Challenges of Multiplex Assays for COVID-19 Research: A Machine Learning Perspective.

Multiplex assays that provide simultaneous measurement of multiple analytes in biological samples have now developed into widely used technologies in the study of diseases, drug discovery, and other medical areas. These approaches span multiple assay systems and can provide readouts of specific assay components with similar accuracy as the respective single assay measurements. Multiplexing allows the consumption of lower sample volumes, lower costs, and higher throughput compared with carrying out single assays. A number of recent studies have demonstrated the impact of multiplex assays in the study of the SARS-CoV-2 virus, the infectious agent responsible for the current COVID-19 pandemic. In this respect, machine learning techniques have proven to be highly valuable in capturing complex disease phenotypes and converting these insights into models which can be applied in real-world settings. This chapter gives an overview of opportunities and challenges of multiplexed biomarker analysis, with a focus on the use of machine learning aimed at identification of biological signatures for increasing our understanding of COVID-19 disease, and for improved diagnostics and prediction of disease outcomes.

A preliminary investigation of circulating extracellular vesicles and biomarker discovery associated with treatment response in head and neck squamous cell carcinoma.

BACKGROUND: There is a paucity of plasma-based biomarkers that prospectively segregate the outcome of patients with head and neck squamous-cell carcinoma (HNSCC) treated with chemoradiation therapy (CRT). Plasma extracellular vesicles (EVs) might be an alternative source for discovery of new specific markers present in patients with HNSCC, which could help to re-direct patients to appropriate curative therapies without delay. METHODS: In order to identify new markers in plasma compartments, Cholerae toxin B chain (CTB) and Annexin V (AV) were used to isolate EVs from pooled plasma samples from patients with locally advanced HNSCC who responded (CR, n = 6) or presented incomplete response (NR, n = 6) to CRT. The crude plasma and EVs cargo were screened by antibody array. RESULTS: Of the 370 polypeptides detected, 119 proteins were specific to NR patients while 38 were exclusive of the CR subjects. The Gene Set Enrichment Analysis (GSEA) and Search Tool for the Retrieval of Interacting Genes (STRING) database analysis indicated that the content of circulating plasma EVs might have a relevant function for the tumor intercellular communication in the HNSCC patients. CONCLUSION: This study provides a list of potential markers present in plasma compartments that might contribute to the development of tools for prediction and assessment of CRT response and potentially guide therapeutic decisions in this context.

Classification of samples from NMR-based metabolomics using principal components analysis and partial least squares with uncertainty estimation.

Recent progress in metabolomics has been aided by the development of analysis techniques such as gas and liquid chromatography coupled with mass spectrometry (GC-MS and LC-MS) and nuclear magnetic resonance (NMR) spectroscopy. The vast quantities of data produced by these techniques has resulted in an increase in the use of machine algorithms that can aid in the interpretation of this data, such as principal components analysis (PCA) and partial least squares (PLS). Techniques such as these can be applied to biomarker discovery, interlaboratory comparison, and clinical diagnoses. However, there is a lingering question whether the results of these studies can be applied to broader sets of clinical data, usually taken from different data sources. In this work, we address this question by creating a metabolomics workflow that combines a previously published consensus analysis procedure ( https://doi.org/10.1016/j.chemolab.2016.12.010 ) with PCA and PLS models using uncertainty analysis based on bootstrapping. This workflow is applied to NMR data that come from an interlaboratory comparison study using synthetic and biologically obtained metabolite mixtures. The consensus analysis identifies trusted laboratories, whose data are used to create classification models that are more reliable than without. With uncertainty analysis, the reliability of the classification can be rigorously quantified, both for data from the original set and from new data that the model is analyzing. Graphical abstract ᅟ.

The 44th Congress of the International Society of Oncology and Biomarkers: Rio de Janeiro, Brazil, 7-10 September 2017.

The 44th Congress of the International Society of Oncology and Biomarkers: Rio de Janeiro, Brazil, 7-10 September 2017 The 44th congress followed the previous one of  International Society of Oncology and Biomarkers (ISOBM) that took place in Chicago (USA) in 2016. The title of the 44th Annual congress was: 'Biomarkers in oncology: new horizons and challenges in the diagnosis and treatment of cancer' [ 1 ]. The congress was co-organized by ISOBM, European Group on Tumor Markers (EGTM) and Brazilian Society of Clinical Pathology SBPC/ML. The event attracted more than 180 participants from all over the world. The program offered many topics regarding discovery, validation, evaluation and use of tumor biomarkers. The presentations were split into the key note lectures, oral presentations, poster presentations and satellite symposiums sponsored by companies. The congress offered participants the opportunity to link clinical and research oncologists to discuss new tools for diagnosis and monitoring of cancer diseases. Prominent people in the field of cancer research and clinical oncology were presented and offered the unique opportunity to exchange experiences and knowledge in an international forum [ 2 ]. Compared with previous ISOBM congresses, it was held in Latin America for the first time, and due to that more participants from Latin America were present.

Chagas Disease Diagnostic Applications: Present Knowledge and Future Steps.

Chagas disease, caused by the protozoan Trypanosoma cruzi, is a lifelong and debilitating illness of major significance throughout Latin America and an emergent threat to global public health. Being a neglected disease, the vast majority of Chagasic patients have limited access to proper diagnosis and treatment, and there is only a marginal investment into R&D for drug and vaccine development. In this context, identification of novel biomarkers able to transcend the current limits of diagnostic methods surfaces as a main priority in Chagas disease applied research. The expectation is that these novel biomarkers will provide reliable, reproducible and accurate results irrespective of the genetic background, infecting parasite strain, stage of disease, and clinical-associated features of Chagasic populations. In addition, they should be able to address other still unmet diagnostic needs, including early detection of congenital T. cruzi transmission, rapid assessment of treatment efficiency or failure, indication/prediction of disease progression and direct parasite typification in clinical samples. The lack of access of poor and neglected populations to essential diagnostics also stresses the necessity of developing new methods operational in point-of-care settings. In summary, emergent diagnostic tests integrating these novel and tailored tools should provide a significant impact on the effectiveness of current intervention schemes and on the clinical management of Chagasic patients. In this chapter, we discuss the present knowledge and possible future steps in Chagas disease diagnostic applications, as well as the opportunity provided by recent advances in high-throughput methods for biomarker discovery.