Lasso Regression
Recently Published Documents





2021 ◽  
Vol 9 ◽  
Cong Sun ◽  
Xinjuan Zhang ◽  
Xin Chen ◽  
Xinhong Wei ◽  
Yufan Chen ◽  

Objectives: This study aimed to evaluate the morphologic features and neurodevelopmental outcomes of individuals prenatally diagnosed with a periventricular pseudocyst (PVPC).Methods: Pregnant women with a fetus prenatally diagnosed with PVPC by MRI were enrolled in this retrospective study. The fetuses with PVPCs were divided into group 1 (isolated PVPC) and group 2 (PVPC with additional findings). The surviving infants underwent brain MRI examinations and the Gesell Developmental Scale (GDS) test after birth. Independent sample t-tests were used to compare the differences in the developmental quotient (DQ) between group 1 and group 2. We also analyzed the correlations among the DQ, location (unilateral/bilateral), size (diameter), and number (single/multiple) of the PVPCs in group 1 using Lasso regression.Results: In total, 131 infants (group 1: 78 infants, group 2: 53 infants) underwent MRI examinations after birth, and 97 infants (group 1: 59 infants, group 2: 38 infants) underwent the GDS test. Upon follow-up, the sizes of the cysts had become smaller or disappeared after birth. The average DQ in group 2 was lower than that in group 1 (all with p < 0.001). In group 1, the location (unilateral/bilateral), size (diameter), and number (single/multiple) of the PVPC did not affect the DQ.Conclusions: The PVPCs became smaller or disappeared after birth. Isolated PVPCs usually have a normal presentation after birth regardless of the location, number, or size. For PVPCs with additional findings, the neurodevelopmental outcomes were inferior to those in isolated PVPCs.

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Changsheng Sun ◽  
Jiatong Han ◽  
Yixin Bai ◽  
Zhaowei Zhong ◽  
Yingtao Song ◽  

Background. The aim of this study was at investigating the association between major depressive disorder (MDD) and periodontitis based on crosstalk genes and neuropeptides. Methods. Datasets for periodontitis (GSE10334, GSE16134, and GSE23586) and MDD (GSE38206 and GSE39653) were downloaded from GEO. Following batch correction, a differential expression analysis was applied (MDD: ∣ log 2 FC ∣ > 0 and periodontitis ∣ log 2 FC ∣ ≥ 0.5 , p < 0.05 ). The neuropeptide data were downloaded from NeuroPep and NeuroPedia. Intersected genes were potential crosstalk genes. The correlation between neuropeptides and crosstalk genes in MDD and periodontitis was analyzed with Pearson correlation coefficient. Subsequently, regression analysis was performed to calculate the differentially regulated link. Cytoscape was used to map the pathways of crosstalk genes and neuropeptides and to construct the protein-protein interaction network. Lasso regression was applied to screen neuropeptides, whereby boxplots were created, and receiver operating curve (ROC) analysis was conducted. Results. The MDD dataset contained 30 case and 33 control samples, and the periodontitis dataset contained 430 case and 139 control samples. 35 crosstalk genes were obtained. A total of 102 neuropeptides were extracted from the database, which were not differentially expressed in MDD and periodontitis and had no intersection with crosstalk genes. Through lasso regression, 9 neuropeptides in MDD and 43 neuropeptides in periodontitis were obtained. Four intersected neuropeptide genes were obtained, i.e., ADM, IGF2, PDYN, and RETN. The results of ROC analysis showed that IGF2 was highly predictive in MDD and periodontitis. ADM was better than the other three genes in predicting MDD disease. A total of 13 crosstalk genes were differentially coexpressed with four neuropeptides, whereby FOSB was highly expressed in MDD and periodontitis. Conclusion. The neuropeptide genes ADM, IGF2, PDYN, and RETN were intersected between periodontitis and MDD, and FOSB was a crosstalk gene related to these neuropeptides on the transcriptomic level. These results are a basis for future research in the field, needing further validation.

