Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Prediction Algorithms”

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 433 records · Page 24Linked to original sources
PubMed1999

Predicting conformational switches in proteins.

We describe a new computational technique to predict conformationally switching elements in proteins from their amino acid sequences. The method, called ASP (Ambivalent Structure Predictor), analyzes results from a secondary structure prediction algorithm to identify regions of conformational ambivalence. ASP identifies ambivalent regions in 16 test protein sequences for which function involves substantial backbone rearrangements. In the test set, all sites previously described as conformational switches are correctly predicted to be structurally ambivalent regions. No such regions are predicted in three negative control protein sequences. ASP may be useful as a guide for experimental studies on protein function and motion in the absence of detailed three-dimensional structural data.

Adenylyl Cyclases↗
PubMed1999

Glasgow head injury outcome prediction program: an independent assessment.

Using an independent data set, the utility of the Glasgow Head Injury Outcome Prediction Program was investigated in terms of possible frequency of use and reliability of outcome prediction in patients with severe head injury, or haematoma requiring evacuation, or coma lasting 6 hours or more, in whom outcome had been reliably assessed at 6 to 24 months after injury. Predictions were calculated on admission, before evacuation of a haematoma, or 24 hours, 3 days, and 7 days after onset of coma lasting 6 hours or more. Three hundred and twenty four patients provided 426 predictions which were possible in 76%, 97%, 19%, 34%, and 53% of patients on admission, before operation, 24 hours, 3 days, and 7 days respectively. Major reasons for non-feasible predictions were that patients were paralysed/ventilated as part of resuscitation or management. Overall, 75.8% of predictions were correct, 14.6% were pessimistic (outcome better than predicted), and 9.6% optimistic (outcome worse than predicted). Of 197 patients (267 predictions) whose eventual outcome was good or moderate, 84.3% of predictions were correct. For death or vegetative survival (96 patients with 110 predictions), 83.6% of predictions were correct but for severe disability (31 patients with 49 predictions), only 12.2% were correctly predicted. The utility of the Glasgow Head Injury Outcome Prediction Program compares favourably with other outcome prediction algorithms for patients with head injury.

Adolescent↗
PubMed2004

A structural requirement for processing the cardiac K+ channel KCNQ1.

Normal membrane protein function requires trafficking from the endoplasmic reticulum. Here, we studied processing of the KCNQ1 channel mutated in LQT1, the commonest form of the long QT syndrome. Serial C terminus truncations identified a small region (amino acids (aa) 610-620) required for normal cell surface expression. Non-trafficked truncations assembled as tetramers but were nevertheless retained in the endoplasmic reticulum. Further mutagenesis did not identify specific residues mediating channel processing; cell surface expression was preserved with the mutation of known trafficking motifs in the channel and with alanine scanning across aa 610-620. Structural prediction algorithms place aa 610-620 at the C-terminal end of an alpha-helix (aa 586-618) that includes a leucine zipper and is part of a coiled coil. Mutants disrupting the leucine zipper but preserving the predicted coiled coil reached the cell surface, whereas those disrupting the coil did not. These data suggest that specific protein-protein interactions are required for normal channel processing. Further biochemical studies ruled out three candidate proteins, namely KCNE1, yotiao, and KCNQ1 itself, as effectors of this coiled coil-mediated trafficking. Four LQT1 mutations within this helix generated little or no current and were not expressed on the cell surface, whereas LQT1 mutations in adjacent residues, which produce a milder clinical phenotype, generate only slightly reduced current and are expressed on the cell surface. These data suggest that mutations within this domain cause human disease by interfering with normal channel processing. More generally, we have identified a domain whose structural integrity is required for normal surface expression of the KCNQ1 channel.

Alanine↗
PubMed2004

Predicting bacteremia in children with fever and chemotherapy-induced neutropenia.

