Least Absolute Shrinkage And Selection Operator Algorithm Research Articles

Identification of hub biomarkers and immune cell infiltration characteristics of polymyositis by bioinformatics analysis.

BackgroundPolymyositis (PM) is an acquirable muscle disease with proximal muscle involvement of the extremities as the main manifestation; it is a category of idiopathic inflammatory myopathy. This study aimed to identify the key biomarkers of PM, while elucidating PM-associated immune cell infiltration and immune-related pathways.MethodsThe gene microarray data related to PM were downloaded from the Gene Expression Omnibus database. The analyses using Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes, gene set enrichment analysis (GSEA), and protein-protein interaction (PPI) networks were performed on differentially expressed genes (DEGs). The hub genes of PM were identified using weighted gene co-expression network analysis (WGCNA) and least absolute shrinkage and selection operator (LASSO) algorithm, and the diagnostic accuracy of hub markers for PM was assessed using the receiver operating characteristic curve. In addition, the level of infiltration of 28 immune cells in PM and their interrelationship with hub genes were analyzed using single-sample GSEA.ResultsA total of 420 DEGs were identified. The biological functions and signaling pathways closely associated with PM were inflammatory and immune processes. A series of four expression modules were obtained by WGCNA analysis, with the turquoise module having the highest correlation with PM; 196 crossover genes were obtained by combining DEGs. Subsequently, six hub genes were finally identified as the potential biomarkers of PM using LASSO algorithm and validation set verification analysis. In the immune cell infiltration analysis, the infiltration of T lymphocytes and subpopulations, dendritic cells, macrophages, and natural killer cells was more significant in the PM.ConclusionWe identified the hub genes closely related to PM using WGCNA combined with LASSO algorithm, which helped clarify the molecular mechanism of PM development and might have great significance for finding new immunotherapeutic targets, and disease prevention and treatment.

Construction and validation model of necroptosis-related gene signature associates with immunity for osteosarcoma patients

Osteosarcoma is the most common malignant tumor in children and adolescents and its diagnosis and treatment still need to be improved. Necroptosis has been associated with many malignancies, but its significance in diagnosing and treating osteosarcoma remains unclear. The objective is to establish a predictive model of necroptosis-related genes (NRGs) in osteosarcoma for evaluating the tumor microenvironment and new targets for immunotherapy. In this study, we download the osteosarcoma data from the TARGET and GEO websites and the average muscle tissue data from GTEx. NRGs were screened by Cox regression analysis. We constructed a prediction model through nonnegative matrix factorization (NMF) clustering and the least absolute shrinkage and selection operator (LASSO) algorithm and verified it with a validation cohort. Kaplan–Meier survival time, ROC curve, tumor invasion microenvironment and CIBERSORT were assessed. In addition, we establish nomograms for clinical indicators and verify them by calibration evaluation. The underlying mechanism was explored through the functional enrichment analysis. Eight NRGs were screened for predictive model modeling. NRGs prediction model through NMF clustering and LASSO algorithm was established. The survival, ROC and tumor microenvironment scores showed significant statistical differences among subgroups (P < 0.05). The validation model further verifies it. By nomogram and calibration, we found that metastasis and risk score were independent risk factors for the poor prognosis of osteosarcoma. GO and KEGG analyses demonstrate that the genes of osteosarcoma cluster in inflammatory, apoptotic and necroptosis signaling pathways. The significant role of the correlation between necroptosis and immunity in promoting osteosarcoma may provide a novel insight into detecting molecular mechanisms and targeted therapy.

Screening and verification of prognostic lncRNA markers related to immune infiltration in the metastasis of osteosarcoma.