2021 ◽  
Miaolong Lu ◽  
Hailun Zhan ◽  
Bolong Liu ◽  
Dongyang Li ◽  
Wenbiao Li ◽  

Abstract Background Bladder cancer (BC) is a commonly occurring malignant tumor of the urinary system, demonstrating high global morbidity and mortality rates. BC currently lacks widely accepted biomarkers and its predictive, preventive, and personalized medicine (PPPM) is still unsatisfactory. N6-methyladenosine (m6A) modification and non-coding RNAs (ncRNAs) have been shown to be effective prognostic and immunotherapeutic responsiveness biomarkers and contribute to PPPM for various tumors. However, their role in BC remains unclear. Methods m6A-related ncRNAs (lncRNAs and miRNAs) were identified through a comprehensive analysis of TCGA, starBase, and m6A2Target databases. Using TCGA dataset (training set), univariate and least absolute shrinkage and selection operator (LASSO) regression analyses were performed to develop an m6A-related ncRNA–based prognostic risk model. Kaplan-Meier analysis of overall survival (OS) and receiver operating characteristic (ROC) curves were used to verify the prognostic evaluation power of the risk model in the GSE154261 dataset (testing set) from Gene Expression Omnibus (GEO). A nomogram containing independent prognostic factors was developed. Differences in BC clinical characteristics, m6A regulators, m6A-related ncRNAs, gene expression patterns, and differentially expressed genes (DEGs)–associated molecular networks between the high- and low-risk groups in TCGA dataset were also analyzed. Additionally, the potential applicability of the risk model in the prediction of immunotherapeutic responsiveness was evaluated based on the “IMvigor210CoreBiologies” data set. Results We identified 183 m6A-related ncRNAs, of which 14 were related to OS. LASSO regression analysis was further used to develop a prognostic risk model that included 10 m6A-related ncRNAs (BAALC-AS1, MIR324, MIR191, MIR25, AC023509.1, AL021707.1, AC026362.1, GATA2-AS1, AC012065.2, and HCP5). The risk model showed an excellent prognostic evaluation performance in both TCGA and GSE154261 datasets, with ROC curve areas under the curve (AUC) of 0.62 and 0.83, respectively. A nomogram containing 3 independent prognostic factors (risk score, age, and clinical stage) was developed and was found to demonstrate high prognostic prediction accuracy (AUC = 0.83). Moreover, the risk model could also predict BC progression. A higher risk score indicated a higher pathological grade and clinical stage. We identified 1058 DEGs between the high- and low-risk groups in TCGA dataset; these DEGs were involved in 3 molecular network systems, i.e., cellular immune response, cell adhesion, and cellular biological metabolism. Furthermore, the expression levels of 8 m6A regulators and 12 m6A-related ncRNAs were significantly different between the two groups. Finally, this risk model could be used to predict immunotherapeutic responses. Conclusion Our study is the first to explore the potential application value of m6A-related ncRNAs in BC. The m6A-related ncRNA–based risk model demonstrated excellent performance in predicting prognosis and immunotherapeutic responsiveness. Based on this model, in addition to identifying high-risk patients early to provide them with focused attention and targeted prevention, we can also select beneficiaries of immunotherapy to deliver personalized medical services. Furthermore, the m6A-related ncRNAs could elucidate the molecular mechanisms of BC and lead to a new direction for the improvement of PPPM for BC.

Vaccines ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 1221
Fan Hu ◽  
Ruijie Gong ◽  
Yexin Chen ◽  
Jinxin Zhang ◽  
Tian Hu ◽  

Since China’s launch of the COVID-19 vaccination, the situation of the public, especially the mobile population, has not been optimistic. We investigated 782 factory workers for whether they would get a COVID-19 vaccine within the next 6 months. The participants were divided into a training set and a testing set for external validation conformed to a ratio of 3:1 with R software. The variables were screened by the Lead Absolute Shrinkage and Selection Operator (LASSO) regression analysis. Then, the prediction model, including important variables, used a multivariate logistic regression analysis and presented as a nomogram. The Receiver Operating Characteristic (ROC) curve, Kolmogorov–Smirnov (K-S) test, Lift test and Population Stability Index (PSI) were performed to test the validity and stability of the model and summarize the validation results. Only 45.54% of the participants had vaccination intentions, while 339 (43.35%) were unsure. Four of the 16 screened variables—self-efficacy, risk perception, perceived support and capability—were included in the prediction model. The results indicated that the model has a high predictive power and is highly stable. The government should be in the leading position, and the whole society should be mobilized and also make full use of peer education during vaccination initiatives.