BACKGROUND: Fever and neutropenia are common clinical problems in pediatric oncology and frequently necessitate emergency hospitalization and immediate empiric broad spectrum antimicrobial therapy. Estimating the risk of bacteremia in fever and neutropenia is a challenge. The purpose of this study was to develop an algorithm predicting the risk of bacteremia and Gram-negative bacteremia in children and adolescents with fever and neutropenia, based on information accessible at presentation. METHODS: We collected information available within 2 h of presentation of children with fever and neutropenia and, on outcome, from all pediatric cancer patients presenting with fever and neutropenia from 1993 through 2001 in a retrospective single center cohort study. After univariate analyses a multivariate decision tree was constructed, and its performance was evaluated by cross-validation. RESULTS: Bacteremia was detected in 87 (24%) and Gram-negative bacteremia in 30 (8%) of 364 episodes of fever and neutropenia. At the predetermined sensitivity level, > or =95%, decision tree models reached cross-validated specificities of 37 and 43%, with negative predictive values of 96 and 99%, for bacteremia and Gram-negative bacteremia, respectively. Absence of a clinically or radiologically evident source of infection and previous episodes of fever and neutropenia were defined as two newly described factors associated with bacteremia. CONCLUSIONS: Based on this retrospective analysis, it appears that bacteremia can be predicted with clinically useful specificity at a high level of sensitivity, using clinical information available at presentation in pediatric cancer patients with fever and neutropenia.

Adolescent↗
PubMed2006

Defining molecular profiles of poor outcome in patients with invasive bladder cancer using oligonucleotide microarrays.

PURPOSE: Bladder cancer is a common malignancy characterized by a poor clinical outcome when tumors progress into invasive disease. We sought to define genetic signatures characteristic of aggressive clinical behavior in advanced bladder tumors. METHODS: Oligonucleotide arrays were utilized to analyze the transcript profiles of 105 bladder tumors: 33 superficial, 72 invasive lesions, and 52 normal urothelium. Hierarchical clustering and supervised algorithms were used to classify and stratify bladder tumors on the basis of stage, node metastases, and overall survival. Immunohistochemical analyses on bladder cancer tissue arrays (n = 294 cases) served to validate associations between marker expression, staging and outcome. RESULTS: Hierarchical clustering classified normal urothelium, superficial, and invasive tumors with 82.2% accuracy, and stratified bladder tumors on the basis of clinical outcome. Predictive algorithms rendered an 89%-correct rate for tumor staging using genes differentially expressed between superficial and invasive tumors. Accuracies of 82% and 90% were obtained for predicting overall survival when considering all patients with bladder cancer or only patients with invasive disease, respectively. A genetic profile consisting of 174 probes was identified in those patients with positive lymph nodes and poor survival. Two independent Global Test runs confirmed the robust association of this profile with lymph node metastases (P = 7.3(-13)) and overall survival (P = 1.9(-14)) simultaneously. Immunohistochemical analyses on tissue arrays sustained the significant association of synuclein with tumor staging and clinical outcome (P = .002). CONCLUSION: Gene profiling provides a genomic-based classification scheme of diagnostic and prognostic utility for stratifying advanced bladder cancer. Identification of this poor outcome profile could assist in selecting patients who may benefit from more aggressive therapeutic intervention.

Gene Expression Profiling↗
PubMed2005

HYPROSP II--a knowledge-based hybrid method for protein secondary structure prediction based on local prediction confidence.

