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 235 records · Page 13Linked to original sources
PubMed2001

Comparison of commercially available three-dimensional treatment planning algorithms for monitor unit calculations in the presence of heterogeneities.

This study uses an anthropomorphic phantom and its computed tomography (CT) data set to evaluate monitor unit (MU) calculations using the CMS Focus Clarkson, the CMS Focus Multigrid Superposition Model, the CMS Focus FFT Convolution Model, and the ADAC Pinnacle Collapsed Cone Convolution Superposition Algorithms. Using heterogeneity corrections, a treatment plan and corresponding MU calculations were generated for several typical clinical situations. A diode detector, placed in an anthropomorphic phantom, was used to compare the treatment planning algorithms' predicted doses with measured data. Differences between diode measurements and the algorithms' calculations were within reasonable levels of acceptability as recommended by Van Dyk et al. [Int. J. Rad. Onc. Biol. Phys. 26, 261-273 (1993)], except for the CMS Clarkson algorithm, which predicted too few MU for delivery of the intended dose to chest wall fields.

Algorithms↗
PubMed1991

A method for prediction of phenytoin levels in the acute clinical setting.

Phenytoin (PHT) administration is complicated by saturation kinetics within the therapeutic range, causing marked changes in drug concentration with small changes in dose. The "half-life" increases with concentration, varying from 8-24 hr up to weeks, making it difficult to obtain the steady state levels needed by most prediction algorithms and nomograms. A Bayesian prediction program (Epidose) is presented which explicitly models PHT absorption and elimination kinetics in the non-steady state. The algorithm accounts for the interdependency of closely spaced sequential samples. Estimates of future PHT concentration were made on 20 hospital inpatients, most of whom were acutely ill and received other medications. Future (mean = 4 day) PHT concentrations were predicted over a range from 4 to 22 micrograms/ml (mean 13.9 micrograms/ml) with a median absolute error of 1.0 microgram/ml. These data demonstrate that the program can be used for accurate PHT concentration predictions in sick patients.

Adult↗
PubMed1997

A virtual screening approach applied to the search for trypanothione reductase inhibitors.

A prediction algorithm of the binding affinity of ligands to trypanothione reductase (TR), the enzyme replacing glutathione reductase in the metabolism of trypanosomatidae, has been used for the "virtual screening" of a data base of 2500 molecular sketches and has detected several structures of putative TR ligands. Most of these compounds turned out to be micromolar inhibitors of TR, as predicted by the algorithm. While their inhibitory potencies are lower than those of previously reported compounds, one of the molecules reported here could represent the lead toward a structurally different class of TR inhibitors. The fully automated prediction algorithm converts the 2D molecular sketches into 3D ligand structures, explores the conformational space of the latter, and performs a grid-based, rigid-body docking of the resulting family of ligand conformations into the TR site, calculating enthalpic and entropic binding indexes and predicting the binding affinity. The docking model has also been used to obtain hints about the binding modes of TR ligands.

Algorithms↗
PubMed2005

pSLIP: SVM based protein subcellular localization prediction using multiple physicochemical properties.

BACKGROUND: Protein subcellular localization is an important determinant of protein function and hence, reliable methods for prediction of localization are needed. A number of prediction algorithms have been developed based on amino acid compositions or on the N-terminal characteristics (signal peptides) of proteins. However, such approaches lead to a loss of contextual information. Moreover, where information about the physicochemical properties of amino acids has been used, the methods employed to exploit that information are less than optimal and could use the information more effectively. RESULTS: In this paper, we propose a new algorithm called pSLIP which uses Support Vector Machines (SVMs) in conjunction with multiple physicochemical properties of amino acids to predict protein subcellular localization in eukaryotes across six different locations, namely, chloroplast, cytoplasmic, extracellular, mitochondrial, nuclear and plasma membrane. The algorithm was applied to the dataset provided by Park and Kanehisa and we obtained prediction accuracies for the different classes ranging from 87.7%-97.0% with an overall accuracy of 93.1%. CONCLUSION: This study presents a physicochemical property based protein localization prediction algorithm. Unlike other algorithms, contextual information is preserved by dividing the protein sequences into clusters. The prediction accuracy shows an improvement over other algorithms based on various types of amino acid composition (single, pair and gapped pair). We have also implemented a web server to predict protein localization across the six classes (available at http://pslip.bii.a-star.edu.sg/).

Algorithms↗
PubMed1998

Elucidating the folding problem of alpha-helices: local motifs, long-range electrostatics, ionic-strength dependence and prediction of NMR parameters.

