Identification of endoplasmic reticulum stress-associated genes and subtypes for prediction of Alzheimer’s disease based on interpretable machine learning

Lai, Yongxing; Lin, Xiao Yan; Lin, Chunjin; Lin, Xing; Chen, Zhihan; Zhang, Li

doi:10.3389/fphar.2022.975774

Cited by 18 publications

(19 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Monica et al [148] compare the performances of the best three models from 'The Alzheimer's disease prediction of Longitudinal evolution' (TADPOLE) challenge concerning prediction and interpretability within a common XAI framework. Based on interpretable machine learning, Lai et al [149] investigate the endoplasmic reticulum (ER) stress-related gene function in AD patients and identify six feature-rich genes (RNF5, UBA C2, DNAJC10, RNF103, DDX3X, and NGLY1) that enable accurate prediction of AD progression. An XAI method can now illustrate which feature-rich gene will influence the prediction output for an ML model.…”

Section: Resultsmentioning

confidence: 99%

“…Another significant lapse in almost all studies we considered is the limited use of medical datasets or the non-availability of a comprehensive benchmark dataset that exhibits variations representing real-world scenarios [166]. It impedes testing of the model on an extensive dataset which is crucial in determining the actual robustness [167,124,148,149]. Hence, most of the studies in the literature ended up with subjective claims but exhibited subpar performance due to generalisability issues when tested on a different dataset [166].…”

Section: Xai Researchers Often Resort To Self-intuition To De-mentioning

confidence: 99%

“…Fig. 26 Yongxing et al [149] make use of learning models AdaBoost, LR, LGBM, DT, XGBoost, RF, kNN, Naive Bayes, and SVM along with SHAP to generate force plots to illustrate profiles of the afflicted patient and normal subjects. In this study, the authors found six genes that could accurately predict AD progression and used SHAP to explain the decision-making process of the model used.…”

Section: Visualmentioning

confidence: 99%

See 2 more Smart Citations

Application of Explainable Artificial Intelligence in Alzheimer's Disease Classification: A Systematic Review

Vimbi¹,

Shaffi²,

Mahmud

et al. 2023

Preprint

View full text Add to dashboard Cite

Context: Artificial Intelligence (AI) in the medical domain has achieved remarkable results on various metrics primarily due to recent advancements in computational capabilities. However, AI models used for Computer Aided Diagnosis (CAD) have limited acceptance and trust due to their typical {Blackbox} nature. Consequently, explainable AI (XAI) is needed to justify the trustworthiness of the machine's predictions. Approach: In this work, we undertake a systematic review based on PRISMA guidelines on research articles investigating Alzheimer's Disease (AD) prediction with XAI for the past decade. The review was driven by carefully formulated research questions (RQ) which helped categorize AI models into different XAI methods(Post-hoc, Ante-hoc, Model-Agnostic, Model-Specific, etc) and frameworks (LIME, SHAP, GradCAM, LRP, etc.). Summary: This categorisation provides broad coverage of the interpretation spectrum from intrinsic (model-specific, ante-hoc models) to complex patterns (model-agnostic, post-hoc models) and by taking local explanations to a global scope. Additionally, the study categorizes merit in terms of different forms of interpretation to provide in-depth insight into the factors that support the clinical diagnosis of AD. Finally, limitations and open research challenges are outlined, and possible prospects are presented.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Xai Researchers Often Resort To Self-intuition To De-mentioning

confidence: 99%

Section: Visualmentioning

confidence: 99%

See 1 more Smart Citation

Application of Explainable Artificial Intelligence in Alzheimer's Disease Classification: A Systematic Review

Vimbi¹,

Shaffi²,

Mahmud

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The iterative learning process of the SVM eventually converges to the optimal hyperplane that provides the largest inter-class span ( 31 ). These machine-learning models were constructed in accordance with our previous study ( 32 ). Briefly, the classification of diseases was recognized as the response variable, and the immune microenvironment-associated DEGs were selected as the explanatory variables.…”

Section: Methodsmentioning

confidence: 99%

Identification of immune microenvironment subtypes and signature genes for Alzheimer’s disease diagnosis and risk prediction based on explainable machine learning

Lai

Lin²,

Lin³

et al. 2022

Front. Immunol.

