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 469 records · Page 26Linked to original sources
PubMed2003

TOUCHSTONE: a unified approach to protein structure prediction.

We have applied the TOUCHSTONE structure prediction algorithm that spans the range from homology modeling to ab initio folding to all protein targets in CASP5. Using our threading algorithm PROSPECTOR that does not utilize input from metaservers, one threads against a representative set of PDB templates. If a template is significantly hit, Generalized Comparative Modeling designed to span the range from closely to distantly related proteins from the template is done. This involves freezing the aligned regions and relaxing the remaining structure to accommodate insertions or deletions with respect to the template. For all targets, consensus predicted side chain contacts from at least weakly threading templates are pooled and incorporated into ab initio folding. Often, TOUCHSTONE performs well in the CM to FR categories, with PROSPECTOR showing significant ability to identify analogous templates. When ab initio folding is done, frequently the best models are closer to the native state than the initial template. Among the particularly good predictions are T0130 in the CM/FR category, T0138 in the FR(H) category, T0135 in the FR(A) category, T0170 in the FR/NF category and T0181 in the NF category. Improvements in the approach are needed in the FR/NF and NF categories. Nevertheless, TOUCHSTONE was one of the best performing algorithms over all categories in CASP5.

Algorithms↗
PubMed2005

Automation of gene assignments to metabolic pathways using high-throughput expression data.

BACKGROUND: Accurate assignment of genes to pathways is essential in order to understand the functional role of genes and to map the existing pathways in a given genome. Existing algorithms predict pathways by extrapolating experimental data in one organism to other organisms for which this data is not available. However, current systems classify all genes that belong to a specific EC family to all the pathways that contain the corresponding enzymatic reaction, and thus introduce ambiguity. RESULTS: Here we describe an algorithm for assignment of genes to cellular pathways that addresses this problem by selectively assigning specific genes to pathways. Our algorithm uses the set of experimentally elucidated metabolic pathways from MetaCyc, together with statistical models of enzyme families and expression data to assign genes to enzyme families and pathways by optimizing correlated co-expression, while minimizing conflicts due to shared assignments among pathways. Our algorithm also identifies alternative ("backup") genes and addresses the multi-domain nature of proteins. We apply our model to assign genes to pathways in the Yeast genome and compare the results for genes that were assigned experimentally. Our assignments are consistent with the experimentally verified assignments and reflect characteristic properties of cellular pathways. CONCLUSION: We present an algorithm for automatic assignment of genes to metabolic pathways. The algorithm utilizes expression data and reduces the ambiguity that characterizes assignments that are based only on EC numbers.

Algorithms↗
PubMed1991

An updated comparison of drug dosing methods. Part III: Aminoglycoside antibiotics.

Aminoglycoside antibiotics continue to be useful for the treatment of Gram-negative infections. Available dosing methods include predictive algorithms and nomograms, pharmacokinetics-based dosing methods, and methods that incorporate Bayesian forecasting. The individualised Sawchuk-Zaske and Bayesian methods have been extensively evaluated since the previous review in the Journal. Both methods continue to be rapid and accurate means of individualising dosage requirements for patients with diverse pharmacokinetic profiles. The predictive performance of the Bayesian method can be further enhanced when population-based parameters reflect the patient population being monitored. There are now several cost-effectiveness studies that demonstrate that pharmacokinetic dosing services for aminoglycosides result in cost savings, better therapeutic concentrations, fewer toxic serum concentrations, and shorter mean durations of hospital stay and aminoglycoside therapy. Further studies are needed for cost-effectiveness and comparison of various dosing methods in paediatric and neonatal patients.

Aminoglycosides↗
PubMed1994

The prediction of human exons by oligonucleotide composition and discriminant analysis of spliceable open reading frames.

Discriminant analysis is applied to the problem of recognition 5'-, internal and 3'-exons in human DNA sequences. Specific recognition functions were developed for revealing exons of particular types. The method based on a splice site prediction algorithm that uses the linear Fisher discriminant to combine the information about significant triplet frequencies of various functional parts of splice site regions and preferences of oligonucleotides in protein coding and intron regions (Solovyev, Lawrence, 1994). The accuracy of our splice site recognition function is about 97%. A discriminant function for 5'-exon prediction includes hexanucleotide composition of upstream region, triplet composition around the ATG codon, ORF coding potential, donor splice site potential and composition of downstream intron region. For internal 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% and a level of pseudoexon ORF prediction of 99.96%. The recognition quality computed at the level of individual nucleotides is 89% for exon sequences and 98% for intron sequences. A discriminant function for 3'-exon prediction includes octanucleotide composition of upstream intron region, triplet composition around the stop codon, ORF coding potential, acceptor splice site potential and hexanucleotide composition of downstream region.(ABSTRACT TRUNCATED AT 250 WORDS)

Computer Simulation↗
PubMed1990

The median frequency of the ECG during ventricular fibrillation: its use in an algorithm for estimating the duration of cardiac arrest.

