The Emerging Role of Long Non-Coding RNAs and MicroRNAs in Neurodegenerative Diseases: A Perspective of Machine Learning

Abstract

Neurodegenerative diseases (NDs) are characterized by progressive neuronal dysfunction and death of brain cells population. As the early manifestations of NDs are similar, their symptoms are difficult to distinguish, making the timely detection and discrimination of each neurodegenerative disorder a priority. Several investigations have revealed the importance of microRNAs and long non-coding RNAs in neurodevelopment, brain function, maturation, and neuronal activity, as well as its dysregulation involved in many types of neurological diseases. Therefore, the expression pattern of these molecules in the different NDs have gained significant attention to improve the diagnostic and treatment at earlier stages. In this sense, we gather the different microRNAs and long non-coding RNAs that have been reported as dysregulated in each disorder. Since there are a vast number of non-coding RNAs altered in NDs, some sort of synthesis, filtering and organization method should be applied to extract the most relevant information. Hence, machine learning is considered as an important tool for this purpose since it can classify expression profiles of non-coding RNAs between healthy and sick people. Therefore, we deepen in this branch of computer science, its different methods, and its meaningful application in the diagnosis of NDs from the dysregulated non-coding RNAs. In addition, we demonstrate the relevance of machine learning in NDs from the description of different investigations that showed an accuracy between 85% to 95% in the detection of the disease with this tool. All of these denote that artificial intelligence could be an excellent alternative to help the clinical diagnosis and facilitate the identification diseases in early stages based on non-coding RNAs.

The Vulnerability of the Developing Brain: Analysis of Highly Expressed Genes in Infant C57BL/6 Mouse Hippocampus in Relation to Phenotypic Annotation Derived From Mutational Studies

“…On the contrary, this study was limited to protein coding genes and future work should include similar analyses on noncoding RNA (ncRNA) expression, such as microRNAs and long noncoding RNAs, as previous studies have shown that such RNAs are expressed in a tissue- and cell-specific manner, involved in neuronal differentiation and function, and implicated in various brain disorders. 88 - 95 However, although databases providing information on ncRNAs along with tissue expression profiles and predicted functions are now available as well as ncRNA knockout mouse models with reported phenotypes, 96 - 101 there is still a lack of databases that compiles the results from mutational studies and which also links the ncRNAs to phenotype in a similar way as the MGI’s Mammalian Phenotype database. Such databases would be of high value when further studying the roles of hippocampus.…”

Context-Dependent Regulation of Gene Expression by Non-Canonical Small RNAs

“…These signs are related to the loss of dopaminergic neurons in the substantia nigra and the pathology spreading to other regions of the brain. The α-synuclein protein elicits the insoluble aggregates that compose the main structure of Lewy bodies leading to the death of dopaminergic neurons [ 90 ]. miR-7 inhibits α-synuclein expression directly through the 3′ UTR of α-synuclein mRNA.…”

Precision machine learning to understand micro-RNA regulation in neurodegenerative diseases

“…Both the regulation of genes controlled by miRNAs and altered miRNA expression have been linked to several neurodegenerative diseases (NDs) such as Alzheimer's disease and Parkinson's disease. In the context of these two diseases, studies using blood samples and postmortem brain tissue from patients have highlighted differential expression of miRNAs such as mir-1, mir-22p, mir-26b -3p, and mir-28-3p (Pritchard et al, 2012;Hu et al, 2016;Kumar et al, 2017;Garcia-Fonseca et al, 2021). Several studies also linked Huntington's disease (HD) pathogenesis to miRNA regulation (Marti et al, 2010;Ghose et al, 2011;Jin et al, 2012).…”

“…These methods can be divided into two main classes of algorithms: supervised learning algorithms and unsupervised learning algorithms. The former class involves feeding the algorithm with labeled data that, after training, enable unknown information to be labeled based on the patterns learned from the data used for training, namely the training set, whereas the purpose of the latter class is to classify the data, based on similar patterns in the data itself (Carpenter and Huang, 2018;Garcia-Fonseca et al, 2021).…”