Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Feature selection”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 1,063 records · Page 59Linked to original sources
PubMed1999

Evidence for early hematopoietic progenitor cell involvement in acute promyelocytic leukemia.

Acute promyelocytic leukemia (APL) represents a subtype of acute myeloid leukemia with characteristic morphologic, molecular, and immunophenotypic features. Previous immunophenotypic analyses have shown that leukemic cells in APL typically express the myeloid markers CD33 and CD13 but lack expression of the early hematopoietic progenitor cell antigens CD34 and HLA-DR. We analyzed selected immunophenotypic features of APL by flow cytometry and showed that 7 (41%) of 17 cases contained significant subsets of CD34+ leukemic cells: CD34+ myeloid cells predominated in 2 APL cases. By using a fluorescence-activated cell sorter-fluorescence in situ hybridization approach, we confirmed that the CD34+ cells harbored the t(15;17) translocation characteristic of APL. By using the same experimental approach, CD34+ populations were stratified into primitive CD34+ CD38- and committed CD34+ CD38+ progenitor cell subpopulations; cells in both subsets contained the t(15;17) translocation. The knowledge that APL may be partly or largely CD34+ is important for proper diagnosis. Furthermore, identification of the t(15;17) translocation in CD34+ CD38- blasts indicates that, in at least some cases, the leukemogenic mutation in APL occurs within primitive hematopoietic progenitor cells.

Antigens, CD34↗
PubMed2003

How selective are V1 cells for pop-out stimuli?

Many neurons in visual area V1 respond better to a pop-out stimulus, such as a single vertical bar among many horizontal bars, than to a homogeneous stimulus, such as a stimulus with all vertical bars. Many studies have suggested such cells represent neural correlates of pop-out, or more generally figure-ground segregation. However, preference for pop-out stimuli over homogeneous stimuli could also arise from a nonspecific selectivity for feature discontinuities between the target and the background, without any specificity for pop-out per se. To distinguish between these two confounding scenarios, we compared the responses of V1 neurons to pop-out stimuli with the responses to "conjunction-target" stimuli, which have more complex feature discontinuities between the target and the surround, as in a stimulus with a blue vertical bar among blue horizontal bars and yellow vertical bars. The target in conjunction-target stimuli does not pop out, which we psychophysically verified. V1 cells in general responded similarly to pop-out and conjunction-target stimuli, and only a small minority of cells (approximately 2% by one measure) distinguished the pop-out and conjunction-target stimuli from each other and from homogeneous stimuli. Nevertheless, the responses of approximately 50% of the cells were significantly modulated across all center-surround stimuli, indicating that V1 cells can convey information about the feature discontinuities between the center and the surround as part of a network of neurons, although individual cells by themselves fail to explicitly represent pop-out. In light of our results, unambiguous pop-out selectivity at the level of individual cells remains to be demonstrated in V1 or elsewhere in the visual cortex.

Animals↗
PubMed1986

Quantitative evaluation of the progressive nuclear abnormalities in urothelial papillary lesions.

The natural history of noninvasive urothelial papillary carcinomas is characterized by structural and nuclear abnormalities of the epithelial lining in the three grades. Morphometry is applied to measure nuclear-related quantitative parameters from the lower (L) and upper (U) halves of urothelial thickness, i.e. perimeter, area and roundness factor. Their mean and SD as well as the derived parameters have values steadily higher from normal-looking urothelium to G3, whereas the relative frequency distribution shows over-lapping among the grades. The multivariate analysis is then applied. First of all the smallest number of least correlated and most discriminant features is selected: SD of nuclear area log (L), percentage of round nuclei (L), mean of the 10 largest values of nuclear area (L) and mean nuclear perimeter (L). The results of the pattern recognition analysis based on these features show the following percentages of agreement between histopathological and computer classifications: 94% in the training set and 80% in the test set. The calculation of the classification probability and the adoption of a threshold approach of 0.25 less than P less than 0.75 are helpful in identifying the 'in-between' cases, i.e., those in the 'intermediate' position between G1 and G2 and between G2 and G3. Morphometry and multivariate analysis allow us to quantify the nuclear abnormalities of urothelial papillary carcinomas and show a progressive and continuous spectrum of modifications.

