scholarly journals What Do Machines Tell us About Dementia? Machine Learning Applied to Aging, Dementia and Traumatic Brain Injury Study

2021 ◽  
Author(s):  
Denis Arthur Pinheiro Moura ◽  
Joao Ricardo Mendes de Oliveira
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Expression Profiles ◽  
Brain Regions ◽  
Machine Learning Algorithms ◽  
Differentially Expressed ◽  
Classification Model ◽  
Specific Gene

Abstract Dementia, a syndrome characterized by the progressive deterioration of memory and cognition, arises from different pathologies, with Alzheimer's Disease (AD) its most common cause. Patterns of gene expression during dementia of different etiologies may function as generalist biomarkers of the condition. We used RNA-Seq data from the Allen Dementia and Traumatic Brain Injury Study (ADTBI) to identify differentially expressed genes in brains with dementia. Machine Learning algorithms Decision Trees (DT) and Random Forest (RF) were used to create models to identify dementia samples based on their gene expression profile. Importance analyses were conducted to identify the most relevant genes in each classification model. A total of 1629 differentially expressed (DE) genes were found in brains with the condition. Gene PAN3-AS1 was the only DE gene across more than three brain regions. The artificial intelligence models were capable of identifying correctly up to 92.85% of dementia samples. Our analyses provide interesting insights regarding using brain-specific gene expression profiles as biomarkers of dementia, identifying genes possibly involved with dementia, and guiding future studies in prediction and early identification of the syndrome.

scholarly journals The role of salivary vesicles as a potential inflammatory biomarker to detect traumatic brain injury in mixed martial artists

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Rani Matuk ◽  
Mandy Pereira ◽  
Janette Baird ◽  
Mark Dooner ◽  
Yan Cheng ◽  
...  
Keyword(s):  
Gene Expression ◽  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Head Injury ◽  
Injury Severity ◽  
Expression Profiles ◽  
High Impact ◽  
Impact Mechanism ◽  
Inflammatory Biomarker ◽  
Potential Biomarker

AbstractTraumatic brain injury (TBI) is of significant concern in the realm of high impact contact sports, including mixed martial arts (MMA). Extracellular vesicles (EVs) travel between the brain and oral cavity and may be isolated from salivary samples as a noninvasive biomarker of TBI. Salivary EVs may highlight acute neurocognitive or neuropathological changes, which may be particularly useful as a biomarker in high impact sports. Pre and post-fight samples of saliva were isolated from 8 MMA fighters and 7 from controls. Real-time PCR of salivary EVs was done using the TaqMan Human Inflammatory array. Gene expression profiles were compared pre-fight to post-fight as well as pre-fight to controls. Largest signals were noted for fighters sustaining a loss by technical knockout (higher impact mechanism of injury) or a full match culminating in referee decision (longer length of fight), while smaller signals were noted for fighters winning by joint or choke submission (lower impact mechanism as well as less time). A correlation was observed between absolute gene information signals and fight related markers of head injury severity. Gene expression was also significantly different in MMA fighters pre-fight compared to controls. Our findings suggest that salivary EVs as a potential biomarker in the acute period following head injury to identify injury severity and can help elucidate pathophysiological processes involved in TBI.

scholarly journals Predicting lithium treatment response in bipolar patients using gender-specific gene expression biomarkers and machine learning

F1000Research ◽  
2018 ◽  
Vol 7 ◽  
pp. 474
Author(s):  
Andy R. Eugene ◽  
Jolanta Masiak ◽  
Beata Eugene
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Linear Models ◽  
Learning Algorithm ◽  
Lithium Treatment ◽  
Study Data ◽  
Differentially Expressed ◽  
Specific Gene ◽  
Pre Treatment ◽  
Bipolar Patients

