learning-Assisted Real-Time Polymerase Chain Reaction and High-Resolution Melt Analysis for SARS-CoV-2 Variant Identification.

Since the declaration of COVID-19 as a pandemic in early 2020, multiple variants of the severe acute respiratory syndrome-related coronavirus (SARS-CoV-2) have been detected. The emergence of multiple variants has raised concerns due to their impact on public health. Therefore, it is crucial to distinguish between different viral variants. Here, we developed a machine learning web-based application for SARS-CoV-2 variant identification via duplex real-time polymerase chain reaction (PCR) coupled with high-resolution melt (qPCR-HRM) analysis. As a proof-of-concept, we investigated the platform's ability to identify the Alpha, Delta, and wild-type strains using two sets of primers. The duplex qPCR-HRM could identify the two variants reliably in as low as 100 copies/µL. Finally, the platform was validated with 167 nasopharyngeal swab samples, which gave a sensitivity of 95.2%. This work demonstrates the potential for use as automated, cost-effective, and large-scale viral variant surveillance.

Facile Coupling of Droplet Magnetofluidic-Enabled Automated Sample Preparation for Digital Nucleic Acid Amplification Testing and Analysis.

Digital nucleic acid amplification testing (dNAAT) and analysis techniques, such as digital polymerase chain reaction (PCR), have become useful clinical diagnostic tools. However, nucleic acid (NA) sample preparation preceding dNAAT is generally laborious and performed manually, thus creating the need for a simple sample preparation technique and a facile coupling strategy for dNAAT. Therefore, we demonstrate a simple workflow which automates magnetic bead-based extraction of NAs with a one-step transfer to dNAAT. Specifically, we leverage droplet magnetofluidics (DM) to automate the movement of magnetic beads between small volumes of reagents commonly employed for NA extraction and purification. Importantly, the buffer typically used to elute the NAs off the magnetic beads is replaced by a carefully selected PCR solution, enabling direct transfer from sample preparation to dNAAT. Moreover, we demonstrate the potential for multiplexing using a digital high-resolution melt (dHRM) after the digital PCR (dPCR). The utility of this workflow is demonstrated with duplexed detection of bacteria in a sample imitating a coinfection. We first purify the bacterial DNA into a PCR solution using our DM-based sample preparation. We then transfer the purified bacterial DNA to our microfluidic nanoarray to amplify 16S rRNA using dPCR and then perform dHRM to identify the two bacterial species.

Defining, distinguishing and detecting the contribution of heterogeneous methylation to cancer heterogeneity.

DNA methylation is a fundamental means of epigenetic gene regulation that occurs in virtually all cell types. In many higher organisms, including humans, it plays vital roles in cell differentiation and homeostatic maintenance of cell phenotype. The control of DNA methylation has traditionally been attributed to a highly coordinated, linear process, whose dysregulation has been associated with numerous pathologies including cancer, where it occurs early in, and even prior to, the development of neoplastic tissues. Recent experimental evidence has demonstrated that, contrary to prevailing paradigms, methylation patterns are actually maintained through inexact, dynamic processes. These processes normally result in minor stochastic differences between cells that accumulate with age. However, various factors, including cancer itself, can lead to substantial differences in intercellular methylation patterns, viz. methylation heterogeneity. Advancements in molecular biology techniques are just now beginning to allow insight into how this heterogeneity contributes to clonal evolution and overall cancer heterogeneity. In the current review, we begin by presenting a didactic overview of how the basal bimodal methylome is established and maintained. We then provide a synopsis of some of the factors that lead to the accrual of heterogeneous methylation and how this heterogeneity may lead to gene silencing and impact the development of cancerous phenotypes. Lastly, we highlight currently available methylation assessment techniques and discuss their suitability to the study of heterogeneous methylation.

Nanoarray Digital Polymerase Chain Reaction with High-Resolution Melt for Enabling Broad Bacteria Identification and Pheno-Molecular Antimicrobial Susceptibility Test.

