A novel gene expression test method of minimizing breast cancer risk in reduced cost and time by improving SVM-RFE gene selection method combined with LASSO.
Ontology highlight
ABSTRACT:
SUBMITTER: Gupta M
PROVIDER: S-EPMC7856389 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BACKGROUND: Identifying genes with essential roles in resisting environmental stress rates high in agronomic importance. Although massive DNA microarray gene expression data have been generated for plants, current computational approaches underutilize these data for studying genotype-trait relationships. Some advanced gene identification methods have been explored for human diseases, but typically these methods have not been converted into publicly available software tools and cannot be applied to plants for identifying genes with agronomic traits. METHODOLOGY: In this study, we used 22 sets of Arabidopsis thaliana gene expression data from GEO to predict the key genes involved in water tolerance. We applied an SVM-RFE (Support Vector Machine-Recursive Feature Elimination) feature selection method for the prediction. To address small sample sizes, we developed a modified approach for SVM-RFE by using bootstrapping and leave-one-out cross-validation. We also expanded our study to predict genes involved in water susceptibility. CONCLUSIONS: We analyzed the top 10 genes predicted to be involved in water tolerance. Seven of them are connected to known biological processes in drought resistance. We also analyzed the top 100 genes in terms of their biological functions. Our study shows that the SVM-RFE method is a highly promising method in analyzing plant microarray data for studying genotype-phenotype relationships. The software is freely available with source code at http://ccst.jlu.edu.cn/JCSB/RFET/.
| S-EPMC3137602 | biostudies-literature
Project description:Background: Systemic sclerosis-associated pulmonary hypertension (SSc-PH) is one of the most common causes of death in patients with systemic sclerosis (SSc). The complexity of SSc-PH and the heterogeneity of clinical features in SSc-PH patients contribute to the difficulty of diagnosis. Therefore, there is a pressing need to develop and optimize models for the diagnosis of SSc-PH. Signal recognition particle (SRP) deficiency has been found to promote the progression of multiple cancers, but the relationship between SRP and SSc-PH has not been explored. Methods: First, we obtained the GSE19617 and GSE33463 datasets from the Gene Expression Omnibus (GEO) database as the training set, GSE22356 as the test set, and the SRP-related gene set from the MSigDB database. Next, we identified differentially expressed SRP-related genes (DE-SRPGs) and performed unsupervised clustering and gene enrichment analyses. Then, we used least absolute shrinkage and selection operator (LASSO) regression and support vector machine-recursive feature elimination (SVM-RFE) to identify SRP-related diagnostic genes (SRP-DGs). We constructed an SRP scoring system and a nomogram model based on the SRP-DGs and established an artificial neural network (ANN) for diagnosis. We used receiver operating characteristic (ROC) curves to identify the SRP-related signature in the training and test sets. Finally, we analyzed immune features, signaling pathways, and drugs associated with SRP and investigated SRP-DGs' functions using single gene batch correlation analysis-based GSEA. Results: We obtained 30 DE-SRPGs and found that they were enriched in functions and pathways such as "protein targeting to ER," "cytosolic ribosome," and "coronavirus disease-COVID-19". Subsequently, we identified seven SRP-DGs whose expression levels and diagnostic efficacy were validated in the test set. As one signature, the area under the ROC curve (AUC) values for seven SRP-DGs were 0.769 and 1.000 in the training and test sets, respectively. Predictions made using the nomogram model are likely beneficial for SSc-PH patients. The AUC values of the ANN were 0.999 and 0.860 in the training and test sets, respectively. Finally, we discovered that some immune cells and pathways, such as activated dendritic cells, complement activation, and heme metabolism, were significantly associated with SRP-DGs and identified ten drugs targeting SRP-DGs. Conclusion: We constructed a reliable SRP-related ANN model for the diagnosis of SSc-PH and investigated the possible role of SRP in the etiopathogenesis of SSc-PH by bioinformatics methods to provide a basis for precision and personalized medicine.
