Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Computational prediction”

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 415 records · Page 23Linked to original sources
PubMed2004

A constrained-syntax genetic programming system for discovering classification rules: application to medical data sets.

This paper proposes a new constrained-syntax genetic programming (GP) algorithm for discovering classification rules in medical data sets. The proposed GP contains several syntactic constraints to be enforced by the system using a disjunctive normal form representation, so that individuals represent valid rule sets that are easy to interpret. The GP is compared with C4.5, a well-known decision-tree-building algorithm, and with another GP that uses Boolean inputs (BGP), in five medical data sets: chest pain, Ljubljana breast cancer, dermatology, Wisconsin breast cancer, and pediatric adrenocortical tumor. For this last data set a new preprocessing step was devised for survival prediction. Computational experiments show that, overall, the GP algorithm obtained good results with respect to predictive accuracy and rule comprehensibility, by comparison with C4.5 and BGP.

Algorithms↗
PubMed2007

In silico drug discovery: solving the "target-rich and lead-poor" imbalance using the genome-to-drug-lead paradigm.

Advances in genomics, proteomics, and structural genomics have identified a large number of protein targets. Virtual screening has gained popularity in identifying drug leads by computationally screening large numbers of chemicals against experimentally determined protein targets. In that context, there continues to be a "target-rich and lead-poor" imbalance, reflecting an insufficiency of chemists pursuing drug discovery in academia, the challenge of engaging more chemists in this area of research, and a paucity of available protein target structures. This imbalance in manpower and structural information can be ameliorated, in part, by adapting a "genome-to-drug-lead" approach, in which chemicals can be virtually screened against computer-predicted protein targets, within the context of the US National Science Foundation's petascale computing initiative. This approach offers a solution to reduce manpower requirements for more chemists to experimentally search for drug leads, which represent one of the greatest limitations to drug discovery and better exploits the extensive availability of drug targets at the gene level, ultimately improving the success of moving discoveries from the laboratory to the patient.

Chemistry, Pharmaceutical↗
PubMed2001

Prediction of quaternary structure from primary structure.

MOTIVATION: The 'sequence implies conformation' principle has been the motivation for the construction of numerous systems of secondary and tertiary structure prediction. Computational experiments have shown that this principle can now be extended to quaternary structure prediction. This work appears to be the first effort to predict quaternary structure properties from sequence. RESULTS: The software developed to conduct these experiments was the Quaternary Structure Explorer (QSE). Successful rule-based classifiers have been found that can discriminate between the primary sequences of homodimers and non-homodimers.

Algorithms↗
PubMed2002

RASPBERRY3 gene encodes a novel protein important for embryo development.

We identified a new gene that is interrupted by T-DNA in an Arabidopsis embryo mutant called raspberry3. raspberry3 has "raspberry-like" cellular protuberances with an enlarged suspensor characteristic of other raspberry embryo mutants, and is arrested morphologically at the globular stage of embryo development. The predicted RASPBERRY3 protein has domains found in proteins present in prokaryotes and algae chloroplasts. Computer prediction analysis suggests that the RASPBERRY3protein may be localized in the chloroplast. Complementation analysis supports the possibility that the RASPBERRY3 protein may be involved in chloroplast development. Our experiments demonstrate the important role of the chloroplast, directly or indirectly, in embryo morphogenesis and development.

Amino Acid Sequence↗
PubMed1999

Prediction of antisense oligonucleotide binding affinity to a structured RNA target.

Antisense oligonucleotides, which act through the pairing of complementary bases to an RNA target sequence, are showing great promise in research and clinical applications. However, the selection of effective antisense oligonucleotides has proven more difficult than initially presumed. We developed a prediction algorithm to identify those sequences with the highest predicted binding affinity for their target mRNA based on a thermodynamic cycle that accounts for the energetics of structural alterations in both the target mRNA and the oligonucleotide. The model was used to predict the binding affinity of antisense oligonucleotides complementary to the rabbit beta-globin (RBG) and mouse tumor necrosis factor-alpha (TNFalpha) mRNAs, for which large experimental datasets were available. Of the top ten candidates identified by the algorithm for the RBG mRNA, six were the most strongly binding sequences determined from an experimental assay. The prediction for the TNFalpha mRNA also identified high affinity sequences with approximately 60% accuracy. Computational prediction of antisense efficacy is more cost-efficient and faster than in vitro or in vivo selection and can potentially speed the development of sequences for both research and clinical applications.