Recent studies have suggested that the initial therapeutic intervention for ventricular fibrillation (VF) may depend on downtime (DT), i.e., the time duration of VF. We characterized the dynamics of the frequency distribution in the power spectrum of the ECG recorded from eleven swine during VF to determine if enough information existed in this domain to estimate DT. We used the median frequency (FM) of the power spectrum to track the frequency distribution. The FM followed a dynamic repeatable course during the first 10 min of VF. Intersubject variability was small. We modeled the FM data of the eleven subjects with a set of first-order polynomial equations and tested the algorithm with data from an additional ten subjects. The algorithm predicted VF duration with an average error of -0.86 min; 71.5% of the predictions fell within the 95% confidence limits of the model. This paper has identified a signal processing tool which may be useful in the prehospital treatment of VF.

Algorithms↗
PubMed2006

A community resource benchmarking predictions of peptide binding to MHC-I molecules.

Recognition of peptides bound to major histocompatibility complex (MHC) class I molecules by T lymphocytes is an essential part of immune surveillance. Each MHC allele has a characteristic peptide binding preference, which can be captured in prediction algorithms, allowing for the rapid scan of entire pathogen proteomes for peptide likely to bind MHC. Here we make public a large set of 48,828 quantitative peptide-binding affinity measurements relating to 48 different mouse, human, macaque, and chimpanzee MHC class I alleles. We use this data to establish a set of benchmark predictions with one neural network method and two matrix-based prediction methods extensively utilized in our groups. In general, the neural network outperforms the matrix-based predictions mainly due to its ability to generalize even on a small amount of data. We also retrieved predictions from tools publicly available on the internet. While differences in the data used to generate these predictions hamper direct comparisons, we do conclude that tools based on combinatorial peptide libraries perform remarkably well. The transparent prediction evaluation on this dataset provides tool developers with a benchmark for comparison of newly developed prediction methods. In addition, to generate and evaluate our own prediction methods, we have established an easily extensible web-based prediction framework that allows automated side-by-side comparisons of prediction methods implemented by experts. This is an advance over the current practice of tool developers having to generate reference predictions themselves, which can lead to underestimating the performance of prediction methods they are not as familiar with as their own. The overall goal of this effort is to provide a transparent prediction evaluation allowing bioinformaticians to identify promising features of prediction methods and providing guidance to immunologists regarding the reliability of prediction tools.

Animals↗
PubMedDate not supplied

Review of studies using multivariable analysis of clinical and exercise test data to predict angiographic coronary artery disease.

Multivariable analysis of clinical and exercise test variables has the potential to become both a useful tool for assisting in the diagnosis of coronary artery disease and reducing the cost of evaluating patients with suspected coronary disease. Managed care and capitation require that tests such as the exercise test or its replacements, be used only when they can accurately and reliably identify which patients need medications, counseling, or further evaluation or intervention. The replacements for the standard exercise electrocardiogram test require expensive equipment and personnel, and their incremental value is currently being evaluated. Because general practitioners are to function as gatekeepers and decide which patients must be referred to the cardiologist, they will need to use the basic tools they have available (ie, history, physical exam, and the exercise test) in an optimal fashion. However, the discriminating power of the variables from the medical history and exercise test remains unclear because of inadequate study design and differences in study populations. There is a need for further evaluation of these routinely obtained variables to improve the accuracy of prediction algorithms especially in women. Of paramount concern is the need to avoid workup bias by having patients agree to testing before the decision for angiography is made. The portability and reliability of these equations must be shown because access to specialized care must be safeguarded. By reviewing the available studies considering clinical and exercise test variables to predict coronary angiographic findings, we have attempted to provide guidelines and recommendations for a more uniform approach to this endeavor in future investigations. Hopefully, the next generation of multivariable equations will be robust and portable, and empower the clinician to assure the cardiac patient access to appropriate cardiac care.

Coronary Angiography↗
PubMed2002

Definition and prediction of the full range of transcription factor binding sites--the hepatocyte nuclear factor 1 dimeric site.

