Classification algorithms applied to blood-based transcriptome meta-analysis to predict idiopathic Parkinson's disease

Hepatitis C virus infection and Parkinson's disease: insights from a joint sex-stratified BioOptimatics meta-analysis

Hepatitis C virus (HCV) infection poses a significant public health challenge and often leads to long-term health complications and even death. Parkinson's disease (PD) is a progressive neurodegenerative disorder with a proposed viral etiology. HCV infection and PD have been previously suggested to be related. This work aimed to identify potential biomarkers and pathways that may play a role in the joint development of PD and HCV infection. Using BioOptimatics-bioinformatics driven by mathematical global optimization-, 22 publicly available microarray and RNAseq datasets for both diseases were analyzed, focusing on sex-specific differences. Our results revealed that 19 genes, including MT1H, MYOM2, and RPL18, exhibited significant changes in expression in both diseases. Pathway and network analyses stratified by sex indicated that these gene expression changes were enriched in processes related to immune response regulation in females and immune cell activation in males. These findings suggest a potential link between HCV infection and PD, highlighting the importance of further investigation into the underlying mechanisms and potential therapeutic targets involved.

Machine Learning Models for Parkinson Disease: Systematic Review

Background

With the increasing availability of data, computing resources, and easier-to-use software libraries, machine learning (ML) is increasingly used in disease detection and prediction, including for Parkinson disease (PD). Despite the large number of studies published every year, very few ML systems have been adopted for real-world use. In particular, a lack of external validity may result in poor performance of these systems in clinical practice. Additional methodological issues in ML design and reporting can also hinder clinical adoption, even for applications that would benefit from such data-driven systems.

Objective

To sample the current ML practices in PD applications, we conducted a systematic review of studies published in 2020 and 2021 that used ML models to diagnose PD or track PD progression.

Methods

We conducted a systematic literature review in accordance with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines in PubMed between January 2020 and April 2021, using the following exact string: "Parkinson's" AND ("ML" OR "prediction" OR "classification" OR "detection" or "artificial intelligence" OR "AI"). The search resulted in 1085 publications. After a search query and review, we found 113 publications that used ML for the classification or regression-based prediction of PD or PD-related symptoms.

Results

Only 65.5% (74/113) of studies used a holdout test set to avoid potentially inflated accuracies, and approximately half (25/46, 54%) of the studies without a holdout test set did not state this as a potential concern. Surprisingly, 38.9% (44/113) of studies did not report on how or if models were tuned, and an additional 27.4% (31/113) used ad hoc model tuning, which is generally frowned upon in ML model optimization. Only 15% (17/113) of studies performed direct comparisons of results with other models, severely limiting the interpretation of results.

Conclusions

This review highlights the notable limitations of current ML systems and techniques that may contribute to a gap between reported performance in research and the real-life applicability of ML models aiming to detect and predict diseases such as PD.

Early-stage idiopathic Parkinson's disease is associated with reduced circular RNA expression

Neurodegeneration in Parkinson's disease (PD) precedes diagnosis by years. Early neurodegeneration may be reflected in RNA levels and measurable as a biomarker. Here, we present the largest quantification of whole blood linear and circular RNAs (circRNA) in early-stage idiopathic PD, using RNA sequencing data from two cohorts (PPMI = 259 PD, 161 Controls; ICICLE-PD = 48 PD, 48 Controls). We identified a replicable increase in TMEM252 and LMNB1 gene expression in PD. We identified novel differences in the expression of circRNAs from ESYT2, BMS1P1 and CCDC9, and replicated trends of previously reported circRNAs. Overall, using circRNA as a diagnostic biomarker in PD did not show any clear improvement over linear RNA, minimising its potential clinical utility. More interestingly, we observed a general reduction in circRNA expression in both PD cohorts, accompanied by an increase in RNASEL expression. This imbalance implicates the activation of an innate antiviral immune response and suggests a previously unknown aspect of circRNA regulation in PD.

