Preprint From Data to Insights: Machine Learning Empowers Prognostic Biomarker Prediction in Autism, 2023, Mehmetbeyoglu et al.

[SNT Gatchaman]

From Data to Insights: Machine Learning Empowers Prognostic Biomarker Prediction in Autism
Ecmel Mehmetbeyoglu; Abdulkerim Duman; Serpil Taheri; Yusuf Ozkul; Minoo Rassoulzadegan

Autism Spectrum Disorder (ASD) poses significant challenges to society and science due to its impact on communication, social interaction, and repetitive behaviour patterns in affected children. The Autism and Developmental Disabilities Monitoring (ADDM) Network continuously monitors ASD prevalence and characteristics. In 2020, ASD prevalence was estimated at one in 36 children, with higher rates than previous estimates.

This study focuses on ongoing ASD research conducted by Erciyes University. Serum samples from 45 ASD patients and 21 unrelated control participants were analysed to assess the expression of 372 microRNAs (miRNAs). Six miRNAs (miR-19a-3p, miR-361-5p, miR-3613-3p, miR-150-5p, miR-126-3p, and miR-499a-5p) exhibited significant downregulation in all ASD patients compared to healthy controls. The current study endeavours to identify dependable diagnostic biomarkers for ASD, addressing the pressing need for non-invasive, accurate, and cost-effective diagnostic tools, as current methods are subjective and time intensive.

A pivotal discovery in this study is the potential diagnostic value of miR-126-3p, offering the promise of earlier and more accurate ASD diagnoses, potentially leading to improved intervention outcomes. Leveraging machine learning, such as the K-nearest neighbours (KNN) model, presents a promising avenue for precise ASD diagnosis using miRNA biomarkers.


Link | PDF (Preprint: BioRxiv)

 

[SNT Gatchaman]

 

[SNT Gatchaman]

These findings suggested that alterations in miRNA expression patterns may contribute to the risk of developing ASD [...]. The significance of the findings is that this study has identified a potential of miR-126-3p, which can serve as a diagnostic biomarker for ASD with high accuracy.

Potential functional implications of miR-126-3p in molecular pathways gave offers valuable information for understanding the molecular interactions. We showed that miR-126-3p highly enriched in mTOR, a serine/threonine kinase, plays a pivotal role in regulating cellular responses to nutrient availability, influencing critical processes such as protein synthesis, cell growth, and proliferation.

Dysregulation in the mTOR pathway has been linked to the development of autism, contributing to aberrant synaptic protein synthesis and associated symptoms, including macrocephaly, seizures, and learning deficits. Notably, approximately 8-10% of autism cases have been associated with abnormalities in the mTOR signaling pathway. Moreover, a substantial proportion of autism predisposition genes directly or indirectly intersect with mTOR signaling activity. These findings collectively underscore the central role of mTOR signaling in autism.

 

[SNT Gatchaman]

miR-126-3p has come up in ME/LC research, with mixed findings.

Assessing diagnostic value of microRNAs from peripheral blood mononuclear cells and extracellular vesicles in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (2020, Nature Scientific Reports) —

Over-expressed in extracellular vesicles.

Role of the MicroRNAs in the Pathogenic Mechanism of Painful Symptoms in Long COVID: Systematic Review (2023, International Journal of Molecular Sciences) —

Reduced in plasma.

Across all studies included in the present review, miR-126-3p expression was found to be downregulated, Garg et al. compared miRNAs expression profiles in the plasma of ICU patients with severe COVID-19 requiring invasive ventilation, mechanically ventilated Influenza-ARDS patients, and healthy controls; the authors found a significant decrease only in the discovery cohort. Grehl et al. (2021) also found a significant downregulation in severe when compared with mild cases. An interesting result comes from the study of Keikha et al.; apart from finding a downregulation of miR-126-3p, they evaluated the patients who responded to treatment and those who did not. In the former, miR-126-3p expression returned to normal levels at week 2 and in the latter the downregulation was greater at 2 weeks. In line with this, Nicoletti et al. compared miRNA expression profiles of patients with COVID-19 and healthy controls, and they found a significant downregulation of miR-126-3p, but between severe and mild patients, this downregulation was not present, perhaps to the lower sample size between these two groups. Finally, Sabbatinelli et al. analyzed serum of COVID-19 patients and found a downregulation of miR-126-3p; they also found a significant positive correlation with miR-126-3p and neutrophils levels, and a significant negative correlation with IL-6 and D-dimer.

Altered endothelial dysfunction-related miRs in plasma from ME/CFS patients (2021, Nature Scientific Reports) —

Increased in plasma.

Our results show that miR‑21, miR‑34a, miR‑92a, miR‑126, and miR‑200c are jointly increased in ME/CFS patients compared to healthy controls.

In line with our findings, miR-126 was also found increased in extracellular vesicles from ME/CFSsa patients. miR-126 is described to exert an endothelial protective role against hypoxia/reoxygenation-induced injury, oxidative stress, and TNF-α by activating the Sirt1/eNOS axis in ECs. The circulating miR-126 was correlated to the improvement of endothelial function in male obese adolescents after exercise and diet control. In addition, miR-126 reduces oxidative stress, IL-6, and TNF-α and activates both eNOS and vascular endothelial growth factor (VEFG) in ECs. Recently, VEGF was found decreased in serum from ME/CFS patients, an interesting finding considering that VEGF promotes survival and stability of ECs. Altogether, higher plasma levels of miR-126 in ME/CFS patients might involve a compensatory mechanism against ED.

miRNAs: A potentially valuable tool in pesticide toxicology assessment-current experimental and epidemiological data review (2022, Chemosphere) —

Deregulated.

In the case of the herbicides, let-7, miR-30, miR-126, miR-181 and miR-320 were found to be commonly deregulated by atrazine, glyphosate and paraquat, which allows us to postulate these miRNAs as candidate molecular markers of herbicide exposure.

Downregulation of miR-363, let-7, miR181, miR-126 and miR-320 by different pesticides might be a cell response directed to block the possible oncogenic function of these miRNAs, while deregulation of miR-363, let-7, miR-181, miR-126 and miR-320, associated with carcinogenesis, may be one of the possible mechanisms of cell injury biomarkers after pesticides exposure.

 

[SNT Gatchaman]

Published (Dec 2023) as From Data to Insights: Machine Learning Empowers Prognostic Biomarker Prediction in Autism (2023, Journal of Personalized Medicine)