Feature Selection of OMIC Data by Ensemble Swarm Intelligence Based Approaches

Yao, Zhaomin; Zhu, Gancheng; Too, Jingwei; Duan, Meiyu; Wang, Zhiguo

doi:10.3389/fgene.2021.793629

Cited by 10 publications

(7 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thereafter, we designated TCGA as our training matrix, while GSE103091, GSE17907, and GSE26304 served as our external validation cohorts. Multiple machine learning paradigms, encompassing Cox boost, Lasso, 21 Elastic Net (Enet), Ridge, survival‐support vector machine (survival‐svm), 22 generalized augmented regression modeling (GBM), Cox's partial least squares Regression (plsRcox), Stepwise Cox, Random Forest (RSF), and Supervised Principal Component (SuperPC), were employed. From these, we forged 101 algorithmic amalgamations.…”

Section: Methodsmentioning

confidence: 99%

Precision unveiled: Synergistic genomic landscapes in breast cancer—Integrating single‐cell analysis and decoding drug toxicity for elite prognostication and tailored therapeutics

Jiang,

Zhang,

Jiang

et al. 2024

Environmental Toxicology

View full text Add to dashboard Cite

BackgroundGlobally, breast cancer, with diverse subtypes and prognoses, necessitates tailored therapies for enhanced survival rates. A key focus is glutamine metabolism, governed by select genes. This study explored genes associated with T cells and linked them to glutamine metabolism to construct a prognostic staging index for breast cancer patients for more precise medical treatment.MethodsTwo frameworks, T‐cell related genes (TRG) and glutamine metabolism (GM), stratified breast cancer patients. TRG analysis identified key genes via hdWGCNA and machine learning. T‐cell communication and spatial transcriptomics emphasized TRG's clinical value. GM was defined using Cox analyses and the Lasso algorithm. Scores categorized patients as TRG_high+GM_high (HH), TRG_high+GM_low (HL), TRG_low+GM_high (LH), or TRG_low+GM_low (LL). Similarities between HL and LH birthed a “Mixed” class and the TRG_GM classifier. This classifier illuminated gene variations, immune profiles, mutations, and drug responses.ResultsUtilizing a composite of two distinct criteria, we devised a typification index termed TRG_GM classifier, which exhibited robust prognostic potential for breast cancer patients. Our analysis elucidated distinct immunological attributes across the classifiers. Moreover, by scrutinizing the genetic variations across groups, we illuminated their unique genetic profiles. Insights into drug sensitivity further underscored avenues for tailored therapeutic interventions.ConclusionUtilizing TRG and GM, a robust TRG_GM classifier was developed, integrating clinical indicators to create an accurate predictive diagnostic map. Analysis of enrichment disparities, immune responses, and mutation patterns across different subtypes yields crucial subtype‐specific characteristics essential for prognostic assessment, clinical decision‐making, and personalized therapies. Further exploration is warranted into multiple fusions between metrics to uncover prognostic presentations across various dimensions.

show abstract

Section: Methodsmentioning

confidence: 99%

Precision unveiled: Synergistic genomic landscapes in breast cancer—Integrating single‐cell analysis and decoding drug toxicity for elite prognostication and tailored therapeutics

Jiang,

Zhang,

Jiang

et al. 2024

Environmental Toxicology

View full text Add to dashboard Cite

show abstract

“…These integrative methods included Lasso, elastic network (Enet), Ridge, stepwise Cox, CoxBoost, partial least squares regression for Cox (plsRcox), RSF, SuperPC, generalized boosted regression modeling (GBM), and survival support vector machine (survival-SVM). The process for creating signatures was as follows: the 173 key genes regulating GM activity were used to fit prediction models based on the leave-one-out cross-validation (LOOCV) framework in the TCGA-LUAD cohort using 117 algorithm combinations ( 23 ). All models were evaluated in eight validation datasets (GSE13213, GSE26939, GSE29016, GSE30219, GSE31210, GSE37745, GSE42127, GSE68465).…”

Section: Methodsmentioning

confidence: 99%

Integrating multiple machine learning methods to construct glutamine metabolism-related signatures in lung adenocarcinoma

Zhang

Pei

et al. 2023

Front. Endocrinol.