Background: We sought to test the hypothesis that transcriptiome-level genes signatures are differentially expressed between male and female bipolar patients, prior to lithium treatment, in a patient cohort who later were clinically classified as lithium treatment responders. Methods: Gene expression study data was obtained from the Lithium Treatment-Moderate dose Use Study data accessed from the National Center for Biotechnology Information’s Gene Expression Omnibus via accession number GSE4548. Differential gene expression analysis was conducted using the Linear Models for Microarray and RNA-Seq (limma) package and the Random Forests machine learning algorithm in R. Results: In pre-treatment lithium responders, the following genes were found having a greater than 0.5 fold-change, and differentially expressed indicating a male bias: RBPMS2, SIDT2, CDH23, LILRA5, and KIR2DS5; while the female-biased genes were: HLA-H, RPS23, FHL3, RPL10A, NBPF14, PSTPIP2, FAM117B, CHST7, and ABRACL. Conclusions: Using machine learning, we developed a pre-treatment gender- and gene-expression-based predictive model selective for lithium responders with an ROC AUC of 0.92 for men and an ROC AUC of 1 for women.

scholarly journals Distinct patterns of structural damage underlie working memory and reasoning deficits after traumatic brain injury

Brain ◽  
2020 ◽  
Vol 143 (4) ◽  
pp. 1158-1176 ◽  
Author(s):  
Amy E Jolly ◽  
Gregory T Scott ◽  
David J Sharp ◽  
Adam H Hampshire
Keyword(s):  
Machine Learning ◽  
Traumatic Brain Injury ◽  
Working Memory ◽  
Brain Injury ◽  
Cognitive Deficits ◽  
Axonal Injury ◽  
Diffuse Axonal Injury ◽  
Brain Regions ◽  
Graph Theoretic ◽  
Cognitive Problems

Abstract It is well established that chronic cognitive problems after traumatic brain injury relate to diffuse axonal injury and the consequent widespread disruption of brain connectivity. However, the pattern of diffuse axonal injury varies between patients and they have a correspondingly heterogeneous profile of cognitive deficits. This heterogeneity is poorly understood, presenting a non-trivial challenge for prognostication and treatment. Prominent amongst cognitive problems are deficits in working memory and reasoning. Previous functional MRI in controls has associated these aspects of cognition with distinct, but partially overlapping, networks of brain regions. Based on this, a logical prediction is that differences in the integrity of the white matter tracts that connect these networks should predict variability in the type and severity of cognitive deficits after traumatic brain injury. We use diffusion-weighted imaging, cognitive testing and network analyses to test this prediction. We define functionally distinct subnetworks of the structural connectome by intersecting previously published functional MRI maps of the brain regions that are activated during our working memory and reasoning tasks, with a library of the white matter tracts that connect them. We examine how graph theoretic measures within these subnetworks relate to the performance of the same tasks in a cohort of 92 moderate-severe traumatic brain injury patients. Finally, we use machine learning to determine whether cognitive performance in patients can be predicted using graph theoretic measures from each subnetwork. Principal component analysis of behavioural scores confirm that reasoning and working memory form distinct components of cognitive ability, both of which are vulnerable to traumatic brain injury. Critically, impairments in these abilities after traumatic brain injury correlate in a dissociable manner with the information-processing architecture of the subnetworks that they are associated with. This dissociation is confirmed when examining degree centrality measures of the subnetworks using a canonical correlation analysis. Notably, the dissociation is prevalent across a number of node-centric measures and is asymmetrical: disruption to the working memory subnetwork relates to both working memory and reasoning performance whereas disruption to the reasoning subnetwork relates to reasoning performance selectively. Machine learning analysis further supports this finding by demonstrating that network measures predict cognitive performance in patients in the same asymmetrical manner. These results accord with hierarchical models of working memory, where reasoning is dependent on the ability to first hold task-relevant information in working memory. We propose that this finer grained information may be useful for future applications that attempt to predict long-term outcomes or develop tailored therapies.

Molecular Phenotype of Malignant CD34+ Hematopoietic Stem and Progenitor Cells in Chronic Myelogenous Leukemia.