Animals↗
PubMed2005

Sequence optimization and designability of enzyme active sites.

We recently found that many residues in enzyme active sites can be computationally predicted by the optimization of scoring functions based on substrate binding affinity, subject to constraints on the geometry of catalytic residues and protein stability. Here, we explore the generality of this surprising observation. First, the impact of hydrogen-bonding networks necessary for catalysis on the accuracy of sequence optimization is assessed; incorporation of these networks, where relevant, into the set of catalytic constraints is found to be essential. Next, the impact of multiple substrate selectivity on sequence optimization is probed by carrying out independent calculations for complexes of deoxyribonucleoside kinases with various cognate ligands, revealing how simultaneous selection pressures determined active-site sequences of these enzymes. Including previous calculations on simpler enzymes, computational sequence optimization correctly predicts 76% of all active-site residues tested (86% correct, with 93% similar, for naturally conserved residues). In these studies, the ligand is fixed in its native conformation. To assess the applicability of these methods to de novo active-site design, the effect of small ligand motions around the native pose is also examined. Robustness of sequence accuracy for topologically similar poses is demonstrated for selected kinases, but not for a model peptidase. Based on these observations, we introduce the notion of the designability of an enzyme active site, a metric that may be used to guide the search for protein scaffolds suitable for the introduction of de novo activity for a desired chemical reaction.

Algorithms↗
PubMed2006

Prediction of genomic functional elements.

As the number of sequenced genomes increases, the ability to deduce genome function becomes increasingly salient. For many genome sequences, the only annotation that will be available for the foreseeable future will be based on computational predictions and comparisons with functional elements in related species. Here we discuss computational approaches for automated genome-wide annotation of functional elements in mammalian genomes. These include methods for ab initio and comparative gene-structure predictions. Gene features such as intron splice sites, 3' untranslated regions, promoters, and cis-regulatory elements are discussed, as is a novel method for predicting DNaseI hypersensitive sites. Recent methodologies for predicting noncoding RNA genes, including microRNA genes and their targets, are also reviewed.

Animals↗
PubMed2006

dbPTM: an information repository of protein post-translational modification.

dbPTM is a database that compiles information on protein post-translational modifications (PTMs), such as the catalytic sites, solvent accessibility of amino acid residues, protein secondary and tertiary structures, protein domains and protein variations. The database includes all of the experimentally validated PTM sites from Swiss-Prot, PhosphoELM and O-GLYCBASE. Only a small fraction of Swiss-Prot proteins are annotated with experimentally verified PTM. Although the Swiss-Prot provides rich information about the PTM, other structural properties and functional information of proteins are also essential for elucidating protein mechanisms. The dbPTM systematically identifies three major types of protein PTM (phosphorylation, glycosylation and sulfation) sites against Swiss-Prot proteins by refining our previously developed prediction tool, KinasePhos (http://kinasephos.mbc.nctu.edu.tw/). Solvent accessibility and secondary structure of residues are also computationally predicted and are mapped to the PTM sites. The resource is now freely available at http://dbPTM.mbc.nctu.edu.tw/.

Amino Acids↗
PubMed2006

Machine learning approaches for estimation of prediction interval for the model output.

A novel method for estimating prediction uncertainty using machine learning techniques is presented. Uncertainty is expressed in the form of the two quantiles (constituting the prediction interval) of the underlying distribution of prediction errors. The idea is to partition the input space into different zones or clusters having similar model errors using fuzzy c-means clustering. The prediction interval is constructed for each cluster on the basis of empirical distributions of the errors associated with all instances belonging to the cluster under consideration and propagated from each cluster to the examples according to their membership grades in each cluster. Then a regression model is built for in-sample data using computed prediction limits as targets, and finally, this model is applied to estimate the prediction intervals (limits) for out-of-sample data. The method was tested on artificial and real hydrologic data sets using various machine learning techniques. Preliminary results show that the method is superior to other methods estimating the prediction interval. A new method for evaluating performance for estimating prediction interval is proposed as well.