MOTIVATION: In our previous approach, we proposed a hybrid method for protein secondary structure prediction called HYPROSP, which combined our proposed knowledge-based prediction algorithm PROSP and PSIPRED. The knowledge base constructed for PROSP contains small peptides together with their secondary structural information. The hybrid strategy of HYPROSP uses a global quantitative measure, match rate, to determine whether PROSP or PSIPRED is to be used for the prediction of a target protein. HYPROSP made slight improvement of Q(3) over PSIPRED because PROSP predicted well for proteins with match rate >80%. As the portion of proteins with match rate >80% is quite small and as the performance of PSIPRED also improves, the advantage of HYPROSP is diluted. To overcome this limitation and further improve the hybrid prediction method, we present in this paper a new hybrid strategy HYPROSP II that is based on a new quantitative measure called local match rate. RESULTS: Local match rate indicates the amount of structural information that each amino acid can extract from the knowledge base. With the local match rate, we are able to define a confidence level of the PROSP prediction results for each amino acid. Our new hybrid approach, HYPROSP II, is proposed as follows: for each amino acid in a target protein, we combine the prediction results of PROSP and PSIPRED using a hybrid function defined on their respective confidence levels. Two datasets in nrDSSP and EVA are used to perform a 10-fold cross validation. The average Q(3) of HYPROSP II is 81.8% and 80.7% on nrDSSP and EVA datasets, respectively, which is 2.0% and 1.1% better than that of PSIPRED. For local structures with match rate >80%, the average Q(3) improvement is 4.4% on the nrDSSP dataset. The use of local match rate improves the accuracy better than global match rate. There has been a long history of attempts to improve secondary structure prediction. We believe that HYPROSP II has greatly utilized the power of peptide knowledge base and raised the prediction accuracy to a new high. The method we developed in this paper could have a profound effect on the general use of knowledge base techniques for various predictionalgorithms. AVAILABILITY: The Linux executable file of HYPROSP II, as well as both nrDSSP and EVA datasets can be downloaded from http://bioinformatics.iis.sinica.edu.tw/HYPROSPII/.

Algorithms↗
PubMed1993

Patterns for prediction of hydration around polar residues in proteins.

The atomic co-ordinates of seven very high resolution (< 1.4 A) proteins have been used to define a water-hydrogen bond template for five polar side-chains (arginine, aspartic acid, glutamic acid, asparagine and glutamine). The average water molecule positions determined were consistent with the hydrogen bonding stereochemistry expected for each side-chain. Hydrogen bonding geometry around nitrogen atoms was significantly better localized than around oxygen atoms, perhaps because of the proton on nitrogen. A prediction algorithm written to locate water molecule sites around these side-chains from the protein co-ordinates only was tested for crambin as well as for two high resolution protein structures not included in the hydrogen bond data base. The root-mean-square deviation of the predicted positions from the crystallographically determined ones for these structures was better than the resolution of these structures. The method also successfully predicted water positions for X-ray refinement of two proteins, indicating that predicted water molecules are within the radius of convergence of refinement. This method has utility for X-ray models as well as for analysis of enzyme hydration and function.

Algorithms↗
PubMed2004

PromoSer: improvements to the algorithm, visualization and accessibility.

PromoSer is a web service that provides an easy and efficient approach to the batch retrieval of a large number of proximal promoters. Since its introduction last year, it has undergone continued development and expansion. At the core, there have been improvements in the filtering of the raw mRNA/EST sequences upon which all predictions are built, improvements in the alignments clustering and transcription start site prediction algorithms, and improvements in the backing database for increased performance. At the user interface level, improvements include enhanced functionality and user options, better integration with other resources on the web and a new visualization tool. PromoSer now also supports queries using a SOAP-based interface and XML-based responses. The service is publicly available at http://biowulf.bu.edu/zlab/PromoSer.

Algorithms↗
PubMed1994

Are most transporters and channels beta barrels?

Given the sequence of transporters or channels of unknown secondary structure, it is usual to predict their putative transmembrane regions as alpha-helical. However, recent evidence for a facilitative glucose transporter (GLUT1) appears inconsistent with such predictions, which has led us to propose an alternative folding model for GLUTs based on the 16-stranded antiparallel beta-barrel of porins. Here we apply the same predictive algorithms we used for GLUTs to several other membrane proteins. For some of them, a high-resolution structure has been derived (beta-barrels: Rhodobacter capsulatus and Escherichia coli porins; multihelical: colicin A, bacteriorhodopsin, and reaction center L chain); we use them to test the prediction procedures. The other proteins we analyze (GLUT1, CHIP28, acetylcholine receptor alpha subunit, lac permease, Na(+)-glucose cotransporter, shaker K+ channel, sarcoplasmic reticulum Ca(2+)-ATPase) are representative of classes of similar membrane proteins. As with GLUTs, we find that the predicted transmembrane segments of these proteins are consistently shorter than expected for transmembrane spanning alpha-helices, but are of the correct length and number for the proteins to fold instead as porin-like beta-barrels.