Blood biomarker-based classification study for neurodegenerative diseases

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) and Parkinson's disease (PD) with the application of multiple feature selection methods. Based on ROC AUC performance, one optimal random forest (RF) model was discovered for AD with 159 gene markers (ROC-AUC = 0.886), while one optimal RF model was discovered for PD (ROC-AUC = 0.743). Additionally, in comparison to traditional ML approaches, deep learning approaches were applied to evaluate their potential applications in future works. We demonstrated that convolutional neural networks perform consistently well across both the Alzheimer's (ROC AUC = 0.810) and Parkinson's (ROC AUC = 0.715) datasets, suggesting its potential in gene expression biomarker detection with increased tuning of their architecture.

Brain-wide transcriptome-based metabolic alterations in Parkinson's disease: human inter-region and human-experimental model correlations

Alterations in brain metabolism are closely associated with the molecular hallmarks of Parkinson's disease (PD). A clear understanding of the main metabolic perturbations in PD is therefore important. Here, we retrospectively analysed the expression of metabolic genes from 34 PD-control post-mortem human brain transcriptome data comparisons from literature, spanning multiple brain regions. We found high metabolic correlations between the Substantia nigra (SN)- and cerebral cortex-derived tissues. Moreover, three clusters of PD patient cohorts were identified based on perturbed metabolic processes in the SN - each characterised by perturbations in (a) bile acid metabolism (b) omega-3 fatty acid metabolism, and (c) lipoic acid and androgen metabolism - metabolic themes not comprehensively addressed in PD. These perturbations were supported by concurrence between transcriptome and proteome changes in the expression patterns for CBR1, ECI2, BDH2, CYP27A1, ALDH1B1, ALDH9A1, ADH5, ALDH7A1, L1CAM, and PLXNB3 genes, providing a valuable resource for drug targeting and diagnosis. Also, we analysed 58 PD-control transcriptome data comparisons from in vivo/in vitro disease models and identified experimental PD models with significant correlations to matched human brain regions. Collectively, our findings suggest metabolic alterations in several brain regions, heterogeneity in metabolic alterations between study cohorts for the SN tissues and the need to optimize current experimental models to advance research on metabolic aspects of PD.

A Diagnostic Gene-Expression Signature in Fibroblasts of Amyotrophic Lateral Sclerosis

Amyotrophic lateral sclerosis (ALS) is a fatal, progressive neurodegenerative disease with limited treatment options. Diagnosis can be difficult due to the heterogeneity and non-specific nature of the initial symptoms, resulting in delays that compromise prompt access to effective therapeutic strategies. Transcriptome profiling of patient-derived peripheral cells represents a valuable benchmark in overcoming such challenges, providing the opportunity to identify molecular diagnostic signatures. In this study, we characterized transcriptome changes in skin fibroblasts of sporadic ALS patients (sALS) and controls and evaluated their utility as a molecular classifier for ALS diagnosis. Our analysis identified 277 differentially expressed transcripts predominantly involved in transcriptional regulation, synaptic transmission, and the inflammatory response. A support vector machine classifier based on this 277-gene signature was developed to discriminate patients with sALS from controls, showing significant predictive power in both the discovery dataset and in six independent publicly available gene expression datasets obtained from different sALS tissue/cell samples. Taken together, our findings support the utility of transcriptional signatures in peripheral cells as valuable biomarkers for the diagnosis of ALS.

The differential diagnosis value of radiomics-based machine learning in Parkinson's disease: a systematic review and meta-analysis

Background

In recent years, radiomics has been increasingly utilized for the differential diagnosis of Parkinson's disease (PD). However, the application of radiomics in PD diagnosis still lacks sufficient evidence-based support. To address this gap, we carried out a systematic review and meta-analysis to evaluate the diagnostic value of radiomics-based machine learning (ML) for PD.

Methods

We systematically searched Embase, Cochrane, PubMed, and Web of Science databases as of November 14, 2022. The radiomics quality assessment scale (RQS) was used to evaluate the quality of the included studies. The outcome measures were the c-index, which reflects the overall accuracy of the model, as well as sensitivity and specificity. During this meta-analysis, we discussed the differential diagnostic value of radiomics-based ML for Parkinson's disease and various atypical parkinsonism syndromes (APS).