Algorithms↗
PubMed2005

Binding mode prediction of cytochrome p450 and thymidine kinase protein-ligand complexes by consideration of water and rescoring in automated docking.

The popular docking programs AutoDock, FlexX, and GOLD were used to predict binding modes of ligands in crystallographic complexes including X-ray water molecules or computationally predicted water molecules. Isoenzymes of two different enzyme systems were used, namely cytochromes P450 (n = 19) and thymidine kinases (n = 19) and three different "water" scenarios: i.e., docking (i) into water-free active sites, (ii) into active sites containing crystallographic water molecules, and (iii) into active sites containing water molecules predicted by a novel approach based on the program GRID. Docking accuracies were determined in terms of the root-mean-square deviation (RMSD) accuracy and, newly defined, in terms of the ligand catalytic site prediction (CSP) accuracy. Consideration of both X-ray and predicted water molecules and the subsequent pooling and rescoring of all solutions (generated by all three docking programs) with the SCORE scoring function significantly improved the quality of prediction of the binding modes both in terms of RMSD and CSP accuracy.

Catalytic Domain↗
PubMed2006

Evidence supporting predicted metabolic pathways for Vibrio cholerae: gene expression data and clinical tests.

Vibrio cholerae, the etiological agent of the diarrheal illness cholera, can kill an infected adult in 24 h. V.cholerae lives as an autochthonous microbe in estuaries, rivers and coastal waters. A better understanding of its metabolic pathways will assist the development of more effective treatments and will provide a deeper understanding of how this bacterium persists in natural aquatic habitats. Using the completed V.cholerae genome sequence and PathoLogic software, we created VchoCyc, a pathway-genome database that predicted 171 likely metabolic pathways in the bacterium. We report here experimental evidence supporting the computationally predicted pathways. The evidence comes from microarray gene expression studies of V.cholerae in the stools of three cholera patients [D. S. Merrell, S. M. Butler, F. Qadri, N. A. Dolganov, A. Alam, M. B. Cohen, S. B. Calderwood, G. K. Schoolnik and A. Camilli (2002) Nature, 417, 642-645.], from gene expression studies in minimal growth conditions and LB rich medium, and from clinical tests that identify V.cholerae. Expression data provide evidence supporting 92 (53%) of the 171 pathways. The clinical tests provide evidence supporting seven pathways, with six pathways supported by both methods. VchoCyc provides biologists with a useful tool for analyzing this organism's metabolic and genomic information, which could lead to potential insights into new anti-bacterial agents. VchoCyc is available in the BioCyc database collection (http://BioCyc.org).

Bacteriological Techniques↗
PubMed2006

The imperative for controlled mechanical stresses in unraveling cellular mechanisms of mechanotransduction.

BACKGROUND: In vitro mechanotransduction studies are designed to elucidate cell behavior in response to a well-defined mechanical signal that is imparted to cultured cells, e.g. through fluid flow. Typically, flow rates are calculated based on a parallel plate flow assumption, to achieve a targeted cellular shear stress. This study evaluates the performance of specific flow/perfusion chambers in imparting the targeted stress at the cellular level. METHODS: To evaluate how well actual flow chambers meet their target stresses (set for 1 and 10 dyn/cm2 for this study) at a cellular level, computational models were developed to calculate flow velocity components and imparted shear stresses for a given pressure gradient. Computational predictions were validated with micro-particle image velocimetry (microPIV) experiments. RESULTS: Based on these computational and experimental studies, as few as 66% of cells seeded along the midplane of commonly implemented flow/perfusion chambers are subjected to stresses within +/-10% of the target stress. In addition, flow velocities and shear stresses imparted through fluid drag vary as a function of location within each chamber. Hence, not only a limited number of cells are exposed to target stress levels within each chamber, but also neighboring cells may experience different flow regimes. Finally, flow regimes are highly dependent on flow chamber geometry, resulting in significant variation in magnitudes and spatial distributions of stress between chambers. CONCLUSION: The results of this study challenge the basic premise of in vitro mechanotransduction studies, i.e. that a controlled flow regime is applied to impart a defined mechanical stimulus to cells. These results also underscore the fact that data from studies in which different chambers are utilized can not be compared, even if the target stress regimes are comparable.