BackgroundWe sought to screen and verify the long non-coding ribonucleic acids (lncRNAs) related to immune infiltration in metastatic osteosarcoma (OS).MethodsWe downloaded the RNA-sequencing expression data from The Cancer Genome Atlas (TCGA) database as the training data set. We downloaded the GSE39055 data set from the National Center for Biotechnology Information, Gene Expression Omnibus as the validation data set. The least absolute shrinkage and selection operator (LASSO) regression algorithm was used to screen the optimized lncRNA combinations. Kaplan-Meier curves were used to evaluate the associations between the lncRNAs and actual prognosis. The independent survival prognosis clinical factors were obtained by univariate and multivariate Cox analyses. A nomogram was established to explore the correlation between survival rate and risk information. The Tumor IMmune Estimation Resource was applied to estimate the composition of 6 subtypes of immune infiltration cells.ResultsIn total, 1,398 lncRNAs and 14,631 messenger RNAs were screened from TCGA data set, and divided into the low and high immunity groups. The Estimation of STromal and Immune cells in MAlignant Tumour tissues using Expression data (ESTIMATE) scores differed significantly between the samples in the two groups. Additionally, 5 optimized lncRNA combinations were obtained using the LASSO algorithm. Risk factors including age, metastatic tumor, and risk-score (RS) were related to the prognosis of OS patients. The survival rates predicted by the nomogram model were consistent with the actual survival rates of OS patients. Finally, we found that RS was negatively correlated with the proportion of immune cells.ConclusionsIn total, 5 feature lncRNAs were identified as novel biomarkers for OS. Next, a RS nomogram model was constructed based on the 5 identified lncRNAs. This model predicted the survival rates and prognoses of OS patients well.

Survival Prediction in Home Hospice Care Patients with Lung Cancer Based on LASSO Algorithm.

PurposeThe aim of the present study was to develop a nomogram for prognostic prediction of patients with lung cancer in hospice.MethodsThe data was collected from 1106 lung cancer patients in hospice between January 2008 and December 2018. The data were split into a training set, which was used to identify the most important prognostic factors by the least absolute shrinkage and selection operator (LASSO) and to build the nomogram, while the testing set was used to validate the nomogram. The performance of the nomogram was assessed by c-index, calibration curve and the decision curve analysis (DCA).ResultsA total of 1106 patients, including 835 (75%) from the training set and 271 (25%) from testing set, were retrospectively analyzed in this study. Using the LASSO regression, 5 most important prognostic predictors that included sex, Karnofsky Performance Scale (KPS), quality-of-life (QOL), edema and anorexia, were selected out of 28 variables. Validated c-indexes of training set at 15, 30, and 90 days were .778 [.737-.818], .776 [.743-.809], and .751 [.713-.790], respectively. Similarly, the validated c-indexes of testing set at 15, 30, and 90 days were .789 [.714-.864], .748 [.685-.811], and .757 [.691-.823], respectively. The nomogram-predicted survival was well calibrated, as the predicted probabilities were close to the expected probabilities. Moreover, the DCA curve showed that nomogram received superior standardized net benefit at a broad threshold.ConclusionsThe study built a non-lab nomogram with important predictor to analyze the clinical parameters using LASSO. It may be a useful tool to allow clinicians to easily estimate the prognosis of the patients with lung cancer in hospice.

Identification of hub genes related to CD4+ memory T cell infiltration with gene co-expression network predicts prognosis and immunotherapy effect in colon adenocarcinoma.

Background: CD4+ memory T cells (CD4+ MTCs), as an important part of the microenvironment affecting tumorigenesis and progression, have rarely been systematically analyzed. Our purpose was to comprehensively analyze the effect of CD4+ MTC infiltration on the prognosis of colon adenocarcinoma (COAD). Methods: Based on RNA-Seq data, weighted gene co-expression network analysis (WGCNA) was used to screen the CD4+ MTC infiltration genes most associated with colon cancer and then identify hub genes and construct a prognostic model using the least absolute shrinkage and selection operator algorithm (LASSO). Finally, survival analysis, immune efficacy analysis, and drug sensitivity analysis were performed to evaluate the role of the prognostic model in COAD. Results: We identified 929 differentially expressed genes (DEGs) associated with CD4+ MTCs and constructed a prognosis model based on five hub genes (F2RL2, TGFB2, DTNA, S1PR5, and MPP2) to predict overall survival (OS) in COAD. Kaplan–Meier analysis showed poor prognosis in the high-risk group, and the analysis of the hub gene showed that overexpression of TGFB2, DTNA, S1PR5, or MPP2 was associated with poor prognosis. Clinical prediction nomograms combining CD4+ MTC-related DEGs and clinical features were constructed to accurately predict OS and had high clinical application value. Immune efficacy and drug sensitivity analysis provide new insights for individualized treatment. Conclusion: We constructed a prognostic risk model to predict OS in COAD and analyzed the effects of risk score on immunotherapy efficacy or drug sensitivity. These studies have important clinical significance for individualized targeted therapy and prognosis.

Application of a combined radiomics nomogram based on CE-CT in the preoperative prediction of thymomas risk categorization.

