Identification of Diagnostic Markers for Major Depressive Disorder Using Machine Learning Methods

MicroRNA classification and discovery for major depressive disorder diagnosis: Towards a robust and interpretable machine learning approach

BACKGROUND

Major depressive disorder (MDD) is notably underdiagnosed and undertreated due to its complex nature and subjective diagnostic methods. Biomarker identification would help provide a clearer understanding of MDD aetiology. Although machine learning (ML) has been implemented in previous studies to study the alteration of microRNA (miRNA) levels in MDD cases, clinical translation has not been feasible due to the lack of interpretability (i.e. too many miRNAs for consideration) and stability.

METHODS

This study applied logistic regression (LR) model to the blood miRNA expression profile to differentiate patients with MDD (n = 60) from healthy controls (HCs, n = 60). Embedded (L1-regularised logistic regression) feature selector was utilised to extract clinically relevant miRNAs, and optimized for clinical application.

RESULTS

Patients with MDD could be differentiated from HCs with the area under the receiver operating characteristic curve (AUC) of 0.81 on testing data when all available miRNAs were considered (which served as a benchmark). Our LR model selected miRNAs up to 5 (known as LR-5 model) emerged as the best model because it achieved a moderate classification ability (AUC = 0.75), relatively high interpretability (feature number = 5) and stability (ϕ̂Z=0.55) compared to the benchmark. The top-ranking miRNAs identified by our model have demonstrated associations with MDD pathways involving cytokine signalling in the immune system, the reelin signalling pathway, programmed cell death and cellular responses to stress.

CONCLUSION

The LR-5 model, which is optimised based on ML design factors, may lead to a robust and clinically usable MDD diagnostic tool.

An integrated machine learning framework for developing and validating a diagnostic model of major depressive disorder based on interstitial cystitis-related genes

BACKGROUND

Major depressive disorder (MDD) and interstitial cystitis (IC) are two highly debilitating conditions that often coexist with reciprocal effect, significantly exacerbating patients' suffering. However, the molecular underpinnings linking these disorders remain poorly understood.

METHODS

Transcriptomic data from GEO datasets including those of MDD and IC patients was systematically analyzed to develop and validate our model. Following removal of batch effect, differentially expressed genes (DEGs) between respective disease and control groups were identified. Shared DEGs of the conditions then underwent functional enrichment analyses. Additionally, immune infiltration analysis was quantified through ssGSEA. A diagnostic model for MDD was constructed by exploring 113 combinations of 12 machine learning algorithms with 10-fold cross-validation on the training sets following by external validation on test sets. Finally, the "Enrichr" platform was utilized to identify potential drugs for MDD.

RESULTS

Totally, 21 key genes closely associated with both MDD and IC were identified, predominantly involved in immune processes based on enrichment analyses. Immune infiltration analysis revealed distinct profiles of immune cell infiltration in MDD and IC compared to healthy controls. From these genes, a robust 11-gene (ABCD2, ATP8B4, TNNT1, AKR1C3, SLC26A8, S100A12, PTX3, FAM3B, ITGA2B, OLFM4, BCL7A) diagnostic signature was constructed, which exhibited superior performance over existing MDD diagnostic models both in training and testing cohorts. Additionally, epigallocatechin gallate and 10 other drugs emerged as potential targets for MDD.

CONCLUSION

Our work developed a diagnostic model for MDD employing a combination of bioinformatic techniques and machine learning methods, focusing on shared genes between MDD and IC.

Effectiveness of artificial intelligence in detecting and managing depressive disorders: Systematic review

OBJECTIVES

This study underscores the importance of exploring AI's creative applications in treating depressive disorders to revolutionize mental health care. Through innovative integration of AI technologies, the research confirms their positive effects on preventing, diagnosing, and treating depression. The systematic review establishes an evidence base for AI in depression management, offering directions for effective interventions.

METHODS

This systematic literature review investigates the effectiveness of AI in depression management by analyzing studies from January 1, 2017, to May 31, 2022. Utilizing search engines like IEEE Xplore, PubMed, and Web of Science, the review focused on keywords such as Depression/Mental Health, Machine Learning/Artificial Intelligence, and Prediction/Diagnosis. The analysis of 95 documents involved classification based on use, data type, and algorithm type.