View full text Add to dashboard Cite

BackgroundGlutamine metabolism (GM) is known to play a critical role in cancer development, including in lung adenocarcinoma (LUAD), although the exact contribution of GM to LUAD remains incompletely understood. In this study, we aimed to discover new targets for the treatment of LUAD patients by using machine learning algorithms to establish prognostic models based on GM-related genes (GMRGs).MethodsWe used the AUCell and WGCNA algorithms, along with single-cell and bulk RNA-seq data, to identify the most prominent GMRGs associated with LUAD. Multiple machine learning algorithms were employed to develop risk models with optimal predictive performance. We validated our models using multiple external datasets and investigated disparities in the tumor microenvironment (TME), mutation landscape, enriched pathways, and response to immunotherapy across various risk groups. Additionally, we conducted in vitro and in vivo experiments to confirm the role of LGALS3 in LUAD.ResultsWe identified 173 GMRGs strongly associated with GM activity and selected the Random Survival Forest (RSF) and Supervised Principal Components (SuperPC) methods to develop a prognostic model. Our model’s performance was validated using multiple external datasets. Our analysis revealed that the low-risk group had higher immune cell infiltration and increased expression of immune checkpoints, indicating that this group may be more receptive to immunotherapy. Moreover, our experimental results confirmed that LGALS3 promoted the proliferation, invasion, and migration of LUAD cells.ConclusionOur study established a prognostic model based on GMRGs that can predict the effectiveness of immunotherapy and provide novel approaches for the treatment of LUAD. Our findings also suggest that LGALS3 may be a potential therapeutic target for LUAD.

show abstract

“…To differentiate GBM patients with low ERG scores from those with high scores based on their immune cell features, we employed the single-sample gene set enrichment analysis (ssGSEA) technique. We also estimated the immune and stromal scores of each glioma sample using the R program “ESTIMATE,” which provides an estimate of the quantities of immune and stromal components present in vivo [ 40 ]. To comprehensively investigate the tumor microenvironment’s heterogeneity in different datasets and cell types, we utilized the Tumor Immune Single-Cell Hub (TISCH) database.…”

Section: Methodsmentioning

confidence: 99%

Interaction, immune infiltration characteristics and prognostic modeling of efferocytosis-related subtypes in glioblastoma

Zhao,

Wang,

Liu

et al. 2023

BMC Med Genomics

View full text Add to dashboard Cite

Background Efferocytosis is a biological process in which phagocytes remove apoptotic cells and vesicles from tissues. This process is initiated by the release of inflammatory mediators from apoptotic cells and plays a crucial role in resolving inflammation. The signals associated with efferocytosis have been found to regulate the inflammatory response and the tumor microenvironment (TME), which promotes the immune escape of tumor cells. However, the role of efferocytosis in glioblastoma multiforme (GBM) is not well understood and requires further investigation. Methods In this study, we conducted a comprehensive analysis of 22 efferocytosis-related genes (ERGs) by searching for studies related to efferocytosis. Using bulk RNA-Seq and single-cell sequencing data, we analyzed the expression and mutational characteristics of these ERGs. By using an unsupervised clustering algorithm, we obtained ERG clusters from 549 GBM patients and evaluated the immune infiltration characteristics of each cluster. We then identified differential genes (DEGs) in the two ERG clusters and classified GBM patients into different gene clusters using univariate cox analysis and unsupervised clustering algorithms. Finally, we utilized the Boruta algorithm to screen for prognostic genes and reduce dimensionality, and the PCA algorithm was applied to create a novel efferocytosis-related scoring system. Results Differential expression of ERGs in glioma cell lines and normal cells was analyzed by rt-PCR. Cell function experiments, on the other hand, validated TIMD4 as a tumor risk factor in GBM. We found that different ERG clusters and gene clusters have distinct prognostic and immune infiltration profiles. The ERG signature we developed provides insight into the tumor microenvironment of GBM. Patients with lower ERG scores have a better survival rate and a higher likelihood of benefiting from immunotherapy. Conclusions Our novel efferocytosis-related signature has the potential to be used in clinical practice for risk stratification of GBM patients and for selecting individuals who are likely to respond to immunotherapy. This can help clinicians design appropriate targeted therapies before initiating clinical treatment.

show abstract

Feature Selection of OMIC Data by Ensemble Swarm Intelligence Based Approaches

Cited by 10 publications

References 54 publications

Precision unveiled: Synergistic genomic landscapes in breast cancer—Integrating single‐cell analysis and decoding drug toxicity for elite prognostication and tailored therapeutics

Precision unveiled: Synergistic genomic landscapes in breast cancer—Integrating single‐cell analysis and decoding drug toxicity for elite prognostication and tailored therapeutics

Integrating multiple machine learning methods to construct glutamine metabolism-related signatures in lung adenocarcinoma

Interaction, immune infiltration characteristics and prognostic modeling of efferocytosis-related subtypes in glioblastoma

Contact Info

Product

Resources

About