Toward combating infectious diseases caused by pathogenic bacteria, there remains an unmet need for diagnostic tools that can broadly identify the causative bacteria and determine their antimicrobial susceptibilities from complex and even polymicrobial samples in a timely manner. To address this need, a microfluidic and machine-learning-based platform that performs broad bacteria identification (ID) and rapid yet reliable antimicrobial susceptibility testing (AST) is developed. Specifically, this platform builds on "pheno-molecular AST", a strategy that transforms nucleic acid amplification tests (NAATs) into phenotypic AST through quantitative detection of bacterial genomic replication, and utilizes digital polymerase chain reaction (PCR) and digital high-resolution melt (HRM) to quantify and identify bacterial DNA molecules. Bacterial species are identified using integrated experiment-machine learning algorithm via HRM profiles. Digital DNA quantification allows for rapid growth measurement that reflects susceptibility profiles of each bacterial species within only 30 min of antibiotic exposure. As a demonstration, multiple bacterial species and their susceptibility profiles in a spiked-in polymicrobial urine specimen were correctly identified with a total turnaround time of ∼4 h. With further development and clinical validation, this platform holds the potential for improving clinical diagnostics and enabling targeted antibiotic treatments.

Integrated Bacterial Identification and Antimicrobial Susceptibility Testing Using PCR and High-Resolution Melt.

Accurate and timely diagnostics are critical for managing bacterial infections. The current gold standard, culture-based diagnostics, can provide clinicians with comprehensive diagnostic information including bacterial identity and antimicrobial susceptibility, but they often require several days of turnaround time, which leads to compromised clinical outcome and promotes the spread of antibiotic resistance. Nucleic acid amplification tests such as PCR have significantly accelerated the detection of specific bacteria but generally lack the capacities for broad-based bacterial identification or antimicrobial susceptibility testing. Here, we report an integrated assay based on PCR and high-resolution melt (HRM) for rapid diagnosis for bacterial infections. In our assay, we measure bacterial growth in the presence or absence of certain antibiotics with real-time quantitative PCR or digital PCR to determine antimicrobial susceptibility. In addition, we use HRM and a machine learning algorithm to identify bacterial species based on melt-curve profiles of the 16S rRNA gene in an automated fashion. As a demonstration, we correctly identified the bacterial species and their antimicrobial susceptibility profiles for multiple unknown samples in blinded tests within ∼6.5 h.

DREAMing: a simple and ultrasensitive method for assessing intratumor epigenetic heterogeneity directly from liquid biopsies.

Many cancers comprise heterogeneous populations of cells at primary and metastatic sites throughout the body. The presence or emergence of distinct subclones with drug-resistant genetic and epigenetic phenotypes within these populations can greatly complicate therapeutic intervention. Liquid biopsies of peripheral blood from cancer patients have been suggested as an ideal means of sampling intratumor genetic and epigenetic heterogeneity for diagnostics, monitoring and therapeutic guidance. However, current molecular diagnostic and sequencing methods are not well suited to the routine assessment of epigenetic heterogeneity in difficult samples such as liquid biopsies that contain intrinsically low fractional concentrations of circulating tumor DNA (ctDNA) and rare epigenetic subclonal populations. Here we report an alternative approach, deemed DREAMing (Discrimination of Rare EpiAlleles by Melt), which uses semi-limiting dilution and precise melt curve analysis to distinguish and enumerate individual copies of epiallelic species at single-CpG-site resolution in fractions as low as 0.005%, providing facile and inexpensive ultrasensitive assessment of locus-specific epigenetic heterogeneity directly from liquid biopsies. The technique is demonstrated here for the evaluation of epigenetic heterogeneity at p14(ARF) and BRCA1 gene-promoter loci in liquid biopsies obtained from patients in association with non-small cell lung cancer (NSCLC) and myelodysplastic/myeloproliferative neoplasms (MDS/MPN), respectively.

Universal digital high-resolution melt: a novel approach to broad-based profiling of heterogeneous biological samples.

