Blood biomarker-based classification study for neurodegenerative diseases.
Ontology highlight
ABSTRACT:
SUBMITTER: Kelly J
PROVIDER: S-EPMC10567903 | biostudies-literature | 2023 Oct
REPOSITORIES: biostudies-literature
Publications
Blood biomarker-based classification study for neurodegenerative diseases.
Kelly Jack J Moyeed Rana R Carroll Camille C Luo Shouqing S Li Xinzhong X
Scientific reports 20231011 1
As the population ages, neurodegenerative diseases are becoming more prevalent, making it crucial to comprehend the underlying disease mechanisms and identify biomarkers to allow for early diagnosis and effective screening for clinical trials. Thanks to advancements in gene expression profiling, it is now possible to search for disease biomarkers on an unprecedented scale.Here we applied a selection of five machine learning (ML) approaches to identify blood-based biomarkers for Alzheimer's (AD) ...[more]
Similar Datasets
Project description:The two most generally diagnosed Neurodegenerative diseases are the Alzheimer and Parkinson diseases. So this paper presents a fully automated early screening system based on the Capsule network for the classification of these two Neurodegenerative diseases. In this study, we hypothesized that the Neurodegenerative diseases-Caps system based on the Capsule network architecture accurately performs the multiclass i.e. three class classification into either the Alzheimer class or Parkinson class or Healthy control and delivers better results in comparison other deep transfer learning models. The real motivation behind choosing the capsule network architecture is its more resilient nature towards the affine transformations as well as rotational & translational invariance, which commonly persists in the medical image datasets. Apart from this, the capsule networks overcomes the pooling layers related deficiencies from which conventional CNNs are mostly affected and unable to delivers accurate results especially in the tasks related to image classification. The various Computer aided systems based on machine learning for the classification of brain tumors and other types of cancers are already available. Whereas for the classification of Neurodegenerative diseases, the amount of research done is very limited and the number of persons suffering from this type of diseases are increasing especially in developing countries like India, China etc. So there is a need to develop an early screening system for the correct multiclass classification into Alzheimer's, Parkinson's and Normal or Healthy control cases. The Alzheimer disease and Parkinson progression (ADPP) dataset is used in this research study for the training of the proposed Neurodegenerative diseases-Caps system. This ADPP dataset is developed with the aid of both the Parkinson's Progression Markers Initiative (PPMI) and Alzheimer's disease Neuroimaging Initiative (ADNI) databases. There is no such early screening system exist yet, which can perform the accurate classification of these two Neurodegenerative diseases. For the sake of genuine comparison, other popular deep transfer learning models like VGG19, VGG16, ResNet50 and InceptionV3 are implemented and also trained over the same ADPP dataset. The proposed Neurodegenerative diseases-Caps system deliver accuracies of 97.81, 98, 96.81% for the Alzheimer, Parkinson and Healthy control or Normal cases with 70/30 (training/validation split) and performs way better as compare to the other popular Deep transfer learning models.Supplementary informationThe online version contains supplementary material available at 10.1007/s11571-022-09787-1.
| S-EPMC9666567 | biostudies-literature
Project description:Sepsis is a clinical syndrome that can be caused by bacteria or fungi. Early knowledge on the nature of the causative agent is a prerequisite for targeted anti-microbial therapy. Besides currently used detection methods like blood culture and PCR-based assays, the analysis of the transcriptional response of the host to infecting organisms holds great promise. In this study, we aim to examine the transcriptional footprint of infections caused by the bacterial pathogens Staphylococcus aureus and Escherichia coli and the fungal pathogens Candida albicans and Aspergillus fumigatus in a human whole-blood model. Moreover, we use the expression information to build a random forest classifier to determine if the pathogen is bacterial, fungal or neither of the two. After normalizing the transcription intensities using stably expressed reference genes, we filtered the gene set for biomarkers of bacterial or fungal blood infections. This selection is based on differential expression and an additional gene relevance measure. In this way, we identified 38 biomarker genes, including IL6, SOCS3, and IRG1 which were already associated to sepsis by other studies. Using these genes, we trained the classifier and assessed its performance. It yielded a 96% accuracy (sensitivities >93%, specificities >97%) for a 10-fold stratified cross-validation and a 92% accuracy (sensitivities and specificities >83%) for an additional dataset comprising Cryptococcus neoformans infections. Furthermore, the noise-robustness of the classifier suggests high rates of correct class predictions on datasets of new species. In conclusion, this genome-wide approach demonstrates an effective feature selection process in combination with the construction of a well-performing classification model. Further analyses of genes with pathogen-dependent expression patterns can provide insights into the systemic host responses, which may lead to new anti-microbial therapeutic advances.