The information about the conformational behavior of monomeric helical peptides in solution, as well as the alpha-helix stability in proteins, has been previously utilized to derive a database with the energy contributions for various interactions taking place in an alpha-helix: intrinsic helical propensities, side-chain-side-chain interactions, main-chain-main-chain hydrogen bonds, and capping effects. This database was implemented in an algorithm based on the helix/coil transition theory (AGADIR). Here, we have modified this algorithm to include previously described local motifs: hydrophobic staple, Schellman motif and Pro-capping motif, new variants of these, and newly described side-chain-side-chain interactions. Based on recent experimental data we have introduced a position dependence of the helical propensities for some of the 20 amino acid residues. A new electrostatic model that takes into consideration all electrostatic interactions up to 12 residues in distance in the helix and random-coil conformations, as well as the effect of ionic strength, has been implemented. We have synthesized and analyzed several peptides, and used data from peptides already analysed by other groups, to test the validity of our electrostatic model. The modified algorithm predicts, with an overall standard deviation value of 6.6 (maximum helix is 100%), the helical, content of 778 peptides of which 223 correspond to wild-type and modified protein fragments. To improve the prediction potential of the algorithm and to have a direct comparison with nuclear magnetic resonance data, the algorithm now predicts the conformational shift of the CalphaH protons, 13Calpha and 3JalphaN values. We have found that for those peptides correctly predicted from the point of view of circular dichroism, the prediction of the NMR parameters is very good.

Algorithms↗
PubMed2005

Prediction of protein signal sequences and their cleavage sites by statistical rulers.

Functioning as an "address tag" or "zip code" that guides nascent proteins (newly synthesized proteins in the cytosol) to wherever they are needed, signal peptides (also called targeting signals or signal sequences) have become a crucial tool in finding new drugs or reprogramming cells for gene therapy. To effectively and timely use such a tool, however, the first important thing is to develop an automated method for quickly and accurately identifying the signal peptide for a given nascent protein. With the avalanche of new protein sequences generated in the post-genomic era, the challenge has become even more urgent and critical. In this paper, five statistical rulers were derived via performing a mutual information analysis. By combining these statistical rulers, a new prediction algorithm was established and high success prediction rates were observed. The new algorithm may play a complementary role to the existing algorithms in this area. It is anticipated that the mutual information approach introduced here may be very useful for studying many other sequence-coupling problems in molecular biology as well.

Algorithms↗
PubMed2003

Selecting informative data for developing peptide-MHC binding predictors using a query by committee approach.

Strategies for selecting informative data points for training prediction algorithms are important, particularly when data points are difficult and costly to obtain. A Query by Committee (QBC) training strategy for selecting new data points uses the disagreement between a committee of different algorithms to suggest new data points, which most rationally complement existing data, that is, they are the most informative data points. In order to evaluate this QBC approach on a real-world problem, we compared strategies for selecting new data points. We trained neural network algorithms to obtain methods to predict the binding affinity of peptides binding to the MHC class I molecule, HLA-A2. We show that the QBC strategy leads to a higher performance than a baseline strategy where new data points are selected at random from a pool of available data. Most peptides bind HLA-A2 with a low affinity, and as expected using a strategy of selecting peptides that are predicted to have high binding affinities also lead to more accurate predictors than the base line strategy. The QBC value is shown to correlate with the measured binding affinity. This demonstrates that the different predictors can easily learn if a peptide will fail to bind, but often conflict in predicting if a peptide binds. Using a carefully constructed computational setup, we demonstrate that selecting peptides with a high QBC performs better than low QBC peptides independently from binding affinity. When predictors are trained on a very limited set of data they cannot be expected to disagree in a meaningful way and we find a data limit below which the QBC strategy fails. Finally, it should be noted that data selection strategies similar to those used here might be of use in other settings in which generation of more data is a costly process.

Algorithms↗
PubMed2002

Identification of immunodominant regions among promiscuous HLA-DR-restricted CD4+ T-cell epitopes on the tumor antigen MAGE-3.