Self Cite

View full text Add to dashboard Cite

BackgroundUsing interpretable machine learning, we sought to define the immune microenvironment subtypes and distinctive genes in AD.MethodsssGSEA, LASSO regression, and WGCNA algorithms were used to evaluate immune state in AD patients. To predict the fate of AD and identify distinctive genes, six machine learning algorithms were developed. The output of machine learning models was interpreted using the SHAP and LIME algorithms. For external validation, four separate GEO databases were used. We estimated the subgroups of the immunological microenvironment using unsupervised clustering. Further research was done on the variations in immunological microenvironment, enhanced functions and pathways, and therapeutic medicines between these subtypes. Finally, the expression of characteristic genes was verified using the AlzData and pan-cancer databases and RT-PCR analysis.ResultsIt was determined that AD is connected to changes in the immunological microenvironment. WGCNA revealed 31 potential immune genes, of which the greenyellow and blue modules were shown to be most associated with infiltrated immune cells. In the testing set, the XGBoost algorithm had the best performance with an AUC of 0.86 and a P-R value of 0.83. Following the screening of the testing set by machine learning algorithms and the verification of independent datasets, five genes (CXCR4, PPP3R1, HSP90AB1, CXCL10, and S100A12) that were closely associated with AD pathological biomarkers and allowed for the accurate prediction of AD progression were found to be immune microenvironment-related genes. The feature gene-based nomogram may provide clinical advantages to patients. Two immune microenvironment subgroups for AD patients were identified, subtype2 was linked to a metabolic phenotype, subtype1 belonged to the immune-active kind. MK-866 and arachidonyltrifluoromethane were identified as the top treatment agents for subtypes 1 and 2, respectively. These five distinguishing genes were found to be intimately linked to the development of the disease, according to the Alzdata database, pan-cancer research, and RT-PCR analysis.ConclusionThe hub genes associated with the immune microenvironment that are most strongly associated with the progression of pathology in AD are CXCR4, PPP3R1, HSP90AB1, CXCL10, and S100A12. The hypothesized molecular subgroups might offer novel perceptions for individualized AD treatment.

show abstract

“…Through an iterative learning process, SVM converges to the optimal hyperplane that maximizes interclass span. These models of machine learning were built based on earlier study [25].…”

Section: Machine Learningmentioning

confidence: 99%

Identification and Validation of Metabolism-Related Genes in Alzheimer’s Disease

Lian

Cai

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

Background：Due to its heterogeneity, the pathogenic mechanisms underlying Alzheimer's disease (AD) are not yet fully elucidated. Emerging evidence has demonstrated the critical role of metabolism in the pathophysiology of AD. This study explored the metabolism-related signature genes of AD and precisely identified AD molecular subclasses. Methods: The AD datasets were obtained from the NCBI GEO, and metabolism-relevant genes were downloaded from a previously published compilation. Consensus clustering was utilized to identify AD subclasses. We evaluated the clinic characteristics, correlations with metabolic signatures and immune infiltration of the AD subclasses. Feature genes were screened by WGCNA and processed for GO and KEGG pathway analysis. Furthermore, we used three machine learning algorithms to further narrow down the selection of feature genes. Finally, we identified the diagnostic value and expression of feature genes using dataset and RT-PCR analysis. Results: Three subclasses of AD were identified and designated as MCA, MCB, and MCC. MCA had high AD progression signatures and maybe a high-risk subgroup compared to the other two groups. MCA displayed high glycolysis, fructose and galactose metabolism, whereas citrate cycle and pyruvate metabolism were decreased, associating with high immune infiltration. Conversely, MCB is chiefly involved in the citrate cycle and exhibits elevated expression of immune checkpoint genes. Through WGCNA, a set of 101 metabolic genes were discovered to having the strongest association with the poor progression of AD. Ultimately, the application of machine learning algorithms enabled us to successfully pinpoint eight feature genes. Employing the nomogram based on the eight feature genes translates to distinct clinical benefits for the patients. As indicated by the datasets and RT-PCR analysis, these eight distinctive genes are intimately linked to the advancement of the AD. Conclusion: Metabolic dysfunction is correlated with AD. Hypothetical molecular subclasses based on metabolic genes may provide new insights for individualized therapy of AD. The metabolic feature genes most robust correlation with the advancement of AD were GFAP, CYB5R3, DARS, KIAA0513, EZR, KCNC1, COLEC12 and TST.

show abstract

Identification of endoplasmic reticulum stress-associated genes and subtypes for prediction of Alzheimer’s disease based on interpretable machine learning

Cited by 18 publications

References 62 publications

Application of Explainable Artificial Intelligence in Alzheimer's Disease Classification: A Systematic Review

Application of Explainable Artificial Intelligence in Alzheimer's Disease Classification: A Systematic Review

Identification of immune microenvironment subtypes and signature genes for Alzheimer’s disease diagnosis and risk prediction based on explainable machine learning

Identification and Validation of Metabolism-Related Genes in Alzheimer’s Disease

Contact Info

Product

Resources

About