Blood ◽  
2005 ◽  
Vol 106 (11) ◽  
pp. 2863-2863
Author(s):  
Ralf Kronenwett ◽  
Elena Diaz-Blanco ◽  
Thorsten Graef ◽  
Ulrich Steidl ◽  
Slawomir Kliszewski ◽  
...  
Keyword(s):  
Gene Expression ◽  
Fatty Acid ◽  
Expression Profiles ◽  
Expression Patterns ◽  
Gene Expression Pattern ◽  
Leukemic Cell ◽  
Differentially Expressed ◽  
Specific Gene ◽  
Hematopoietic Stem ◽  
Cd34 Cells

Abstract In this study, we examined gene expression profiles of immunomagnetically enriched CD34+ cells from bone marrow (BM) of 9 patients with untreated CML in chronic phase and from 8 healthy volunteers using Affymetrix GeneChips. Additionally, in 3 patients CD34+ from peripheral blood (PB) were compared with those from BM. Differential expression of 12 candidate genes was corroborated by quantitative real-time RT-PCR. Following hybridization of labelled cRNA to Affymetrix GeneChips covering 8793 genes we used the statistical scripting language “R” for data analysis. For normalization a method of variance stabilization transformations was used. To identify significantly differentially expressed genes we used the Significance Analysis of Microarrays (SAM) algorithm. The intraindividual comparison of CD34+ cells from BM and PB in CML showed no differentially expressed genes which is different to normal CD34+ cells which had distinct gene expression patterns comparing circulating and sedentary CD34+ cells (Steidl et al., Blood, 2002). Comparing malignant BM CD34+ cells from CML with normal BM CD34+ cells 792 genes were significantly differentially expressed (fold change: >1.3; q-value: <0.03). 735 genes had a higher and 57 genes a lower expression in CML. Gene expression patterns reflected BCR-ABL-induced functional alterations such as increased cell-cycle and proteasome activity as well as decreased apoptosis. Downregulation of several genes involved in DNA repair and detoxification in CML might be the basis for DNA instability and progression to blast crisis. An interesting finding was an upregulation of fetal hemoglobin (Hb) components such as Hb gamma A and G in leukemic progenitor cells whereas no difference in adult Hb expression was observed suggesting an induction of fetal Hb synthesis in CML. Looking at genes involved in stem cell maintenance we found an upregulation of GATA2 and a reduced expression of proteins from the Wnt signalling pathway suggesting an increased self-renewal of CML hematopoietic stem cells compared to the normal counterpart. Moreover, several genes playing a role in ubiquitin-dependent protein catabolism and in fatty acid biosynthesis such as fatty acid synthase (FAS) were stronger expressed in CML. The functional role of FAS for leukemic cell growth was assessed in cell culture experiments. Incubation of the leukemic cell line K562 with the FAS inhibitor cerulenin (10 μg/ml) for 3 days resulted in death of 99% of cells suggesting that survival of leukemic cells depends upon endogenous fatty acid synthesis. In an attempt to find a specific gene expression pattern associated with response to imatinib therapy we divided the patients included in this study into two groups: maximal reduction of BCR-ABL transcript level <3-log vs. >3-log (major molecular remission) during therapy. Comparing pretherapeutic gene expression profiles of both groups we could not identify a pattern predictive for major molecular response. In conclusion, malignant CD34+ cells in CML have a specific gene expression pattern which seems not to be predictive for response to imatinib therapy.

scholarly journals Machine learning algorithms reveal unique gene expression profiles in muscle biopsies from patients with different types of myositis

2020 ◽  
Vol 79 (9) ◽  
pp. 1234-1242 ◽  
Author(s):  
Iago Pinal-Fernandez ◽  
Maria Casal-Dominguez ◽  
Assia Derfoul ◽  
Katherine Pak ◽  
Frederick W Miller ◽  
...  
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Learning Algorithm ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Machine Learning Algorithms ◽  
Recursive Feature Elimination ◽  
Machine Learning Algorithm ◽  
Unique Gene ◽  
Muscle Biopsies