The molecular characterization of the CD4(+) T-cell epitope repertoire on human tumor antigens would contribute to both clinical investigation and cancer immunotherapy. In particular, the identification of promiscuous epitopes would be beneficial to a large number of patients with neoplastic diseases regardless of their HLA-DR type. MAGE-3 is a tumor-specific antigen widely expressed in solid and hematologic malignancies; therefore, is an excellent candidate antigen. We used a major histocompatability complex (MHC) class II epitope prediction algorithm, the TEPITOPE software, to predict 11 sequence segments of MAGE-3 that could form promiscuous CD4(+) T-cell epitopes. In binding assays, the synthetic peptides corresponding to the 11 predicted sequences bound at least 3 different HLA-DR alleles. Nine of the 11 peptides induced proliferation of CD4(+) T cells from both healthy subjects and melanoma patients. Four immunodominant regions (residues 111-125, 146-160, 191-205, and 281-295), containing naturally processed epitopes, were recognized by most of the donors, in association with 3 to 4 different HLA-DR alleles, thus covering up to 94% of the alleles expressed in whites. On the contrary, the other promiscuous regions (residues 161-175 and 171-185) contained epitopes not naturally processed in vitro. The immunodominant epitopes identified will be useful in the design of peptide-based cancer vaccines and in the study of the functional state of tumor-specific CD4(+) T cells in patients bearing tumors expressing MAGE-3.

Algorithms↗
PubMed2003

Fold recognition methods.

We are still missing a basic understanding of sequence/structure/function relationships in proteins. Analogy-based prediction algorithms remain the only reliable fold prediction tools. New methods, such as threading and hybrid threading/sequence fold recognition, can often recognize even the most distant homologues and, in some cases, even unrelated proteins with similar overall structures. This knowledge pushed the envelope of analogy-based function analysis to the point that the majority of newly sequenced genomes can be tentatively assigned to already characterized protein superfamilies. However, at this evolutionary distance, fold prediction is no longer equivalent to function prediction. Instead of having the same exact function, distantly related proteins might share some functional analogy that is not obvious to the casual observer. The main challenge facing the fold recognition field is to develop tools to follow the structure prediction with function prediction and analysis.

Algorithms↗
PubMed2003

Inherent protein structural flexibility at the RNA-binding interface of L30e.

The Saccharomyces cerevisiae ribosomal protein L30 autoregulates its own expression by binding to a purine-rich internal loop in its pre-mRNA and mRNA. NMR studies of L30 and its RNA complex showed that both the internal loop of the RNA as well as a region of the protein become substantially more ordered upon binding. A crystal structure of a maltose binding protein (MBP)-L30 fusion protein with two copies in the asymmetric unit has been determined. The flexible RNA-binding region in the L30 copies has two distinct conformations, one resembles the RNA bound form solved by NMR and the other is unique. Structure prediction algorithms also had difficulty accurately predicting this region, which is consistent with conformational flexibility seen in the NMR and X-ray crystallography studies. Inherent conformational flexibility may be a hallmark of regions involved in intermolecular interactions.

Amino Acid Sequence↗
PubMed2001

Prediction of energy expenditure in a whole body indirect calorimeter at both low and high levels of physical activity.

OBJECTIVES: In studies that involve the use of a room calorimeter, 24 h energy intake is often larger than 24 h energy expenditure (24 h EE) because of a decrease in activity energy expenditure due to the confined space. This positive energy balance can have large consequences for the interpretation of substrate balances. The objective of this study was to develop a method for predicting an individual's 24 h EE in a room calorimeter at both low (1.4xRMR) and high (1.8xRMR) levels of physical activity. METHODS: Two methods are presented that predict an individual's 24 h EE in a metabolic chamber. The first method was based on three components: (1) a 30 min measurement of resting metabolic rate (RMR) using a ventilated hood system; (2) measurement of exercise energy expenditure during 10 min of treadmill walking; and (3) estimation of free-living energy expenditure using a tri-axial motion sensor. Using these measurements we calculated the amount of treadmill time needed for each individual in order to obtain a total 24 h EE at either a low (1.4xRMR) or a high (1.8xRMR) level of physical activity. We also developed a method to predict total 24 h EE during the chamber stay by using the energy expenditure values for the different levels of activity as measured during the hours already spent in the chamber. This would provide us with a tool to adjust the exercise time and/or energy intake during the chamber stay. RESULTS: Method 1: there was no significant difference in expected and measured 24 h EE under either low (9.35+/-0.56 vs 9.51+/-0.47 MJ/day; measured vs predicted) or high activity conditions (13.41+/-0.74 vs 13.97+/-0.78 MJ/day; measured vs predicted). Method 2: the developed algorithm predicted 24 h EE for 97.6+/-4.0% of the final value at 3 h into the test day, and for 98.6+/-3.7% at 7 h into the test day. CONCLUSION: Both methods provide accurate prediction of energy expenditure in a room calorimeter at both high and low levels of physical activity. It equally shows that it is possible to accurately predict total 24 h EE from energy expenditure values obtained at 3 and 7 h into the study.