| S-EPMC9742487 | biostudies-literature
Project description:Parkinson's disease (PD) is a common progressive neurodegenerative disorder. Various evidence has revealed the possible penetration of peripheral immune cells in the substantia nigra, which may be essential for PD. Our study uses machine learning (ML) to screen for potential PD genetic biomarkers. Gene expression profiles were screened from the Gene Expression Omnibus (GEO). Differential expression genes (DEGs) were selected for the enrichment analysis. A protein-protein interaction (PPI) network was built with the STRING database (Search Tool for the Retrieval of Interacting Genes), and two ML approaches, namely least absolute shrinkage and selection operator (LASSO) and support vector machine recursive feature elimination (SVM-RFE), were employed to identify candidate genes. The external validation dataset further tested the expression degree and diagnostic value of candidate biomarkers. To assess the validity of the diagnosis, we determined the receiver operating characteristic (ROC) curve. A convolution tool was employed to evaluate the composition of immune cells by CIBERSORT, and we performed correlation analyses on the basis of the training dataset. Twenty-seven DEGs were screened in the PD and control samples. Our results from the enrichment analysis showed a close association with inflammatory and immune-associated diseases. Both the LASSO and SVM algorithms screened eight and six characteristic genes. AGTR1, GBE1, TPBG, and HSPA6 are overlapping hub genes strongly related to PD. Our results of the area under the ROC (AUC), including AGTR1 (AUC = 0.933), GBE1 (AUC = 0.967), TPBG (AUC = 0.767), and HSPA6 (AUC = 0.633), suggested that these genes have good diagnostic value, and these genes were significantly associated with the degree of immune cell infiltration. AGTR1, GBE1, TPBG, and HSPA6 were identified as potential biomarkers in the diagnosis of PD and provide a novel viewpoint for further study on PD immune mechanism and therapy.
| S-EPMC9953979 | biostudies-literature
Project description:Voxel-based morphometry (VBM) studies have revealed gray matter alterations in smokers, but this type of analysis has poor predictive value for individual cases, which limits its applicability in clinical diagnoses and treatment. A predictive model would essentially embody a complex biomarker that could be used to evaluate treatment efficacy. In this study, we applied VBM along with a multivariate classification method consisting of a support vector machine with recursive feature elimination to discriminate smokers from nonsmokers using their structural MRI data. Mean gray matter volumes in 1,024 cerebral cortical regions of interest created using a subparcellated version of the Automated Anatomical Labeling template were calculated from 60 smokers and 60 nonsmokers, and served as input features to the classification procedure. The classifier achieved the highest accuracy of 69.6% when taking the 139 highest ranked features via 10-fold cross-validation. Critically, these features were later validated on an independent testing set that consisted of 28 smokers and 28 nonsmokers, yielding a 64.04% accuracy level (binomial P = 0.01). Following classification, exploratory post hoc regression analyses were performed, which revealed that gray matter volumes in the putamen, hippocampus, prefrontal cortex, cingulate cortex, caudate, thalamus, pre-/postcentral gyrus, precuneus, and the parahippocampal gyrus, were inversely related to smoking behavioral characteristics. These results not only indicate that smoking related gray matter alterations can provide predictive power for group membership, but also suggest that machine learning techniques can reveal underlying smoking-related neurobiology.