Cell Nucleus↗
PubMed1993

Perceptual ranking versus visual evoked potentials for different local features in texture segregation.

PURPOSE: To validate recent reports of specific visual evoked potentials associated with preattentive texture segregation (tsVEPs) and to quantitatively compare perceptual segregation strength and tsVEP amplitudes across different local features. METHODS: Four local features were selected: crossed vs noncrossed, line segments differing in orientation by 90 degrees, U-shapes differing in orientation by 90 degrees, and U-shapes differing in orientation by 180 degrees. The two variants of each local feature were spatially arranged in a checkerboard pattern; for the first three features this led to pop-out of a "preattentive checkerboard." In seven subjects, perceptual segregation strength was assessed using ranking, and tsVEPs were recorded in these and three additional subjects. RESULTS: Statistically significant tsVEPs were obtained for the features crossed vs noncrossed and 90 degrees-line segments. Ranking results and tsVEP amplitudes were highly correlated (P < 0.001); the order of perceptual ranking and the order of tsVEP amplitudes were identical; 180 degrees-U-shapes had lowest ranking, mean tsVEP amplitude was 0.1 microV, close to noise. Line segments had maximal ranking, tsVEP amplitude was 1.5 microV. CONCLUSIONS: The results suggest that tsVEPs quantitatively reflect the activity of cortical mechanisms involved in texture segregation across various features.

Adult↗
PubMed2005

Chitinase and Fizz family members are a generalized feature of nematode infection with selective upregulation of Ym1 and Fizz1 by antigen-presenting cells.

Ym1 and Fizz1 are secreted proteins that have been identified in a variety of Th2-mediated inflammatory settings. We originally found Ym1 and Fizz1 as highly expressed macrophage genes in a Brugia malayi infection model. Here, we show that their expression is a generalized feature of nematode infection and that they are induced at the site of infection with both the tissue nematode Litomosoides sigmodontis and the gastrointestinal nematode Nippostrongylus brasiliensis. At the sites of infection with N. brasiliensis, we also observed induction of other chitinase and Fizz family members (ChaFFs): acidic mammalian chitinase (AMCase) and Fizz2. The high expression of both Ym1 and AMCase in the lungs of infected mice suggests that abundant chitinase production is an important feature of Th2 immune responses in the lung. In addition to expression of ChaFFs in the tissues, Ym1 and Fizz1 expression was observed in the lymph nodes. Expression both in vitro and in vivo was restricted to antigen-presenting cells, with the highest expression in B cells and macrophages. ChaFFs may therefore be important effector or wound-repair molecules at the site of nematode infection, with potential regulatory roles for Ym1 and Fizz1 in the draining lymph nodes.

Amino Acid Sequence↗
PubMed2002

Split-second sequential selective activation in human secondary visual cortex.

This work addressed early selection based on nonspatial visual features, using event-related potentials (ERPs) with high temporal resolution and dipole-source modeling. Subjects were presented rapid sequences of gratings varying in spatial frequency and orientation, and were instructed to attend to gratings with one spatial frequency and ignore those with another. Attention effects started at 120-msec latency as anterior positivity and proceeded as posterior negativity (200 msec) and anterior negativity (265 msec). Dipole-source modeling suggested that these effects reflect the sequential selective activation of, on average, posterior dorsal-medial, posterior ventral-lateral, and anterior medial cortical areas. In contrast, stimulus-specific activity was observed well before 100-msec latency and characterized by dipoles with locations significantly posterior to those of the attention-modulated activity. These results indicate that even with highly discriminable spatial frequencies, selection is not as early as before the 100-msec latency, unlike what is often found for location selection. It is also separated in time and anatomically from the earliest stimulus-specific cortical activity. Reducing discriminability of the selection feature resulted in longer selection latencies, becoming manifest only at 175 msec as an apparent combination of posterior and anterior negativities, and in an elevated criterion for overt responding.

