Machine learning applied to gene expression analysis of T-lymphocytes in patients with cGVHD

Novel biomarkers of preterm brain injury from blood transcriptome in sheep model of intrauterine asphyxia

BACKGROUND

Infants born preterm have a higher incidence of neurological deficits. A key step in finding effective treatments is to identify biomarkers that reliably predict outcome.

METHODS

Following umbilical cord occlusion (UCO) in pregnant sheep, whole fetal blood RNA was sequenced pre- and post-UCO, brain injury outcome was determined by battery of neuropathology scoring and the transcriptome signature correlated to the degree of brain injury. Additionally, we developed a novel analytical procedure to deduce cell blood composition over time.

RESULTS

Sixty-one genes were identified with significant altered expression after UCO. In pre-UCO blood, the level of three mRNAs (Trex2, Znf280b, novel miRNA) and in post-UCO, four mRNAs (Fam184a, Angptl2, novel lincRNA and an unknown protein-coding gene) were associated to brain injury (FDR < 0.01). Several of these mRNAs are related to inflammation and angiogenesis. Pathway analysis highlighted genes playing a role in perinatal death and growth failure. Results also indicate that several leukocyte populations undergo significant changes after UCO.

CONCLUSION

We have used a whole transcriptomic approach to uncover novel biomarkers in fetal blood that correlate to neuropathology in the preterm sheep brain. The current data forms a basis for future studies to investigate mechanisms of these mRNAs in the injury progression.

IMPACT

Trend analysis of genes following asphyxia reveal a group of genes associated with perinatal death and growth failure. Several pre-asphyxia transcripts were associated to brain injury severity suggesting genomic susceptibility to injury. Several post-asphyxia transcripts were correlated to brain injury severity, thus, serve as potential novel biomarkers of injury outcome. Successfully adaptation of cell profiling algorithms suggests significant changes in blood cell composition following asphyxia.

Inflammaging, an Imbalanced Immune Response That Needs to Be Restored for Cancer Prevention and Treatment in the Elderly

Nowadays, new advances in society and health have brought an increased life expectancy. However, at the same time, aging comes with complications that impact the development of autoimmunity, neurodegenerative diseases and cancer. These complications affect the quality of life and impact the public health system. Specifically, with aging, a low-grade chronic sterile systemic inflammation with self-reactivity in the absence of acute infection occurs termed inflammaging. Inflammaging is related to an imbalanced immune response that can be either naturally acquired with aging or accelerated due to external triggers. Different molecules, metabolites and inflammatory forms of cell death are highly involved in these processes. Importantly, adoptive cellular immunotherapy is a modality of treatment for cancer patients that administers ex vivo expanded immune cells in the patient. The manipulation of these cells confers them enhanced proinflammatory properties. A general consequence of proinflammatory events is the development of autoimmune diseases and cancer. Herein, we review subsets of immune cells with a pertinent role in inflammaging, relevant proteins involved in these inflammatory events and external triggers that enhance and accelerate these processes. Moreover, we mention relevant preclinical studies that demonstrate associations of chronic inflammation with cancer development.

A Systematic Review of Machine Learning Techniques in Hematopoietic Stem Cell Transplantation (HSCT)

Machine learning techniques are widely used nowadays in the healthcare domain for the diagnosis, prognosis, and treatment of diseases. These techniques have applications in the field of hematopoietic cell transplantation (HCT), which is a potentially curative therapy for hematological malignancies. Herein, a systematic review of the application of machine learning (ML) techniques in the HCT setting was conducted. We examined the type of data streams included, specific ML techniques used, and type of clinical outcomes measured. A systematic review of English articles using PubMed, Scopus, Web of Science, and IEEE Xplore databases was performed. Search terms included "hematopoietic cell transplantation (HCT)," "autologous HCT," "allogeneic HCT," "machine learning," and "artificial intelligence." Only full-text studies reported between January 2015 and July 2020 were included. Data were extracted by two authors using predefined data fields. Following PRISMA guidelines, a total of 242 studies were identified, of which 27 studies met the inclusion criteria. These studies were sub-categorized into three broad topics and the type of ML techniques used included ensemble learning (63%), regression (44%), Bayesian learning (30%), and support vector machine (30%). The majority of studies examined models to predict HCT outcomes (e.g., survival, relapse, graft-versus-host disease). Clinical and genetic data were the most commonly used predictors in the modeling process. Overall, this review provided a systematic review of ML techniques applied in the context of HCT. The evidence is not sufficiently robust to determine the optimal ML technique to use in the HCT setting and/or what minimal data variables are required.