RESULTS

The study revealed that AI in depression management excelled in accuracy, particularly in monitoring and prediction. Biomarker-derived data demonstrated the highest accuracy, with the CNN algorithm proving most effective. The findings affirm the therapeutic benefits of AI, including treatment, detection, and disease prediction, highlighting its potential in analyzing monitored data for depression management.

LIMITATIONS

This study exclusively examined the application of AI in individuals with depressive disorders. Interpretation should be cautious due to the limited scope of subjects to this specific population.

CONCLUSIONS

To introduce digital healthcare and therapies for ongoing depression management, it's crucial to present empirical evidence on the medical fee payment system, safety, and efficacy. These findings support enhanced medical accessibility through digital healthcare, offering personalized disease management for patients seeking non-face-to-face treatment.

Bioinformatics Analysis Reveals HIST1H2BH as a Novel Diagnostic Biomarker for Atrial Fibrillation-Related Cardiogenic Thromboembolic Stroke

Atrial fibrillation (AF) is a significant precursor to cerebral embolism. Our study sought to unearth new diagnostic biomarkers for atrial fibrillation-related cerebral embolism (AF-CE) by meticulously examining multiple GEO datasets and meta-analysis. The gene expression omnibus (GEO) database provided RNA sequencing data associated with AF and stroke. We began by pinpointing genes with varied expressions in AF-CE patient blood samples. A meta-analysis was subsequently undertaken using several RNA sequencing datasets to verify these genes. LASSO regression discerned key genes for AF-CE, with their diagnostic prowess verified through ROC curve examination. Active signaling pathways within stroke patients were discerned via GO and KEGG enrichment, with PPI interactions detailing gene interplay. Differential gene analysis revealed an upregulation of sixteen genes and a downregulation of four in stroke patient blood samples. Eight genes showcased varied expression in the meta-analysis. LASSO regression zeroed in on five of these, culminating in HIST1H2BH's identification as a characteristic gene. HIST1H2BH's prowess in predicting AF-CE was confirmed through ROC. Integrin signaling, platelet activation, ECM interactions, and the PI3K-Akt pathway were found active in stroke victims. HIST1H2BH's interaction with the notably upregulated ITGA2B was spotlighted by PPI. Additionally, HIST1H2BH exhibited links with NK cells and eosinophils. HIST1H2BH emerges as an insightful diagnostic beacon for AF-CE. Its presence, post AF, potentially modulates pathways, accentuating platelet activation and consequent thrombus generation, leading to cerebral embolism.

Analysis and validation of biomarkers of immune cell-related genes in postmenopausal osteoporosis: An observational study

Postmenopausal osteoporosis (PMOP) is a common metabolic inflammatory disease. In conditions of estrogen deficiency, chronic activation of the immune system leads to a hypo-inflammatory phenotype and alterations in its cytokine and immune cell profile, although immune cells play an important role in the pathology of osteoporosis, studies on this have been rare. Therefore, it is important to investigate the role of immune cell-related genes in PMOP. PMOP-related datasets were downloaded from the Gene Expression Omnibus database. Immune cells scores between high bone mineral density (BMD) and low BMD samples were assessed based on the single sample gene set enrichment analysis method. Subsequently, weighted gene co-expression network analysis was performed to identify modules highly associated with immune cells and obtain module genes. Differential analysis between high BMD and low BMD was also performed to obtain differentially expressed genes. Module genes are intersected with differentially expressed genes to obtain candidate genes, and functional enrichment analysis was performed. Machine learning methods were used to filter out the signature genes. The receiver operating characteristic (ROC) curves of the signature genes and the nomogram were plotted to determine whether the signature genes can be used as a molecular marker. Gene set enrichment analysis was also performed to explore the potential mechanism of the signature genes. Finally, RNA expression of signature genes was validated in blood samples from PMOP patients and normal control by real-time quantitative polymerase chain reaction. Our study of PMOP patients identified differences in immune cells (activated dendritic cell, CD56 bright natural killer cell, Central memory CD4 T cell, Effector memory CD4 T cell, Mast cell, Natural killer T cell, T follicular helper cell, Type 1 T-helper cell, and Type 17 T-helper cell) between high and low BMD patients. We obtained a total of 73 candidate genes based on modular genes and differential genes, and obtained 5 signature genes by least absolute shrinkage and selection operator and random forest model screening. ROC, principal component analysis, and t-distributed stochastic neighbor embedding down scaling analysis revealed that the 5 signature genes had good discriminatory ability between high and low BMD samples. A logistic regression model was constructed based on 5 signature genes, and both ROC and column line plots indicated that the model accuracy and applicability were good. Five signature genes were found to be associated with proteasome, mitochondria, and lysosome by gene set enrichment analysis. The real-time quantitative polymerase chain reaction results showed that the expression of the signature genes was significantly different between the 2 groups. HIST1H2AG, PYGM, NCKAP1, POMP, and LYPLA1 might play key roles in PMOP and be served as the biomarkers of PMOP.