In animals, transcription factor binding sites are hard to recognize because of their extensive variation. We therefore characterized the general relationship between a specific protein-binding site and its DNA sequence and used this relationship to generate a predictive algorithm for searching other DNA sequences. The experimental process was defined by studying hepatocyte nuclear factor 1 (HNF1), which binds DNA as a dimer on two inverted-repeat 7-bp half sites separated by one base. The binding model was based on the equivalence of the two half sites, which was confirmed in examples where specific modified sites were compared. Binding competition analysis was used to determine the effects of substitution of all four bases at each position in the half site. From these data, a weighted half-site matrix was generated and the full site was evaluated as the sum of two half-site scores. This process accurately predicted even weak binding sites that were significantly different from the consensus sequence. The predictions also showed a direct correlation with measured protein binding.

Algorithms↗
PubMed2004

Raman spectroscopy for identification of epithelial cancers.

There is a real need for improvements in cancer detection. Significant problems are encountered when utilising the gold standard of excisional biopsy combined with histopathology. This can include missed lesions, perforation and high levels of inter- and intra-observer discrepancies. The clinical requirements for an objective, non-invasive real time probe for accurate and repeatable measurement of tissue pathological state are overwhelming. This study has evaluated the potential for Raman spectroscopy to achieve this goal. The technique measures the molecular specific inelastic scattering of laser light within tissue, thus enabling the analysis of biochemical changes that precede and accompany disease processes. Initial work has been carried out to optimise a commercially available Raman microspectrometer for tissue measurements; to target potential malignancies with a clinical need for diagnostic improvements (oesophagus. colon, breast, andd prostate) and to build and test spectral libraries and prediction algorithms for tissue types and pathologies. This study has followed rigorous sample collection protocols and histopathological analysis using a board of expert pathologists. Only the data from samples with full agreement of a homogeneous pathology have been used to construct a training data set of Raman spectra. Measurements of tissue specimens from the full spectrum of different pathological groups found in each tissue have been made. Diagnostic predictive models have been constructed and optimised using multivariate analysis techniques. They have been tested using cross-validation or leave-one-out and demonstrated high levels of discrimination between pathology groups (greater than 90% sensitivity and specificity for all tissues). However larger sample numbers are required for further evaluation. The discussions outline the likely work required for successful implementation of in vivo Raman detection of early malignancies.

Algorithms↗
PubMed2001

Evolutionarily conserved RNA secondary structures in coding and non-coding sequences at the 3' end of the hepatitis G virus/GB-virus C genome.

Hepatitis G virus (HGV)/GB virus C (GBV-C) causes persistent, non-pathogenic infection in a large proportion of the human population. Epidemiological and genetic evidence indicates a long-term association between HGV/GBV-C and related viruses and a range of primate species, and the co-speciation of these viruses with their hosts during primate evolution. Using a combination of covariance scanning and analysis of variability at synonymous sites, we previously demonstrated that the coding regions of HGV/GBV-C may contain extensive secondary structure of undefined function (Simmonds & Smith, Journal of Virology 73, 5787-5794, 1999 ). In this study we have carried out a detailed comparison of the structure of the 3'untranslated region (3'UTR) of HGV/GBV-C with that of the upstream NS5B coding sequence. By investigation of free energies on folding, secondary structure predictive algorithms and analysis of covariance between HGV/GBV-C genotypes 1-4 and the more distantly related HGV/GBV-C chimpanzee variant, we obtained evidence for extensive RNA secondary structure formation in both regions. In particular, the NS5B region contained long stem-loop structures of up to 38 internally paired nucleotides which were evolutionarily conserved between human and chimpanzee HGV/GBV-C variants. The prediction of similar structures in the same region of hepatitis C virus may allow the functions of these structures to be determined with a more tractable experimental model.

3' Untranslated Regions↗
PubMed2006

YASSPP: better kernels and coding schemes lead to improvements in protein secondary structure prediction.