ObjectiveThis study aimed to establish a combined radiomics nomogram to preoperatively predict the risk categorization of thymomas by using contrast-enhanced computed tomography (CE-CT) images.Materials and MethodsThe clinical, pathological, and CT data of 110 patients with thymoma (50 patients with low-risk thymomas and 60 patients with high-risk thymomas) collected in our Hospital from July 2017 to March 2022 were retrospectively analyzed. The study subjects were randomly divided into the training set (n = 77) and validation set (n = 33) in a 7:3 ratio. Radiomics features were extracted from the CT images, and the least absolute shrinkage and selection operator (LASSO) algorithm was performed to select 13 representative features. Five models, including logistic regression (LR), support vector machine (SVM), random forest (RF), decision tree (DT), and gradient boosting decision tree (GBDT) were constructed to predict thymoma risks based on these features. A combined radiomics nomogram was further established based on the clinical factors and radiomics scores. The performance of the models was evaluated using receiver operating characteristic (ROC) curve, DeLong tests, and decision curve analysis.ResultsMaximum tumor diameter and boundary were selected to build the clinical factors model. Thirteen features were acquired by LASSO algorithm screening as the optimal features for machine learning model construction. The LR model exhibited the highest AUC value (0.819) among the five machine learning models in the validation set. Furthermore, the radiomics nomogram combining the selected clinical variables and radiomics signature predicted the categorization of thymomas at different risks more effectively (the training set, AUC = 0.923; the validation set, AUC = 0.870). Finally, the calibration curve and DCA were utilized to confirm the clinical value of this combined radiomics nomogram.ConclusionWe demonstrated the clinical diagnostic value of machine learning models based on CT semantic features and the selected clinical variables, providing a non-invasive, appropriate, and accurate method for preoperative prediction of thymomas risk categorization.

Prediction of high infiltration levels in pituitary adenoma using MRI-based radiomics and machine learning

BackgroundInfiltration is important for the surgical planning and prognosis of pituitary adenomas. Differences in preoperative diagnosis have been noted. The aim of this article is to assess the accuracy of machine learning analysis of texture-derived parameters of pituitary adenoma obtained from preoperative MRI for the prediction of high infiltration.MethodsA total of 196 pituitary adenoma patients (training set: n = 176; validation set: n = 20) were enrolled in this retrospective study. In total, 4120 quantitative imaging features were extracted from CE-T1 MR images. To select the most informative features, the least absolute shrinkage and selection operator (LASSO) and variance threshold method were performed. The linear support vector machine (SVM) was used to fit the predictive model based on infiltration features. Furthermore, the receiver operating characteristic curve (ROC) was generated, and the diagnostic performance of the model was evaluated by calculating the area under the curve (AUC), accuracy, precision, recall, and F1 value.ResultsA variance threshold of 0.85 was used to exclude 16 features with small differences using the LASSO algorithm, and 19 optimal features were finally selected. The SVM models for predicting high infiltration yielded an AUC of 0.86 (sensitivity: 0.81, specificity 0.79) in the training set and 0.73 (sensitivity: 0.87, specificity: 0.80) in the validation set. The four evaluation indicators of the predictive model achieved good diagnostic capabilities in the training set (accuracy: 0.80, precision: 0.82, recall: 0.81, F1 score: 0.81) and independent verification set (accuracy: 0.85, precision: 0.93, recall: 0.87, F1 score: 0.90).ConclusionsThe radiomics model developed in this study demonstrates efficacy for the prediction of pituitary adenoma infiltration. This model could potentially aid neurosurgeons in the preoperative prediction of infiltration in PAs and contribute to the selection of ideal surgical strategies.

Quantitative evaluation of the hemodynamic differences between ruptured and unruptured cerebral arteriovenous malformations using angiographic parametric imaging-derived radiomics features.

Imaging features of cerebral arteriovenous malformations (AVMs) are mainly interpreted according to demographic and qualitative anatomical characteristics. This study aimed to use angiographic parametric imaging (API)-derived radiomics features to explore whether these features extracted from digital subtraction angiography (DSA) were associated with the hemorrhagic presentation of AVMs. Patients with AVM were retrospectively evaluated. Among them, 80% were randomly assigned to a training dataset, and the remaining 20% were assigned to an independent test dataset. Radiomics features were extracted from DSA by API. Then, informative features were selected from radiomics features and clinical features using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. A model was constructed based on the selected features to classify the dichotomous hemorrhagic presentation in the training dataset. The model performance was evaluated in the test dataset with confusion matrix-related metrics. A total of 529 consecutive patients with AVMs between July 2011 and December 2020 were included in this study. After being selected by the LASSO algorithm and analyzed by multivariable logistic regression, three clinical features, namely, age (p = 0.01), nidus size (p < 0.001), and venous drainage patterns (p < 0.001), and four radiomics features were used to construct a model in the training dataset. On the independent test dataset, the model demonstrated a sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 0.852, 0.844, 0.881, 0.809, and 0.849, respectively. The radiomics features extracted from DSA by API could be potential indicators for the hemorrhagic presentation of AVMs.