Incorporating machine learning and PPI networks to identify mitochondrial fission-related immune markers in abdominal aortic aneurysms

Purpose

The aim of this study is to investigate abdominal aortic aneurysm (AAA), a disease characterised by inflammation and progressive vasodilatation, for novel gene-targeted therapeutic loci.

Methods

To do this, we used weighted co-expression network analysis (WGCNA) and differential gene analysis on samples from the GEO database. Additionally, we carried out enrichment analysis and determined that the blue module was of interest. Additionally, we performed an investigation of immune infiltration and discovered genes linked to immune evasion and mitochondrial fission. In order to screen for feature genes, we used two PPI network gene selection methods and five machine learning methods. This allowed us to identify the most featrue genes (MFGs). The expression of the MFGs in various cell subgroups was then evaluated by analysis of single cell samples from AAA. Additionally, we looked at the expression levels of the MFGs as well as the levels of inflammatory immune-related markers in cellular and animal models of AAA. Finally, we predicted potential drugs that could be targeted for the treatment of AAA.

Results

Our research identified 1249 up-regulated differential genes and 3653 down-regulated differential genes. Through WGCNA, we also discovered 44 genes in the blue module. By taking the point where several strategies for gene selection overlap, the MFG (ITGAL and SELL) was produced. We discovered through single cell research that the MFG were specifically expressed in T regulatory cells, NK cells, B lineage, and lymphocytes. In both animal and cellular models of AAA, the MFGs' mRNA levels rose.

Conclusion

We searched for the AAA novel targeted gene (ITGAL and SELL), which most likely function through lymphocytes of the B lineage, NK cells, T regulatory cells, and B lineage. This analysis gave AAA a brand-new goal to treat or prevent the disease.

Modulation of GABA A receptor trafficking by WWC2 reveals class-specific mechanisms of synapse regulation by WWC family proteins

WWC2 (WW and C2 domain-containing protein) is implicated in several neurological disorders, however its function in the brain has yet to be determined. Here, we demonstrate that WWC2 interacts with inhibitory but not excitatory postsynaptic scaffolds, consistent with prior proteomic identification of WWC2 as a putative component of the inhibitory postsynaptic density. Using mice lacking WWC2 expression in excitatory forebrain neurons, we show that WWC2 suppresses GABA A R incorporation into the plasma membrane and regulates HAP1 and GRIP1, which form a complex promoting GABA A R recycling to the membrane. Inhibitory synaptic transmission is dysregulated in CA1 pyramidal cells lacking WWC2. Furthermore, unlike the WWC2 homolog KIBRA (WWC1), a key regulator of AMPA receptor trafficking at excitatory synapses, deletion of WWC2 does not affect synaptic AMPAR expression. In contrast, loss of KIBRA does not affect GABA A R membrane expression. These data reveal unique, synapse class-selective functions for WWC proteins as regulators of ionotropic neurotransmitter receptors and provide insight into mechanisms regulating GABA A R membrane expression.

Discovering biomarkers associated and predicting cardiovascular disease with high accuracy using a novel nexus of machine learning techniques for precision medicine

Personalized interventions are deemed vital given the intricate characteristics, advancement, inherent genetic composition, and diversity of cardiovascular diseases (CVDs). The appropriate utilization of artificial intelligence (AI) and machine learning (ML) methodologies can yield novel understandings of CVDs, enabling improved personalized treatments through predictive analysis and deep phenotyping. In this study, we proposed and employed a novel approach combining traditional statistics and a nexus of cutting-edge AI/ML techniques to identify significant biomarkers for our predictive engine by analyzing the complete transcriptome of CVD patients. After robust gene expression data pre-processing, we utilized three statistical tests (Pearson correlation, Chi-square test, and ANOVA) to assess the differences in transcriptomic expression and clinical characteristics between healthy individuals and CVD patients. Next, the recursive feature elimination classifier assigned rankings to transcriptomic features based on their relation to the case-control variable. The top ten percent of commonly observed significant biomarkers were evaluated using four unique ML classifiers (Random Forest, Support Vector Machine, Xtreme Gradient Boosting Decision Trees, and k-Nearest Neighbors). After optimizing hyperparameters, the ensembled models, which were implemented using a soft voting classifier, accurately differentiated between patients and healthy individuals. We have uncovered 18 transcriptomic biomarkers that are highly significant in the CVD population that were used to predict disease with up to 96% accuracy. Additionally, we cross-validated our results with clinical records collected from patients in our cohort. The identified biomarkers served as potential indicators for early detection of CVDs. With its successful implementation, our newly developed predictive engine provides a valuable framework for identifying patients with CVDs based on their biomarker profiles.

