SEARCH · PubMed Health

Results for “feature selection”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 235 records · Page 13Linked to original sources

PubMed2004

A method for quantifying and visualizing the diversity of QSAR models.

Feature selection is one of the most commonly used and reliable methods for deriving predictive quantitative structure-activity relationships (QSAR). Many feature selection algorithms are stochastic in nature and often produce different solutions depending on the initialization conditions. Because some features may be highly correlated, models that are based on different sets of descriptors may capture essentially the same information, however, such models are difficult to recognize. Here, we introduce a measure of similarity between QSAR models that captures the correlation between the underlying features. This measure can be used in conjunction with stochastic proximity embedding (SPE) or multi-dimensional scaling (MDS) to create a meaningful visual representation of structure-activity model space and aid in the post-processing and analysis of results of feature selection calculations.

Algorithms↗

PubMed2004

Support vector channel selection in BCI.

Designing a brain computer interface (BCI) system one can choose from a variety of features that may be useful for classifying brain activity during a mental task. For the special case of classifying electroencephalogram (EEG) signals we propose the usage of the state of the art feature selection algorithms Recursive Feature Elimination and Zero-Norm Optimization which are based on the training of support vector machines (SVM). These algorithms can provide more accurate solutions than standard filter methods for feature selection. We adapt the methods for the purpose of selecting EEG channels. For a motor imagery paradigm we show that the number of used channels can be reduced significantly without increasing the classification error. The resulting best channels agree well with the expected underlying cortical activity patterns during the mental tasks. Furthermore we show how time dependent task specific information can be visualized.

Algorithms↗

PubMed1999

Selective effects of nicotine on attentional processes.

RATIONALE: It is now well established from electrophysiological and behavioural evidence that nicotine has effects on information processing. The results are usually explained either by a primary effect of nicotine or by a reversal effect of a nicotine-induced, abstinence deficit. In addition, there is dispute about the cognitive processes underlying the changes in performance. METHODS: This study has approached the first question by using the nicotine patch, in order to administer nicotine chronically. In addition, we examined the effects of nicotine on attention with a selection of tests which assessed the intensity and selectivity features of attention, using the Random Letter Generation test, the Flexibility of Attention test and the Stroop test. RESULTS: Nicotine enhanced the speed of number generation and the speed of processing in both the control and interference conditions of the Stroop test. There were no effects on attentional switching of the Flexibility of Attention test. CONCLUSION: The results are consistent with the hypothesis that nicotine mainly improves the intensity feature of attention, rather than the selectivity feature.

Adolescent↗

PubMed2006

Wavelet basis selection and feature extraction for shift invariant ultrasound foreign body classification.

This paper proposes a novel technique for automatic ultrasound non-destructive foreign body (FB) detection and classification. A signal registration process is introduced to eliminate shift variations commonly encountered in ultrasound signals. Information theory based methods are then developed for wavelet basis selection and feature extraction to facilitate robust FB classification. Probabilistic neural networks are used for FB classification. Experimental results confirm that the wavelet basis selected by the proposed method improves the FB classification accuracy. It is concluded that low order wavelet bases have better ability to distinguish classes with great similarities than their higher order counterparts, while the reverse is true for more divergent classes.

Algorithms↗

PubMed2002

Bayesian automatic relevance determination algorithms for classifying gene expression data.

MOTIVATION: We investigate two new Bayesian classification algorithms incorporating feature selection. These algorithms are applied to the classification of gene expression data derived from cDNA microarrays. RESULTS: We demonstrate the effectiveness of the algorithms on three gene expression datasets for cancer, showing they compare well with alternative kernel-based techniques. By automatically incorporating feature selection, accurate classifiers can be constructed utilizing very few features and with minimal hand-tuning. We argue that the feature selection is meaningful and some of the highlighted genes appear to be medically important.

Algorithms↗

PubMed2003

Developmental interdependence between selected somatic features and the weight of internal organs in human male and female foetuses.

The study material comprised 3889 foetuses of both sexes, aged 20-42 weeks and focused on developmental interdependence between the weight of the internal organs and their relation to selected somatic features during the prenatal period. The study also attempted to distinguish potential sex-related differences in the degree of statistical interdependence between the analysed variables. As a result, the analysis of linear and canonical correlation coefficients for consecutive weeks of foetal life has been carried out. High correlation coefficients have been obtained which indicate strong developmental interdependence between those organs and the somatic features. However, no significant sex-related differences in the developmental interdependence of the analysed variables have been observed.

Anthropometry↗

PubMedDate not supplied

Similarity searching of chemical databases using atom environment descriptors (MOLPRINT 2D): evaluation of performance.