| S-EPMC5531448 | biostudies-literature
Project description:BackgroundSupport vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of observations. However, originally, application of SVM to analyze biomedical data was limited because SVM was not designed to evaluate importance of predictor variables. Creating predictor models based on only the most relevant variables is essential in biomedical research. Currently, substantial work has been done to allow assessment of variable importance in SVM models but this work has focused on SVM implemented with linear kernels. The power of SVM as a prediction model is associated with the flexibility generated by use of non-linear kernels. Moreover, SVM has been extended to model survival outcomes. This paper extends the Recursive Feature Elimination (RFE) algorithm by proposing three approaches to rank variables based on non-linear SVM and SVM for survival analysis.ResultsThe proposed algorithms allows visualization of each one the RFE iterations, and hence, identification of the most relevant predictors of the response variable. Using simulation studies based on time-to-event outcomes and three real datasets, we evaluate the three methods, based on pseudo-samples and kernel principal component analysis, and compare them with the original SVM-RFE algorithm for non-linear kernels. The three algorithms we proposed performed generally better than the gold standard RFE for non-linear kernels, when comparing the truly most relevant variables with the variable ranks produced by each algorithm in simulation studies. Generally, the RFE-pseudo-samples outperformed the other three methods, even when variables were assumed to be correlated in all tested scenarios.ConclusionsThe proposed approaches can be implemented with accuracy to select variables and assess direction and strength of associations in analysis of biomedical data using SVM for categorical or time-to-event responses. Conducting variable selection and interpreting direction and strength of associations between predictors and outcomes with the proposed approaches, particularly with the RFE-pseudo-samples approach can be implemented with accuracy when analyzing biomedical data. These approaches, perform better than the classical RFE of Guyon for realistic scenarios about the structure of biomedical data.
| S-EPMC6245920 | biostudies-literature
Project description:BackgroundOsteoporosis is a bone disease that increases the patient's risk of fracture. We aimed to identify robust marker genes related to osteoporosis based on different bioinformatic methods and multiple datasets.MethodsThree datasets from Gene Expression Omnibus (GEO) were utilized for analysis separately. Significantly differentially expressed genes (DEGs) from comparing high hip and low hip low bone mineral density (BMD) groups in the first dataset were identified for Gene Ontology (GO), Gene set enrichment analysis (GSEA) and Kyoto encyclopedia of genes and genomes (KEGG) to investigate the discrepantly enriched biological processes between high hip and low hip group. Last absolute shrinkage and selection operator (LASSO), SVM model and protein-protein interaction (PPI) regulatory network were performed and generated robust marker genes for downstream TF-target and miRNA-target prediction.ResultsSeveral DEGs between high hip BMD group and low hip BMD group were obtained. And the metabolism-related pathways such as metabolic pathways, carbon metabolism, glyoxylate and dicarboxylate metabolism shown enrichment in these DEGs. Integration with LASSO regression analysis, 8 differential expression genes (SH3BP1, NARF, ANKRD34B, RNF40, ZNF473, AKT1, SHMT1, and VASH1) in GSE62402 were identified as the optimal differential genes combination. Moreover, the SVM validation analysis in GSE56814 and GSE56815 datasets showed that the characteristic gene combinations presented high diagnostic effects, and the model AUC areas for GSE56814 was 0.899 and for GSE56815 was 0.921. Furthermore, the subcellular localization analysis of the 8 genes revealed that 4 proteins were located in the cytoplasm, 3 proteins were located in the nucleus, and 1 protein was located in the mitochondria. Additionally, the related TFs and miRNAs by performing TF-target and miRNA-target prediction for 5 genes (AKT1, SHMT1, ZNF473, RNF40 and VASH1) were investigated from PPI network.ConclusionThe optimal differential genes combination (SH3BP1, NARF, ANKRD34B, RNF40, ZNF473, AKT1, SHMT1, and VASH1) presented high diagnostic effect for osteoporosis risk.
| S-EPMC8801634 | biostudies-literature
Project description:Team formation, which aims to form a team to complete a given task by covering its required skills, furnishes a natural way to help organizers complete projects effectively. In this work, we propose a new team hiring problem. Given a set of projects [Formula: see text] with required skills, and a pool of experts [Formula: see text], each of which has his own skillset, compensation demand and participation constraint (i.e., the maximum number of projects the expert can participate in simultaneously), we seek to hire a team of participation-constrained experts [Formula: see text] to complete all the projects so that the overall compensation is minimized. We refer to this as the participation constrained team hire problem. To the best of our knowledge, this is the first work to investigate the problem. We also study a special case of the problem, where the number of projects is within the participation constraint of each expert and design an exact algorithm for it. Since participation constrained team hire problem is proven to be NP-hard, we design three novel efficient approximate algorithms as its solution, each of which focuses on a particular perspective of the problem. We perform extensive experimental studies, on both synthetic and real datasets, to evaluate the performance of our algorithms. Experimental results show that our exact algorithm far surpasses the brute-force solutions and works well in practice. Besides, the three algorithms behave differently when distinct facets of the problem are involved.