Identification and Analyses of Crucial Genes Associated with Pathogenesis of Major Depressive Disorder

Background

Major depressive disorder is a debilitating mental condition that causes severe disability leading to a high fatality rate. No valid blood-based biomarkers for major depressive disorder are currently available. The purpose of this research is to investigate gene biomarkers and pathways that may be linked to major depressive disorder pathogenesis.

Methods

Two microarray databases were retrieved from Gene Expression Omnibus for screening of candidate differentially expressed genes. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway analyses were performed followed by protein-protein interaction network of differentially expressed genes.

Results

About 1181 differentially expressed genes were identified from the microarray databases. Gene Ontology analyses indicated that these differentially expressed genes were significantly enriched in mRNA splicing via spliceosome, neutrophil degranulation, peptide antigen assembly with MHC class II protein complex, and immunoglobulin production-mediated immune response. The most enriched Kyoto Encyclopedia of Genes and Genomes pathway terms of the 10 significant were Hematopoietic cell lineage. About 20 genes were identified as hub genes after pathway analyses, mostly involved in colorectal cancer and the composition of ribosomes and protein processing, including KRAS, CD86, RPL9, RPL3, and RPL18.

Conclusion

New candidate genes have been identified using bioinformatic approaches that suggest their involvement in the pathogenesis of major depressive disorder and serve as potential genetic diagnostic markers as well as new therapeutic targets.

IntelliGenes: a novel machine learning pipeline for biomarker discovery and predictive analysis using multi-genomic profiles

SUMMARY

In this article, we present IntelliGenes, a novel machine learning (ML) pipeline for the multi-genomics exploration to discover biomarkers significant in disease prediction with high accuracy. IntelliGenes is based on a novel approach, which consists of nexus of conventional statistical techniques and cutting-edge ML algorithms using multi-genomic, clinical, and demographic data. IntelliGenes introduces a new metric, i.e. Intelligent Gene (I-Gene) score to measure the importance of individual biomarkers for prediction of complex traits. I-Gene scores can be utilized to generate I-Gene profiles of individuals to comprehend the intricacies of ML used in disease prediction. IntelliGenes is user-friendly, portable, and a cross-platform application, compatible with Microsoft Windows, macOS, and UNIX operating systems. IntelliGenes not only holds the potential for personalized early detection of common and rare diseases in individuals, but also opens avenues for broader research using novel ML methodologies, ultimately leading to personalized interventions and novel treatment targets.

AVAILABILITY AND IMPLEMENTATION

The source code of IntelliGenes is available on GitHub (https://github.com/drzeeshanahmed/intelligenes) and Code Ocean (https://codeocean.com/capsule/8638596/tree/v1).

Ferroptosis-related genes as diagnostic markers for major depressive disorder and their correlations with immune infiltration

Background

Major depression disorder (MDD) is a devastating neuropsychiatric disease, and one of the leading causes of suicide. Ferroptosis, an iron-dependent form of regulated cell death, plays a pivotal role in numerous diseases. The study aimed to construct and validate a gene signature for diagnosing MDD based on ferroptosis-related genes (FRGs) and further explore the biological functions of these genes in MDD.

Methods

The datasets were downloaded from the Gene Expression Omnibus (GEO) database and FRGs were obtained from the FerrDb database and other literatures. Least absolute shrinkage and selection operator (LASSO) regression and stepwise logistic regression were performed to develop a gene signature. Receiver operating characteristic (ROC) curves were utilized to assess the diagnostic power of the signature. Gene ontology (GO) enrichment analysis was used to explore the biological roles of these diagnostic genes, and single sample gene set enrichment analysis (ssGSEA) algorithm was used to evaluate immune infiltration in MDD. Animal model of depression was constructed to validate the expression of the key genes.

