Machine Learning Analysis Using RNA Sequencing to Distinguish Neuromyelitis Optica from Multiple Sclerosis and Identify Therapeutic Candidates.

This study aims to identify RNA biomarkers distinguishing neuromyelitis optica (NMO) from relapsing-remitting multiple sclerosis (RRMS) and explore potential therapeutic applications leveraging machine learning (ML). An ensemble approach was developed using differential gene expression analysis and competitive ML methods, interrogating total RNA-sequencing data sets from peripheral whole blood of treatment-naïve patients with RRMS and NMO and healthy individuals. Pathway analysis of candidate biomarkers informed the biological context of disease, transcription factor activity, and small-molecule therapeutic potential. ML models differentiated between patients with NMO and RRMS, with the performance of certain models exceeding 90% accuracy. RNA biomarkers driving model performance were associated with ribosomal dysfunction and viral infection. Regulatory networks of kinases and transcription factors identified biological associations and identified potential therapeutic targets. Small-molecule candidates capable of reversing perturbed gene expression were uncovered. Mitoxantrone and vorinostat-two identified small molecules with previously reported use in patients with NMO and experimental autoimmune encephalomyelitis-reinforced discovered expression signatures and highlighted the potential to identify new therapeutic candidates. Putative RNA biomarkers were identified that accurately distinguish NMO from RRMS and healthy individuals. The application of multivariate approaches in analysis of RNA-sequencing data further enhances the discovery of unique RNA biomarkers, accelerating the development of new methods for disease detection, monitoring, and therapeutics. Integrating biological understanding further enhances detection of disease-specific signatures and possible therapeutic targets.

Analytical Validation of qPCR-Based Multivariate Index Assays in a Clinical Laboratory: Practical Challenges and Limitations.

BACKGROUND: Multivariate index assays (MIAs) to evaluate disease status and/or therapeutic efficacy are increasingly being used in clinical laboratories as laboratory-developed tests (LDTs). Before clinical use, diagnostic and analytical performance specifications of LDTs must be established. Several regulatory guidelines have been published that address specific components of validation procedures, but the interpretation for the analytical validation of MIAs is ambiguous and creates confusion when implementing a novel MIA in the clinical laboratory. CONTENT: CLSI guidelines and published methods were evaluated to develop a validation strategy to establish analytical sensitivity, precision, specificity, and stability for qPCR-based MIAs. Limitations and challenges identified while evaluating guidelines and literature and implementing this strategy are discussed in this review, including sample sourcing and integrity, laboratory contamination, and sample throughput. Due to the diversity of qPCR-based MIAs, we discuss additional considerations for researchers intending to transfer MIAs to a clinical laboratory. SUMMARY: A practical strategy to assess the analytical performance characteristics for validation of qPCR-based MIAs was developed and tested before diagnostic clinical use. Several important limitations, challenges, and considerations were identified during development of the analytical validation procedures that are not addressed in regulatory guidelines or published literature. The described strategy can provide insight for future developers of MIAs and clinical laboratories implementing MIAs as LDTs.

miRNA profiling on high-throughput OpenArray™ system.

Micro RNA (miRNAs) are a class of 17-25 nucleotides noncoding RNAs that have been shown to have critical functions in a wide variety of biological processes. Measuring quantity of miRNAs in tissues of different physiological and pathological conditions is an important first step to investigate the functions of miRNAs. To this date, the number of identified miRNA consists of around 850 different species, and more sequence-predicted miRNA genes are awaiting experimental confirmation. The need for high-throughput technologies allowing to profile all known miRNAs with power similar to microarray and precision/specificity of qPCR is evident. The example of such system based on high-density array of nanoliter PCR assays is described here. Functionally equivalent to a microtiter plate, a single OpenArray™ nanoplate makes possible to do up to 3,072 real-time PCRs at a single experiment. Methods for miRNA profiling using the dual-label probe chemistry (Taqman(®)) are outlined in this chapter, and experimental data illustrating system performance are provided.