2015-03-11 | GSE65088 | GEO
Project description:Sepsis is a clinical syndrome that can be caused by bacteria or fungi. Early knowledge on the nature of the causative agent is a prerequisite for targeted anti-microbial therapy. Besides currently used detection methods like blood culture and PCR-based assays, the analysis of the transcriptional response of the host to infecting organisms holds great promise. In this study, we aim to examine the transcriptional footprint of infections caused by the bacterial pathogens Staphylococcus aureus and Escherichia coli and the fungal pathogens Candida albicans and Aspergillus fumigatus in a human whole-blood model. Moreover, we use the expression information to build a random forest classifier to determine if the pathogen is bacterial, fungal or neither of the two. After normalizing the transcription intensities using stably expressed reference genes, we filtered the gene set for biomarkers of bacterial or fungal blood infections. This selection is based on differential expression and an additional gene relevance measure. In this way, we identified 38 biomarker genes, including IL6, SOCS3, and IRG1 which were already associated to sepsis by other studies. Using these genes, we trained the classifier and assessed its performance. It yielded a 96% accuracy (sensitivities >93%, specificities >97%) for a 10-fold stratified cross-validation and a 92% accuracy (sensitivities and specificities >83%) for an additional dataset comprising Cryptococcus neoformans infections. Furthermore, the noise-robustness of the classifier suggests high rates of correct class predictions on datasets of new species. In conclusion, this genome-wide approach demonstrates an effective feature selection process in combination with the construction of a well-performing classification model. Further analyses of genes with pathogen-dependent expression patterns can provide insights into the systemic host responses, which may lead to new anti-microbial therapeutic advances. Analysis of innate immune activation on the basis of gene expression of whole blood cells during ex vivo whole blood infection with bacterial (Staphylococcus aureus, Escherichia coli) and fungal pathogens (Candida albicans, Aspergillus fumigatus) in comparison to mock-treated blood.
2015-03-11 | E-GEOD-65088 | biostudies-arrayexpress
Project description:Retinal alterations have recently been associated with numerous neurodegenerative diseases. Rhodopsin is a G-protein coupled receptor found in the rod cells of the retina. As a biomarker associated with retinal thinning and degeneration, it bears potential in the early detection and monitoring of several neurodegenerative diseases. In this review article, we summarize the findings of correlations between rhodopsin and several neurodegenerative disorders as well as the potential of a novel technique, cSLO, in the quantification of rhodopsin.
| S-EPMC7175229 | biostudies-literature
Project description:Progranulin is a growth factor involved in the regulation of multiple processes including tumorigenesis, wound repair, development, and inflammation. The recent discovery that mutations in the gene encoding for progranulin (GRN) cause frontotemporal lobar degeneration (FTLD), and other neurodegenerative diseases leading to dementia, has brought renewed interest in progranulin and its functions in the central nervous system. GRN null mutations cause protein haploinsufficiency, leading to a significant decrease in progranulin levels that can be detected in plasma, serum and cerebrospinal fluid (CSF) of mutation carriers. The dosage of circulating progranulin sped up the identification of GRN mutations thus favoring genotype-phenotype correlation studies. Researchers demonstrated that, in GRN null mutation carriers, the shortage of progranulin invariably precedes clinical symptoms and thus mutation carriers are "captured" regardless of their disease status. GRN is a particularly appealing gene for drug targeting, in the way that boosting its expression may be beneficial for mutation carriers, preventing or delaying the onset of GRN-related neurodegenerative diseases. Physiological regulation of progranulin expression level is only partially known. Progranulin expression reflects mutation status and, intriguingly, its levels can be modulated by some additional factor (i.e. genetic background; drugs). Thus, factors increasing the production and secretion of progranulin from the normal gene are promising potential therapeutic avenues. In conclusion, peripheral progranulin is a nonintrusive highly accurate biomarker for early identification of mutation carriers and for monitoring future treatments that might boost the level of this protein.