Hyperspectral estimation of petroleum hydrocarbon content in soil using ensemble learning method and LASSO feature extraction

ABSTRACT Rapid and accurate estimation of soil petroleum hydrocarbon content is crucial for analyzing the degree of soil pollution and evaluating pollution status. Surface soil samples and hyperspectral measurements in the reservoir area in Lenghu Town, Qinghai Province, China, were viewed as research objects, and the correlation between different spectral forms of original data and petroleum hydrocarbon content in soil was analyzed. To improve the estimation accuracy, we proposed a solution that introduces least absolute shrinkage and selection operator (LASSO) combined with extremely randomized trees (ERT) and gradient boosting decision tree (GBDT) ensemble learning for constructing hyperspectral estimation model. The results show: LASSO algorithm can not only solve the spectral multicollinearity problem effectively but also reduce the number and calculation complexity of soil hyperspectral variables to a great extent. Compared with traditional machine learning, ERT and GBDT perform superior. In particular, the estimation accuracy of the LASSO-GBDT model is the highest.

Identification of Candidate Genes Associated With Prognosis in Glioblastoma.

BackgroundGlioblastoma (GBM) is the most common malignant primary brain tumor, which associated with extremely poor prognosis.MethodsData from datasets GSE16011, GSE7696, GSE50161, GSE90598 and The Cancer Genome Atlas (TCGA) were analyzed to identify differentially expressed genes (DEGs) between patients and controls. DEGs common to all five datasets were analyzed for functional enrichment and for association with overall survival using Cox regression. Candidate genes were further screened using least absolute shrinkage and selection operator (LASSO) and random forest algorithms, and the effects of candidate genes on prognosis were explored using a Gaussian mixed model, a risk model, and concordance cluster analysis. We also characterized the GBM landscape of immune cell infiltration, methylation, and somatic mutations.ResultsWe identified 3,139 common DEGs, which were associated mainly with PI3K-Akt signaling, focal adhesion, and Hippo signaling. Cox regression identified 106 common DEGs that were significantly associated with overall survival. LASSO and random forest algorithms identified six candidate genes (AEBP1, ANXA2R, MAP1LC3A, TMEM60, PRRG3 and RPS4X) that predicted overall survival and GBM recurrence. AEBP1 showed the best prognostic performance. We found that GBM tissues were heavily infiltrated by T helper cells and macrophages, which correlated with higher AEBP1 expression. Stratifying patients based on the six candidate genes led to two groups with significantly different overall survival. Somatic mutations in AEBP1 and modified methylation of MAP1LC3A were associated with GBM.ConclusionWe have identified candidate genes, particularly AEBP1, strongly associated with GBM prognosis, which may help in efforts to understand and treat the disease.

Identification of hub genes and their correlation with immune infiltration in coronary artery disease through bioinformatics and machine learning methods.

