Identification of contributing genes of Huntington's disease by machine learning

CMS121 Partially Attenuates Disease Progression in Mouse Models of Huntington's Disease

There are currently no drugs that meaningfully slow down the progression of Huntington's disease (HD). Moreover, drug candidates against a single molecular target have not had significant success. Therefore, a different approach to HD drug discovery is needed. Previously we showed that the flavonol fisetin is efficacious in mouse and fly models of HD (Hum. Mol. Gen. 20:261, 2011). It is also effective in animal models of Alzheimer's disease (AD), ischemic stroke, and the CNS complications of diabetes, all of which share some pathological features with HD. Potent derivatives of fisetin with improved pharmacology were made that maintain its multiple biological activities (J. Med. Chem. 55:378, 2012). From 160 synthetic fisetin derivatives, one, CMS121, was selected for further study in the context of HD based on pharmacological parameters and its efficacy in animal models of AD. Both R6/2 and YAC128 mouse models of HD were used in these studies. We examined motor function using multiple assays as well as survival. In the R6/2 mice, we also looked at the effects of CMS121 on striatal gene expression. In both models, we found a slowing of motor dysfunction and an increase in median life span. Interestingly, in the YAC128 mice, the effects on the slowing in motor function loss became increasingly more pronounced as the mice aged. CMS121 also reduced HD-driven changes in the expression of genes associated with the proteasome and oxidative phosphorylation. Overall, these results suggest that CMS121 could provide some benefits for HD patients, particularly with regard to increasing health span.

A Comprehensive Bioinformatics Approach to Identify Molecular Signatures and Key Pathways for the Huntington Disease

Huntington disease (HD) is a degenerative brain disease caused by the expansion of CAG (cytosine-adenine-guanine) repeats, which is inherited as a dominant trait and progressively worsens over time possessing threat. Although HD is monogenetic, the specific pathophysiology and biomarkers are yet unknown specifically, also, complex to diagnose at an early stage, and identification is restricted in accuracy and precision. This study combined bioinformatics analysis and network-based system biology approaches to discover the biomarker, pathways, and drug targets related to molecular mechanism of HD etiology. The gene expression profile data sets GSE64810 and GSE95343 were analyzed to predict the molecular markers in HD where 162 mutual differentially expressed genes (DEGs) were detected. Ten hub genes among them (DUSP1, NKX2-5, GLI1, KLF4, SCNN1B, NPHS1, SGK2, PITX2, S100A4, and MSX1) were identified from protein-protein interaction (PPI) network which were mostly expressed as down-regulated. Following that, transcription factors (TFs)-DEGs interactions (FOXC1, GATA2, etc), TF-microRNA (miRNA) interactions (hsa-miR-340, hsa-miR-34a, etc), protein-drug interactions, and disorders associated with DEGs were predicted. Furthermore, we used gene set enrichment analysis (GSEA) to emphasize relevant gene ontology terms (eg, TF activity, sequence-specific DNA binding) linked to DEGs in HD. Disease interactions revealed the diseases that are linked to HD, and the prospective small drug molecules like cytarabine and arsenite was predicted against HD. This study reveals molecular biomarkers at the RNA and protein levels that may be beneficial to improve the understanding of molecular mechanisms, early diagnosis, as well as prospective pharmacologic targets for designing beneficial HD treatment.

miRNA profiling as a complementary diagnostic tool for amyotrophic lateral sclerosis

Amyotrophic lateral sclerosis (ALS), the most prevalent motor neuron disease characterized by its complex genetic structure, lacks a single diagnostic test capable of providing a conclusive diagnosis. In order to demonstrate the potential for genetic diagnosis and shed light on the pathogenic role of miRNAs in ALS, we developed an ALS diagnostic rule by training the model using 80% of a miRNA profiling dataset consisting of 253 ALS samples and 103 control samples. Subsequently, we validated the diagnostic rule using the remaining 20% of unseen samples. The diagnostic rule we developed includes miR-205-5p, miR-206, miR-376a-5p, miR-412-5p, miR-3927-3p, miR-4701-3p, miR-6763-5p, and miR-6801-3p. Remarkably, the rule achieved an 82% true positive rate and a 73% true negative rate when predicting the unseen samples. Furthermore, the identified miRNAs target 21 genes in the PI3K-Akt pathway and 27 genes in the ALS pathway, including notable genes such as BCL2, NEFH, and OPTN. We propose that miRNA profiling may serve as a complementary diagnostic tool to supplement the clinical presentation and aid in the early recognition of ALS.