Comprehensive profiling of nucleic acids in genetically heterogeneous samples is important for clinical and basic research applications. Universal digital high-resolution melt (U-dHRM) is a new approach to broad-based PCR diagnostics and profiling technologies that can overcome issues of poor sensitivity due to contaminating nucleic acids and poor specificity due to primer or probe hybridization inaccuracies for single nucleotide variations. The U-dHRM approach uses broad-based primers or ligated adapter sequences to universally amplify all nucleic acid molecules in a heterogeneous sample, which have been partitioned, as in digital PCR. Extensive assay optimization enables direct sequence identification by algorithm-based matching of melt curve shape and Tm to a database of known sequence-specific melt curves. We show that single-molecule detection and single nucleotide sensitivity is possible. The feasibility and utility of U-dHRM is demonstrated through detection of bacteria associated with polymicrobial blood infection and microRNAs (miRNAs) associated with host response to infection. U-dHRM using broad-based 16S rRNA gene primers demonstrates universal single cell detection of bacterial pathogens, even in the presence of larger amounts of contaminating bacteria; U-dHRM using universally adapted Lethal-7 miRNAs in a heterogeneous mixture showcases the single copy sensitivity and single nucleotide specificity of this approach.

Rapid electrochemical detection of coronavirus SARS-CoV-2.

Coronavirus disease 2019 (COVID-19) is a highly contagious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Diagnosis of COVID-19 depends on quantitative reverse transcription PCR (qRT-PCR), which is time-consuming and requires expensive instrumentation. Here, we report an ultrasensitive electrochemical biosensor based on isothermal rolling circle amplification (RCA) for rapid detection of SARS-CoV-2. The assay involves the hybridization of the RCA amplicons with probes that were functionalized with redox active labels that are detectable by an electrochemical biosensor. The one-step sandwich hybridization assay could detect as low as 1 copy/µL of N and S genes, in less than 2 h. Sensor evaluation with 106 clinical samples, including 41 SARS-CoV-2 positive and 9 samples positive for other respiratory viruses, gave a 100% concordance result with qRT-PCR, with complete correlation between the biosensor current signals and quantitation cycle (Cq) values. In summary, this biosensor could be used as an on-site, real-time diagnostic test for COVID-19.

Leveraging locus-specific epigenetic heterogeneity to improve the performance of blood-based DNA methylation biomarkers.

BACKGROUND: Variation in intercellular methylation patterns can complicate the use of methylation biomarkers for clinical diagnostic applications such as blood-based cancer testing. Here, we describe development and validation of a methylation density binary classification method called EpiClass (available for download at https://github.com/Elnitskilab/EpiClass ) that can be used to predict and optimize the performance of methylation biomarkers, particularly in challenging, heterogeneous samples such as liquid biopsies. This approach is based upon leveraging statistical differences in single-molecule sample methylation density distributions to identify ideal thresholds for sample classification. RESULTS: We developed and tested the classifier using reduced representation bisulfite sequencing (RRBS) data derived from ovarian carcinoma tissue DNA and controls. We used these data to perform in silico simulations using methylation density profiles from individual epiallelic copies of ZNF154, a genomic locus known to be recurrently methylated in numerous cancer types. From these profiles, we predicted the performance of the classifier in liquid biopsies for the detection of epithelial ovarian carcinomas (EOC). In silico analysis indicated that EpiClass could be leveraged to better identify cancer-positive liquid biopsy samples by implementing precise thresholds with respect to methylation density profiles derived from circulating cell-free DNA (cfDNA) analysis. These predictions were confirmed experimentally using DREAMing to perform digital methylation density analysis on a cohort of low volume (1-ml) plasma samples obtained from 26 EOC-positive and 41 cancer-free women. EpiClass performance was then validated in an independent cohort of 24 plasma specimens, derived from a longitudinal study of 8 EOC-positive women, and 12 plasma specimens derived from 12 healthy women, respectively, attaining a sensitivity/specificity of 91.7%/100.0%. Direct comparison of CA-125 measurements with EpiClass demonstrated that EpiClass was able to better identify EOC-positive women than standard CA-125 assessment. Finally, we used independent whole genome bisulfite sequencing (WGBS) datasets to demonstrate that EpiClass can also identify other cancer types as well or better than alternative methylation-based classifiers. CONCLUSIONS: Our results indicate that assessment of intramolecular methylation density distributions calculated from cfDNA facilitates the use of methylation biomarkers for diagnostic applications. Furthermore, we demonstrated that EpiClass analysis of ZNF154 methylation was able to outperform CA-125 in the detection of etiologically diverse ovarian carcinomas, indicating broad utility of ZNF154 for use as a biomarker of ovarian cancer.