The accurate prediction of a protein's secondary structure plays an increasingly critical role in predicting its function and tertiary structure, as it is utilized by many of the current state-of-the-art methods for remote homology, fold recognition, and ab initio structure prediction. We developed a new secondary structure prediction algorithm called YASSPP, which uses a pair of cascaded models constructed from two sets of binary SVM-based models. YASSPP uses an input coding scheme that combines both position-specific and nonposition-specific information, utilizes a kernel function designed to capture the sequence conservation signals around the local window of each residue, and constructs a second-level model by incorporating both the three-state predictions produced by the first-level model and information about the original sequence. Experiments on three standard datasets (RS126, CB513, and EVA common subset 4) show that YASSPP is capable of producing the highest Q3 and SOV scores than that achieved by existing widely used schemes such as PSIPRED, SSPro 4.0, SAM-T99sec, as well as previously developed SVM-based schemes. On the EVA dataset it achieves a Q3 and SOV score of 79.34 and 78.65%, which are considerably higher than the best reported scores of 77.64 and 76.05%, respectively.

Algorithms↗
PubMed2006

How artificial intelligence tools can be used to assess individual patient risk in cardiovascular disease: problems with the current methods.

BACKGROUND: In recent years a number of algorithms for cardiovascular risk assessment has been proposed to the medical community. These algorithms consider a number of variables and express their results as the percentage risk of developing a major fatal or non-fatal cardiovascular event in the following 10 to 20 years DISCUSSION: The author has identified three major pitfalls of these algorithms, linked to the limitation of the classical statistical approach in dealing with this kind of non linear and complex information. The pitfalls are the inability to capture the disease complexity, the inability to capture process dynamics, and the wide confidence interval of individual risk assessment. Artificial Intelligence tools can provide potential advantage in trying to overcome these limitations. The theoretical background and some application examples related to artificial neural networks and fuzzy logic have been reviewed and discussed. SUMMARY: The use of predictive algorithms to assess individual absolute risk of cardiovascular future events is currently hampered by methodological and mathematical flaws. The use of newer approaches, such as fuzzy logic and artificial neural networks, linked to artificial intelligence, seems to better address both the challenge of increasing complexity resulting from a correlation between predisposing factors, data on the occurrence of cardiovascular events, and the prediction of future events on an individual level.

Artificial Intelligence↗
PubMed2004

Quantitative analysis of prion-protein degradation by constitutive and immuno-20S proteasomes indicates differences correlated with disease susceptibility.

The main part of cytosolic protein degradation depends on the ubiquitin-proteasome system. Proteasomes degrade their substrates into small peptide fragments, some of which are translocated into the endoplasmatic reticulum and loaded onto MHC class I molecules, which are then transported to the cell surface for inspection by CTL. A reliable prediction of proteasomal cleavages in a given protein for the identification of CTL epitopes would benefit immensely from additional cleavage data for the training of prediction algorithms. To increase the knowledge about proteasomal specificity and to gain more insight into the relation of proteasomal activity and susceptibility to prion disease, we digested sheep prion protein with human constitutive and immuno-20S proteasomes. All fragments generated in the digest were quantified. Our results underline the different cleavage specificities of constitutive and immunoproteasomes and provide data for the training of prediction programs for proteasomal cleavages. Furthermore, the kinetic analysis of proteasomal digestion of two different alleles of prion protein shows that even small changes in a protein sequence can affect the overall efficiency of proteasomal processing and thus provides more insight into the possible molecular background of allelic variations and the pathogenicity of prion proteins.

Alleles↗
PubMed2004

Effect of the initial implant fitting on the predicted secondary stability of a cementless stem.

A numerical model able to investigate the influence of biomechanical factors on the long-term secondary stability of implants would be extremely useful for the design of new cementless prosthetic devices. A purely biomechanical model of osseo-integration has been developed, formulated as a rule-based adaptation scheme. Due to its complexity, the problem was divided into three steps: preliminary implementation of the model (proof of concept); implementation of the complete model and investigation of the model solution; and model validation. The paper describes the first of these three steps. The model was implemented as a discrete-states machine, and the few parameters required were derived from the literature. It was then applied to a real clinical case. The study was conducted using the frictional contact finite element model of a human femur implanted with a cementless anatomical stem. A stable solution was achieved after between three and 15 iterations for all initial positions considered. Similar initial conditions yielded similar final configurations. The model predicted all initial configurations, with the exception of a partial osseo-integration, ranging between 62% (distal fit) and 78% (proximal fit) of the viable interface. This is in good agreement with the values reported in the literature that never exceed 75%, even in the best conditions, and report better clinical results for proximal fit. For the varus configuration, which lacks cortical support, the algorithm predicted a completed loosening.

Arthroplasty, Replacement, Hip↗
PubMed1995

Time-efficient docking of flexible ligands into active sites of proteins.