A molecular similarity searching technique based on atom environments, information-gain-based feature selection, and the naive Bayesian classifier has been applied to a series of diverse datasets and its performance compared to those of alternative searching methods. Atom environments are count vectors of heavy atoms present at a topological distance from each heavy atom of a molecular structure. In this application, using a recently published dataset of more than 100000 molecules from the MDL Drug Data Report database, the atom environment approach appears to outperform fusion of ranking scores as well as binary kernel discrimination, which are both used in combination with Unity fingerprints. Overall retrieval rates among the top 5% of the sorted library are nearly 10% better (more than 14% better in relative numbers) than those of the second best method, Unity fingerprints and binary kernel discrimination. In 10 out of 11 sets of active compounds the combination of atom environments and the naive Bayesian classifier appears to be the superior method, while in the remaining dataset, data fusion and binary kernel discrimination in combination with Unity fingerprints is the method of choice. Binary kernel discrimination in combination with Unity fingerprints generally comes second in performance overall. The difference in performance can largely be attributed to the different molecular descriptors used. Atom environments outperform Unity fingerprints by a large margin if the combination of these descriptors with the Tanimoto coefficient is compared. The naive Bayesian classifier in combination with information-gain-based feature selection and selection of a sensible number of features performs about as well as binary kernel discrimination in experiments where these classification methods are compared. When used on a monoaminooxidase dataset, atom environments and the naive Bayesian classifier perform as well as binary kernel discrimination in the case of a 50/50 split of training and test compounds. In the case of sparse training data, binary kernel discrimination is found to be superior on this particular dataset. On a third dataset, the atom environment descriptor shows higher retrieval rates than other 2D fingerprints tested here when used in combination with the Tanimoto similarity coefficient. Feature selection is shown to be a crucial step in determining the performance of the algorithm. The representation of molecules by atom environments is found to be more effective than Unity fingerprints for the type of biological receptor similarity calculations examined here. Combining information prior to scoring and including information about inactive compounds, as in the Bayesian classifier and binary kernel discrimination, is found to be superior to posterior data fusion (in the datasets tested here).

Journal Article↗

PubMed2005

Modeling of activity of cyclic urea HIV-1 protease inhibitors using regularized-artificial neural networks.

Artificial neural networks (ANNs) were used to model both inhibition of HIV-1 protease (K(i)) and inhibition of HIV replication (IC90) for 55 cyclic urea derivatives using constitutional and 2D descriptors. As a preliminary step, linear dependences were established by multiple linear regression (MLR) approaches, selecting the relevant descriptors by genetic algorithm (GA) feature selection. For ANN models non-linear GA feature selection was also applied. Non-linear modeling of K(i) overcame the results of the linear one using four properties, keeping in mind standard Pearson R correlation coefficients (0.931 vs. 0.862) and leave one out (LOO) cross-validation analysis (Q(LOO)2 = 0.703 vs. 0.510). On the other hand, IC90 modeling was insoluble by a linear approach: no predictive model was achieved; however, a non-linear relation was encountered according to statistic results (R = 0.891; Q(LOO)2 = 0.568). The best non-linear models suggested the influence of the presence of nitrogen atoms and the molecular volume distribution in the inhibitor structures on the HIV-1 protease inhibition as well as that the inhibition of HIV replication was dependent on the occurrence of five-member rings. Finally, inhibitors were well distributed regarding its activity levels in a Kohonen self-organizing map built using the input variables of the best non-linear models.

Algorithms↗

PubMed1997

Feature subset selection for classification of histological images.

Classification of histological images is considered in this paper. The task is to distinguish different classes of tumours of the central nervous system on the basis of features extracted from microscopic slides. The number of extracted features is relatively high and some of them seem to be irrelevant for classification of the images. Thus, the main objective of this study is to select such a feature subset that improves the predictive accuracy of the classifier. The wrapper approach is chosen to obtain this aim, where a search for the good subset of features is made using a non-parametric case-base classifier. To guide a search process, a forward beam selection algorithm is introduced. It sequentially adds relevant features in a parallel way for the most promising subsets. It is shown that the proposed approach gives good predictive accuracy for the considered histopathological problem.

Algorithms↗

PubMed2005

[Research on pattern classification methods using gene expression data].

One of the applications of cDNA microarrays is to recognize the class and subclass of diseases such as cancers on the basis of statistical pattern classification methods using gene expression data. In this paper, we apply 2000 genes expression dataset provided by Affymatrix Company: 40 samples of intestine cancer tissue and 22 samples of normal tissue. We compare the performance of four pattern classification methods based on different feature selection methods. These pattern classification methods include: Fisher linear discriminate, Logit nonlinear discriminate, the least distance and K-nearest neighbor classifier. The results show firstly that four pattern classifiers based on the feature selection methods of t-test and classification tree all have better performance than those based on the stochastic feature selection methods, secondly that K-nearest neighbor classifier has the best performance, thirdly that both the least distance classifier and K-nearest neighbor classifier have better generalization, fourthly that four classifiers are less sensitive to the composition of samples.

