Mining genetic and transcriptomic data using machine learning approaches in Parkinson's disease

TransGeneSelector: using a transformer approach to mine key genes from small transcriptomic datasets in plant responses to various environments

Gene mining is crucial for understanding the regulatory mechanisms underlying complex biological processes, particularly in plants responding to environmental conditions. Traditional machine learning methods, while useful, often overlook important gene relationships due to their reliance on manual feature selection and limited ability to capture complex inter-gene regulatory dynamics. Deep learning approaches, while powerful, are often unsuitable for small sample sizes. This study introduces TransGeneSelector, the first deep learning framework specifically designed for mining key genes from small transcriptomic datasets. By integrating a Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) for sample generation and a Transformer-based network for classification, TransGeneSelector efficiently addresses the challenges of small-sample transcriptomic data, capturing both global gene regulatory interactions and specific biological processes. Evaluated in Arabidopsis thaliana, the model achieved high classification accuracy in predicting seed germination and heat stress conditions, outperforming traditional methods like Random Forest and Support Vector Machines (SVM). Moreover, Shapley Additive Explanations (SHAP) analysis and gene regulatory network construction revealed that TransGeneSelector effectively identified genes that appear to have upstream regulatory functions based on our analyses, enriching them in multiple key pathways which are critical for seed germination and heat stress response. RT-qPCR validation further confirmed the model's gene selection accuracy, demonstrating consistent expression patterns across varying germination conditions. The findings underscore the potential of TransGeneSelector as a robust tool for gene mining, offering deeper insights into gene regulation and organism adaptation under diverse environmental conditions. This work provides a framework that leverages deep learning for key gene identification in small transcriptomic datasets.

Unlocking therapeutic frontiers: harnessing artificial intelligence in drug discovery for neurodegenerative diseases

Neurodegenerative diseases (NDs) pose serious healthcare challenges with limited therapeutic treatments and high social burdens. The integration of artificial intelligence (AI) into drug discovery has emerged as a promising approach to address these challenges. This review explores the application of AI techniques to unravel therapeutic frontiers for NDs. We examine the current landscape of AI-driven drug discovery and discuss the potentials of AI in accelerating the identification of novel therapeutic targets on ND research and drug development, optimization of drug candidates, and expediating personalized medicine approaches. Finally, we outline future directions and challenges in harnessing AI for the advancement of therapeutics in this critical area by emphasizing the importance of interdisciplinary collaboration and ethical considerations.

Alterations in Blood Methylome as Potential Epigenetic Biomarker in Sporadic Parkinson's Disease

OBJECTIVE

To characterize DNA methylation (DNAm) differences between sporadic Parkinson's disease (PD) and healthy control (HC) individuals enrolled in the Parkinson's Progression Markers Initiative (PPMI).

METHODS

Using whole blood, we characterized longitudinal differences in DNAm between sporadic PD patients (n = 196) and HCs (n = 86) enrolled in PPMI. RNA sequencing (RNAseq) was used to conduct gene expression analyses for genes mapped to differentially methylated cytosine-guanine sites (CpGs).

RESULTS

At the time of patient enrollment, 5,178 CpGs were differentially methylated (2,683 hypermethylated and 2,495 hypomethylated) in PD compared to HC. Of these, 579 CpGs underwent significant methylation changes over 3 years. Several differentially methylated CpGs were found near the cytochrome P450 family 2 subfamily E member 1 (CYP2E1) gene. Additionally, multiple hypermethylated CpGs were associated with the N-myc downregulated gene family member 4 (NDRG4) gene. RNA-Seq analyses showed 75 differentially expressed genes in PD patients compared to controls. An integrative analysis of both differentially methylated sites and differentially expressed genes revealed 20 genes that exhibited hypomethylation concomitant with overexpression. Additionally, 1 gene, cathepsin H (CTSH), displayed hypermethylation that was associated with its decreased expression.

INTERPRETATION

We provide initial evidence of alterations in DNAm in blood of PD patients that may serve as potential epigenetic biomarker of disease. To evaluate the significance of these changes throughout the progression of PD, additional profiling at longer intervals and during the prodromal stages of disease will be necessary. ANN NEUROL 2024;95:1162-1172.