Integrated Bacterial Identification and Antimicrobial Susceptibility Testing for Polymicrobial Infections Using Digital PCR and Digital High-Resolution Melt in a Microfluidic Array Platform.

In diagnosing bacterial infection, rapid bacterial identification (ID) and antimicrobial susceptibility testing (AST) are critical to clinicians in order to provide an effective treatment in a timely manner. The gold standard, culture-based approach provides both ID and antimicrobial susceptibility but requires several days of turnaround time. Especially in polymicrobial infections, where there are more than one organisms interacting collectively that can complicate the treatment. Here, we demonstrate a rapid bacterial diagnostic approach that is capable of bacterial ID/AST in heterogeneous samples within less than 4 hours by using digital PCR (dPCR) and digital high-resolution melt via microfluidic devices. By utilizing dPCR, we are able to quantify amount of nucleic acid, which correlates to phenotypic responses of {\bf individual pathogens in a mixed sample and also shorten the required time of antibiotic exposure. In addition, we employ a machine learning algorithm to automatically identify bacterial species based on melt profiles of 16S rRNA gene.

Methylomic Analysis of Ovarian Cancers Identifies Tumor-Specific Alterations Readily Detectable in Early Precursor Lesions.

PURPOSE: High-grade serous ovarian carcinoma (HGSOC) typically remains undiagnosed until advanced stages when peritoneal dissemination has already occurred. Here, we sought to identify HGSOC-specific alterations in DNA methylation and assess their potential to provide sensitive and specific detection of HGSOC at its earliest stages. EXPERIMENTAL DESIGN: MethylationEPIC genome-wide methylation analysis was performed on a discovery cohort comprising 23 HGSOC, 37 non-HGSOC malignant, and 36 histologically unremarkable gynecologic tissue samples. The resulting data were processed using selective bioinformatic criteria to identify regions of high-confidence HGSOC-specific differential methylation. Quantitative methylation-specific real-time PCR (qMSP) assays were then developed for 8 of the top-performing regions and analytically validated in a cohort of 90 tissue samples. Lastly, qMSP assays were used to assess and compare methylation in 30 laser-capture microdissected (LCM) fallopian tube epithelia samples obtained from cancer-free and serous tubal intraepithelial carcinoma (STIC) positive women. RESULTS: Bioinformatic selection identified 91 regions of robust, HGSOC-specific hypermethylation, 23 of which exhibited an area under the receiver-operator curve (AUC) value ≥ 0.9 in the discovery cohort. Seven of 8 top-performing regions demonstrated AUC values between 0.838 and 0.968 when analytically validated by qMSP in a 90-patient cohort. A panel of the 3 top-performing genes (c17orf64, IRX2, and TUBB6) was able to perfectly discriminate HGSOC (AUC 1.0). Hypermethylation within these loci was found exclusively in LCM fallopian tube epithelia from women with STIC lesions, but not in cancer-free fallopian tubes. CONCLUSIONS: A panel of methylation biomarkers can be used to accurately identify HGSOC, even at precursor stages of the disease.

Microbial Typing by Machine Learned DNA Melt Signatures.

