Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “classifier”

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 703 records · Page 39Linked to original sources
PubMed2006

Framework for describing and classifying decision-making systems using technology assessment to determine the reimbursement of health technologies (fourth hurdle systems).

OBJECTIVES: Australia, Canada, and many European countries now use various forms of health technology assessment (HTA) in decision making regarding the reimbursement of drugs and other health technologies. To achieve a better understanding of the potential for use of HTA in this context, an analytical framework was developed to describe and classify existing fourth hurdle systems. METHODS: Based on a review of published literature, and official documentation, the key aspects of a fourth hurdle system were identified at two levels: policy implementation and individual technology decision. Characteristics of the systems were grouped under four main headings: constitution and governance, objectives, use of evidence and decision processes, and accountability. The comprehensiveness and relevance of this framework was assessed by an independent group of experts in HTA. A pilot study was undertaken, using only published sources, to test the feasibility of obtaining the information needed to complete the framework. RESULTS: The framework was found to be sufficiently broad to encompass all the issues of interest regarding the systems, but the proportion of information available from published sources was variable between sections of the framework and between countries, with average availability of 45 percent. CONCLUSIONS: The analytical framework will help researchers and policy makers in individual countries to understand their own systems and will allow some preliminary sharing of experience between countries. More experience of its application is needed to judge whether it will provide the basis for more formal comparison of systems and whether it will determine their appropriateness for particular decision contexts.

Australia↗
PubMedDate not supplied

Total luminescence intensity as a tool to classify degradable polyethylene films by early degradation detection and changes in activation energy.

Total luminescence intensity (TLI) was shown to be a valuable tool to monitor early degradation and thereby classify degradable polyethylene. The photo oxidation and thermal oxidation of polyethylene films containing different prooxidant systems were monitored. The chemiluminescence results were compared with results from FTIR, DSC, and SEC measurements. TLI gave an earlier detection of degradation and offered complementary information regarding changes in activation energies during the course of the degradation. TLI measurements were more sensitive to relative differences in degradation between the materials than the carbonyl index and crystallinity measurements, especially in the case of the UV-aged samples.

Calorimetry, Differential Scanning↗
PubMedDate not supplied

Using ensembles to classify compounds for drug discovery.

This paper introduces Signal, a novel method for classifying activity against a small molecule drug target. Signal creates an ensemble, or collection, of meaningful descriptors chosen from a much larger property space. The method works with a variety of descriptor types, including fingerprints that represent four-point pharmacophores or shape descriptors. It also exploits information from both active and inactive compounds and generates predictive models suitable for high throughput screening data analysis. Given the fingerprints and activity data for a set of compounds, Signal is a two step process. The first step is to Evaluate the Descriptors: for each descriptor in the fingerprint, quantify and rank the correlation between the activity of the compounds and the presence of that descriptor. The second step is to Create an Ensemble Model: use the high ranking descriptors to create a model of activity against the biological target. For the first step, two possible ranking strategies were investigated: mutual information and chi-square. For the second step, two types of ensemble models were investigated: high ranking and a novel method called high ranking set cover. Of the four possible pairings, the combination of chi-square and high ranking set cover performed the best on a Thrombin data set.

Algorithms↗
PubMedDate not supplied

Molecular similarity searching using atom environments, information-based feature selection, and a naïve Bayesian classifier.

A novel technique for similarity searching is introduced. Molecules are represented by atom environments, which are fed into an information-gain-based feature selection. A naïve Bayesian classifier is then employed for compound classification. The new method is tested by its ability to retrieve five sets of active molecules seeded in the MDL Drug Data Report (MDDR). In comparison experiments, the algorithm outperforms all current retrieval methods assessed here using two- and three-dimensional descriptors and offers insight into the significance of structural components for binding.

Journal Article↗
PubMedDate not supplied

Enrichment of high-throughput screening data with increasing levels of noise using support vector machines, recursive partitioning, and laplacian-modified naive bayesian classifiers.

High-throughput screening (HTS) plays a pivotal role in lead discovery for the pharmaceutical industry. In tandem, cheminformatics approaches are employed to increase the probability of the identification of novel biologically active compounds by mining the HTS data. HTS data is notoriously noisy, and therefore, the selection of the optimal data mining method is important for the success of such an analysis. Here, we describe a retrospective analysis of four HTS data sets using three mining approaches: Laplacian-modified naive Bayes, recursive partitioning, and support vector machine (SVM) classifiers with increasing stochastic noise in the form of false positives and false negatives. All three of the data mining methods at hand tolerated increasing levels of false positives even when the ratio of misclassified compounds to true active compounds was 5:1 in the training set. False negatives in the ratio of 1:1 were tolerated as well. SVM outperformed the other two methods in capturing active compounds and scaffolds in the top 1%. A Murcko scaffold analysis could explain the differences in enrichments among the four data sets. This study demonstrates that data mining methods can add a true value to the screen even when the data is contaminated with a high level of stochastic noise.