A comprehensive analysis of gene expression profiling data in COVID-19 patients for discovery of specific and differential blood biomarker signatures

COVID-19 is a newly recognized illness with a predominantly respiratory presentation. Although initial analyses have identified groups of candidate gene biomarkers for the diagnosis of COVID-19, they have yet to identify clinically applicable biomarkers, so we need disease-specific diagnostic biomarkers in biofluid and differential diagnosis in comparison with other infectious diseases. This can further increase knowledge of pathogenesis and help guide treatment. Eight transcriptomic profiles of COVID-19 infected versus control samples from peripheral blood (PB), lung tissue, nasopharyngeal swab and bronchoalveolar lavage fluid (BALF) were considered. In order to find COVID-19 potential Specific Blood Differentially expressed genes (SpeBDs), we implemented a strategy based on finding shared pathways of peripheral blood and the most involved tissues in COVID-19 patients. This step was performed to filter blood DEGs with a role in the shared pathways. Furthermore, nine datasets of the three types of Influenza (H1N1, H3N2, and B) were used for the second step. Potential Differential Blood DEGs of COVID-19 versus Influenza (DifBDs) were found by extracting DEGs involved in only enriched pathways by SpeBDs and not by Influenza DEGs. Then in the third step, a machine learning method (a wrapper feature selection approach supervised by four classifiers of k-NN, Random Forest, SVM, Naïve Bayes) was utilized to narrow down the number of SpeBDs and DifBDs and find the most predictive combination of them to select COVID-19 potential Specific Blood Biomarker Signatures (SpeBBSs) and COVID-19 versus influenza Differential Blood Biomarker Signatures (DifBBSs), respectively. After that, models based on SpeBBSs and DifBBSs and the corresponding algorithms were built to assess their performance on an external dataset. Among all the extracted DEGs from the PB dataset (from common PB pathways with BALF, Lung and Swab), 108 unique SpeBD were obtained. Feature selection using Random Forest outperformed its counterparts and selected IGKC, IGLV3-16 and SRP9 among SpeBDs as SpeBBSs. Validation of the constructed model based on these genes and Random Forest on an external dataset resulted in 93.09% Accuracy. Eighty-three pathways enriched by SpeBDs and not by any of the influenza strains were identified, including 87 DifBDs. Using feature selection by Naive Bayes classifier on DifBDs, FMNL2, IGHV3-23, IGLV2-11 and RPL31 were selected as the most predictable DifBBSs. The constructed model based on these genes and Naive Bayes on an external dataset was validated with 87.2% accuracy. Our study identified several candidate blood biomarkers for a potential specific and differential diagnosis of COVID-19. The proposed biomarkers could be valuable targets for practical investigations to validate their potential.

Leveraging Computational Intelligence Techniques for Diagnosing Degenerative Nerve Diseases: A Comprehensive Review, Open Challenges, and Future Research Directions

Degenerative nerve diseases such as Alzheimer's and Parkinson's diseases have always been a global issue of concern. Approximately 1/6th of the world's population suffers from these disorders, yet there are no definitive solutions to cure these diseases after the symptoms set in. The best way to treat these disorders is to detect them at an earlier stage. Many of these diseases are genetic; this enables machine learning algorithms to give inferences based on the patient's medical records and history. Machine learning algorithms such as deep neural networks are also critical for the early identification of degenerative nerve diseases. The significant applications of machine learning and deep learning in early diagnosis and establishing potential therapies for degenerative nerve diseases have motivated us to work on this review paper. Through this review, we covered various machine learning and deep learning algorithms and their application in the diagnosis of degenerative nerve diseases, such as Alzheimer's disease and Parkinson's disease. Furthermore, we also included the recent advancements in each of these models, which improved their capabilities for classifying degenerative nerve diseases. The limitations of each of these methods are also discussed. In the conclusion, we mention open research challenges and various alternative technologies, such as virtual reality and Big data analytics, which can be useful for the diagnosis of degenerative nerve diseases.