Animals↗
PubMed1994

Development and validation of computed tomography derived anthropometric regression equations for estimating abdominal adipose tissue distribution.

The purpose of this study was twofold: (1) to develop multiple regression equations for predicting computed tomography (CT) derived intra-abdominal (IAF), subcutaneous (SCF), and total (TOTF= IAF+SCF) abdominal adipose tissue areas from anthropometric measures in adult white males with a large range of age (18-71 years) and percent body fat (2.0-40.6); and (2) to validate the new and existing equations that used similar Hounsfield Units (HU) for determining IAF for estimating these fat depots. One hundred fifty-one white male subjects had IAF, SCF, and TOTF determined by a single CT scan, skinfold and circumference measures taken and body density determined. Linear intra-correlations and factor analysis procedures were used to identify variables for inclusion in stepwise multiple regression solutions. IAF was estimated from age, waist circumference, the sum of mid-thigh and lower thigh circumferences, and vertical abdominal skinfold. SCF was estimated from age, umbilicus circumference, chest and suprailiac skinfolds. TOTF was estimated from age, body mass index (BMI), chest skinfold, and umbilicus circumference. R2 for IAF, SCF, and TOTF was .73, .77, and .86 respectively. The existing and the new equations were validated on an independent sub-sample of 51 subjects. The only existing equation that met validation criteria had a validation R2 = .67 for IAF. All three new equations met validation criteria with R2 validations of .75, .79, and .85 for IAF, SCF, and TOTF respectively. It is concluded that the new equations might be used as an inexpensive estimation of IAF, SCF, and TOTF in adult white males varying greatly in age and percent body fat.

Abdomen↗
PubMedDate not supplied

Computer simulation helps predict cerebral aneurysms.

Researchers have recently proven the ability of computer simulation to predict the behaviour of cerebral aneurysms. Accurately simulating the flow of blood within the aneurysm helps researchers to predict the growth pattern of the aneurysm and the danger of rupturing. As this tool is further developed into a practical diagnostic tool, it is expected to dramatically improve the ability of surgeons to weigh the results of alternate treatment methods. The simulation method used, computational fluid dynamics (CFD), provides much more information than current diagnostic tools, including particularly shear stress levels at various stages of the cardiac cycle, which help to pinpoint areas of aneurysm formation and growth.

Animals↗
PubMed2004

Computational protein biomarker prediction: a case study for prostate cancer.

BACKGROUND: Recent technological advances in mass spectrometry pose challenges in computational mathematics and statistics to process the mass spectral data into predictive models with clinical and biological significance. We discuss several classification-based approaches to finding protein biomarker candidates using protein profiles obtained via mass spectrometry, and we assess their statistical significance. Our overall goal is to implicate peaks that have a high likelihood of being biologically linked to a given disease state, and thus to narrow the search for biomarker candidates. RESULTS: Thorough cross-validation studies and randomization tests are performed on a prostate cancer dataset with over 300 patients, obtained at the Eastern Virginia Medical School using SELDI-TOF mass spectrometry. We obtain average classification accuracies of 87% on a four-group classification problem using a two-stage linear SVM-based procedure and just 13 peaks, with other methods performing comparably. CONCLUSIONS: Modern feature selection and classification methods are powerful techniques for both the identification of biomarker candidates and the related problem of building predictive models from protein mass spectrometric profiles. Cross-validation and randomization are essential tools that must be performed carefully in order not to bias the results unfairly. However, only a biological validation and identification of the underlying proteins will ultimately confirm the actual value and power of any computational predictions.