Gene Expression↗

PubMed2004

Data mining techniques for cancer detection using serum proteomic profiling.

OBJECTIVE: Pathological changes in an organ or tissue may be reflected in proteomic patterns in serum. It is possible that unique serum proteomic patterns could be used to discriminate cancer samples from non-cancer ones. Due to the complexity of proteomic profiling, a higher order analysis such as data mining is needed to uncover the differences in complex proteomic patterns. The objectives of this paper are (1) to briefly review the application of data mining techniques in proteomics for cancer detection/diagnosis; (2) to explore a novel analytic method with different feature selection methods; (3) to compare the results obtained on different datasets and that reported by Petricoin et al. in terms of detection performance and selected proteomic patterns. METHODS AND MATERIAL: Three serum SELDI MS data sets were used in this research to identify serum proteomic patterns that distinguish the serum of ovarian cancer cases from non-cancer controls. A support vector machine-based method is applied in this study, in which statistical testing and genetic algorithm-based methods are used for feature selection respectively. Leave-one-out cross validation with receiver operating characteristic (ROC) curve is used for evaluation and comparison of cancer detection performance. RESULTS AND CONCLUSIONS: The results showed that (1) data mining techniques can be successfully applied to ovarian cancer detection with a reasonably high performance; (2) the classification using features selected by the genetic algorithm consistently outperformed those selected by statistical testing in terms of accuracy and robustness; (3) the discriminatory features (proteomic patterns) can be very different from one selection method to another. In other words, the pattern selection and its classification efficiency are highly classifier dependent. Therefore, when using data mining techniques, the discrimination of cancer from normal does not depend solely upon the identity and origination of cancer-related proteins.

Biomarkers, Tumor↗

PubMed1997

Phenotypic features of selective T cell deficiency characterized by absence of CD8+ T lymphocytes and undetectable mRNA for ZAP-70 kinase.

Selective T cell deficiency is a rare immune deficiency characterized by the absence of CD8+ T lymphocytes and depressed/absent T cell function. This syndrome has been associated with mutations in the gene for ZAP-70, a tyrosine kinase that has profound effects on signaling via the T cell receptor. In this paper we describe a patient with selective T cell deficiency and certain phenotypic features that are unique among the small number of patients described. The patient had virtually absent T cell function, hypogammaglobulinemia, and no response to vaccination. The T lymphocytes failed to respond to mitogenic stimuli, even in the presence of exogenous interleukin 2. Similar to other patients with this disorder, the T cells were capable of proliferating when stimulated by pharmacologic agents such as phorbol ester and ionomycin. While peripheral blood T cells had limited capability to increase cytosolic Ca2+ levels in response to mitogenic stimulation, thymocytes responded to a large panel of antibodies and mitogens. This report broadens the spectrum of clinical presentations associated with selective T cell deficiency and, for the first time, compares the responses of both peripheral T cells and thymocytes. The data support the concept that the defect in signal transduction resulting from the absence of ZAP-70 is primarily manifested following export of T lymphocytes from the thymus and that selection of CDS-positive T cells is dependent on the presence of ZAP-70.

CD8-Positive T-Lymphocytes↗

PubMed2025

A comparative study highlights superiority of LSTM in crop genomic prediction.

We systematically evaluated three key determinants affecting prediction accuracy and the algorithm performance differences based on fifteen state-of-the-art GP methods, and found LSTM suitable for capturing additive and epistatic effects. Genomic prediction (GP) has been developed as an important method supporting crop breeding. By utilizing the phenotype values result from GP, breeders could make decisions in the seedling stage that consequently benefit for cost saving. In recent years, machine learning emerged as an efficient technology to solve modeling problems in many fields, including crop breeding. However, numerous modeling approaches have hindered the application of GP since breeders struggle to choose. Therefore, a comprehensively methodological research with guiding significance is extremely necessary. In the present study, we systematically evaluated three key determinants affecting prediction accuracy and the algorithm performance differences based on fifteen state-of-the-art GP methods. As for genomic feature processing, we found feature selection (SNP filtering approach) performed better than feature extraction (PCA method). Specifically, the feature relationship dependent methods (GBLUP, RNN, and LSTM) as well as DNN architecture showed superior performance with feature selection. Marker density analysis showed positive correlation with prediction accuracy in a limited threshold. Comparison on effect of population size demonstrated a positive correlation between trait genetic complexity and the optimal population size required. By testing fifteen modeling methods, we found LSTM network displayed superior performance, achieving the highest average STScore (0.967) across six datasets. Further research using all cell states or the latest cell states of LSTM inputs demonstrated its architecture particularly adept with capturing additive and epistatic QTL effects among SNPs. In conclusion, our findings provide basic principles for implementing GP in breeding project to maximize prediction accuracy while maintaining cost-effectiveness.