There is still an ongoing demand for a simple broad-spectrum molecular diagnostic assay for pathogenic bacteria. For this purpose, we developed a single-plex High Resolution Melt (HRM) assay that generates complex melt curves for bacterial identification. Using internal transcribed spacer (ITS) region as the phylogenetic marker for HRM, we observed complex melt curve signatures as compared to 16S rDNA amplicons with enhanced interspecies discrimination. We also developed a novel Naïve Bayes curve classification algorithm with statistical interpretation and achieved 95% accuracy in differentiating 89 bacterial species in our library using leave-one-out cross-validation. Pilot clinical validation of our method correctly identified the etiologic organisms at the species-level in 59 culture-positive mono-bacterial blood culture samples with 90% accuracy. Our findings suggest that broad bacterial sequences may be simply, reliably and automatically profiled by ITS HRM assay for clinical adoption.

Nested Machine Learning Facilitates Increased Sequence Content for Large-Scale Automated High Resolution Melt Genotyping.

High Resolution Melt (HRM) is a versatile and rapid post-PCR DNA analysis technique primarily used to differentiate sequence variants among only a few short amplicons. We recently developed a one-vs-one support vector machine algorithm (OVO SVM) that enables the use of HRM for identifying numerous short amplicon sequences automatically and reliably. Herein, we set out to maximize the discriminating power of HRM + SVM for a single genetic locus by testing longer amplicons harboring significantly more sequence information. Using universal primers that amplify the hypervariable bacterial 16 S rRNA gene as a model system, we found that long amplicons yield more complex HRM curve shapes. We developed a novel nested OVO SVM approach to take advantage of this feature and achieved 100% accuracy in the identification of 37 clinically relevant bacteria in Leave-One-Out-Cross-Validation. A subset of organisms were independently tested. Those from pure culture were identified with high accuracy, while those tested directly from clinical blood bottles displayed more technical variability and reduced accuracy. Our findings demonstrate that long sequences can be accurately and automatically profiled by HRM with a novel nested SVM approach and suggest that clinical sample testing is feasible with further optimization.

Droplet Array Platform for High-Resolution Melt Analysis of DNA Methylation Density.

High-resolution melting (HRM) has garnered significant interest as an analytical technique for a number of applications, including DNA methylation detection, due to its inherent sensitivity and robustness. In this study, we describe a miniaturized assay platform for quantitative methylation density analysis using a microfluidic droplet array cartridge. We demonstrate that the DNA methylation level of the RASSF1A promoter can be directly analyzed using HRM. PCR products were generated by amplifying bisulfite-treated DNA with varying CpG densities using CpG island-flanking primer sets. Subsequent HRM analysis on the miniaturized droplet platform shows distinct melting curve profiles associated with methylation levels, which was verified using a conventional benchtop PCR-HRM system. The characteristic melting temperature (Tm) of the PCR products was used to directly quantify the respective levels of DNA methylation density. Our approach provides a key advantage over current gold standard methods such as methylation-specific PCR (MSP), which are incapable of providing specific information regarding the overall methylation density of the target genes. The miniaturized platform establishes a practical approach to methylation density profiling from multiple DNA samples with a potential application in point-of-care diagnostics.

Trainable high resolution melt curve machine learning classifier for large-scale reliable genotyping of sequence variants.

High resolution melt (HRM) is gaining considerable popularity as a simple and robust method for genotyping sequence variants. However, accurate genotyping of an unknown sample for which a large number of possible variants may exist will require an automated HRM curve identification method capable of comparing unknowns against a large cohort of known sequence variants. Herein, we describe a new method for automated HRM curve classification based on machine learning methods and learned tolerance for reaction condition deviations. We tested this method in silico through multiple cross-validations using curves generated from 9 different simulated experimental conditions to classify 92 known serotypes of Streptococcus pneumoniae and demonstrated over 99% accuracy with 8 training curves per serotype. In vitro verification of the algorithm was tested using sequence variants of a cancer-related gene and demonstrated 100% accuracy with 3 training curves per sequence variant. The machine learning algorithm enabled reliable, scalable, and automated HRM genotyping analysis with broad potential clinical and epidemiological applications.