| S-EPMC3560461 | biostudies-literature
Project description:Sepsis is a clinical syndrome that can be caused by bacteria or fungi. Early knowledge on the nature of the causative agent is a prerequisite for targeted anti-microbial therapy. Besides currently used detection methods like blood culture and PCR-based assays, the analysis of the transcriptional response of the host to infecting organisms holds great promise. In this study, we aim to examine the transcriptional footprint of infections caused by the bacterial pathogens Staphylococcus aureus and Escherichia coli and the fungal pathogens Candida albicans and Aspergillus fumigatus in a human whole-blood model. Moreover, we use the expression information to build a random forest classifier to classify if a sample contains a bacterial, fungal, or mock-infection. After normalizing the transcription intensities using stably expressed reference genes, we filtered the gene set for biomarkers of bacterial or fungal blood infections. This selection is based on differential expression and an additional gene relevance measure. In this way, we identified 38 biomarker genes, including IL6, SOCS3, and IRG1 which were already associated to sepsis by other studies. Using these genes, we trained the classifier and assessed its performance. It yielded a 96% accuracy (sensitivities >93%, specificities >97%) for a 10-fold stratified cross-validation and a 92% accuracy (sensitivities and specificities >83%) for an additional test dataset comprising Cryptococcus neoformans infections. Furthermore, the classifier is robust to Gaussian noise, indicating correct class predictions on datasets of new species. In conclusion, this genome-wide approach demonstrates an effective feature selection process in combination with the construction of a well-performing classification model. Further analyses of genes with pathogen-dependent expression patterns can provide insights into the systemic host responses, which may lead to new anti-microbial therapeutic advances.
| S-EPMC4356159 | biostudies-literature
Project description:BackgroundSubjective cognitive complaints (SCC) have been mostly studied in the context of Alzheimer's disease in memory clinic settings. The potential of combining SCC with genetic information and blood biomarkers of neurodegenerative diseases for risk assessment of dementia and depression in the absence of dementia among community-dwelling older adults has so far not been explored.MethodsData were based on a population-based cohort of 6357 participants with a 17-year follow-up (ESTHER study) and a clinic-based cohort of 422 patients. Participants of both cohorts were grouped according to the diagnosis of dementia (yes/no) and the diagnosis of depression in the absence of dementia (yes/no). Participants without dementia included both cognitively unimpaired participants and cognitively impaired participants. Genetic information (APOE ε4 genotype) and blood-based biomarkers of neurodegenerative diseases (glial fibrillary acidic protein; GFAP, neurofilament light chain; NfL, phosphorylated tau181; p-tau181) were available in the ESTHER study and were determined with Simoa Technology in a nested case-control design. Logistic regression models adjusted for relevant confounders were run for the outcomes of all-cause dementia and depression in the absence of dementia.ResultsThe results showed that persistent SCC were associated both with increased risk of all-cause dementia and of depression without dementia, independently of the diagnostic setting. However, the results for the ESTHER study also showed that the combination of subjective complaints with APOE ε4 and with increased GFAP concentrations in the blood yielded a substantially increased risk of all-cause dementia (OR 5.35; 95%CI 3.25-8.81, p-value < 0.0001 and OR 7.52; 95%CI 2.79-20.29, p-value < 0.0001, respectively) but not of depression. Associations of NfL and p-tau181 with risk of all-cause dementia and depression were not statistically significant, either alone or in combination with SCC, but increased concentrations of p-tau181 seemed to be associated with an increased risk for depression.ConclusionIn community and clinical settings, SCC predict both dementia and depression in the absence of dementia. The addition of GFAP could differentiate between the risk of all-cause dementia and the risk of depression among individuals without dementia.