BackgroundCoronary artery disease (CAD) is a multifactorial disease and its pathogenesis remains unclear. We aimed to explore the optimal feature genes (OFGs) for CAD and to investigate the function of immune cell infiltration of CAD. It will be helpful for better understanding of the pathogenesis and the development of genetic prediction of CAD.MethodsDatasets related to CAD were obtained from the Gene Expression Omnibus (GEO) database. Cases from the datasets met diagnostic criteria including clinical symptoms, electrocardiographic (ECG) and angiographic evidence. We identified differentially expressed genes (DEGs) and conducted functional enrichment analysis. OFGs were obtained from the least absolute shrinkage and selection operator (LASSO) algorithm, support vector machine recursive feature elimination (SVM-RFE) algorithm, and random forest (RF) algorithm. CIBERSORT was used to compare immune infiltration between CAD patients and normal controls, and the correlation between OFGs and immune cells was analyzed.ResultsDEGs were involved in the interleukin (IL)-17 signaling pathway, nuclear factor (NF)-kappa B signaling pathway, and tumor necrosis factor (TNF) signaling pathway. Gene Ontology (GO) analysis revealed DEGs were enriched in lipopolysaccharide (LPS), tertiary granule, and pattern recognition receptor activity. Disease Ontology (DO) analysis suggested DEGs were enriched in lung disease, arteriosclerotic cardiovascular disease (CVD). Matrix metalloproteinase 9 (MMP9), Pellino E3 ubiquitin protein ligase 1 (PELI1), thrombomodulin (THBD), and zinc finger protein 36 (ZFP36) were screened by the intersection of OFGs obtained from LASSO, SVM-REF, and RF algorithms. CAD patients had a lower proportion of memory B cells (P=0.019), CD8 T cells (P<0.001), resting memory CD4 T cells (P<0.001), regulatory T cells (P=0.028), and gamma delta T cells (P<0.001) than normal controls, while the proportion of activated memory CD4 T cells (P=0.014), resting natural killer (NK) cells (P<0.001), monocytes (P<0.001), M0 macrophages (P=0.023), activated mast cells (P<0.001), and neutrophils (P<0.001) in CAD patients were higher than normal controls. MMP9, PELI1, THBD, and ZFP36 were correlated with immune cells.ConclusionsMMP9, PELI1, THBD, and ZFP36 may be predicted biomarkers for CAD. The OFGs and association between OFGs and immune infiltration may provide potential biomarkers for CAD prediction along with the better assessment of the disease.

Identification of Critical Biomarkers and Immune Infiltration in Rheumatoid Arthritis Based on WGCNA and LASSO Algorithm.

Rheumatoid arthritis(RA) is the most common inflammatory arthritis, and a significant cause of morbidity and mortality. RA patients’ synovial inflammation contains a variety of genes and signalling pathways that are poorly understood. It was the goal of this research to discover the major biomarkers related to the course of RA and how they connect to immune cell infiltration. The Gene Expression Omnibus was used to download gene microarray data. Differential expression analysis, weighted gene co-expression network analysis (WGCNA), and least absolute shrinkage and selection operator (LASSO) regression were used to identify hub markers for RA. Single-sample GSEA was used to examine the infiltration levels of 28 immune cells and their connection to hub gene markers. The hub genes’ expression in RA-HFLS and HFLS cells was verified by RT-PCR. The CCK-8 assay was applied to determine the roles of hub genes in RA. In this study, we identified 21 differentially expressed genes (DEGs) in RA. WGCNA yielded two co-expression modules, one of which exhibited the strongest connection with RA. Using a combination of differential genes, a total of 6 intersecting genes was discovered. Six hub genes were identified as possible biomarkers for RA after a lasso analysis was performed on the data. Three hub genes, CKS2, CSTA, and LY96, were found to have high diagnostic value using ROC curve analysis. They were shown to be closely related to the concentrations of several immune cells. RT-PCR confirmed that the expressions of CKS2, CSTA and LY96 were distinctly upregulated in RA‐HFLS cells compared with HFLS cells. More importantly, knockdown of CKS2 suppressed the proliferation of RA‐HFLS cells. Overall, to help diagnose and treat RA, it’s expected that CKS2, CSTA, and LY96 will be available, and the aforementioned infiltration of immune cells may have a significant impact on the onset and progression of the disease.

Machine learning and LACE index for predicting 30-day readmissions after heart failure hospitalization in elderly patients

Machine learning (ML) techniques may improve readmission prediction performance in heart failure (HF) patients. This study aimed to assess the ability of ML algorithms to predict unplanned all-cause 30-day readmissions in HF elderly patients, and to compare them with conventional LACE (Length of hospitalization, Acuity, Comorbidities, Emergency department visits) index. All patients aged ≥ 65years discharged alive between 2010 and 2019 after a hospitalization for acute HF were included in this retrospective cohort study. We applied MICE (Multivariate Imputation via Chained Equations) method to obtain a balanced, fully valued dataset and LASSO (Least Absolute Shrinkage and Selection Operator) algorithm to get the most significant features. Training (80% of records) and test (20%) cohorts were randomly selected. Study population: 3079 patients, 394 (12.8%) presented at least one readmission within 30days, and 2685 (87.2%) did not. In the test cohort AUCs (IC95%) of XGBoost, Ada Boost Classifier, Random forest, and Gradient Boosting, and LACE Index were: 0.803 (0.734-0.872), 0.782 (0.711-0.854), 0.776 (0.703-0.848), 0.786 (0.715-0.857), and 0.504 (0.414-0.594), respectively, for predicting readmissions. A SHAP analysis was performed to offer a breakdown of the ML variables associated with readmission. Positive and negative predicting values estimates of the different ML models and LACE index were also provided, for several values of readmission rate prevalence. Among elderly patients, the rate of all-cause unplanned 30-day readmissions after hospitalization due to an acute HF was high. ML models performed better than the conventional LACE index for predicting readmissions. ML models can be proposed as promising tools for the identification of subjects at high risk of hospitalization in this clinical setting, enabling care teams to target interventions for improving overall clinical outcomes.