Results

Eleven differentially expressed FRGs were identified in MDD patients compared with healthy controls. A signature of three FRGs (ALOX15B, RPLP0, and HP) was constructed for diagnosis of MDD. Afterwards, ROC analysis confirmed the signature's discriminative capacity (AUC = 0.783, 95% CI = 0.719-0.848). GO enrichment analysis revealed that the differentially expressed genes (DEGs) related to these three FRGs were mainly involved in immune response. Furthermore, spearman correlation analysis demonstrated that these three FRGs were associated with infiltrating immune cells. ALOX15B and HP were significantly upregulated and RPLP0 was significantly downregulated in peripheral blood of the lipopolysaccharide (LPS)-induced depressive model.

Conclusion

Our results suggest that the novel FRG signature had a good diagnostic performance for MDD, and these three FRGs correlated with immune infiltration in MDD.

EEG alpha band characteristics in patients with a depressive episode within recurrent and bipolar depression

BACKGROUND

The search for biological markers for the differential diagnosis of recurrent depression and bipolar depression is an important undertaking in modern psychiatry. Electroencephalography (EEG) is one of the promising tools in addressing this challenge.

AIM

To identify differences in the quantitative characteristics of the electroencephalographic alpha band activity in patients with a depressive episode within the framework of recurrent depression and bipolar depression.

METHODS

Two groups of patients (all women) were formed: one consisting of subjects with recurrent depressive disorder and one with subjects experiencing a current mild/moderate episode (30 patients), and subjects with bipolar affective disorder or a current episode of mild or moderate depression (30 patients). The groups did not receive pharmacotherapy and did not differ in their socio-demographic parameters or total score on the Hamilton depression scale. A baseline electroencephalogram was recorded, and the quantitative characteristics of the alpha band activity were analyzed, including the absolute spectral power, interhemispheric coherence, and EEG activation.

RESULTS

The patients with recurrent depressive disorder demonstrated statistically significantly lower values of the average absolute spectral power of the alpha band (z=2.481; p=0.042), as well as less alpha attenuation from eyes closed to eyes open (z=2.573; p=0.035), as compared with the patients with bipolar affective disorder.

CONCLUSION

The presented quantitative characteristics of alpha activity are confirmation that patients with affective disorders of different origins also display distinctive electrophysiological features which can become promising biomarkers and could help separate bipolar depression from the recurrent type.

Optimizing the predictive power of depression screenings using machine learning

Objective

Mental health self-report and clinician-rating scales with diagnoses defined by sum-score cut-offs are often used for depression screening. This study investigates whether machine learning (ML) can detect major depressive episodes (MDE) based on screening scales with higher accuracy than best-practice clinical sum-score approaches.

Methods

Primary data was obtained from two RCTs on the treatment of depression. Ground truth were DSM 5 MDE diagnoses based on structured clinical interviews (SCID) and PHQ-9 self-report, clinician-rated QIDS-16, and HAM-D-17 were predictors. ML models were trained using 10-fold cross-validation. Performance was compared against best-practice sum-score cut-offs. Primary outcome was the Area Under the Curve (AUC) of the Receiver Operating Characteristic curve. DeLong's test with bootstrapping was used to test for differences in AUC. Secondary outcomes were balanced accuracy, precision, recall, F1-score, and number needed to diagnose (NND).

Results

A total of k = 1030 diagnoses (no diagnosis: k = 775; MDE: k = 255) were included. ML models achieved an AUCQIDS-16 = 0.94, AUCHAM-D-17 = 0.88, and AUCPHQ-9 = 0.83 in the testing set. ML AUC was significantly higher than sum-score cut-offs for QIDS-16 and PHQ-9 (ps ≤ 0.01; HAM_D-17: p = 0.847). Applying optimal prediction thresholds, QIDS-16 classifier achieved clinically relevant improvements (Δbalanced accuracy = 8%, ΔF1-score = 14%, ΔNND = 21%). Differences for PHQ_9 and HAM-D-17 were marginal.

Conclusions

ML augmented depression screenings could potentially make a major contribution to improving MDE diagnosis depending on questionnaire (e.g., QIDS-16). Confirmatory studies are needed before ML enhanced screening can be implemented into routine care practice.