Results

Twenty-eight articles with a total of 6,057 participants were included. The mean RQS score for all included articles was 10.64, with a relative score of 29.56%. The pooled c-index, sensitivity, and specificity of radiomics for predicting PD were 0.862 (95% CI: 0.833-0.891), 0.91 (95% CI: 0.86-0.94), and 0.93 (95% CI: 0.87-0.96) in the training set, and 0.871 (95% CI: 0.853-0.890), 0.86 (95% CI: 0.81-0.89), and 0.87 (95% CI: 0.83-0.91) in the validation set, respectively. Additionally, the pooled c-index, sensitivity, and specificity of radiomics for differentiating PD from APS were 0.866 (95% CI: 0.843-0.889), 0.86 (95% CI: 0.84-0.88), and 0.80 (95% CI: 0.75-0.84) in the training set, and 0.879 (95% CI: 0.854-0.903), 0.87 (95% CI: 0.85-0.89), and 0.82 (95% CI: 0.77-0.86) in the validation set, respectively.

Conclusion

Radiomics-based ML can serve as a potential tool for PD diagnosis. Moreover, it has an excellent performance in distinguishing Parkinson's disease from APS. The support vector machine (SVM) model exhibits excellent robustness when the number of samples is relatively abundant. However, due to the diverse implementation process of radiomics, it is expected that more large-scale, multi-class image data can be included to develop radiomics intelligent tools with broader applicability, promoting the application and development of radiomics in the diagnosis and prediction of Parkinson's disease and related fields.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=383197, identifier ID: CRD42022383197.

Uncovering ferroptosis in Parkinson's disease via bioinformatics and machine learning, and reversed deducing potential therapeutic natural products

Objective: Ferroptosis, a novel form of cell death, is closely associated with excessive iron accumulated within the substantia nigra in Parkinson's disease (PD). Despite extensive research, the underlying molecular mechanisms driving ferroptosis in PD remain elusive. Here, we employed a bioinformatics and machine learning approach to predict the genes associated with ferroptosis in PD and investigate the interactions between natural products and their active ingredients with these genes. Methods: We comprehensively analyzed differentially expressed genes (DEGs) for ferroptosis associated with PD (PDFerDEGs) by pairing 3 datasets (GSE7621, GSE20146, and GSE202665) from the NCBI GEO database and the FerrDb V2 database. A machine learning approach was then used to screen PDFerDEGs for signature genes. We mined the interacted natural product components based on screened signature genes. Finally, we mapped a network combined with ingredients and signature genes, then carried out molecular docking validation of core ingredients and targets to uncover potential therapeutic targets and ingredients for PD. Results: We identified 109 PDFerDEGs that were significantly enriched in biological processes and KEGG pathways associated with ferroptosis (including iron ion homeostasis, iron ion transport and ferroptosis, etc.). We obtained 29 overlapping genes and identified 6 hub genes (TLR4, IL6, ADIPOQ, PTGS2, ATG7, and FADS2) by screening with two machine learning algorithms. Based on this, we screened 263 natural product components and subsequently mapped the "Overlapping Genes-Ingredients" network. According to the network, top 5 core active ingredients (quercetin, 17-beta-estradiol, glycerin, trans-resveratrol, and tocopherol) were molecularly docked to hub genes to reveal their potential role in the treatment of ferroptosis in PD. Conclusion: Our findings suggested that PDFerDEGs are associated with ferroptosis and play a role in the progression of PD. Taken together, core ingredients (quercetin, 17-beta-estradiol, glycerin, trans-resveratrol, and tocopherol) bind well to hub genes (TLR4, IL6, ADIPOQ, PTGS2, ATG7, and FADS2), highlighting novel biomarkers for PD.

Identification of PLOD3 and LRRN3 as potential biomarkers for Parkinson's disease based on integrative analysis