2021 ◽  
Vol 11 (1) ◽  
Dankun Luo ◽  
Wenchao Yao ◽  
Qiang Wang ◽  
Qiu Yang ◽  
Xuxu Liu ◽  

AbstractLong non-coding RNA (lncRNA) is a prognostic biomarker for many types of cancer. Here, we aimed to study the prognostic value of lncRNA in Breast Invasive Carcinoma (BRCA). We downloaded expression profiles from The Cancer Genome Atlas (TCGA) datasets. Subsequently, we screened the differentially expressed genes between normal tissues and tumor tissues. Univariate Cox, LASSO regression, and multivariate Cox regression analysis were used to construct a lncRNA prognostic model. Finally, a nomogram based on the lncRNAs model was developed, and weighted gene co-expression network analysis (WGCNA) was used to predict mRNAs related to the model, and to perform function and pathway enrichment. We constructed a 6-lncRNA prognostic model. Univariate and multivariate Cox regression analysis showed that the 6-lncRNA model could be used as an independent prognostic factor for BRCA patients. We developed a nomogram based on the lncRNAs model and age, and showed good performance in predicting the survival rates of BRCA patients. Also, functional pathway enrichment analysis showed that genes related to the model were enriched in cell cycle-related pathways. Tumor immune infiltration analysis showed that the types of immune cells and their expression levels in the high-risk group were significantly different from those in the low-risk group. In general, the 6-lncRNA prognostic model and nomogram could be used as a practical and reliable prognostic tool for invasive breast cancer.

2021 ◽  
pp. 2101181
Britt Clynick ◽  
Tamera J. Corte ◽  
Helen E. Jo ◽  
Iain Stewart ◽  
Ian N. Glaspole ◽  

RationaleIdiopathic Pulmonary Fibrosis (IPF) is a progressive lung disease in which circulatory biomarkers has the potential for guiding management in clinical practice.ObjectivesWe assessed the prognostic role of serum biomarkers in three independent IPF cohorts, the Australian IPF Registry (AIPFR), Trent Lung Fibrosis (TLF) and Prospective Observation of Fibrosis in the Lung Clinical Endpoints (PROFILE).MethodsIn the AIPFR, candidate proteins were assessed by ELISA as well as in an unbiased proteomic approach. Least absolute shrinkage and selection operator (LASSO) regression was used to restrict the selection of markers that best accounted for the progressor phenotype at one-year in AIPFR, and subsequently prospectively selected for replication in the validation TLF cohort and assessed retrospectively in PROFILE. Four significantly replicating biomarkers were aggregated into a progression index (PI) model based on tertiles of circulating concentrations.Main ResultsOne-hundred and eighty-nine participants were included in the AIPFR cohort, 205 participants from the TLF, and 122 participants from the PROFILE cohorts. Differential biomarker expression was observed by ELISA and replicated for osteopontin, matrix metallopeptidase-7, intercellular adhesion molecule-1 and periostin for those with a progressor phenotype at one-year. Proteomic data did not replicate. The PI in the AIPFR, TLF and PROFILE predicted risk of progression, mortality and progression-free survival. A statistical model incorporating PI demonstrated the capacity to distinguish disease progression at 12 months, which was increased beyond the clinical GAP model alone in all cohorts, and significantly so within incidence based TLF and PROFILE cohorts.ConclusionA panel of circulatory biomarkers can provide potentially valuable clinical assistance in the prognosis of IPF patients.

2021 ◽  
Peter McAnena ◽  
Brian Moloney ◽  
Robert Browne ◽  
Niamh O’Halloran ◽  
Leon Walsh ◽  

Abstract Background Medical image analysis has evolved to facilitate the development of methods for high-throughput extraction of quantitative features that can potentially contribute to the diagnostic and treatment paradigm of cancer. There is a need for further improvement in the accuracy of predictive markers of response to neo-adjuvant chemotherapy (NAC). The aim of this study was to develop a radiomic classifier to enhance current approaches to predicting the response to NAC breast cancer. Methods Data on patients treated for breast cancer with NAC prior to surgery who had a pre-NAC dynamic contrast enhanced (DCE) breast MRI were included. Response to NAC was assessed using the Miller-Payne system on the excised tumour. Tumour segmentation was carried out manually under the supervision of a consultant breast radiologist. Features were selected using least absolute shrinkage selection operator (LASSO) regression. A support vector machine (SVM) learning model was used to classify response to NAC. Results 74 patients were included. Patients were classified as having a poor response to NAC (reduction in cellularity <90%, n=44) and an excellent response (>90% reduction in cellularity, n=30). 4 radiomics features (discretized kurtosis, NGDLM contrast, GLZLM_SZE and GLZLM_ZP) were identified as pertinent predictors of response to NAC. A SVM model using these features stratified patients into poor and excellent response groups producing an AUC of 0.75. Addition of estrogen receptor (ER) status improved the accuracy of the model with an AUC of 0.811. Conclusion This study identified a radiomic classifier incorporating 4 radiomics features to augment subtype based classification of response to NAC in breast cancer.