Adult↗
PubMed2003

Wavelet-packet-based texture analysis for differentiation between benign and malignant liver tumours in ultrasound images.

The purpose of this study was to apply a novel method of multiscale echo texture analysis for distinguishing benign (hemangiomas) from malignant (hepatocellular carcinomas (HCCs) and metastases) focal liver lesions in B-mode ultrasound images. In this method, regions of interest (ROIs) extracted from within the lesions were decomposed into subimages by wavelet packets. Multiscale texture features that quantify homogeneity of the echogenicity were calculated from these subimages and were combined by an artificial neural network (ANN). A subset of the multiscale features was selected that yielded the highest performance in the classification of lesions measured by the area under the receiver operating characteristic curve (Az). In an analysis of 193 ROIs consisting of 50 hemangiomas, 87 hepatocellular carcinomas and 56 metastases, the multiscale features yielded a high A: value of 0.92 in distinguishing benign from malignant lesions, 0.93 in distinguishing hemangiomas from HCCs and 0.94 in distinguishing hemangiomas from metastases. Our new multiscale texture analysis method can effectively differentiate malignant from benign lesions, and thus has the potential to increase the accuracy of diagnosis of focal liver lesions in ultrasound images.

Carcinoma, Hepatocellular↗
PubMed2004

The emergence of selective 5-HT 2B antagonists structures, activities and potential therapeutic applications.

5-HT(2) receptors mediate a large array of physiological and behavioral functions in humans via three distinct subtypes: 5-HT(2A), 5-HT(2B)and 5-HT(2C). While selective 5-HT(2A)antagonists have been known for some time, knowledge of the precise role played by the 5-HT(2B)receptor was hampered by the existence of solely 5-HT(2B)5-HT(2C) mixed antagonists. However, selective 5-HT(2B)antagonists began recently to emerge in the literature. Indeed, four structural classes belonging to the piperazine, indole, naphthylpyrimidine and tetrahydro-beta-carboline scaffolds were reported. In this paper, we will briefly review the structural and pharmacological features of selective 5-HT(2B) antagonists, including patent literature of the last five years.

Animals↗
PubMedDate not supplied

Discovery and design of novel vasopressin hypotensive peptide agonists.

This presentation will trace the serendipitous discovery of novel vasopressin (VP) hypotensive agonists d(CH2)5[D-Tyr(Et)2,X3]VAVP (where X = Arg, Lys). These peptides were uncovered as part of an ongoing program aimed at the design of potent and selective VP antidiuretic (V2 receptor) antagonists. We will also present highlights of our subsequent preliminary studies seeking (i) to design high affinity radioiodinatable ligands for the localization and characterization of the putative VP vasodilatory (V1c?) receptor; (ii) to identify the structural features of selective and non-selective cyclic and linear VP and oxytocin (OT) antagonists of the V2 receptor, the vascular (V1a) receptor and of the uterine (OT) receptor required for hypotensive agonism and; (iii) to enhance hypotensive potency. These novel VP hypotensive agonists could serve as valuable research tools in studies on the roles of VP in blood pressure regulation and may also lead to the development of a new class of therapeutically useful antihypertensives.

Affinity Labels↗
PubMed2000

What clinical features are most useful to distinguish definite multiple system atrophy from Parkinson's disease?