Algorithms↗
PubMed1994

Predicting internal exons by oligonucleotide composition and discriminant analysis of spliceable open reading frames.

A new method which predicts internal exon sequences in human DNA has been developed. The method is based on a splice site prediction algorithm that uses the linear discriminant function to combine information about significant triplet frequencies of various functional parts of splice site regions and preferences of oligonucleotides in protein coding and intron regions. The accuracy of our splice site recognition function is 97% for donor splice sites and 96% for acceptor splice sites. For exon prediction, we combine in a discriminant function the characteristics describing the 5'-intron region, donor splice site, coding region, acceptor splice site and 3'-intron region for each open reading frame flanked by GT and AG base pairs. The accuracy of precise internal exon recognition on a test set of 451 exon and 246693 pseudoexon sequences is 77% with a specificity of 79%. The recognition quality computed at the level of individual nucleotides is 89% for exon sequences and 98% for intron sequences. This corresponds to a correlation coefficient for exon prediction of 0.87. The precision of this approach is better than other methods and has been tested on a larger data set. We have also developed a means for predicting exon-exon junctions in cDNA sequences, which can be useful for selecting optimal PCR primers.

Algorithms↗
PubMed2005

A universally applicable method of operon map prediction on minimally annotated genomes using conserved genomic context.

An important step in understanding the regulation of a prokaryotic genome is the generation of its transcription unit map. The current strongest operon predictor depends on the distributions of intergenic distances (IGD) separating adjacent genes within and between operons. Unfortunately, experimental data on these distance distributions are limited to Escherichia coli and Bacillus subtilis. We suggest a new graph algorithmic approach based on comparative genomics to identify clusters of conserved genes independent of IGD and conservation of gene order. As a consequence, distance distributions of operon pairs for any arbitrary prokaryotic genome can be inferred. For E.coli, the algorithm predicts 854 conserved adjacent pairs with a precision of 85%. The IGD distribution for these pairs is virtually identical to the E.coli operon pair distribution. Statistical analysis of the predicted pair IGD distribution allows estimation of a genome-specific operon IGD cut-off, obviating the requirement for a training set in IGD-based operon prediction. We apply the method to a representative set of eight genomes, and show that these genome-specific IGD distributions differ considerably from each other and from the distribution in E.coli.

Algorithms↗
PubMed2004

Evaluation of a panel of non-invasive serum markers to differentiate mild from moderate-to-advanced liver fibrosis in chronic hepatitis C patients.

BACKGROUND/AIMS: In chronic hepatitis C (CHC) infection, a liver biopsy provides important information that guides treatment decisions, but is invasive, expensive and associated with possible complications. Extracellular matrix remodeling proteins may be useful non-invasive markers of fibrosis. The aim of this study was to evaluate the diagnostic accuracy of a panel of these markers in CHC patients, develop a predictive algorithm that differentiates no/mild (METAVIR F0-F1) from moderate/severe (F2-F4) fibrosis, and validate the model in external cohorts. METHODS: A combination of matrix markers were initially evaluated and optimized in 294 CHC patients from a single center, and validated in an external cohort of 402 patients. RESULTS: Hyaluronic acid, TIMP-1 and alpha2-macroglobulin were selected as having the best predictive accuracy for F2-F4 fibrosis (combined AUROC = 0.831). At an index cut-off >0.36 and prevalence for F2-F4 of 52%, results in all 696 patients indicated positive and negative predictive values of 74.3 and 75.8% with an accuracy of 75%. CONCLUSIONS: The three-marker panel may reliably differentiate CHC patients with moderate/severe fibrosis from those with no/mild fibrosis, although accurate delineation between stages was not possible. Prospective studies are required to determine the potential utility of the marker panel in guiding treatment decisions and following disease progression.

Adult↗
PubMed2005

GeneLook: a novel ab initio gene identification system suitable for automated annotation of prokaryotic sequences.