Plant Breeding↗

PubMed2006

Relevance feedback for CBIR: a new approach based on probabilistic feature weighting with positive and negative examples.

In content-based image retrieval, understanding the user's needs is a challenging task that requires integrating him in the process of retrieval. Relevance feedback (RF) has proven to be an effective tool for taking the user's judgement into account. In this paper, we present a new RF framework based on a feature selection algorithm that nicely combines the advantages of a probabilistic formulation with those of using both the positive example (PE) and the negative example (NE). Through interaction with the user, our algorithm learns the importance he assigns to image features, and then applies the results obtained to define similarity measures that correspond better to his judgement. The use of the NE allows images undesired by the user to be discarded, thereby improving retrieval accuracy. As for the probabilistic formulation of the problem, it presents a multitude of advantages and opens the door to more modeling possibilities that achieve a good feature selection. It makes it possible to cluster the query data into classes, choose the probability law that best models each class, model missing data, and support queries with multiple PE and/or NE classes. The basic principle of our algorithm is to assign more importance to features with a high likelihood and those which distinguish well between PE classes and NE classes. The proposed algorithm was validated separately and in image retrieval context, and the experiments show that it performs a good feature selection and contributes to improving retrieval effectiveness.

Algorithms↗

PubMed2005

Features of selective kinase inhibitors.

Small-molecule inhibitors of protein and lipid kinases have emerged as indispensable tools for studying signal transduction. Despite the widespread use of these reagents, there is little consensus about the biochemical criteria that define their potency and selectivity in cells. We discuss some of the features that determine the cellular activity of kinase inhibitors and propose a framework for interpreting inhibitor selectivity.

Animals↗

PubMed1981

Selection of optimal features for classification of electrocardiograms.

The forward sequential selection and backward sequential rejection algorithms and the optimal branch and bound algorithm were evaluated in selection of features for classification of electrocardiograms of 237 patients with old myocardial infarction and 299 subjects without infarction. The branch and bound algorithm proved suitable for small sets of ECG features. However, the computational effort required was orders of magnitude greater than that for the other two methods and became prohibitive with large features sets. A satisfactory and consistent overall classification accuracy was achieved by using the sequential selection algorithms for selecting continuous features by maximizing the Mahalanobis distance at each step of the feature selection process. Maximization of the association index can produce better results but requires more computing effort. Feature selection based on maximizing sensitivity at each step for a fixed level of specificity is less satisfactory when a high level of specificity is required.

Computers↗

PubMed2001

Feature subset selection by genetic algorithms and estimation of distribution algorithms. A case study in the survival of cirrhotic patients treated with TIPS.

The transjugular intrahepatic portosystemic shunt (TIPS) is an interventional treatment for cirrhotic patients with portal hypertension. In the light of our medical staff's experience, the consequences of TIPS are not homogeneous for all the patients and a subgroup dies in the first 6 months after TIPS placement. Actually, there is no risk indicator to identify this subgroup of patients before treatment. An investigation for predicting the survival of cirrhotic patients treated with TIPS is carried out using a clinical database with 107 cases and 77 attributes. Four supervised machine learning classifiers are applied to discriminate between both subgroups of patients. The application of several feature subset selection (FSS) techniques has significantly improved the predictive accuracy of these classifiers and considerably reduced the amount of attributes in the classification models. Among FSS techniques, FSS-TREE, a new randomized algorithm inspired on the new EDA (estimation of distribution algorithm) paradigm has obtained the best average accuracy results for each classifier.

Algorithms↗

PubMed2005

Multiple SVM-RFE for gene selection in cancer classification with expression data.

This paper proposes a new feature selection method that uses a backward elimination procedure similar to that implemented in support vector machine recursive feature elimination (SVM-RFE). Unlike the SVM-RFE method, at each step, the proposed approach computes the feature ranking score from a statistical analysis of weight vectors of multiple linear SVMs trained on subsamples of the original training data. We tested the proposed method on four gene expression datasets for cancer classification. The results show that the proposed feature selection method selects better gene subsets than the original SVM-RFE and improves the classification accuracy. A Gene Ontology-based similarity assessment indicates that the selected subsets are functionally diverse, further validating our gene selection method. This investigation also suggests that, for gene expression-based cancer classification, average test error from multiple partitions of training and test sets can be recommended as a reference of performance quality.

Algorithms↗