Prediction of early recurrence of hepatocellular carcinoma after liver transplantation based on computed tomography radiomics nomogram

BackgroundEarly recurrence results in poor prognosis of patients with hepatocellular carcinoma (HCC) after liver transplantation (LT). This study aimed to explore the value of computed tomography (CT)-based radiomics nomogram in predicting early recurrence of patients with HCC after LT. MethodsA cohort of 151 patients with HCC who underwent LT between December 2013 and July 2019 were retrospectively enrolled. A total of 1218 features were extracted from enhanced CT images. The least absolute shrinkage and selection operator algorithm (LASSO) logistic regression was used for dimension reduction and radiomics signature building. The clinical model was constructed after the analysis of clinical factors, and the nomogram was constructed by introducing the radiomics signature into the clinical model. The predictive performance and clinical usefulness of the three models were evaluated using receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA), respectively. Calibration curves were plotted to assess the calibration of the nomogram. ResultsThere were significant differences in radiomics signature among early recurrence patients and non-early recurrence patients in the training cohort (P < 0.001) and validation cohort (P < 0.001). The nomogram showed the best predictive performance, with the largest area under the ROC curve in the training (0.882) and validation (0.917) cohorts. Hosmer-Lemeshow testing confirmed that the nomogram showed good calibration in the training (P = 0.138) and validation (P = 0.396) cohorts. DCA showed if the threshold probability is within 0.06-1, the nomogram had better clinical usefulness than the clinical model. ConclusionsOur CT-based radiomics nomogram can preoperatively predict the risk of early recurrence in patients with HCC after LT.

Comprehensive Molecular Analyses of a Macrophage-Related Gene Signature With Regard to Prognosis, Immune Features, and Biomarkers for Immunotherapy in Hepatocellular Carcinoma Based on WGCNA and the LASSO Algorithm.

Macrophages have been reported to exert a crucial role in hepatocellular carcinoma (HCC). This study aimed to explore the macrophage-related genes and establish a macrophage-related signature (MRS) model to predict the overall survival (OS) of patients with HCC based on these genes’ expression. We screened the macrophage-related gene module by weighted gene coexpression network analysis (WGCNA), the least absolute shrinkage and selection operator (LASSO) Cox regression analysis was utilized for further selection, and the selected genes were entered into stepwise regression to develop the MRS model, which was further validated in the Gene Expression Omnibus (GEO) and International Cancer Genome Consortium (ICGC) datasets. We analyzed the biological phenotypes associated with macrophages in terms of functional enrichment, tumor immune signature, and tumor mutational signature. The patient’s response to immunotherapy was inferred by the tumor immune dysfunction and exclusion (TIDE) score, the immunophenotype score (IPS), and the IMvigor210 dataset. A novel MRS model was established based on the LASSO regression coefficients of the genes PON1, IL15RA, NEIL3, HILPDA, PFN2, HAVCR1, ANXA10, CDCA8, EPO, S100A9, TTK, KLRB1, SPP1, STC2, CYP26B1, GPC1, G6PD, and CBX2. In either dataset, MRS was identified as an independent risk factor for OS in HCC patients. Additionally, our research indicated that a high-risk score in the MRS model was significantly correlated with tumor staging, pathological grade, tumor–node–metastasis (TNM) stage, and survival. Several genes of the human leukocyte antigen (HLA) family and immune checkpoints were highly expressed in the high-risk group. In addition, the frequency of tumor mutations was also higher in the high-risk group. According to our analyses, a higher risk score in the MRS model may predict a better response to immunotherapy.

TGFβ-Associated Signature Predicts Prognosis and Tumor Microenvironment Infiltration Characterization in Gastric Carcinoma.