Journal Article↗
PubMedDate not supplied

Using artificial neural networks to classify the activity of capsaicin and its analogues.

Back-propagation artificial neural networks (ANNs) were trained with parameters derived from different molecular structure representation methods, including topological indices, molecular connectivity, and novel physicochemical descriptors to model the structure--activity relationship of a large series of capsaicin analogues. The ANN QSAR model produced a high level of correlation between the experimental and predicted data. After optimization, using cross-validation and selective pruning techniques, the ANNs predicted the EC50 values of 101 capsaicin analogues, correctly classifying 34 of 41 inactive compounds and 58 of 60 active compounds. These results demonstrate the capability of ANNs for predicting the biological activity of drugs, when trained on an optimal set of input parameters derived from a combination of different molecular structure representations.

Capsaicin↗
PubMed2003

Classifying NOM-organic sorbate interactions using compound transfer from an inert solvent to the hydrated sorbent.

Interactions of a wide set of organic compounds with model natural organic matter (NOM, Pahokee peat) were examined using a new approach that converts aqueous sorption to compound transfer from n-hexadecane to the hydrated NOM. This conversion accounts for solute-water interactions and applies the same inert reference medium for all compounds of interest, making it possible to classify sorbates according to the strength of sorbate-NOM interactions. Differences in strength of organic compound interactions in the sorbed phase as great as 4-5 orders of magnitude are demonstrated. The strongest interactions were observed for compounds with well-established H-bonding potentials. Considering hydrocarbons and Cl-substituted hydrocarbons, aliphatic compounds gain more upon distribution from the n-hexadecane medium to NOM than do aromatic compounds. Sorption nonlinearity was tested by comparing the change in n-hexadecane-hydrated NOM distribution coefficient (K(d,i)) versus sorbed concentration for the different compounds. Only those compounds that interact most strongly with NOM demonstrated significant sorption nonlinearity, expressed by a strong reduction in K(d,i) as a function of sorbed concentration. The relationship between compound ability to interact with NOM and reduction in K(d,i) as a function of sorbed concentration can be used to characterize compound distribution among different sorption domains.

Adsorption↗
PubMed2001

Nutrient distribution and phenolic antioxidants in air-classified fractions of beach pea (Lathyrus maritimus L.).

Beach pea (Lathyrus maritimus L.) cotyledons and hulls were air-classified into different fractions. The crude protein content (%N x 6.25) of samples ranged from 32.8 to 35.3% in cotyledons and 14.7 to 16.8% in hulls. Crude fiber content was higher in hulls fraction 1 (37.13%) and fraction 2 (36.85%) than in cotyledons (2.83, 2.99, and 3.08% in fractions 1, 2, and 3, respectively). Condensed tannins of cotyledons ranged from 5.76 to 6.90% and of hulls ranged from 52.49 to 57.24%, expressed as catechin equivalents. Minerals, namely P, K, and Zn, were higher in cotyledons, but Ca and Mn were more prevalent in hulls. Nonprotein nitrogen was concentrated in hulls, whereas phytic acid was more abundant in the cotyledons. The UV absorption pattern showed that flavonoids were present in fractions (I-III) from hulls separated on Sephadex LH-20. Fraction III from hulls had the highest content of total phenolics and condensed tannins, but no condensed tannins were detected in fractions I and II from hulls. The antioxidant activity of fractions separated on Sephadex LH-20 from hulls and crude extracts in a beta-carotene-linoleate model system was in the order of fraction III > crude extract > fraction II > fraction I. Spots on silica gel TLC plates, sprayed with a solution of beta-carotene and linoleic acid, indicated that many of the individual compounds were antioxidative in nature. Further, separation of fraction III from hulls on a semipreparative HPLC showed the presence of (+) catechin and (-) epicatechin as the main low-molecular-weight phenolic compounds present.

Antioxidants↗
PubMed2004

Combination of a naive Bayes classifier with consensus scoring improves enrichment of high-throughput docking results.

We have previously shown that a machine learning technique can improve the enrichment of high-throughput docking (HTD) results. In the previous cases studied, however, the application of a naive Bayes classifier failed to improve enrichment for instances where HTD alone was unable to generate an acceptable enrichment. We present here a protocol to rescue poor docking results a priori using a combination of rank-by-median consensus scoring and naive Bayesian categorization.

Algorithms↗
PubMed2002

Joint versus separate estimation of state and change in category frequencies from repeat stratified two-phase sampling with a fallible classifier.