Gene Signatures Associated with Temporal Rhythm as Diagnostic Markers of Major Depressive Disorder and Their Role in Immune Infiltration

Temporal rhythm (TR) is involved in the pathophysiology and treatment response of major depressive disorder (MDD). However, there have been few systematic studies on the relationship between TR-related genes (TRRGs) and MDD. This study aimed to develop a novel prognostic gene signature based on the TRRGs in MDD. We extracted expression information from the Gene Expression Omnibus (GEO) database and retrieved TRRGs from GeneCards. Expressed genes (TRRDEGs) were identified differentially, and their potential biological functions were analyzed. Subsequently, association analysis and receiver operating characteristic (ROC) curves were adopted for the TRRDEGs. Further, upstream transcription factor (TF)/miRNA and potential drugs targeting MDD were predicted. Finally, the CIBERSORT algorithm was used to estimate the proportions of immune cell subsets. We identified six TRRDEGs that were primarily involved in malaria, cardiac muscle contraction, and the calcium-signaling pathway. Four genes (CHGA, CCDC47, ACKR1, and FKBP11) with an AUC of >0.70 were considered TRRDEGs hub genes for ROC curve analysis. Outcomes showed that there were a higher ratio of T cells, gamma-delta T cells, monocytes, and neutrophils, and lower degrees of CD8+ T cells, and memory resting CD4+ T cells in TRRDEGs. Four new TRRDEG signatures with excellent diagnostic performance and a relationship with the immune microenvironment were identified.

Novel feature selection methods for construction of accurate epigenetic clocks

Epigenetic clocks allow us to accurately predict the age and future health of individuals based on the methylation status of specific CpG sites in the genome and are a powerful tool to measure the effectiveness of longevity interventions. There is a growing need for methods to efficiently construct epigenetic clocks. The most common approach is to create clocks using elastic net regression modelling of all measured CpG sites, without first identifying specific features or CpGs of interest. The addition of feature selection approaches provides the opportunity to optimise the identification of predictive CpG sites. Here, we apply novel feature selection methods and combinatorial approaches including newly adapted neural networks, genetic algorithms, and ‘chained’ combinations. Human whole blood methylation data of ~470,000 CpGs was used to develop clocks that predict age with R2 correlation scores of greater than 0.73, the most predictive of which uses 35 CpG sites for a R2 correlation score of 0.87. The five most frequent sites across all clocks were modelled to build a clock with a R2 correlation score of 0.83. These two clocks are validated on two external datasets where they maintain excellent predictive accuracy. When compared with three published epigenetic clocks (Hannum, Horvath, Weidner) also applied to these validation datasets, our clocks outperformed all three models. We identified gene regulatory regions associated with selected CpGs as possible targets for future aging studies. Thus, our feature selection algorithms build accurate, generalizable clocks with a low number of CpG sites, providing important tools for the field.

Epigenetic clocks accurately predict a person’s age by measuring the levels of a chemical mark (methylation) at specific sites of the DNA. More of these clocks are being built all the time, and there is a need for tools to best construct these clocks, and particularly to pick the specific DNA sites to include. We propose several novel machine-learning tools for the optimised selection of these DNA sites, known as feature selection approaches. We applied our approaches to a large human blood dataset to develop several clocks that accurately predict age using 35 or less DNA sites with more accuracy than previously published clocks when applied to other datasets for validation. Some of the DNA sites identified may be associated with interesting genes to explore further for their role in aging. These approaches should enable the building of more accurate, generalizable age prediction clocks from a low number of DNA sites.

A machine learning model for predicting patients with major depressive disorder: A study based on transcriptomic data

Background

Identifying new biomarkers of major depressive disorder (MDD) would be of great significance for its early diagnosis and treatment. Herein, we constructed a diagnostic model of MDD using machine learning methods.

Methods

The GSE98793 and GSE19738 datasets were obtained from the Gene Expression Omnibus database, and the limma R package was used to analyze differentially expressed genes (DEGs) in MDD patients. Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed to identify potential molecular functions and pathways. A protein-protein interaction network (PPI) was constructed, and hub genes were predicted. Random forest (RF) and artificial neural network (ANN) machine-learning algorithms were used to select variables and construct a robust diagnostic model.

Results

A total of 721 DEGs were identified in peripheral blood samples of patients with MDD. GO and KEGG analyses revealed that the DEGs were mainly enriched in cytokines, defense responses to viruses, responses to biotic stimuli, immune effector processes, responses to external biotic stimuli, and immune systems. A PPI network was constructed, and CytoHubba plugins were used to screen hub genes. Furthermore, a robust diagnostic model was established using a RF and ANN algorithm with an area under the curve of 0.757 for the training model and 0.685 for the test cohort.