Background: Gastric carcinoma (GC) is a carcinoma with a high incidence rate, and it is a deadly carcinoma globally. An effective tool, that is, able to predict different survival outcomes for GC patients receiving individualized treatments is deeply needed. Methods: In total, data from 975 GC patients were collected from TCGA-STAD, GSE15459, and GSE84437. Then, we performed a comprehensive unsupervised clustering analysis based on 54 TGFβ-pathway-related genes and correlated these patterns with tumor microenvironment (TME) cell-infiltrating characteristics. WGCNA was then applied to find the module that had the closest relation with these patterns. The least absolute shrinkage and selection operator (LASSO) algorithm was combined with cross validation to narrow down variables and random survival forest (RSF) was used to create a risk score. Results: We identified two different TGFβ regulation patterns and named them as TGFβ Cluster 1 and Cluster 2. TGFβ Cluster 1 was linked to significantly poorer survival outcomes and represented an inflamed TME subtype of GC. Using WGCNA, a module (magenta) with the closest association with the TGFβ clusters was identified. After narrowing down the gene list by univariate Cox regression analysis, the LASSO algorithm and cross validation, four of the 243 genes in the magenta module were applied to build a risk score. The group with a higher risk score exhibited a considerably poorer survival outcome with high predictive accuracy. The risk score remained an independent risk factor in multivariate Cox analysis. Moreover, we validated this risk score using GSE15459 and GSE84437. Furthermore, we found that the group with a higher risk score represented an inflamed TME according to the evidence that the risk score was remarkably correlated with several steps of cancer immunity cycles and a majority of the infiltrating immune cells. Consistently, the risk score was significantly related to immune checkpoint genes and T cell–inflamed gene expression profiles (GEPs), indicating the value of predicting immunotherapy. Conclusions: We have developed and validated a TGFβ-associated signature, that is, capable of predicting the survival outcome as well as depicting the TME immune characteristics of GC. In summary, this signature may contribute to precision medicine for GC.

Application of MR Imaging Features in Differentiation of Renal Changes in Patients With Stage III Type 2 Diabetic Nephropathy and Normal Subjects.

ObjectiveThe objective of the study was to explore the value of MRI texture features based on T1WI, T2-FS and diffusion-weighted imaging (DWI) in differentiation of renal changes in patients with stage III type 2 diabetic nephropathy (DN) and normal subjects.Materials and MethodsA retrospective analysis was performed to analyze 44 healthy volunteers (group A) and 40 patients with stage III type 2 diabetic nephropathy (group B) with microalbuminuria. Urinary albumin to creatinine ratio (ACR) <30 mg/g, estimated glomerular filtration rate (eGFR) in the range of 60–120 ml/(min 1.73 m2), and randomly divided into primary cohort and test cohort. Conventional MRI and DWI of kidney were performed using 1.5 T magnetic resonance imaging (MRI). The outline of the renal parenchyma was manually labeled in fat-suppressed T2-weighted imaging (FS-T2WI), and PyRadiomics was used to extract radiomics features. The radiomics features were then selected by the least absolute shrinkage and selection operator (LASSO) method.ResultsThere was a significant difference in sex and body mass index (BMI) (P <0.05) in the primary cohort, with no significant difference in age. In the final results, the wavelet and Laplacian–Gaussian filtering are used to extract 1,892 image features from the original T1WI image, and the LASSO algorithm is used for selection. One first-order feature and six texture features are selected through 10 cross-validations. In the mass, 1,638 imaging extracts features from the original T2WI image.1 first-order feature and 5 texture features were selected. A total of 1,241 imaging features were extracted from the original ADC images, and 5 texture features were selected. Using LASSO-Logistic regression analysis, 10 features were selected for modeling, and a combined diagnosis model of diabetic nephropathy based on texture features was established. The average unit cost in the logistic regression model was 0.98, the 95% confidence interval for the predictive efficacy was 0.9486–1.0, specificity 0.97 and precision 0.93, particularly. ROC curves also revealed that the model could distinguish with high sensitivity of at least 92%.ConclusionIn consequence, the texture features based on MR have broad application prospects in the early detection of DN as a relatively simple and noninvasive tool without contrast media administration.

Exploring Prognostic Signatures of Hepatocellular Carcinoma and the Potential Implications in Tumor Immune Microenvironment.