| S-EPMC6112644 | biostudies-literature
Project description:The spot instance model is a virtual machine pricing scheme in which some resources of cloud providers are offered to the highest bidder. This leads to the formation of a spot price, whose fluctuations can determine customers to be overbid by other users and lose the virtual machine they rented. In this paper we propose OptiSpot, a heuristic to automate application deployment decisions on cloud providers that offer the spot pricing model. In particular, with our approach it is possible to determine: (i) which and how many resources to rent in order to run a cloud application, (ii) how to map the application components to the rented resources, and (iii) what spot price bids to use to minimize the total cost while maintaining an acceptable level of performance. To drive the decision making, our algorithm combines a multi-class queueing network model of the application with a Markov model that describes the stochastic evolution of the spot price and its influence on virtual machine reliability. We show, using a model developed for a real enterprise application and historical traces of the Amazon EC2 spot instance prices, that our heuristic finds low cost solutions that indeed guarantee the required levels of performance. The performance of our heuristic method is compared to that of nonlinear programming and shown to markedly accelerate the finding of low-cost optimal solutions.
| S-EPMC6959408 | biostudies-literature
Project description:Purpose:Patients with chronic obstructive pulmonary disease (COPD) would have a poor prognosis if they were not continuously managed according to the Global Initiative for Chronic Obstructive Lung Disease (GOLD) guidelines. We aim to develop a model to classify whether COPD patients have been continuously managed according to GOLD in the previous year. Methods:The Managed group were COPD patients from a prospective cohort from November 2017 to November 2019, who have been continuously managed according to GOLD for 1 year. The Control group were COPD patients who were not continuously managed according to GOLD. They were from a retrospective cohort from October 2016 to October 2017 in the same hospitals as the Managed group. A synthetic minority over-sampling technique (SMOTE) algorithm was used to up-sample the Managed group in a training dataset. Features for classification were selected using a support vector machine recursive feature elimination (SVM-RFE) algorithm. The classification model was developed using LibSVM, and its performance was assessed on the testing dataset. Results:The final analysis included 15 subjects in the Managed group and 191 in the Control group. SVM-RFE selects nine features including smoking history, post-bronchodilator (post-)FVC before management, and those after 1-year follow-up (BMI, moderate and severe AECOPD frequency in previous 12 months, mMRC score, post-FEV1, post-FEV1%pred, post-FVC, and post-FEV1/FVC). For our model, positive predictive value is 66.7%, F1 score is 0.978, and AUC is 0.987. Conclusion:SVM classifier combined with SVM-REF feature selection algorithm could achieve good classification between COPD patients who are or are not continuously managed. This model could be applied in clinical practice to help doctors make decisions and enhance COPD patients' compliance with standard treatment.
| S-EPMC7649211 | biostudies-literature
Project description:BackgroundFunctional annotation of rapidly amassing nucleotide and protein sequences presents a challenging task for modern bioinformatics. This is particularly true for protein families sharing extremely low sequence identity, as for lipocalins, a family of proteins with varied functions and great diversity at the sequence level, yet conserved structures.ResultsIn the present study we propose a SVM based method for identification of lipocalin protein sequences. The SVM models were trained with the input features generated using amino acid, dipeptide and secondary structure compositions as well as PSSM profiles. The model derived using both PSSM and secondary structure emerged as the best model in the study. Apart from achieving a high prediction accuracy (>90% in leave-one-out), lipocalinpred correctly differentiates closely related fatty acid-binding proteins and triabins as non-lipocalins.ConclusionThe method offers a promising approach as a lipocalin prediction tool, complementing PROSITE, Pfam and homology modelling methods.
| S-EPMC2813246 | biostudies-literature