OBJECTIVES: Few studies have attempted to identify what premortem features best differentiate multiple system atrophy (MSA) from Parkinson's disease (PD). These studies are limited by small sample size, clinical heterogeneity, or lack of postmortem validation. We evaluated the sensitivity and specificity of different clinical features in distinguishing pathologically established MSA from PD. METHODS: One hundred consecutive cases of pathologically confirmed PD and 38 cases of pathologically confirmed MSA in one Parkinson's disease brain bank were included. All cases had their clinical notes reviewed by one observer (AH). Clinical features were divided into two groups: those occurring up to 5 years after onset of disease and those occurring up to death. Statistical analysis comprised multivariate logistic regression analysis to choose and weight key variables for the optimum predictive model. RESULTS: The selected early features and their weightings were: autonomic features (2), poor initial levodopa response (2), early motor fluctuations (2), and initial rigidity (2). A cut off of 4 or more on the ROC curve resulted in a sensitivity of 87.1% and specificity of 70.5%. A better predictive model occurred if the following features up to death were included: poor response to levodopa (2), autonomic features (2), speech or bulbar dysfunction (3), absence of dementia (2), absence of levodopa induced confusion (4), and falls (4). The resulting ROC curve based on individual scores showed a best cut off score of at least 11 of 17 (sensitivity 90.3%, specificity 92.6%). CONCLUSIONS: Predictive models may help differentiate MSA and PD premortem. Hitherto poorly recognised features, suggestive of MSA, included preserved cognitive function and absence of psychiatric effects from antiparkinsonian medication. Diagnostic accuracy was higher in those models taking into account all clinical features occurring up to death. Further studies need to be based on new incident cohorts of parkinsonian patients with subsequent neuropathological evaluation.

Adult↗
PubMed2001

Clinical features of dementia associated with apolipoprotein epsilon4: discrimination with a neural network genetic algorithm.

BACKGROUND: It is unclear whether the APOE epsilon4 allele is associated with distinct clinical features in dementia. METHOD: 100 cases meeting ICD criteria for dementia were interviewed using standardized instruments and genotyped for APOE. The presence of the epsilon4 allele was used by a genetic algorithm neural network (GANN) to discriminate symptoms and signs. RESULTS: The GANN selected six features: gender, systolic blood pressure, absence of ankle tendon reflexes, history of weight loss, history of falls, and interviewer observed lability of mood. Using these features, a neural network discriminated cases according to epsilon4 highly accurately (area under receiver operating characteristic=0.83, sensitivity=0.78, specificity=0.78). CONCLUSIONS: A GANN is able to discriminate a clinically distinct group of features among dementia patients who express the epsilon4 allele.

Accidental Falls↗
PubMed2006

Pacemaker-related endocarditis: clinical features and treatment.

BACKGROUND AND AIM OF THE STUDY: Removal of the entire infected system is the traditionally indicated management of pacemaker lead endocarditis (PLE), based on expert recommendations. Herein is described the present authors' experience with this condition. METHODS: Between 1987 and 2004, all consecutive patients with PLE treated at a tertiary referral university hospital and a community hospital were prospectively selected. Clinical features, management and outcome were analyzed. RESULTS: Thirteen cases of PLE were diagnosed. Surgery was performed in 10 cases, and medical treatment alone in three (due to advanced age in two cases and because of terminal colon cancer in one case). Four subjects died before discharge: three deaths occurred after surgery (one patient died due to refractory ventricular arrhythmia and two from persistent sepsis), and one unoperated patient died from sepsis and severe renal failure. No deaths or late surgeries were observed after a mean follow up period of 37 +/- 14 months. Both patients who survived hospitalization and underwent only medical treatment were free from late complications after 30 and 60 months follow up, respectively. CONCLUSION: Some patients with PLE present a good evolution without surgery, suggesting that surgical treatment is not mandatory in this situation. However, an indication for surgery may be similar to that for other cases of infective endocarditis.

Adult↗
PubMed2005

Use of molecular markers to enhance resistance of livestock to disease: a global approach.