| S-EPMC10638700 | biostudies-literature
Project description:IntroductionBrain-derived extracellular vesicles (BEVs) in blood allows for minimally-invasive investigations of central nervous system (CNS) -specific markers of age-related neurodegenerative diseases (NDDs). Polymer-based EV- and immunoprecipitation (IP)-based BEV-enrichment protocols from blood have gained popularity. We systematically investigated protocol consistency across studies, and determined CNS-specificity of proteins associated with these protocols.MethodsNDD articles investigating BEVs in blood using polymer-based and/or IP-based BEV enrichment protocols were systematically identified, and protocols compared. Proteins used for BEV-enrichment and/or post-enrichment were assessed for CNS- and brain-cell-type-specificity, extracellular domains (ECD+), and presence in EV-databases.ResultsA total of 82.1% of studies used polymer-based (ExoQuick) EV-enrichment, and 92.3% used L1CAM for IP-based BEV-enrichment. Centrifugation times differed across studies. A total of 26.8% of 82 proteins systematically identified were CNS-specific: 50% ECD+, 77.3% were listed in EV-databases.ConclusionsWe identified protocol steps requiring standardization, and recommend additional CNS-specific proteins that can be used for BEV-enrichment or as BEV-biomarkers.HighlightsAcross NDDs, we identified protocols commonly used for EV/BEV enrichment from blood. We identified protocol steps showing variability that require harmonization. We assessed CNS-specificity of proteins used for BEV-enrichment or found in BEV cargo. CNS-specific EV proteins with ECD+ or without were identified. We recommend evaluation of blood-BEV enrichment using these additional ECD+ proteins.
| S-EPMC11247682 | biostudies-literature
Project description:Gene therapy is making a comeback. With its twin promise of targeting disease etiology and 'long-term correction', gene-based therapies (defined here as all forms of genome manipulation) are particularly appealing for neurodegenerative diseases, for which conventional pharmacologic approaches have been largely disappointing. The recent success of a viral-vector-based gene therapy in spinal muscular atrophy-promoting survival and motor function with a single intravenous injection-offers a paradigm for such therapeutic intervention and a platform to build on. Although challenges remain, the newfound optimism largely stems from advances in the development of viral vectors that can diffusely deliver genes throughout the CNS, as well as genome-engineering tools that can manipulate disease pathways in ways that were previously impossible. Surely spinal muscular atrophy cannot be the only neurodegenerative disease amenable to gene therapy, and one can imagine a future in which the toolkit of a clinician will include gene-based therapeutics. The goal of this Review is to highlight advances in the development and application of gene-based therapies for neurodegenerative diseases and offer a prospective look into this emerging arena.
| S-EPMC8394447 | biostudies-literature
Project description:Neurodegenerative diseases are common causes of impaired mobility and cognition in the elderly. Among them, tauopathies and α-synucleinopathies were considered. The neurodegenerative processes and relative differential diagnosis were addressed through a qEEG non-linear analytic method. Study aims were to test accuracy of the power law exponent β applied to EEG in differentiating neurodegenerative diseases and to explore differences in neuronal connectivity among different neurodegenerative processes based on β. N = 230 patients with a diagnosis of tauopathy or α-synucleinopathy and at least one artifact-free EEG recording were selected. Periodogram was applied to EEG signal epochs from continuous recordings. Power law exponent β was determined by the slope of the signal power spectrum versus frequency in logarithmic scale. A data-driven clustering based on β values was performed to identify independent subgroups. Data-driven clustering based on β differentiated tauopathies (overall lower β values) from α-synucleinopathies (higher β values) with high sensitivity and specificity. Tauopathies also presented lower values in the correlation coefficients matrix among frontal sites of recording. In conclusion, significant differences in β values were found between tauopathies and α-synucleinopathies. Hence, β is proposed as a possible biomarker of differential diagnosis and neuronal connectivity.
| S-EPMC11487174 | biostudies-literature