Joint maximum likelihood estimates (JML) of category frequencies and change from repeat stratified two-phase sampling surveys with a fallible classifier are often seriously biased and have large root mean square errors when they are obtained for small populations (<5,000) with three or more categories and a moderate to small phase II sample size (<1,000). JML estimates of state also depend on antecedent or posterior data, a recipe for inconsistency. In these situations, a separate maximum likelihood estimation (SML) of category frequencies at each survey date appears preferable. SML estimates of net change are obtained as the difference in states. SML standard errors of change are obtained via an estimate of the temporal correlation and variances of state. A bivariate binary logistic model of change provided the estimate of temporal correlation. SML generally outperformed JML significantly in terms of bias and root mean square errors in eight case studies.

Data Collection↗
PubMed2002

OsARF1, an auxin response factor from rice, is auxin-regulated and classifies as a primary auxin responsive gene.

We screened for auxin-induced genes with an expression correlated to the auxin-induced growth response from rice coleoptiles by fluorescent differential display. A rice homologue of the auxin response factor (ARF) family of transcriptional regulators, OsARF1, was identified. An OsARF1:GFP fusion protein was localized to the nucleus. Steady-state levels of OsARF1 mRNA correlated positively with auxin-dependent differential growth: gravitropic stimulation enhanced the amount of OsARF1 transcript in the lower, faster-growing flank accompanied by a decrease in the upper flank of gravitropically stimulated rice coleoptiles. Exogenous auxin up-regulated the steady-state level of OsARF1 mRNA within 15-30 min. This up-regulation is independent of de novo protein synthesis. Thus, OsARF1 is the first ARF that classifies as an early auxin-responsive gene. The observed auxin-dependent regulation comprises a new level of regulation in auxin-induced gene expression and is discussed as a possible feedback mechanism in plant growth control.

Amino Acid Sequence↗
PubMed2002

Diabetes and elimination of antipyrine in man: an analysis of 298 patients classified by type of diabetes, age, sex, duration of disease and liver involvement.

UNLABELLED: Effects of diabetes on hepatic drug metabolism in man has not yet been adequately clarified. Two hundred ninety-eight diabetic patients, classified by type of the disease, age, gender, duration of therapy and liver involvement, were investigated. The antipyrine plasma clearance rate and cytochrome P450 content determinations in liver biopsies of subjects with diagnostic liver biopsy were used as indices of hepatic drug metabolising capacity. Drug metabolism was reduced as a function of age. Antipyrine elimination rate was dependent on the type of diabetes (type 1 versus type 2) and gender. Untreated type 1 patients eliminated antipyrine rapidly and insulin treatment normalised antipyrine elimination (clearance rates 89.5 +/- 20.3 versus 58.8 +/- 17.2 ml/min.; P<0.001). Males aged 16-59 years, but not over 60, who responded insufficiently to insulin therapy, had a rapid antipyrine elimination, which could be normalised by readjustment of insulin administration. Women with insufficient glucose control on insulin therapy had antipyrine elimination rate comparable to controls. Among type 2 diabetic patients, women metabolised antipyrine normally, but men over 40 years of age showed a reduced antipyrine metabolism. IN CONCLUSION: Drug metabolism in diabetes is affected by the type of disease, therapy and its effectiveness, and age and gender of the patients. These factors should be taken into account when evaluating overall drug metabolism in diabetic patients. This is especially important when investigating pharmacokinetics of new drugs for diabetic patients at different phases of the disease.

Adolescent↗
PubMed1986

Classifying multidimensional stimuli: stimulus, task, and observer factors.

When observers decide how to classify stimuli, they often employ one of two types of information: identity along one particular dimension or overall similarity. The present studies examined interrelations among the factors which determine the use of these types of information. Participants' classifications of certain types of materials (e.g., size and brightness, length and density) revealed strong individual differences, were related to the individual's response tempo and selective processing ability, and were influenced by task demands. Classifications of other materials (e.g., saturation and brightness) did not reveal individual differences, were not affected by response tempo and selective processing ability, and were unaffected by changes in task demands. The former, but not the latter, types of materials have also been found to be influenced by developmental differences. The results are consistent with the idea that differences in response tempo and selective processing ability underlie observer differences (both individual and developmental) and that certain types of stimuli which are not susceptible to such influences set boundary conditions for observer differences. The results are discussed within an integral-to-separable model of processing.

Adult↗
PubMed2000

Validation of a system of classifying female substance abusers on the basis of personality and motivational risk factors for substance abuse.

This study explored the validity of classifying a community-recruited sample of substance-abusing women (N = 293) according to 4 personality risk factors for substance abuse (anxiety sensitivity, introversion-hopelessness, sensation seeking, and impulsivity). Cluster analyses reliably identified 5 subtypes of women who demonstrated differential lifetime risk for various addictive and nonaddictive disorders. An anxiety-sensitive subtype demonstrated greater lifetime risk for anxiolytic dependence, somatization disorder, and simple phobia, whereas an introverted-hopeless subtype evidenced a greater lifetime risk for opioid dependence, social phobia, and panic and depressive disorders. Sensation seeking was associated with exclusive alcohol dependence, and impulsivity was associated with higher rates of antisocial personality disorder and cocaine and alcohol dependence. Finally, a low personality risk subtype demonstrated lower lifetime rates of substance dependence and psychopathology.