Biomarkers, Tumor↗
PubMed2003

Comparative analysis of avian BMAL1 and CLOCK protein sequences: a search for features associated with owl nocturnal behaviour.

Animals differ widely in the phasing of their daily rhythms with respect to daily environmental rhythms. While birds are predominantly day-active, nocturnal activity is a characteristic feature of the order Strigiformes (owls). To study the evolution of owl night-activity cDNA sequences encoding the circadian core oscillator (CCO) proteins BMAL1 and CLOCK were obtained from barn owl (Tyto alba). The predicted proteins showed high sequence identity with their Galliform homologues (BMAL1: 99%; CLOCK: 95.6%). A computer-predicted chicken BMAL1 casein kinase-1 phosphorylation site is absent from T. alba BMAL1, but also absent from homologues of other six bird species (5 orders) (night-active (n=2), day-active (n=4)) indicating no evolutionary association with night activity. Sequence differences between T. alba and Galliform CLOCK frequently involved serine and threonine residues suggesting potential differences in their phosphorylation. The length of a poly-glutamine string in the CLOCK C-terminus varied between and within 25 species (6 orders) examined, however, no discernible feature distinguishing day and night active species was found. No differences were found between day (n=5) and night (n=7)-active species (12 species, 6 orders) in a region of the PER2 protein implicated in altered rhythm phasing in humans. In conclusion the avian CCO components examined showed strong evolutionary conservation. Molecular evolution associated with owl night-activity may have involved alterations in the CCO relationship with 'output' genes rather than in the molecular structure of the CCO itself.

Amino Acid Sequence↗
PubMed2003

Structural analysis of a Lotus japonicus genome. V. Sequence features and mapping of sixty-four TAC clones which cover the 6.4 mb regions of the genome.

We determined the nucleotide sequences of 64 TAC (transformation-competent artificial chromosome) clones selected from genomic libraries of Lotus japonicus accession Miyakojima MG-20 based on the sequence information of expressed sequence tags (ESTs), cDNAs, genes and DNA markers from L. japonicus and other legumes. The length of the DNA regions sequenced in this study was 6,370,255 bp, and the total length of the L. japonicus genome sequenced so far is 32,537,698 bp together with the nucleotide sequences of 256 TAC clones previously reported. Five hundred forty-eight potential protein-encoding genes with known or predicted functions, 127 gene segments and 224 pseudogenes were assigned to the newly sequenced regions by computer prediction and similarity searches against the sequences in protein and EST databases. Based on the nucleotide sequences of the clones, simple sequence repeat length polymorphism (SSLP) or derived cleaved amplified polymorphic sequence (dCAPS) markers were generated, and each clone was genetically localized onto the linkage map of two accessions of L. japonicus, MG-20 and Gifu B-129. The sequence data, gene information and mapping information are available through the World Wide Web at http://www.kazusa.or.jp/lotus/.

Base Sequence↗
PubMed2001

A computational approach to identify genes for functional RNAs in genomic sequences.

Currently there is no successful computational approach for identification of genes encoding novel functional RNAs (fRNAs) in genomic sequences. We have developed a machine learning approach using neural networks and support vector machines to extract common features among known RNAs for prediction of new RNA genes in the unannotated regions of prokaryotic and archaeal genomes. The Escherichia coli genome was used for development, but we have applied this method to several other bacterial and archaeal genomes. Networks based on nucleotide composition were 80-90% accurate in jackknife testing experiments for bacteria and 90-99% for hyperthermophilic archaea. We also achieved a significant improvement in accuracy by combining these predictions with those obtained using a second set of parameters consisting of known RNA sequence motifs and the calculated free energy of folding. Several known fRNAs not included in the training datasets were identified as well as several hundred predicted novel RNAs. These studies indicate that there are many unidentified RNAs in simple genomes that can be predicted computationally as a precursor to experimental study. Public access to our RNA gene predictions and an interface for user predictions is available via the web.

Computational Biology↗