Visualizing genomic characteristics across an RNA-Seq based reference landscape of normal and neoplastic brain

In order to better understand the relationship between normal and neoplastic brain, we combined five publicly available large-scale datasets, correcting for batch effects and applying Uniform Manifold Approximation and Projection (UMAP) to RNA-Seq data. We assembled a reference Brain-UMAP including 702 adult gliomas, 802 pediatric tumors and 1409 healthy normal brain samples, which can be utilized to investigate the wealth of information obtained from combining several publicly available datasets to study a single organ site. Normal brain regions and tumor types create distinct clusters and because the landscape is generated by RNA-Seq, comparative gene expression profiles and gene ontology patterns are readily evident. To our knowledge, this is the first meta-analysis that allows for comparison of gene expression and pathways of interest across adult gliomas, pediatric brain tumors, and normal brain regions. We provide access to this resource via the open source, interactive online tool Oncoscape, where the scientific community can readily visualize clinical metadata, gene expression patterns, gene fusions, mutations, and copy number patterns for individual genes and pathway over this reference landscape.

Relational Learning Improves Prediction of Mortality in COVID-19 in the Intensive Care Unit

Traditional Machine Learning (ML) models have had limited success in predicting Coronoavirus-19 (COVID-19) outcomes using Electronic Health Record (EHR) data partially due to not effectively capturing the inter-connectivity patterns between various data modalities. In this work, we propose a novel framework that utilizes relational learning based on a heterogeneous graph model (HGM) for predicting mortality at different time windows in COVID-19 patients within the intensive care unit (ICU). We utilize the EHRs of one of the largest and most diverse patient populations across five hospitals in major health system in New York City. In our model, we use an LSTM for processing time varying patient data and apply our proposed relational learning strategy in the final output layer along with other static features. Here, we replace the traditional softmax layer with a Skip-Gram relational learning strategy to compare the similarity between a patient and outcome embedding representation. We demonstrate that the construction of a HGM can robustly learn the patterns classifying patient representations of outcomes through leveraging patterns within the embeddings of similar patients. Our experimental results show that our relational learning-based HGM model achieves higher area under the receiver operating characteristic curve (auROC) than both comparator models in all prediction time windows, with dramatic improvements to recall.

Noncoding RNAs in Extracellular Fluids as Cancer Biomarkers: The New Frontier of Liquid Biopsies

The last two decades of cancer research have been devoted in two directions: (1) understanding the mechanism of carcinogenesis for an effective treatment, and (2) improving cancer prevention and screening for early detection of the disease. This last aspect has been developed, especially for certain types of cancers, thanks also to the introduction of new concepts such as liquid biopsies and precision medicine. In this context, there is a growing interest in the application of alternative and noninvasive methodologies to search for cancer biomarkers. The new frontiers of the research lead to a search for RNA molecules circulating in body fluids. Searching for biomarkers in extracellular body fluids represents a better option for patients because they are easier to access, less painful, and potentially more economical. Moreover, the possibility for these types of samples to be taken repeatedly, allows a better monitoring of the disease progression or treatment efficacy for a better intervention and dynamic treatment of the patient, which is the fundamental basis of personalized medicine. RNA molecules, freely circulating in body fluids or packed in microvesicles, have all the characteristics of the ideal biomarkers owing to their high stability under storage and handling conditions and being able to be sampled several times for monitoring. Moreover, as demonstrated for many cancers, their plasma/serum levels mirror those in the primary tumor. There are a large variety of RNA species noncoding for proteins that could be used as cancer biomarkers in liquid biopsies. Among them, the most studied are microRNAs, but recently the attention of the researcher has been also directed towards Piwi-interacting RNAs, circular RNAs, and other small noncoding RNAs. Another class of RNA species, the long noncoding RNAs, is larger than microRNAs and represents a very versatile and promising group of molecules which, apart from their use as biomarkers, have also a possible therapeutic role. In this review, we will give an overview of the most common noncoding RNA species detectable in extracellular fluids and will provide an update concerning the situation of the research on these molecules as cancer biomarkers.