With the rapid increases in the amounts of sequence data for prokaryotic genomes, it has become important to develop systems for automated and accurate genome annotation. We present herein a novel ab initio gene identification system, GeneLook, that predicts protein-coding open reading frames (ORFs) with high sensitivity and specificity with no prior knowledge of the sequence composition. The system predicts protein-coding ORFs in two stages, seed ORF selection and main prediction. In the selection of reliable seed ORFs containing at least 200 codons, GeneLook predicts translation start sites and operon structures through searches for ribosome-binding sites and a novel operon prediction algorithm. The codon and nucleotide frequencies of seed ORFs are then used to determine values for two new coding-potential parameters for identification of protein-coding ORFs of at least 34 codons and for another parameter that improves the prediction accuracy for GC-rich genomes. In the main prediction, GeneLook uses these parameters to identify the most likely genes of a given minimal length. We assessed the performance of GeneLook with two indices, sensitivity and specificity that are defined as true positives (TP)/(TP+false negatives) and TP/(TP+false positives), respectively. This system predicted protein-coding ORFs for Escherichia coli and Bacillus subtilis with sensitivities of 96.5% and 96.2%, respectively, and specificities of 96.9% and 96.1%, respectively. The system also identified 94.1% of annotated genes of the Pseudomonas aeruginosa genome, which is GC-rich, with high specificity (97.2%). Furthermore, GeneLook identified protein-coding ORFs with high accuracy from a wide variety of prokaryotic genomes.

Bacillus subtilis↗
PubMed2000

From fold to function predictions: an apoptosis regulator protein BID.

With the rapidly increasing pace of genome sequencing projects and the resulting flood of predicted amino acid sequences of uncharacterized proteins, protein sequence analysis, and in particular, protein structure prediction is quickly gaining in importance. Prediction algorithms can be used for preliminary annotation of newly sequenced proteins and, at least in some cases, provide insights into their function and specific mode of action. Such annotations for several microbial genomes were performed by several groups and placed in public domain for evaluation. An example presented in this work comes from a related project of structural and functional predictions for proteins involved in the process of controlled cell death (apoptosis). The BID protein belongs to an important class of regulators of apoptosis identified by short sequence motifs. Here, several fold prediction methods are used to build a series of three-dimensional models. Structure analysis of the models with reference to the biological data available allows selection of the most appropriate model. It is found that the most likely structural model of BID is built on the structure of Bcl-X(L). The model is discussed in terms of experimental data on specific proteolytic cleavage of BID and its effect on BID interactions with other proteins and membranes.

Algorithms↗
PubMed2001

Impact of simple tissue inhomogeneity correction algorithms on conformal radiotherapy of lung tumours.

BACKGROUND AND PURPOSE: Conformal radiotherapy requires accurate dose calculation at the dose specification point, at other points in the planning target volume (PTV) and in organs at risk. To assess the limitations of treatment planning of lung tumours, errors in dose values, calculated by some simple tissue inhomogeneity correction algorithms available in a number of currently applied treatment planning systems, have been quantified. MATERIALS AND METHODS: Single multileaf collimator-shaped photon beams of 6, 8, 15 and 18 MV nominal energy were used to irradiate a 50 mm diameter spherical solid tumour, simulated by polystyrene, which was located centrally inside lung tissue, simulated by cork. The planned dose distribution was made conformal to the PTV, which was a 15 mm three-dimensional expansion of the tumour. Values of both the absolute dose at the International Commission on Radiation Units and Measurement (ICRU) reference point and relative dose distributions inside the PTV and in the lung were calculated using three inhomogeneity correction algorithms. The algorithms investigated in this study are the pencil beam algorithm with one-dimensional corrections, the modified Batho algorithm and the equivalent path length algorithm. The calculated data were compared with measurements for a simple beam set-up using radiographic film and ionization chambers. RESULTS: For this specific configuration, deviations of up to 3.5% between calculated and measured values of the dose at the ICRU reference point were found. Discrepancies between measured and calculated beam fringe values (distance between the 50 and 90% isodose lines) of up to 14 mm have been observed. The differences in beam fringe and penumbra width (20-80%) increase with increasing beam energy. Our results demonstrate that an underdosage of the PTV up to 20% may occur if calculated dose values are used for treatment planning. The three algorithms predict a considerably higher dose in the lung, both along the central beam axis and in the lateral direction, compared with the actual delivered dose values. CONCLUSIONS: The dose at the ICRU reference point of such a tumour in lung geometry is calculated with acceptable accuracy. Differences between calculated and measured dose distributions are primarily due to changes in electron transport in the lung, which are not adequately taken into account by the simple tissue inhomogeneity correction algorithms investigated in this study. Particularly for high photon beam energies, clinically unacceptable errors will be introduced in the choice of field sizes employed for conformal treatments, leading to underdosage of the PTV. In addition, the dose to the lung will be wrongly predicted which may influence the choice of the prescribed dose level in dose-escalation studies.