Parkinson's disease (PD) is one of the most prevalent movement disorders and its diagnosis relies heavily on the typical clinical manifestations in the late stages. This study aims to screen and identify biomarkers of PD for earlier intervention. We performed a differential analysis of postmortem brain transcriptome studies. Weighted Gene Co-expression Network Analysis (WGCNA) was used to identify biomarkers related to Braak stage. We found 58 genes with significantly different expression in both PD brain tissue and blood samples. PD gene signature and risk score model consisting of nine genes were constructed using least absolute shrinkage and selection operator regression (LASSO) and logistic regression. PLOD3 and LRRN3 in gene signature were identified to serve as key genes as well as potential risk factors in PD. Gene function enrichment analysis and evaluation of immune cell infiltration revealed that PLOD3 was implicated in suppression of cellular metabolic function and inflammatory cell infiltration, whereas LRRN3 exhibited an inverse trend. The cellular subpopulation expression of the PLOD3 and LRRN3 has significant distributional variability. The expression of PLOD3 was more enriched in inflammatory cell subpopulations, such as microglia, whereas LRRN3 was more enriched in neurons and oligodendrocyte progenitor cells clusters (OPC). Additionally, the expression of PLOD3 and LRRN3 in Qilu cohort was verified to be consistent with previous results. Collectively, we screened and identified the functions of PLOD3 and LRRN3 based the integrated study. The combined detection of PLOD3 and LRRN3 expression in blood samples can improve the early detection of PD.

Development of a Pancreatic Fistula Prediction Model After Pancreaticoduodenectomy Based on a Decision Tree and Random Forest Algorithm

BACKGROUND

The incidence of postoperative pancreatic fistula (POPF) after pancreaticoduodenectomy (PD) is high. We sought to develop a POPF prediction model based on a decision tree (DT) and random forest (RF) algorithm after PD and to explore its clinical value.

METHODS

The case data of 257 patients who underwent PD in a tertiary general hospital from 2013 to 2021 were retrospectively collected in China. The RF model was used to select features by ranking the importance of variables, and both algorithms were used to build the prediction model after automatic adjustment of parameters by setting the respective hyperparameter intervals and resampling as a 10-fold cross-validation method, etc. The prediction model's performance was assessed by the receiver operating characteristic curve (ROC) and the area under curve (AUC).

RESULTS

Postoperative pancreatic fistula occurred in 56 cases (56/257, 21.8%). The DT model had an AUC of .743 and an accuracy of .840, while the RF model had an AUC of .977 and an accuracy of .883. The DT plot visualized the process of inferring the risk of pancreatic fistula from the DT model on independent individuals. The top 10 important variables were selected for ranking in the RF variable importance ranking.

CONCLUSION

This study successfully developed a DT and RF algorithm for the POPF prediction model, which can be used as a reference for clinical health care professionals to optimize treatment strategies to reduce the incidence of POPF.

A computational approach based on weighted gene co-expression network analysis for biomarkers analysis of Parkinson's disease and construction of diagnostic model

Background

Parkinson's disease (PD) is a common age-related chronic neurodegenerative disease. There is currently no affordable, effective, and less invasive test for PD diagnosis. Metabolite profiling in blood and blood-based gene transcripts is thought to be an ideal method for diagnosing PD.

Aim

In this study, the objective is to identify the potential diagnostic biomarkers of PD by analyzing microarray gene expression data of samples from PD patients.

Methods

A computational approach, namely, Weighted Gene Co-expression Network Analysis (WGCNA) was used to construct co-expression gene networks and identify the key modules that were highly correlated with PD from the GSE99039 dataset. The Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis was performed to identify the hub genes in the key modules with strong association with PD. The selected hub genes were then used to construct a diagnostic model based on logistic regression analysis, and the Receiver Operating Characteristic (ROC) curves were used to evaluate the efficacy of the model using the GSE99039 dataset. Finally, Reverse Transcription-Polymerase Chain Reaction (RT-PCR) was used to validate the hub genes.

Results

WGCNA identified two key modules associated with inflammation and immune response. Seven hub genes, LILRB1, LSP1, SIPA1, SLC15A3, MBOAT7, RNF24, and TLE3 were identified from the two modules and used to construct diagnostic models. ROC analysis showed that the diagnostic model had a good diagnostic performance for PD in the training and testing datasets. Results of the RT-PCR experiments showed that there were significant differences in the mRNA expression of LILRB1, LSP1, and MBOAT7 among the seven hub genes.

Conclusion

The 7-gene panel (LILRB1, LSP1, SIPA1, SLC15A3, MBOAT7, RNF24, and TLE3) will serve as a potential diagnostic signature for PD.