Adaptation, Physiological↗
PubMed1996

Epitopes recognized by human T lymphocytes in the ROP2 protein antigen of Toxoplasma gondii.

The ROP2 protein of Toxoplasma gondii possesses immunological and biological properties which have led to its proposal as a vaccine candidate. To identify epitopes recognized by human T cells in the ROP2 antigen, we submitted the sequence of this protein to three reported T-cell epitope prediction algorithms. Three sequences that were predicted by all three methods were selected (sequences 197 to 216, 393 to 410, and 501 to 524), and the corresponding peptides were synthesized. The peptides were first tested in a proliferation assay with a DPw4-restricted, ROP2-specific human T-cell clone, and the peptide corresponding to residues 197 to 216 was shown to stimulate the T-cell clone. The three peptides were further tested in proliferation assays with peripheral blood mononuclear cells from a panel of T. gondii-seropositive and -seronegative individuals. We found that cells from a high proportion of the seropositive donors (64%) recognized at least one of the three peptides. The most frequently recognized ones were peptides 197 to 216 (45%) and 501 to 524 (36%). None of the seronegative donors responded to any peptide. These results show that the ROP2 antigen of T. gondii contains T-cell epitopes recognized by a high percentage of the immune population and further strengthen its potential as a vaccine candidate.

Amino Acid Sequence↗
PubMed2004

Clinical trial design for microarray predictive marker discovery and assessment.

Transcriptional profiling technologies that simultaneously measure the expression of thousands of mRNA species represent a powerful new clinical research tool. Similar to previous laboratory analytical methods including immunohistochemistry, PCR and in situ hybridization, this new technology may also find its niche in routine diagnostics. Outcome predictors discovered by these methods may be quite different from previous single-gene markers. These novel tests will probably combine the information embedded in the expression of multiple genes with mathematical prediction algorithms to formulate classification rules and predict outcome. The performance of machine learning-algorithm-based diagnostic tests may improve as they are trained on larger and larger sets of samples, and several generations of tests with improving accuracy may be introduced sequentially. Several gene-expression profiling-technology platforms are mature enough for clinical testing. The most important next step that is needed for further progress is the development and validation of multigene predictors in prospectively designed clinical trials to determine the true accuracy and clinical value of this new technology. This manuscript reviews methodological and statistical issues relevant to clinical trial design to discover and validate multigene predictors of response to therapy.

Clinical Trials as Topic↗
PubMed2004

ProMate: a structure based prediction program to identify the location of protein-protein binding sites.

Is the whole protein surface available for interaction with other proteins, or are specific sites pre-assigned according to their biophysical and structural character? And if so, is it possible to predict the location of the binding site from the surface properties? These questions are answered quantitatively by probing the surfaces of proteins using spheres of radius of 10 A on a database (DB) of 57 unique, non-homologous proteins involved in heteromeric, transient protein-protein interactions for which the structures of both the unbound and bound states were determined. In structural terms, we found the binding site to have a preference for beta-sheets and for relatively long non-structured chains, but not for alpha-helices. Chemically, aromatic side-chains show a clear preference for binding sites. While the hydrophobic and polar content of the interface is similar to the rest of the surface, hydrophobic and polar residues tend to cluster in interfaces. In the crystal, the binding site has more bound water molecules surrounding it, and a lower B-factor already in the unbound protein. The same biophysical properties were found to hold for the unbound and bound DBs. All the significant interface properties were combined into ProMate, an interface prediction program. This was followed by an optimization step to choose the best combination of properties, as many of them are correlated. During optimization and prediction, the tested proteins were not used for data collection, to avoid over-fitting. The prediction algorithm is fully automated, and is used to predict the location of potential binding sites on unbound proteins with known structures. The algorithm is able to successfully predict the location of the interface for about 70% of the proteins. The success rate of the predictor was equal whether applied on the unbound DB or on the disjoint bound DB. A prediction is assumed correct if over half of the predicted continuous interface patch is indeed interface. The ability to predict the location of protein-protein interfaces has far reaching implications both towards our understanding of specificity and kinetics of binding, as well as in assisting in the analysis of the proteome.

Algorithms↗
PubMed1998

Algorithms and software for support of gene identification experiments.