Transcriptomic analysis reveals associations of blood-based A-to-I editing with Parkinson's disease

BACKGROUND

Adenosine-to-inosine (A-to-I) editing is the most common type of RNA editing in humans and the role of A-to-I RNA editing remains unclear in Parkinson's disease (PD).

OBJECTIVE

We aimed to explore the potential causal association between A-to-I editing and PD, and to assess whether changes in A-to-I editing were associated with cognitive progression in PD.

METHODS

The RNA-seq data from 380 PD patients and 178 healthy controls in the Parkinson's Progression Marker Initiative cohort was used to quantify A-to-I editing sites. We performed cis-RNA editing quantitative trait loci analysis and a two-sample Mendelian Randomization (MR) study by integrating genome-wide association studies to infer the potential causality between A-to-I editing and PD pathogenesis. The potential causal A-to-I editing sites were further confirmed by Summary-data-based MR analysis. Spearman's correlation analysis was performed to characterize the association between longitudinal A-to-I editing and cognitive progression in patients with PD.

RESULTS

We identified 17 potential causal A-to-I editing sites for PD and indicated that genetic risk variants may contribute to the risk of PD through A-to-I editing. These A-to-I editing sites were located in genes NCOR1, KANSL1 and BST1. Moreover, we observed 57 sites whose longitudinal A-to-I editing levels correlated with cognitive progression in PD.

CONCLUSIONS

We found potential causal A-to-I editing sites for PD onset and longitudinal changes of A-to-I editing were associated with cognitive progression in PD. We anticipate this study will provide new biological insights and drive the discovery of the epitranscriptomic role underlying Parkinson's disease.

Preclinical translational platform of neuroinflammatory disease biology relevant to neurodegenerative disease

Neuroinflammation is a key driver of neurodegenerative disease, however the tools available to model this disease biology at the systems level are lacking. We describe a translational drug discovery platform based on organotypic culture of murine cortical brain slices that recapitulate disease-relevant neuroinflammatory biology. After an acute injury response, the brain slices assume a chronic neuroinflammatory state marked by transcriptomic profiles indicative of activation of microglia and astrocytes and loss of neuronal function. Microglia are necessary for manifestation of this neuroinflammation, as depletion of microglia prior to isolation of the brain slices prevents both activation of astrocytes and robust loss of synaptic function genes. The transcriptomic pattern of neuroinflammation in the mouse platform is present in published datasets derived from patients with amyotrophic lateral sclerosis, Huntington's disease, and frontotemporal dementia. Pharmacological utility of the platform was validated by demonstrating reversal of microglial activation and the overall transcriptomic signature with transforming growth factor-β. Additional anti-inflammatory targets were screened and inhibitors of glucocorticoid receptors, COX-2, dihydrofolate reductase, and NLRP3 inflammasome all failed to reverse the neuroinflammatory signature. Bioinformatics analysis of the neuroinflammatory signature identified protein tyrosine phosphatase non-receptor type 11 (PTPN11/SHP2) as a potential target. Three structurally distinct inhibitors of PTPN11 (RMC-4550, TN0155, IACS-13909) reversed the neuroinflammatory disease signature. Collectively, these results highlight the utility of this novel neuroinflammatory platform for facilitating identification and validation of targets for neuroinflammatory neurodegenerative disease drug discovery.

Transcriptomic research in atherosclerosis: Unravelling plaque phenotype and overcoming methodological challenges

Atherosclerotic disease is a major cause of acute cardiovascular events. A deeper understanding of its underlying mechanisms will allow advancing personalized and patient-centered healthcare. Transcriptomic research has proven to be a powerful tool for unravelling the complex molecular pathways that drive atherosclerosis. However, low reproducibility of research findings and lack of standardization of procedures pose significant challenges in this field. In this review, we discuss how transcriptomic research can help in understanding the different phenotypes of the atherosclerotic plaque that contribute to the development and progression of atherosclerosis. We highlight the methodological challenges that need to be addressed to improve research outputs, and emphasize the importance of research protocols harmonization. We also discuss recent advances in transcriptomic research, including bulk or single-cell sequencing, and their added value in plaque phenotyping. Finally, we explore how integrated multiomics data and machine learning improve understanding of atherosclerosis and provide directions for future research.