2021 ◽  
Jihua Yang ◽  
Xiaohong Wei ◽  
Fang Hu ◽  
Dong Wei ◽  
Liao Sun

Abstract Background: Molecular markers play an important role in predicting clinical outcomes in pancreatic adenocarcinoma (PAAD) patients. Analysis of the ferroptosis-related genes may provide novel potential targets for the prognosis and treatment of PAAD. Methods: RNA-sequence data of PAAD was downloaded from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) public databases. The PAAD samples were clustered by a non-negative matrix factorization (NMF) algorithm. The R software package clusterProfiler was used for functional enrichment analysis. By LASSO regression, we established a multi-gene prognostic model, and the model was validated by qPCR and immunohistochemistry and T3M4 cell line. Results: Three molecular subtypes were identified, and a 3-gene signature model (ALOX5, ALOX12, and CISD1) was constructed. The prognostic model showed good independent prognostic ability in PAAD. In the GSE62452 external validation set, the molecular model also showed good risk prediction. The predictive efficiency of the 3-gene signature-based nomogram was significantly better than that of traditional clinical features. Finally, qPCR and immunohistochemical staining and cell function results suggested that ALOX5 may be an oncogene and ALOX12 and CISD1 may be tumor suppressor genes. Conclusions: We present a novel prognostic molecular model for PAAD based on ferroptosis-related genes, which serves as a potentially effective tool for prognostic differentiation in pancreatic cancer patients.

2021 ◽  
Vol 11 ◽  
Jian Wu ◽  
Yifang Sun ◽  
Junzheng Li ◽  
Maomao Ai ◽  
Lihua You ◽  

BackgroundThe incidence of thyroid cancer (THCA) continues to increase in recent decades. Accumulating evidence showed that the unbalanced alternative splicing (AS) promotes the occurrence of cancers and leads to poor prognosis of patients. However, the research on alternative splicing events in THCA is lacking, and its underlying mechanism is not fully understood. This study identifies a novel prognostic signature based on AS events to reveal the relationship of AS with tumor immune microenvironment.MethodsBased on the AS data, transcriptional data, and clinical information, the differentially expressed alternative splicings (DEASs) were screened out. Least absolute shrinkage and selection operator (LASSO) regression and multi-Cox regression analyses were employed to identify prognostic results related to AS events and establish a prognostic signature. The predictive ability of the signature was assessed by Kaplan-Meier (K-M) survival curve, risk plots, and receiver operating characteristic (ROC) curves. Furthermore, correlations between tumor-infiltrating immune cells, immune checkpoints, immune score and prognostic signature were analyzed.ResultsAccording to the LASSO regression analysis, a total of five AS events were selected to construct the signature. K-M survival curve showed that the higher the risk score, the worse the OS of the patients. Risk plots further confirmed this result. ROC curves indicated the high predictive efficiency of the prognostic signature. As for tumor immune microenvironment, patients in the high-risk group had a higher proportion of immune cells, including plasma cell, CD8+ T cell, macrophages (M0 and M2), and activated dendritic cell. Immune checkpoint proteins, such as PDCD1LG2, HAVCR2, CD274, etc., were significantly higher in the high-risk group. We also found that the ESTIMATE score, stromal score, and immune score were lower in the high-risk group, while the result of tumor purity was the opposite.ConclusionsCollectively, a prognostic signature consisting of five AS events in THCA was established. Furthermore, there was an inextricable correlation between immune cell infiltration, immune checkpoint proteins, and AS events. This study will provide a basis for THCA immunotherapy in the future.

2021 ◽  
Vol 11 (1) ◽  
Shuang Song ◽  
Shugang Li ◽  
Tianjun Zhang ◽  
Li Ma ◽  
Lei Zhang ◽  

AbstractThe evaluation of the coal mine gas drainage effect is affected by many factors, such as flow rate, wind speed, drainage negative pressure, concentration, and temperature. This paper starts from actual coal mine production monitoring data and based on the lasso regression algorithm, features selection of multiple parameters of the preprocessed gas concentration time series to construct gas concentration feature selection based on the algorithm. The three-time smoothing index method is used to fill in the missing values. Aiming at the problem of different dimensions in the gas concentration time series, the MinMaxScaler method is used to normalize the data. The lasso regression algorithm is used to perform feature selection on the multivariable gas concentration time series, and the gas concentration time series selected by the lasso feature and the gas concentration time series without feature selection are input. The performance of the ANN algorithm for gas concentration prediction is compared and analyzed. The optimal α value and L1 norm are selected based on the grid search method to determine the strong explanatory gas concentration time series feature set of the working face, and an experimental comparison of the gas concentration prediction results before and after the lasso feature selection is performed. We verify the effectiveness of the algorithm.

Sign in / Sign up

Export Citation Format

Share Document