MOTIVATION: Gene annotation is the final goal of gene prediction algorithms. However, these algorithms frequently make mistakes and therefore the use of gene predictions for sequence annotation is hardly possible. As a result, biologists are forced to conduct time-consuming gene identification experiments by designing appropriate PCR primers to test cDNA libraries or applying RT-PCR, exon trapping/amplification, or other techniques. This process frequently amounts to 'guessing' PCR primers on top of unreliable gene predictions and frequently leads to wasting of experimental efforts. RESULTS: The present paper proposes a simple and reliable algorithm for experimental gene identification which bypasses the unreliable gene prediction step. Studies of the performance of the algorithm on a sample of human genes indicate that an experimental protocol based on the algorithm's predictions achieves an accurate gene identification with relatively few PCR primers. Predictions of PCR primers may be used for exon amplification in preliminary mutation analysis during an attempt to identify a gene responsible for a disease. We propose a simple approach to find a short region from a genomic sequence that with high probability overlaps with some exon of the gene. The algorithm is enhanced to find one or more segments that are probably contained in the translated region of the gene and can be used as PCR primers to select appropriate clones in cDNA libraries by selective amplification. The algorithm is further extended to locate a set of PCR primers that uniformly cover all translated regions and can be used for RT-PCR and further sequencing of (unknown) mRNA.

Algorithms↗
PubMed1993

Predicted probabilities of hospital death as a measure of admission severity of illness.

This paper evaluates a new method for assessing hospital admission severity of illness based on disease-specific models (logistic regression) of the probability of in-hospital mortality. Results for the 26 disease groups in MDC 4--Diseases of the Respiratory System, MDC 5--Diseases of the Circulatory System, and MDC 6--Diseases of the Digestive System are presented using data on all 1991 admissions from 111 hospitals throughout the United States. These disease models are empirically derived using clinical findings from laboratory, radiology, pathology, diagnostic procedures, patient history and physical exam, as well as patient age and sex. Each predictive algorithm is presented, and the strong predictive performance of these models is indicated by the average C statistic of .870. A predicted probability of death is calculated for each hospital patient in the study sample, and these probabilities comprise a continuous variable that indicates admission severity of illness.

Algorithms↗
PubMed2003

The secreted protein discovery initiative (SPDI), a large-scale effort to identify novel human secreted and transmembrane proteins: a bioinformatics assessment.

A large-scale effort, termed the Secreted Protein Discovery Initiative (SPDI), was undertaken to identify novel secreted and transmembrane proteins. In the first of several approaches, a biological signal sequence trap in yeast cells was utilized to identify cDNA clones encoding putative secreted proteins. A second strategy utilized various algorithms that recognize features such as the hydrophobic properties of signal sequences to identify putative proteins encoded by expressed sequence tags (ESTs) from human cDNA libraries. A third approach surveyed ESTs for protein sequence similarity to a set of known receptors and their ligands with the BLAST algorithm. Finally, both signal-sequence prediction algorithms and BLAST were used to identify single exons of potential genes from within human genomic sequence. The isolation of full-length cDNA clones for each of these candidate genes resulted in the identification of >1000 novel proteins. A total of 256 of these cDNAs are still novel, including variants and novel genes, per the most recent GenBank release version. The success of this large-scale effort was assessed by a bioinformatics analysis of the proteins through predictions of protein domains, subcellular localizations, and possible functional roles. The SPDI collection should facilitate efforts to better understand intercellular communication, may lead to new understandings of human diseases, and provides potential opportunities for the development of therapeutics.

Cell Adhesion Molecules, Neuronal↗
PubMed1998

The role of biopsy pathology, quantitative nuclear morphometry, and biomarkers in the preoperative prediction of prostate cancer staging and prognosis.

The focus of this review is to survey pretreatment biopsy and patient-derived information applicable to predicting pathological stage and prognosis of men with a diagnosis of prostate cancer. Various sources of clinical and pathological information that may contribute to building decision support tools (DSTs) for application by the urologist to manage prostate cancer patients are presented. These DSTs use serum biomarkers and objective, well-established, pathology information extracted by experienced pathologists from needle-core tissue samples that describe tumor size, grade, and location. Other valuable data can be derived from the biopsy tissue, such as computer-assisted image cytometry-derived DNA ploidy and nuclear morphometry informatics, as well as select tissue biomarker results that may provide supplemental prognostic information. Also discussed are the technical and clinical limitations of these DSTs with respect to the prediction accuracy. A commercially available pretreatment prediction algorithm (UroScore, Oklahoma City, OK) was applied to predict the disease organ confinement status of the prostate cancer test case. Finally, the authors present existing and future applications of computer-derived computational solutions for incorporating all patient history, clinical laboratory, and pathology information into algorithms that can generate patient-specific predictive probability estimates of stage, recurrence, and progression.

Biomarkers, Tumor↗