The objective of this study is to construct a prognostic model using genetic markers of liver cancer and explore the signature genes associated with the tumor immune microenvironment. Cox proportional hazards regression analysis was carried out to screen the significant HR using the dataset of TCGA Liver Cancer (LIHC) gene expression data. Then LASSO (least absolute shrinkage and selection operator) was performed to select the minimal variables with significant HR of genes. Thus, the prognostic model was constructed by the minimal variables with their HR. Time-dependent receiver-operating characteristic (ROC) curve and area under the ROC curve (AUC) value was used to assess the prognostic performance. Then the patients were divided into high and low-risk groups by the median of the model. Survival analysis was performed on the two groups with testing and an independent dataset. Furthermore, enrichment analysis of signature mRNAs and lncRNAs and their co-expression genes was performed. Then, Spearman rank correlation was used to calculate the correlation between immune cells and genes in the prognostic model, and abundance difference of the immune cells in high and low risks groups was tested. A total of 5989 genes with significant HR were identified. 6 key genes (three mRNAs: DHX37, SMIM7, and MFSD1, three lncRNAs: PIWIL4, KCNE5, and LOC100128398) screened by LASSO were used to construct the model with their HR value respectively. The AUC values of 1 and 5-year overall survival were 0.78 and 0.76 in discovery data and 0.67 and 0.68 in testing data. Survival analysis performed significantly discriminated high and low groups with testing and independent data. Furthermore, many immune cells such as nTreg found a significant correlation with the genes in the prognostic model, and many immune cells showed significantly different abundance in high and low-risk groups. In the study, we used Univariate Cox analyses and LASSO algorithm with TCGA gene expression data to construct the prognostic model in liver cancer patients. The prognostic model comprised of three mRNAs, including DHX37, SMIM7, MFSD1, and three lncRNAs, including PIWIL4, KCNE5, and LOC100128398. Furthermore, these gene expression levels were associated with the abundance of some immune cells, such as nTreg. Also, many immune cells have significantly different abundance in high and low-risk groups. All these results indicated that the combination with all these six genes could be the potential biomarker for the prognosis of liver cancer.

Online Sparse DOA Estimation Based on Sub–Aperture Recursive LASSO for TDM–MIMO Radar

The least absolute shrinkage and selection operator (LASSO) algorithm is a promising method for sparse source location in time–division multiplexing (TDM) multiple–input, multiple–output (MIMO) radar systems, with notable performance gains in regard to resolution enhancement and side lobe suppression. However, the current batch LASSO algorithm suffers from high–computational complexity when dealing with massive TDM–MIMO observations, due to high–dimensional matrix operations and the large number of iterations. In this paper, an online LASSO method is proposed for efficient direction–of–arrival (DOA) estimation of the TDM–MIMO radar based on the receiving features of the sub–aperture data blocks. This method recursively refines the location parameters for each receive (RX) block observation that becomes available sequentially in time. Compared with the conventional batch LASSO method, the proposed online DOA method makes full use of the TDM–MIMO reception time to improve the real–time performance. Additionally, it allows for much less iterations, avoiding high–dimensional matrix operations, allowing the computational complexity to be reduced from OK3 to OK2. Simulated and real–data results demonstrate the superiority and effectiveness of the proposed method.

LASSO based compensation method for geometric errors of large coordinate measuring machine

The quasi-rigid body model is the relationship model between the volume error and the geometric error of the CMM under the consideration of simple deformation. The quasi-rigid body model reflects the comprehensive influence of all geometric errors and ensures the calibration accuracy of geometric errors. However, the geometric error solution based on the quasi-rigid body model has the problem of multicollinearity. To solve this problem, in this study, the geometric errors of CMM are compensated using laser tracing multistation measurement technology and the LASSO (Least absolute shrinkage and selection operator, LASSO) algorithm. First, a laser tracing multi-station measurement model is established, and then the coordinates of the laser tracer station are obtained by solving the redundant equations provided by the laser tracer multi-station measurement system using the L-M (Levenberg Marquardt) algorithm. The global positioning system localization principle combined with the L-M algorithm is used to determine the actual position of the CMM measurement point. Then, the volume error is determined by calculating the difference between the actual position of the measurement point and the planned position. A mathematical model of the volumetric and geometric errors is obtained from the CMM quasi-rigid body model, and the LASSO algorithm is used to solve the model to obtain the 17 geometric errors of the CMM. Using the relationship between the volume error and the uniaxial geometric error, the 4 rotational errors are solved of εz (x), εx- (z), εv (z), εz (z). To verify the measurement accuracy of the compensated CMM, the compensation effect is verified by using the XL80 interferometer with the measuring block. The experimental results indicate that when error compensation is performed, the measurement accuracy of the CMM is improved by >50% compared to the initial state, and no mechanical processing is involved.