We present an algorithm for placing flexible molecules in active sites of proteins. The two major goals in the development of our docking program, called FLEXX, are the explicit exploitation of molecular flexibility of the ligand and the development of a model of the docking process that includes the physico-chemical properties of the molecules. The algorithm consists of three phases: The selection of a base fragment, the placement of the base fragment in the active site, and the incremental construction of the ligand inside the active site. Except for the selection of the base fragment, the algorithm runs without manual intervention. The algorithm is tested by reproducing 11 receptor-ligand complexes known from X-ray crystallography. In all cases, the algorithm predicts a placement of the ligand which is similar to the crystal structure (about 1.5 A RMS deviation or less) in a few minutes on a workstation, assuming that the receptor is given in the bound conformation.

Algorithms↗
PubMed1992

Dosimetric evaluation of a two-dimensional, arc electron, pencil-beam algorithm in water and PMMA.

The accuracy of dose calculations from a pencil-beam algorithm developed specifically for arc electron beam therapy was evaluated at 10 and 15 MeV. Mid-arc depth-doses were measured for 0 degrees and 90 degrees arcs using 12 and 15 cm radius cylindrical water phantoms. Calculated depth-doses for the 90 degrees arced beams in the build-up region were as much as 3% less than measured values; the maximum dose was similar in magnitude but at a greater depth; and the therapeutic depth, R80, was 2-4 mm deeper. Calculated values of output (dose per monitor unit) at the depth of the maximum calculated dose were compared with measured values; for arcs ranging from 0-90 degrees, 12 and 15 cm radius water phantoms, and collimator widths of 4, 5 and 6 cm, results showed differences as great as 7%. Isodose countours for a 90 degrees arc were also measured in a 15 cm radius PMMA phantom. At the depth of maximum dose the algorithm predicted doses in the penumbral regions, both with and without collimation, which agreed within a few per cent of measured values. The largest discrepancies were 5%, which occurred in the penumbral portion of the depth-dose fall-off region. Differences between measurement and calculation are not believed to be clinically significant and are believed to be primarily due to the fact that the algorithm models neither large-angle scattering nor the effects of range straggling on the pencil-beam dose distribution.

Algorithms↗
PubMed2005

Messenger RNA processing sites in Trypanosoma brucei.

In Kinetoplastids, protein-coding genes are transcribed polycistronically by RNA polymerase II. Individual mature mRNAs are generated from polycistronic precursors by 5' trans splicing of a 39-nt capped leader RNA and 3' polyadenylation. It was previously known that trans splicing generally occurs at an AG dinucleotide downstream of a polypyrimidine tract, and that polyadenylation is coupled to downstream trans splicing. The few polyadenylation sites that had been examined were 100-400 nt upstream of the polypyrimidine tract which marked the adjacent trans splice site. We wished to define the sequence requirements for trypanosome mRNA processing more tightly and to generate a predictive algorithm. By scanning all available Trypanosoma brucei cDNAs for splicing and polyadenylation sites, we found that trans splicing generally occurs at the first AG following a polypyrimidine tract of 8-25 nt, giving rise to 5'-UTRs of a median length of 68 nt. We also found that in general, polyadenylation occurs at a position with one or more A residues located between 80 and 140 nt from the downstream polypyrimidine tract. These data were used to calibrate free parameters in a grammar model with distance constraints, enabling prediction of polyadenylation and trans splice sites for most protein-coding genes in the trypanosome genome. The data from the genome analysis and the program are available from: .

5' Untranslated Regions↗
PubMed2001

Bioinformatic identification of potential autocrine signaling loops in cancers from gene expression profiles.

Many biological signaling pathways involve autocrine ligand-receptor loops; misregulation of these signaling loops can contribute to cancer phenotypes. Here we present an algorithm for detecting such loops from gene expression profiles. Our method is based on the hypothesis that for some autocrine pathways, the ligand and receptor are regulated by coupled mechanisms at the level of transcription, and thus ligand-receptor pairs comprising such a loop should have correlated mRNA expression. Using our database of experimentally known ligand-receptor signaling partners, we found examples of ligand-receptor pairs with significantly correlated expression in five cancer-based gene expression datasets. The correlated ligand-receptor pairs we identified are consistent with known autocrine signaling events in cancer cells. In addition, our algorithm predicts new autocrine signaling loops that can be verified experimentally. Chemokines were commonly members of these potential autocrine pathways. Our analysis also revealed ligand-receptor pairs with expression patterns that may indicate cellular mechanisms for preventing autocrine signaling.

Algorithms↗