The improvement and utilisation of host genetic resistance to disease is an attractive option as a component of livestock disease control in a wide range of situations. This paper reviews the situations where genetic resistance of the host is likely to be a useful component of disease control and provides a framework for deciding whether genetic improvement of resistance is likely to be worthwhile. Discussion is focused on low-input production systems in the developing world, where disease resistance is particularly important. The authors propose an integrated strategy for the use of molecular markers in assessing genetic diversity and in utilising and improving host genetic resistance to disease. The integrated approach assures that there is value in the molecular genetic information whether or not it proves useful in genetic selection, a feature that should prove attractive to funding and executing agencies.

Animals↗
PubMed2005

Studies on a German (Münster) version of the temperament auto-questionnaire TEMPS-A: construction and validation of the briefTEMPS-M.

BACKGROUND: Based on classic German concepts of a continuum between depressive, hyperthymic, cyclothymic, and irritable temperaments and affective disorder (and adding an anxious type to the four), Akiskal and co-workers developed the Temperament Evaluation of Memphis, Pisa, Paris and San Diego both in interview (TEMPS-I) and auto-questionnaire (TEMPS-A) versions. It is the aim of the present analyses to validate a brief German version of TEMPS-A. METHODS: A total of 1056 students of the Westfalische-Wilhelms-Universitat in Munster, Germany, filled out the long 110-item version of the TEMPS-A (Munster translation by Erfurth: TEMPS-M) modified into a five gradation Likert format and with the items randomized. Based on this data we constructed a brief version of the TEMPS-M. In a second study, a sample of 151 students were recruited who filled out the briefTEMPS-M twice, approximately 1 month apart. RESULTS: Our psychometric procedures resulted in the retention of 35 items from the original 110. The proposed five-factor structure of the original TEMPS-A was upheld, with relatively few item reclassification (mainly due to some overlap between depressive and anxious traits). Internal consistency (Cronbach alpha values ranging from 0.69 to 0.84) and test-retest reliability were shown. Most importantly, all temperaments in the briefTEMPS-M correlated quite well (Pearson r values ranging from 0.49 to 0.72) with their respective original versions in the longer TEMPS-M. As for construct validity, significant correlation was shown with the Beck Depression Inventory for all but the hyperthymic temperament; the hyperthymic, cyclothymic and irritable correlated highest with the self-report Manic Inventory. LIMITATIONS: The study sample of university students was selective. CONCLUSIONS: We were able to construct a brief German version of the TEMPS-A auto-questionnaire. We submit this shorter version will be suitable for both clinical (psychiatric and general medical) and neurobiological research, as well as in studies on temperament features in selected populations, e.g., allowing comparisons between regions or different (German-speaking) countries.

Adolescent↗
PubMed2003

Three-dimensional pharmacophore mapping of certain anticancer alpha-methylene-gamma-butyrolactones.

A definition of pharmacophore hypotheses for certain anticancer alpha-methylene-gamma-butyrolactones was carried out by consideration of a three-dimensional model that correlates the chemical structures of a series of alpha-methylene-gamma-butyrolactones with their cytostatic activity. Training sets consisting of 20 alpha-methylene-gamma-butyrolactones were selected in each case on the basis of the information content of the structures and the activity data as required by the HypoGen program in the Catalyst software. In this case, the best pharmacophore in terms of statistics and predictive value consisted of four features: two hydrogen bond acceptors (HBA), one hydrophobic (HP) feature, and one aromatic ring (AR) feature. The selected pharmacophore hypothesis yielded a correlation coefficient of 0.942 with a cost difference (null cost minus total cost) of 40.342. The pharmacophore was validated on a set of test compounds. This validation study provided confidence for the usefulness of the selected pharmacophore model to identify compounds with diverse structures from a database search. This investigation has demonstrated a practical approach toward the development of anticancer lead compounds through a three-dimensional pharmacophore mapping.

4-Butyrolactone↗
PubMed1998

Gap junctions in vascular smooth muscle.

