Development of a long noncoding RNA-based machine learning model to predict COVID-19 in-hospital mortality.

Tools for predicting COVID-19 outcomes enable personalized healthcare, potentially easing the disease burden. This collaborative study by 15 institutions across Europe aimed to develop a machine learning model for predicting the risk of in-hospital mortality post-SARS-CoV-2 infection. Blood samples and clinical data from 1286 COVID-19 patients collected from 2020 to 2023 across four cohorts in Europe and Canada were analyzed, with 2906 long non-coding RNAs profiled using targeted sequencing. From a discovery cohort combining three European cohorts and 804 patients, age and the long non-coding RNA LEF1-AS1 were identified as predictive features, yielding an AUC of 0.83 (95% CI 0.82-0.84) and a balanced accuracy of 0.78 (95% CI 0.77-0.79) with a feedforward neural network classifier. Validation in an independent Canadian cohort of 482 patients showed consistent performance. Cox regression analysis indicated that higher levels of LEF1-AS1 correlated with reduced mortality risk (age-adjusted hazard ratio 0.54, 95% CI 0.40-0.74). Quantitative PCR validated LEF1-AS1's adaptability to be measured in hospital settings. Here, we demonstrate a promising predictive model for enhancing COVID-19 patient management.

Autoimmune response after SARS-CoV-2 infection and SARS-CoV-2 vaccines.

The complicated relationships between autoimmunity, COVID-19, and COVID-19 vaccinations are described, giving insight into their intricacies. Antinuclear antibodies (ANA), anti-Ro/SSA, rheumatoid factor, lupus anticoagulant, and antibodies against interferon (IFN)-I have all been consistently found in COVID-19 patients, indicating a high prevalence of autoimmune reactions following viral exposure. Furthermore, the discovery of human proteins with structural similarities to SARS-CoV-2 peptides as possible autoantigens highlights the complex interplay between the virus and the immune system in initiating autoimmunity. An updated summary of the current status of COVID-19 vaccines is presented. We present probable pathways underpinning the genesis of COVID-19 autoimmunity, such as bystander activation caused by hyperinflammatory conditions, viral persistence, and the creation of neutrophil extracellular traps. These pathways provide important insights into the development of autoimmune-related symptoms ranging from organ-specific to systemic autoimmune and inflammatory illnesses, demonstrating the wide influence of COVID-19 on the immune system.

Statistical and Machine Learning Techniques in Human Microbiome Studies: Contemporary Challenges and Solutions.

The human microbiome has emerged as a central research topic in human biology and biomedicine. Current microbiome studies generate high-throughput omics data across different body sites, populations, and life stages. Many of the challenges in microbiome research are similar to other high-throughput studies, the quantitative analyses need to address the heterogeneity of data, specific statistical properties, and the remarkable variation in microbiome composition across individuals and body sites. This has led to a broad spectrum of statistical and machine learning challenges that range from study design, data processing, and standardization to analysis, modeling, cross-study comparison, prediction, data science ecosystems, and reproducible reporting. Nevertheless, although many statistics and machine learning approaches and tools have been developed, new techniques are needed to deal with emerging applications and the vast heterogeneity of microbiome data. We review and discuss emerging applications of statistical and machine learning techniques in human microbiome studies and introduce the COST Action CA18131 "ML4Microbiome" that brings together microbiome researchers and machine learning experts to address current challenges such as standardization of analysis pipelines for reproducibility of data analysis results, benchmarking, improvement, or development of existing and new tools and ontologies.

Perceptions of students in health and molecular life sciences regarding pharmacogenomics and personalized medicine.

BACKGROUND: Increasing evidence is demonstrating that a patient's unique genetic profile can be used to detect the disease's onset, prevent its progression, and optimize its treatment. This led to the increased global efforts to implement personalized medicine (PM) and pharmacogenomics (PG) in clinical practice. Here we investigated the perceptions of students from different universities in Bosnia and Herzegovina (BH) towards PG/PM as well as related ethical, legal, and social implications (ELSI). This descriptive, cross-sectional study is based on the survey of 559 students from the Faculties of Medicine, Pharmacy, Health Studies, Genetics, and Bioengineering and other study programs. RESULTS: Our results showed that 50% of students heard about personal genome testing companies and 69% consider having a genetic test done. A majority of students (57%) agreed that PM represents a promising healthcare model, and 40% of students agreed that their study program is well designed for understanding PG/PM. This latter opinion seems to be particularly influenced by the field of study (7.23, CI 1.99-26.2, p = 0.003). Students with this opinion are also more willing to continue their postgraduate education in the PM (OR = 4.68, CI 2.59-8.47, p < 0.001). Furthermore, 45% of students are aware of different ethical aspects of genetic testing, with most of them (46%) being concerned about the patient's privacy. CONCLUSIONS: Our results indicate a positive attitude of biomedical students in Bosnia and Herzegovina towards genetic testing and personalized medicine. Importantly, our results emphasize the key importance of pharmacogenomic education for more efficient translation of precision medicine into clinical practice.