Conclusion

We analyzed potential driver genes in patients with MDD and built a potential diagnostic model as an adjunct tool to assist psychiatrists in the clinical diagnosis and treatment of MDD.

Artificial intelligence and machine learning approaches using gene expression and variant data for personalized medicine

Precision medicine uses genetic, environmental and lifestyle factors to more accurately diagnose and treat disease in specific groups of patients, and it is considered one of the most promising medical efforts of our time. The use of genetics is arguably the most data-rich and complex components of precision medicine. The grand challenge today is the successful assimilation of genetics into precision medicine that translates across different ancestries, diverse diseases and other distinct populations, which will require clever use of artificial intelligence (AI) and machine learning (ML) methods. Our goal here was to review and compare scientific objectives, methodologies, datasets, data sources, ethics and gaps of AI/ML approaches used in genomics and precision medicine. We selected high-quality literature published within the last 5 years that were indexed and available through PubMed Central. Our scope was narrowed to articles that reported application of AI/ML algorithms for statistical and predictive analyses using whole genome and/or whole exome sequencing for gene variants, and RNA-seq and microarrays for gene expression. We did not limit our search to specific diseases or data sources. Based on the scope of our review and comparative analysis criteria, we identified 32 different AI/ML approaches applied in variable genomics studies and report widely adapted AI/ML algorithms for predictive diagnostics across several diseases.

A novel 4 immune-related genes as diagnostic markers and correlated with immune infiltrates in major depressive disorder

Background

Immune response is prevalently related with major depressive disorder (MDD) pathophysiology. However, the study on the relationship between immune-related genes (IRGs) and immune infiltrates of MDD remains scarce.

Methods

We extracted expression data of 148 MDD patients from 2 cohorts, and systematically characterized differentially expressed IRGs by using limma package in R software. Then, the LASSO and multivariate logistic regression analysis was used to identify the most powerful IRGs. Next, we analyzed the relationship between IRGs and immune infiltrates of MDD. Finally, GSE76826 was used to to verificate of IRGs as a diagnostic markers in MDD.

Results

203 different IRGs s in MDD has been identified (P < 0.05). GSEA revealed that the different IRGs was more likely to be enriched in immune-specific pathways. Then, a 9 IRGs was successfully established to predict MDD based on LASSO. Next, 4 IRGs was obtained by multivariate logistic regression analysis, and AUC for CD1C, SPP1, CD3D, CAMKK2, and IRGs model was 0.733, 0.767, 0.816, 0.800, and 0.861, suggesting that they have a good diagnostic performance. Furthermore, the proportion of T cells CD8, T cells γδ, macrophages M0, and NK cells resting in MDD group was lower than that in the healthy controls, suggesting that the immune system in MDD group is impaired. Simultaneously, CD3D was validated a reliable marker in MDD, and was positively correlated with T cells CD8. GSEA revealed high expression CD3D was more likely to be enriched in immune-specific pathways, and low expression CD3D was more likely to be enriched in glucose metabolism metabolism-specific pathways.

Conclusions

We applied bioinformatics approaches to suggest that a 4 IRGs could serve as diagnostic markers to provide a novel direction to explore the pathogenesis of MDD.

A Review on Recent Progress in Machine Learning and Deep Learning Methods for Cancer Classification on Gene Expression Data

Data-driven model with predictive ability are important to be used in medical and healthcare. However, the most challenging task in predictive modeling is to construct a prediction model, which can be addressed using machine learning (ML) methods. The methods are used to learn and trained the model using a gene expression dataset without being programmed explicitly. Due to the vast amount of gene expression data, this task becomes complex and time consuming. This paper provides a recent review on recent progress in ML and deep learning (DL) for cancer classification, which has received increasing attention in bioinformatics and computational biology. The development of cancer classification methods based on ML and DL is mostly focused on this review. Although many methods have been applied to the cancer classification problem, recent progress shows that most of the successful techniques are those based on supervised and DL methods. In addition, the sources of the healthcare dataset are also described. The development of many machine learning methods for insight analysis in cancer classification has brought a lot of improvement in healthcare. Currently, it seems that there is highly demanded further development of efficient classification methods to address the expansion of healthcare applications.