Gap junction channels are the only class of channels which span two closely apposed plasma membranes. There are over a dozen identified subunit proteins or connexins. Three generic types of gap junction channels are possible. They are the homotypic, heterotypic and heteromeric types, each of which has a distinct connexin distribution. The major connexin found in vascular smooth muscle is connexin43. Connexin40 has also been found in vascular smooth muscle. The biosynthesis, trafficking and degradation of connexin43 has only recently been studied but the data reveal some interesting features such as a short half-life of only 1.5-3.5 h. The gating characteristics of connexin43 reveal mode shifting behaviours which result in prolonged closure of the majority of the gap junction channels. The channel also displays weak voltage dependence and is poorly selective. These features suggest that dynamical regulation of cell-to-cell coupling is best designed to reduce cell-to-cell coupling, rather than enhance it, by down regulation of channel activity through the biosynthesis, trafficking, degradation pathways and gating via mode shifting.

Animals↗
PubMed2006

Computational models with thermodynamic and composition features improve siRNA design.

BACKGROUND: Small interfering RNAs (siRNAs) have become an important tool in cell and molecular biology. Reliable design of siRNA molecules is essential for the needs of large functional genomics projects. RESULTS: To improve the design of efficient siRNA molecules, we performed a comparative, thermodynamic and correlation analysis on a heterogeneous set of 653 siRNAs collected from the literature. We used this training set to select siRNA features and optimize computational models. We identified 18 parameters that correlate significantly with silencing efficiency. Some of these parameters characterize only the siRNA sequence, while others involve the whole mRNA. Most importantly, we derived an siRNA position-dependent consensus, and optimized the free-energy difference of the 5' and 3' terminal dinucleotides of the siRNA antisense strand. The position-dependent consensus is based on correlation and t-test analyses of the training set, and accounts for both significantly preferred and avoided nucleotides in all sequence positions. On the training set, the two parameters' correlation with silencing efficiency was 0.5 and 0.36, respectively. Among other features, a dinucleotide content index and the frequency of potential targets for siRNA in the mRNA added predictive power to our model (R = 0.55). We showed that our model is effective for predicting the efficiency of siRNAs at different concentrations. We optimized a neural network model on our training set using three parameters characterizing the siRNA sequence, and predicted efficiencies for the test siRNA dataset recently published by Novartis. On this validation set, the correlation coefficient between predicted and observed efficiency was 0.75. Using the same model, we performed a transcriptome-wide analysis of optimal siRNA targets for 22,600 human mRNAs. CONCLUSION: We demonstrated that the properties of the siRNAs themselves are essential for efficient RNA interference. The 5' ends of antisense strands of efficient siRNAs are U-rich and possess a content similarity to the pyrimidine-rich oligonucleotides interacting with the polypurine RNA tracks that are recognized by RNase H. The advantage of our method over similar methods is the small number of parameters. As a result, our method requires a much smaller training set to produce consistent results. Other mRNA features, though expensive to compute, can slightly improve our model.

Artificial Intelligence↗
PubMed2006

Extraction subject-specific motor imagery time-frequency patterns for single trial EEG classification.

We introduce a new adaptive time-frequency plane feature extraction strategy for the segmentation and classification of electroencephalogram (EEG) corresponding to left and right hand motor imagery of a brain-computer interface task. The proposed algorithm adaptively segments the time axis by dividing the EEG data into non-uniform time segments over a dyadic tree. This is followed by grouping the expansion coefficients in the frequency axis in each segment. The most discriminative features are selected from the segmented time-frequency plane and fed to a linear discriminant for classification. The proposed algorithm achieved an average classification accuracy of 84.3% on six subjects by selecting the most discriminant subspaces for each one. For comparison, classification results based on an autoregressive model are also presented where the mean accuracy of the same subjects turned out to be 79.5%. Interestingly the subjects and two hemispheres of each subject are represented by distinct segmentations and features. This indicates that the proposed method can handle inter-subject variability when constructing brain-computer interfaces.

Algorithms↗