ObjectivesMyositis is a heterogeneous family of diseases that includes dermatomyositis (DM), antisynthetase syndrome (AS), immune-mediated necrotising myopathy (IMNM), inclusion body myositis (IBM), polymyositis and overlap myositis. Additional subtypes of myositis can be defined by the presence of myositis-specific autoantibodies (MSAs). The purpose of this study was to define unique gene expression profiles in muscle biopsies from patients with MSA-positive DM, AS and IMNM as well as IBM.MethodsRNA-seq was performed on muscle biopsies from 119 myositis patients with IBM or defined MSAs and 20 controls. Machine learning algorithms were trained on transcriptomic data and recursive feature elimination was used to determine which genes were most useful for classifying muscle biopsies into each type and MSA-defined subtype of myositis.ResultsThe support vector machine learning algorithm classified the muscle biopsies with >90% accuracy. Recursive feature elimination identified genes that are most useful to the machine learning algorithm and that are only overexpressed in one type of myositis. For example, CAMK1G (calcium/calmodulin-dependent protein kinase IG), EGR4 (early growth response protein 4) and CXCL8 (interleukin 8) are highly expressed in AS but not in DM or other types of myositis. Using the same computational approach, we also identified genes that are uniquely overexpressed in different MSA-defined subtypes. These included apolipoprotein A4 (APOA4), which is only expressed in anti-3-hydroxy-3-methylglutaryl-CoA reductase (HMGCR) myopathy, and MADCAM1 (mucosal vascular addressin cell adhesion molecule 1), which is only expressed in anti-Mi2-positive DM.ConclusionsUnique gene expression profiles in muscle biopsies from patients with MSA-defined subtypes of myositis and IBM suggest that different pathological mechanisms underly muscle damage in each of these diseases.

scholarly journals Transcriptomic Analysis of Mouse Brain After Traumatic Brain Injury Reveals That the Angiotensin Receptor Blocker Candesartan Acts Through Novel Pathways

2021 ◽  
Vol 15 ◽  
Author(s):  
Peter J. Attilio ◽  
Dustin M. Snapper ◽  
Milan Rusnak ◽  
Akira Isaac ◽  
Anthony R. Soltis ◽  
...  
Keyword(s):  
Gene Expression ◽  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Brain Region ◽  
Molecular Mechanisms ◽  
Angiotensin Receptor Blockers ◽  
Differentially Expressed ◽  
Lesion Volume ◽  
Angiotensin Receptor ◽  
Post Injury

Traumatic brain injury (TBI) results in complex pathological reactions, where the initial lesion is followed by secondary inflammation and edema. Our laboratory and others have reported that angiotensin receptor blockers (ARBs) have efficacy in improving recovery from traumatic brain injury in mice. Treatment of mice with a subhypotensive dose of the ARB candesartan results in improved functional recovery, and reduced pathology (lesion volume, inflammation and gliosis). In order to gain a better understanding of the molecular mechanisms through which candesartan improves recovery after controlled cortical impact injury (CCI), we performed transcriptomic profiling on brain regions after injury and drug treatment. We examined RNA expression in the ipsilateral hippocampus, thalamus and hypothalamus at 3 or 29 days post injury (dpi) treated with either candesartan (0.1 mg/kg) or vehicle. RNA was isolated and analyzed by bulk mRNA-seq. Gene expression in injured and/or candesartan treated brain region was compared to that in sham vehicle treated mice in the same brain region to identify genes that were differentially expressed (DEGs) between groups. The most DEGs were expressed in the hippocampus at 3 dpi, and the number of DEGs reduced with distance and time from the lesion. Among pathways that were differentially expressed at 3 dpi after CCI, candesartan treatment altered genes involved in angiogenesis, interferon signaling, extracellular matrix regulation including integrins and chromosome maintenance and DNA replication. At 29 dpi, candesartan treatment reduced the expression of genes involved in the inflammatory response. Some changes in gene expression were confirmed in a separate cohort of animals by qPCR. Fewer DEGs were found in the thalamus, and only one in the hypothalamus at 3 dpi. Additionally, in the hippocampi of sham injured mice, 3 days of candesartan treatment led to the differential expression of 384 genes showing that candesartan in the absence of injury had a powerful impact on gene expression specifically in the hippocampus. Our results suggest that candesartan has broad actions in the brain after injury and affects different processes at acute and chronic times after injury. These data should assist in elucidating the beneficial effect of candesartan on recovery from TBI.

Sign in / Sign up

Export Citation Format

Share Document