Algorithms↗
PubMedDate not supplied

Validation of probabilistic predictions.

Current advances in high-speed computing and increased availability of statistical software have led to widespread use of statistical methods for the development of computerized protocols predictive of binary health outcomes. If these predictive algorithms are to be used in settings other than those for which they were developed, e.g., applied in a different geographic setting or extrapolated for use in a slightly different population, then they should be carefully validated to ensure appropriate application. Miller et al. (Stat Med. 1991) provided a comprehensive methodology for external validation of logistic prediction models, and applied these methods in a temporal validation setting. In this article, the authors emphasize how these methods can be applied to general forms of probabilistic predictions and provide several SAS macros for computation of the desired statistics.

Adolescent↗
PubMed2000

Characterization of a panel of insertion mutants in human cytomegalovirus glycoprotein B.

Glycoprotein B (gB; gpUL55) of human cytomegalovirus (HCMV) plays a critical role in virus entry and cell-to-cell spread of infection. To define the structure-function relationships in gB, a panel of linker-insertion mutations was generated throughout the coding region. This strategy yielded a panel of 22 mutants with four amino acid insertions and 3 large truncation mutants. Assessment of the mutant proteins' biosynthetic properties and folding patterns analyzed in context with predicted secondary features revealed novel insights into gB's structure and trafficking properties. All of the insertion mutants were able to assemble into oligomers, suggesting that oligomerization is tolerant of small insertions and/or that multiple regions of the protein may be involved. Computer algorithm predictions of gB's secondary structure indicate that the furin-recognized cleavage site falls within an exposed loop. This loop may be particularly sensitive to structural alterations, since insertions upstream and downstream of the cleavage site rendered the mutant proteins cleavage defective. In addition, a strong correlation existed between terminal folding and cleavage of gB. Interestingly, terminal folding was not correlated with delivery to the cell surface but may influence the rate of transport to the cell surface. Nine mutants, containing insertions in both the extracellular and intracellular portions of gB, retained wild-type structural properties. This panel of characterized gB mutants, the first of this type for an HCMV protein, will be a useful tool in dissecting the role of gB during HCMV infection.

Antibodies, Monoclonal↗
PubMed2006

Measures for the assessment of fuzzy predictions of protein secondary structure.

Many of the recent secondary structure prediction methods incorporate the idea of fuzzy set theory, where instead of assigning a definite secondary structure to a query residue, probability for the residue being in each of the conformational states is estimated. Moreover, continuous assignment of conformational states to the experimentally observed protein structures can be performed in order to reflect inherent flexibility. Although various measures have been developed for evaluating performances of secondary structure prediction methods, they depend only on the most probable secondary structures. They do not assess the accuracy of the probabilities produced by fuzzy prediction methods, and they cannot incorporate information contained in continuous assignments of conformational states to observed structures. Three important measures for evaluating performance of a secondary structure prediction algorithm, Q score, Segment OVerlap (SOV) measure, and the k-state correlation coefficient (Corr), are deformed into fuzzy measures F score, Fuzzy OVerlap (FOV) measure, and the fuzzy correlation coefficient (Forr), so that the new measures not only assess probabilistic outputs of fuzzy prediction methods, but also incorporate information from continuous assignments of secondary structure. As an example of application, prediction results of four fuzzy secondary structure prediction methods, PSIPRED, PROFking, SABLE, and PREDICT, are assessed using the new fuzzy measures.

Computer Simulation↗