Bioinformatics analysis and machine learning approach applied to the identification of novel key genes involved in non-alcoholic fatty liver disease

Non-alcoholic fatty liver disease (NAFLD) comprises a range of chronic liver diseases that result from the accumulation of excess triglycerides in the liver, and which, in its early phases, is categorized NAFLD, or hepato-steatosis with pure fatty liver. The mortality rate of non-alcoholic steatohepatitis (NASH) is more than NAFLD; therefore, diagnosing the disease in its early stages may decrease liver damage and increase the survival rate. In the current study, we screened the gene expression data of NAFLD patients and control samples from the public dataset GEO to detect DEGs. Then, the correlation betweenbetween the top selected DEGs and clinical data was evaluated. In the present study, two GEO datasets (GSE48452, GSE126848) were downloaded. The dysregulated expressed genes (DEGs) were identified by machine learning methods (Penalize regression models). Then, the shared DEGs between the two training datasets were validated using validation datasets. ROC-curve analysis was used to identify diagnostic markers. R software analyzed the interactions between DEGs, clinical data, and fatty liver. Ten novel genes, including ABCF1, SART3, APC5, NONO, KAT7, ZPR1, RABGAP1, SLC7A8, SPAG9, and KAT6A were found to have a differential expression between NAFLD and healthy individuals. Based on validation results and ROC analysis, NR4A2 and IGFBP1b were identified as diagnostic markers. These key genes may be predictive markers for the development of fatty liver. It is recommended that these key genes are assessed further as possible predictive markers during the development of fatty liver.

Applications of Machine Learning to Diagnosis of Parkinson's Disease

BACKGROUND

Accurate diagnosis of Parkinson's disease (PD) is challenging due to its diverse manifestations. Machine learning (ML) algorithms can improve diagnostic precision, but their generalizability across medical centers in China is underexplored.

OBJECTIVE

To assess the accuracy of an ML algorithm for PD diagnosis, trained and tested on data from different medical centers in China.

METHODS

A total of 1656 participants were included, with 1028 from Beijing (training set) and 628 from Fuzhou (external validation set). Models were trained using the least absolute shrinkage and selection operator-logistic regression (LASSO-LR), decision tree (DT), random forest (RF), eXtreme gradient boosting (XGboost), support vector machine (SVM), and k-nearest neighbor (KNN) techniques. Hyperparameters were optimized using five-fold cross-validation and grid search techniques. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, accuracy, sensitivity (recall), specificity, precision, and F1 score. Variable importance was assessed for all models.

RESULTS

SVM demonstrated the best differentiation between healthy controls (HCs) and PD patients (AUC: 0.928, 95% CI: 0.908-0.947; accuracy: 0.844, 95% CI: 0.814-0.871; sensitivity: 0.826, 95% CI: 0.786-0.866; specificity: 0.861, 95% CI: 0.820-0.898; precision: 0.849, 95% CI: 0.807-0.891; F1 score: 0.837, 95% CI: 0.803-0.868) in the validation set. Constipation, olfactory decline, and daytime somnolence significantly influenced predictability.

CONCLUSION

We identified multiple pivotal variables and SVM as a precise and clinician-friendly ML algorithm for prediction of PD in Chinese patients.

Modern Methods of Diagnostics and Treatment of Neurodegenerative Diseases and Depression

This paper discusses the promising areas of research into machine learning applications for the prevention and correction of neurodegenerative and depressive disorders. These two groups of disorders are among the leading causes of decline in the quality of life in the world when estimated using disability-adjusted years. Despite decades of research, the development of new approaches for the assessment (especially pre-clinical) and correction of neurodegenerative diseases and depressive disorders remains among the priority areas of research in neurophysiology, psychology, genetics, and interdisciplinary medicine. Contemporary machine learning technologies and medical data infrastructure create new research opportunities. However, reaching a consensus on the application of new machine learning methods and their integration with the existing standards of care and assessment is still a challenge to overcome before the innovations could be widely introduced to clinics. The research on the development of clinical predictions and classification algorithms contributes towards creating a unified approach to the use of growing clinical data. This unified approach should integrate the requirements of medical professionals, researchers, and governmental regulators. In the current paper, the current state of research into neurodegenerative and depressive disorders is presented.