Adult↗
PubMed2002

The latent structure of analogue depression: should the Beck Depression Inventory be used to classify groups?

Research on depression is often conducted with analogue samples that have been divided into depressed and nondepressed groups using a cutoff score on the Beck Depression Inventory (BDI). Although the relative merits of different cut scores are frequently debated, no study has yet determined whether the use of any cut score is valid, that is, whether the latent structure of BDI depression is categorical or dimensional in analogue samples. The BDI responses of 2,260 college students were submitted to 3 taxometric procedures whose results were compared with those of simulated data sets with equivalent parameters. Analyses provided converging evidence for the dimensionality of analogue depression, arguing against the use of the BDI to classify analogue participants into groups. Analyses also illustrated the notable impact of pronounced skew on taxometric results and the value of using simulated comparison data as an interpretive aid.

Adult↗
PubMed1976

Methods of classifying and ascertaining children's tumours.

Several methods of ascertaining and classifying childhood neoplasms for epidemiological study have been evaluated using material from the University of Manchester Children's Tumour Registry (CTR), which includes data from several sources on children with neoplasms first seen in the period 1954-73 who were under 15 years old and living in the Manchester Regional Hospital Board area at the time. Two systems of classification-the International Classification of Diseases (ICD) and the Morphology Section of the Manual of Tumor Nomenclature and Coding (MOTNAC; Percy, Berg and Thomas, 1968)-were tested. No major problems arose with the Morphology Section of MOTNAC, and we recommend that the revised version of this section, in the proposed "International Classification of Diseases for Oncology", should be used in epidemiological reports on children's tumours whenever possible. The ICD discriminates less well between the commoner types of childhood neoplasms, but must be retained as a supplementary classification to facilitate international comparisons. A comparison of the completeness of ascertainment achieved in recent years by each source of data showed that more than 98% of the serious cases (neoplasms that were malignant and/or lay within the craniovertebral canal) could have been identified using a combination of Hospital Activity Analysis (HAA) and cancer registration records, and more than 95% using HAA and death records. But in an analysis of 2 years' HAA returns and 6 years' cancer registrations of serious cases, nearly one quarter of the former and one fifth of the latter were shown to record diagnoses which differed from those finally assigned at the CTR. It is concluded that, in epedimiological studies based on routine records, the diagnoses given should always be checked centrally, by experts, in the light of all the available clinical and pathological material (including histological preparations).

Adolescent↗
PubMed2005

MicroRNA expression profiles classify human cancers.

Recent work has revealed the existence of a class of small non-coding RNA species, known as microRNAs (miRNAs), which have critical functions across various biological processes. Here we use a new, bead-based flow cytometric miRNA expression profiling method to present a systematic expression analysis of 217 mammalian miRNAs from 334 samples, including multiple human cancers. The miRNA profiles are surprisingly informative, reflecting the developmental lineage and differentiation state of the tumours. We observe a general downregulation of miRNAs in tumours compared with normal tissues. Furthermore, we were able to successfully classify poorly differentiated tumours using miRNA expression profiles, whereas messenger RNA profiles were highly inaccurate when applied to the same samples. These findings highlight the potential of miRNA profiling in cancer diagnosis.

Animals↗
PubMed2006

Gene expression profiling of primary cultures of ovarian epithelial cells identifies novel molecular classifiers of ovarian cancer.

In order to elucidate the biological variance between normal ovarian surface epithelial (NOSE) and epithelial ovarian cancer (EOC) cells, and to build a molecular classifier to discover new markers distinguishing these cells, we analysed gene expression patterns of 65 primary cultures of these tissues by oligonucleotide microarray. Unsupervised clustering highlights three subgroups of tumours: low malignant potential tumours, invasive solid tumours and tumour cells derived from ascites. We selected 18 genes with expression profiles that enable the distinction of NOSE from these three groups of EOC with 92% accuracy. Validation using an independent published data set derived from tissues or primary cultures confirmed a high accuracy (87-96%). The distinctive expression pattern of a subset of genes was validated by quantitative reverse transcription-PCR. An ovarian-specific tissue array representing tissues from NOSE and EOC samples of various subtypes and grades was used to further assess the protein expression patterns of two differentially expressed genes (Msln and BMP-2) by immunohistochemistry. This study highlights the relevance of using primary cultures of epithelial ovarian cells as a model system for gene profiling studies and demonstrates that the statistical analysis of gene expression profiling is a useful approach for selecting novel molecular tumour markers.

Biomarkers, Tumor↗