Bioinformatics and systems biology approaches to identify the effects of COVID-19 on neurodegenerative diseases: A review

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), causing coronavirus disease (COVID-19), has been devastated by COVID-19 in an increasing number of countries and health care systems around the world since its announcement of a global pandemic on 11 March 2020. During the pandemic, emerging novel viral mutant variants have caused multiple outbreaks of COVID-19 around the world and are prone to genetic evolution, causing serious damage to human health. As confirmed cases of COVID-19 spread rapidly, there is evidence that SARS-CoV-2 infection involves the central nervous system (CNS) and peripheral nervous system (PNS), directly or indirectly damaging neurons and further leading to neurodegenerative diseases (ND), but the molecular mechanisms of ND and CVOID-19 are unknown. We employed transcriptomic profiling to detect several major diseases of ND: Alzheimer 's disease (AD), Parkinson' s disease (PD), and multiple sclerosis (MS) common pathways and molecular biomarkers in association with COVID-19, helping to understand the link between ND and COVID-19. There were 14, 30 and 19 differentially expressed genes (DEGs) between COVID-19 and Alzheimer 's disease (AD), Parkinson' s disease (PD) and multiple sclerosis (MS), respectively; enrichment analysis showed that MAPK, IL-17, PI3K-Akt and other signaling pathways were significantly expressed; the hub genes (HGs) of DEGs between ND and COVID-19 were CRH, SST, TAC1, SLC32A1, GAD2, GAD1, VIP and SYP. Analysis of transcriptome data suggests multiple co-morbid mechanisms between COVID-19 and AD, PD, and MS, providing new ideas and therapeutic strategies for clinical prevention and treatment of COVID-19 and ND.

Blood-based gene-expression biomarkers identification for the non-invasive diagnosis of Parkinson's disease using two-layer hybrid feature selection

Parkinson's disease (PD) is one of the most prevalent neurodegenerative diseases. Understanding the molecular mechanism and identifying potential biomarkers of PD promote effective treatments to the patients. Due to less invasiveness and easy accessibility, biomarkers from blood support early detection and diagnosis of PD. This study combined three independent PD microarray gene expression data from blood samples applying the early integration approach. Moderated t-statistics was employed to identify differentially expressed genes (DEGs). Relevant genes were selected using a two-layer embedded wrapper feature selection method with gradient boosting machine (GBM) in the first layer followed by an ensemble of wrappers including Recursive Feature Elimination (RFE), Genetic algorithm (GA) and Bi-directional elimination (Stepwise). All three wrappers were based on logistic regression classifier (LR). The PD-predictability of the generated signature was tested using nine supervised classification models, including eight shallow machine learning and one deep learning. On an independent dataset, GSE72267, Support Vector Machine-Radial (SVMR), and Deep Neural Network (DNN) showed the best performance with AUC 0.821 and 0.82, respectively. Comparison with existing blood-based PD signatures and the biological analysis verified the reliability of the proposed signature.

Longitudinal intronic RNA-Seq analysis of Parkinson's disease patients reveals disease-specific nascent transcription

Transcriptomic studies usually focus on either gene or exon-based annotations, and only limited experiments have reported changes in reads mapping to introns. The analysis of intronic reads allows the detection of nascent transcription that is not influenced by steady-state RNA levels and provides information on actively transcribed genes. Here, we describe substantial intronic transcriptional changes in Parkinson's disease (PD) patients compared to healthy controls (CO) at two different timepoints; at the time of diagnosis (BL) and three years later (V08). We used blood RNA-Seq data from the Parkinson's Progression Markers Initiative (PPMI) cohort and identified significantly changed transcription of intronic reads only in PD patients during this follow-up period. In CO subjects, only nine transcripts demonstrated differentially expressed introns between visits. However, in PD patients, 4873 transcripts had differentially expressed introns at visit V08 compared to BL, many of them in genes previously associated with neurodegenerative diseases, such as LRRK2, C9orf72, LGALS3, KANSL1AS1, and ALS2. In addition, at the time of diagnosis (BL visit), we identified 836 transcripts (e.g. SNCA, DNAJC19, PRRG4) and at visit V08, 2184 transcripts (e.g. PINK1, GBA, ALS2, PLEKHM1) with differential intronic expression specific to PD patients. In contrast, reads mapping to exonic regions demonstrated little variation indicating highly specific changes only in intronic transcription. Our study demonstrated that PD is characterized by substantial changes in the nascent transcription, and description of these changes could help to understand the molecular pathology underpinning this disease.