Machine learning-based prediction of cognitive outcomes in de novo Parkinson's disease

Cognitive impairment is a debilitating symptom in Parkinson's disease (PD). We aimed to establish an accurate multivariate machine learning (ML) model to predict cognitive outcome in newly diagnosed PD cases from the Parkinson's Progression Markers Initiative (PPMI). Annual cognitive assessments over an 8-year time span were used to define two cognitive outcomes of (i) cognitive impairment, and (ii) dementia conversion. Selected baseline variables were organized into three subsets of clinical, biofluid and genetic/epigenetic measures and tested using four different ML algorithms. Irrespective of the ML algorithm used, the models consisting of the clinical variables performed best and showed better prediction of cognitive impairment outcome over dementia conversion. We observed a marginal improvement in the prediction performance when clinical, biofluid, and epigenetic/genetic variables were all included in one model. Several cerebrospinal fluid measures and an epigenetic marker showed high predictive weighting in multiple models when included alongside clinical variables.

Predicting the effect of sirolimus on disease activity in patients with systemic lupus erythematosus using machine learning

WHAT IS KNOWN AND OBJECTIVES

The present study aimed to predict the effect of sirolimus on disease activity in patients with systemic lupus erythematosus (SLE) using machine learning and to recommend appropriate sirolimus dosage regimen for patients with SLE.

METHODS

The E_max model was selected for machine learning, where the evaluation indicator was the change rate of systemic lupus erythematosus disease activity index from baseline value.

RESULTS

A total 103 patients with SLE were included for modelling, where the E_max , ET₅₀ were -53.9%, 1.53 months in the final model respectively, and the evaluation of the final model was good. Further simulation found that the follow-up time to achieve 25%, 50%, 75% and 80% (plateau) E_max of sirolimus effecting on disease activity in patients with SLE were 0.51, 1.53, 4.59 and 6.12 months, respectively. In addition, the sirolimus dosage was flexible and adjusted according to drug concentration, where the intersection of sirolimus concentration range included in this study was about 8-10 ng/ml.

WHAT IS NEW AND CONCLUSIONS

This study was the first time to predict the effect of sirolimus on disease activity in patients with SLE and in order to achieve better therapeutic effect maintaining a concentration of 8-10 ng/ml sirolimus for at least 6.12 months was necessary.

Deep Learning Paradigm for Cardiovascular Disease/Stroke Risk Stratification in Parkinson's Disease Affected by COVID-19: A Narrative Review

Background and Motivation: Parkinson's disease (PD) is one of the most serious, non-curable, and expensive to treat. Recently, machine learning (ML) has shown to be able to predict cardiovascular/stroke risk in PD patients. The presence of COVID-19 causes the ML systems to become severely non-linear and poses challenges in cardiovascular/stroke risk stratification. Further, due to comorbidity, sample size constraints, and poor scientific and clinical validation techniques, there have been no well-explained ML paradigms. Deep neural networks are powerful learning machines that generalize non-linear conditions. This study presents a novel investigation of deep learning (DL) solutions for CVD/stroke risk prediction in PD patients affected by the COVID-19 framework. Method: The PRISMA search strategy was used for the selection of 292 studies closely associated with the effect of PD on CVD risk in the COVID-19 framework. We study the hypothesis that PD in the presence of COVID-19 can cause more harm to the heart and brain than in non-COVID-19 conditions. COVID-19 lung damage severity can be used as a covariate during DL training model designs. We, therefore, propose a DL model for the estimation of, (i) COVID-19 lesions in computed tomography (CT) scans and (ii) combining the covariates of PD, COVID-19 lesions, office and laboratory arterial atherosclerotic image-based biomarkers, and medicine usage for the PD patients for the design of DL point-based models for CVD/stroke risk stratification. Results: We validated the feasibility of CVD/stroke risk stratification in PD patients in the presence of a COVID-19 environment and this was also verified. DL architectures like long short-term memory (LSTM), and recurrent neural network (RNN) were studied for CVD/stroke risk stratification showing powerful designs. Lastly, we examined the artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients in the presence of COVID-19. Conclusion: The DL is a very powerful tool for predicting CVD/stroke risk in PD patients affected by COVID-19.