Recent developments in the management of Huntington's disease

Huntington's disease (HD) is a rare, incurable, inheritedneurodegenerative disorder manifested by chorea, hyperkinetic, and hypokinetic movements. The FDA has approved only two drugs, viz. tetrabenazine, and deutetrabenazine, to manage the chorea associated with HD. However, several other drugs are used as an off-label to manage chorea and other symptoms such as depression, anxiety, muscle tremors, and cognitive dysfunction associated with HD. So far, there is no disease-modifying treatment available. Drug repurposing has been a primary drive to search for new anti-HD drugs. Numerous molecular targets along with a wide range of small molecules and gene therapies are currently under clinical investigation. More than 200 clinical studies are underway for HD, 75% are interventional, and 25% are observational studies. The present review discusses the small molecule clinical pipeline and molecular targets for HD. Furthermore, the biomarkers, diagnostic tests, gene therapies, behavioral and observational studies for HD were also deliberated.

Non-Cell Autonomous and Epigenetic Mechanisms of Huntington's Disease

Huntington's disease (HD) is a rare neurodegenerative disorder caused by an expansion of CAG trinucleotide repeat located in the exon 1 of Huntingtin (HTT) gene in human chromosome 4. The HTT protein is ubiquitously expressed in the brain. Specifically, mutant HTT (mHTT) protein-mediated toxicity leads to a dramatic degeneration of the striatum among many regions of the brain. HD symptoms exhibit a major involuntary movement followed by cognitive and psychiatric dysfunctions. In this review, we address the conventional role of wild type HTT (wtHTT) and how mHTT protein disrupts the function of medium spiny neurons (MSNs). We also discuss how mHTT modulates epigenetic modifications and transcriptional pathways in MSNs. In addition, we define how non-cell autonomous pathways lead to damage and death of MSNs under HD pathological conditions. Lastly, we overview therapeutic approaches for HD. Together, understanding of precise neuropathological mechanisms of HD may improve therapeutic approaches to treat the onset and progression of HD.

Hypoxia-Inducible Factor (HIF) in Ischemic Stroke and Neurodegenerative Disease

Hypoxia is one of the most common pathological conditions, which can be induced by multiple events, including ischemic injury, trauma, inflammation, tumors, etc. The body's adaptation to hypoxia is a highly important phenomenon in both health and disease. Most cellular responses to hypoxia are associated with a family of transcription factors called hypoxia-inducible factors (HIFs), which induce the expression of a wide range of genes that help cells adapt to a hypoxic environment. Basic mechanisms of adaptation to hypoxia, and particularly HIF functions, have being extensively studied over recent decades, leading to the 2019 Nobel Prize in Physiology or Medicine. Based on their pivotal physiological importance, HIFs are attracting increasing attention as a new potential target for treating a large number of hypoxia-associated diseases. Most of the experimental work related to HIFs has focused on roles in the liver and kidney. However, increasing evidence clearly demonstrates that HIF-based responses represent an universal adaptation mechanism in all tissue types, including the central nervous system (CNS). In the CNS, HIFs are critically involved in the regulation of neurogenesis, nerve cell differentiation, and neuronal apoptosis. In this mini-review, we provide an overview of the complex role of HIF-1 in the adaptation of neurons and glia cells to hypoxia, with a focus on its potential involvement into various neuronal pathologies and on its possible role as a novel therapeutic target.

Machine learning compensates fold-change method and highlights oxidative phosphorylation in the brain transcriptome of Alzheimer's disease

Alzheimer's disease (AD) is a neurodegenerative disorder causing 70% of dementia cases. However, the mechanism of disease development is still elusive. Despite the availability of a wide range of biological data, a comprehensive understanding of AD's mechanism from machine learning (ML) is so far unrealized, majorly due to the lack of needed data density. To harness the AD mechanism's knowledge from the expression profiles of postmortem prefrontal cortex samples of 310 AD and 157 controls, we used seven predictive operators or combinations of RapidMiner Studio operators to establish predictive models from the input matrix and to assign a weight to each attribute. Besides, conventional fold-change methods were also applied as controls. The identified genes were further submitted to enrichment analysis for KEGG pathways. The average accuracy of ML models ranges from 86.30% to 91.22%. The overlap ratio of the identified genes between ML and conventional methods ranges from 19.7% to 21.3%. ML exclusively identified oxidative phosphorylation genes in the AD pathway. Our results highlighted the deficiency of oxidative phosphorylation in AD and suggest that ML should be considered as complementary to the conventional fold-change methods in transcriptome studies.