Artificial Intelligence Predictor for Alzheimer’s Disease Trained on Blood Transcriptome: The Role of Oxidative Stress

Alzheimer’s disease (AD) is an incurable neurodegenerative disease diagnosed by clinicians through healthcare records and neuroimaging techniques. These methods lack sensitivity and specificity, so new antemortem non-invasive strategies to diagnose AD are needed. Herein, we designed a machine learning predictor based on transcriptomic data obtained from the blood of AD patients and individuals without dementia (non-AD) through an 8 × 60 K microarray. The dataset was used to train different models with different hyperparameters. The support vector machines method allowed us to reach a Receiver Operating Characteristic score of 93% and an accuracy of 89%. High score levels were also achieved by the neural network and logistic regression methods. Furthermore, the Gene Ontology enrichment analysis of the features selected to train the model along with the genes differentially expressed between the non-AD and AD transcriptomic profiles shows the “mitochondrial translation” biological process to be the most interesting. In addition, inspection of the KEGG pathways suggests that the accumulation of β-amyloid triggers electron transport chain impairment, enhancement of reactive oxygen species and endoplasmic reticulum stress. Taken together, all these elements suggest that the oxidative stress induced by β-amyloid is a key feature trained by the model for the prediction of AD with high accuracy.

A Machine Learning Approach to Parkinson’s Disease Blood Transcriptomics

The increased incidence and the significant health burden associated with Parkinson’s disease (PD) have stimulated substantial research efforts towards the identification of effective treatments and diagnostic procedures. Despite technological advancements, a cure is still not available and PD is often diagnosed a long time after onset when irreversible damage has already occurred. Blood transcriptomics represents a potentially disruptive technology for the early diagnosis of PD. We used transcriptome data from the PPMI study, a large cohort study with early PD subjects and age matched controls (HC), to perform the classification of PD vs. HC in around 550 samples. Using a nested feature selection procedure based on Random Forests and XGBoost we reached an AUC of 72% and found 493 candidate genes. We further discussed the importance of the selected genes through a functional analysis based on GOs and KEGG pathways.

Bias Investigation in Artificial Intelligence Systems for Early Detection of Parkinson's Disease: A Narrative Review

Background and Motivation: Diagnosis of Parkinson's disease (PD) is often based on medical attention and clinical signs. It is subjective and does not have a good prognosis. Artificial Intelligence (AI) has played a promising role in the diagnosis of PD. However, it introduces bias due to lack of sample size, poor validation, clinical evaluation, and lack of big data configuration. The purpose of this study is to compute the risk of bias (RoB) automatically.

METHOD

The PRISMA search strategy was adopted to select the best 39 AI studies out of 85 PD studies closely associated with early diagnosis PD. The studies were used to compute 30 AI attributes (based on 6 AI clusters), using AP(ai)Bias 1.0 (AtheroPointTM, Roseville, CA, USA), and the mean aggregate score was computed. The studies were ranked and two cutoffs (Moderate-Low (ML) and High-Moderate (MH)) were determined to segregate the studies into three bins: low-, moderate-, and high-bias.

RESULT

The ML and HM cutoffs were 3.50 and 2.33, respectively, which constituted 7, 13, and 6 for low-, moderate-, and high-bias studies. The best and worst architectures were "deep learning with sketches as outcomes" and "machine learning with Electroencephalography," respectively. We recommend (i) the usage of power analysis in big data framework, (ii) that it must undergo scientific validation using unseen AI models, and (iii) that it should be taken towards clinical evaluation for reliability and stability tests.

CONCLUSION

The AI is a vital component for the diagnosis of early PD and the recommendations must be followed to lower the RoB.

Machine Learning and Intracranial Aneurysms: From Detection to Outcome Prediction

Machine learning (ML) is a rapidly rising research tool in biomedical sciences whose applications include segmentation, classification, disease detection, and outcome prediction. With respect to traditional statistical methods, ML algorithms have the potential to learn and improve their predictive performance when fed with large data sets without the need of being specifically programmed. In recent years, this technology has been increasingly applied for tackling clinical issues in intracranial aneurysm (IA) research. Several studies attempted to provide reliable models for enhanced aneurysm detection. Convolutional neural networks trained with variable degrees of human interaction on data from diverse imaging modalities showed high sensitivity in aneurysm detection tasks, also outperforming expert image analysis. Algorithms were also shown to differentiate ruptured from unruptured IAs, with however limited clinical relevance. For prediction of rupture and stability assessment, ML was preliminarily shown to achieve better performance compared to conventional statistical methods and existing risk scores. ML-based complication and functional outcome prediction in the event of SAH have been more extensively reported, in contrast with periprocedural outcome investigation in unruptured IA patients. ML has the potential to be a game changer in IA patient management. Currently clinical translation of experimental results is limited.

Machine learning meets omics: applications and perspectives

The innovation of biotechnologies has allowed the accumulation of omics data at an alarming rate, thus introducing the era of 'big data'. Extracting inherent valuable knowledge from various omics data remains a daunting problem in bioinformatics. Better solutions often need some kind of more innovative methods for efficient handlings and effective results. Recent advancements in integrated analysis and computational modeling of multi-omics data helped address such needs in an increasingly harmonious manner. The development and application of machine learning have largely advanced our insights into biology and biomedicine and greatly promoted the development of therapeutic strategies, especially for precision medicine. Here, we propose a comprehensive survey and discussion on what happened, is happening and will happen when machine learning meets omics. Specifically, we describe how artificial intelligence can be applied to omics studies and review recent advancements at the interface between machine learning and the ever-widest range of omics including genomics, transcriptomics, proteomics, metabolomics, radiomics, as well as those at the single-cell resolution. We also discuss and provide a synthesis of ideas, new insights, current challenges and perspectives of machine learning in omics.

Exploring photoacoustic spectroscopy-based machine learning together with metabolomics to assess breast tumor progression in a xenograft model ex vivo

In the current study, a breast tumor xenograft was established in athymic nude mice by subcutaneous injection of the MCF-7 cell line and assessed the tumor progression by photoacoustic spectroscopy combined with machine learning tools. The advancement of breast tumors in nude mice was validated by tumor volume kinetics and histopathology and corresponding image analysis by TissueQuant software compared to controls. The ex vivo tumors in progressive conditions belonging to time points, day 5th, 10th, 15th & 20th, were excited with 281 nm pulsed laser light and recorded the corresponding photoacoustic spectra in time domain. The spectra were then pre-processed, augmented for a 10-fold increase in the data strength, and subjected to wavelet packet transformation for feature extraction and selection using MATLAB software. In the present study, the top 10 features from all the time point groups under study were selected based on their prediction ranking values using the mRMR algorithm. The chosen features of all the time-point groups were then subjected to multi-class Support Vector Machine (SVM) algorithms for learning and classifying into respective time point groups under study. The analysis demonstrated accuracy values of 95.2%, 99.5%, and 80.3% with SVM- Radial Basis Function (SVM-RBF), SVM-Polynomial & SVM-Linear, respectively. The serum metabolomic levels during tumor progression complemented photoacoustic patterns of tumor progression, depicting breast cancer pathophysiology.

Genetic and Transcriptomic Biomarkers in Neurodegenerative Diseases: Current Situation and the Road Ahead

Neurodegenerative diseases are etiologically and clinically heterogeneous conditions, often reflecting a spectrum of disease rather than well-defined disorders. The underlying molecular complexity of these diseases has made the discovery and validation of useful biomarkers challenging. The search of characteristic genetic and transcriptomic indicators for preclinical disease diagnosis, prognosis, or subtyping is an area of ongoing effort and interest. The next generation of biomarker studies holds promise by implementing meaningful longitudinal and multi-modal approaches in large scale biobank and healthcare system scale datasets. This work will only be possible in an open science framework. This review summarizes the current state of genetic and transcriptomic biomarkers in Parkinson's disease, Alzheimer's disease, and amyotrophic lateral sclerosis, providing a comprehensive landscape of recent literature and future directions.