Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Machine learning.”

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 1,333 records · Page 74Linked to original sources
PubMed2006

Improving the accuracy of protein secondary structure prediction using structural alignment.

BACKGROUND: The accuracy of protein secondary structure prediction has steadily improved over the past 30 years. Now many secondary structure prediction methods routinely achieve an accuracy (Q3) of about 75%. We believe this accuracy could be further improved by including structure (as opposed to sequence) database comparisons as part of the prediction process. Indeed, given the large size of the Protein Data Bank (>35,000 sequences), the probability of a newly identified sequence having a structural homologue is actually quite high. RESULTS: We have developed a method that performs structure-based sequence alignments as part of the secondary structure prediction process. By mapping the structure of a known homologue (sequence ID >25%) onto the query protein's sequence, it is possible to predict at least a portion of that query protein's secondary structure. By integrating this structural alignment approach with conventional (sequence-based) secondary structure methods and then combining it with a "jury-of-experts" system to generate a consensus result, it is possible to attain very high prediction accuracy. Using a sequence-unique test set of 1644 proteins from EVA, this new method achieves an average Q3 score of 81.3%. Extensive testing indicates this is approximately 4-5% better than any other method currently available. Assessments using non sequence-unique test sets (typical of those used in proteome annotation or structural genomics) indicate that this new method can achieve a Q3 score approaching 88%. CONCLUSION: By using both sequence and structure databases and by exploiting the latest techniques in machine learning it is possible to routinely predict protein secondary structure with an accuracy well above 80%. A program and web server, called PROTEUS, that performs these secondary structure predictions is accessible at http://wishart.biology.ualberta.ca/proteus. For high throughput or batch sequence analyses, the PROTEUS programs, databases (and server) can be downloaded and run locally.

Algorithms↗
PubMed2006

Protein disorder prediction by condensed PSSM considering propensity for order or disorder.

BACKGROUND: More and more disordered regions have been discovered in protein sequences, and many of them are found to be functionally significant. Previous studies reveal that disordered regions of a protein can be predicted by its primary structure, the amino acid sequence. One observation that has been widely accepted is that ordered regions usually have compositional bias toward hydrophobic amino acids, and disordered regions are toward charged amino acids. Recent studies further show that employing evolutionary information such as position specific scoring matrices (PSSMs) improves the prediction accuracy of protein disorder. As more and more machine learning techniques have been introduced to protein disorder detection, extracting more useful features with biological insights attracts more attention. RESULTS: This paper first studies the effect of a condensed position specific scoring matrix with respect to physicochemical properties (PSSMP) on the prediction accuracy, where the PSSMP is derived by merging several amino acid columns of a PSSM belonging to a certain property into a single column. Next, we decompose each conventional physicochemical property of amino acids into two disjoint groups which have a propensity for order and disorder respectively, and show by experiments that some of the new properties perform better than their parent properties in predicting protein disorder. In order to get an effective and compact feature set on this problem, we propose a hybrid feature selection method that inherits the efficiency of uni-variant analysis and the effectiveness of the stepwise feature selection that explores combinations of multiple features. The experimental results show that the selected feature set improves the performance of a classifier built with Radial Basis Function Networks (RBFN) in comparison with the feature set constructed with PSSMs or PSSMPs that adopt simply the conventional physicochemical properties. CONCLUSION: Distinguishing disordered regions from ordered regions in protein sequences facilitates the exploration of protein structures and functions. Results based on independent testing data reveal that the proposed predicting model DisPSSMP performs the best among several of the existing packages doing similar tasks, without either under-predicting or over-predicting the disordered regions. Furthermore, the selected properties are demonstrated to be useful in finding discriminating patterns for order/disorder classification.

Amino Acid Sequence↗
PubMed2006

CRNPRED: highly accurate prediction of one-dimensional protein structures by large-scale critical random networks.

BACKGROUND: One-dimensional protein structures such as secondary structures or contact numbers are useful for three-dimensional structure prediction and helpful for intuitive understanding of the sequence-structure relationship. Accurate prediction methods will serve as a basis for these and other purposes. RESULTS: We implemented a program CRNPRED which predicts secondary structures, contact numbers and residue-wise contact orders. This program is based on a novel machine learning scheme called critical random networks. Unlike most conventional one-dimensional structure prediction methods which are based on local windows of an amino acid sequence, CRNPRED takes into account the whole sequence. CRNPRED achieves, on average per chain, Q3 = 81% for secondary structure prediction, and correlation coefficients of 0.75 and 0.61 for contact number and residue-wise contact order predictions, respectively. CONCLUSION: CRNPRED will be a useful tool for computational as well as experimental biologists who need accurate one-dimensional protein structure predictions.

Algorithms↗
PubMed2006

Predicting the effect of missense mutations on protein function: analysis with Bayesian networks.

BACKGROUND: A number of methods that use both protein structural and evolutionary information are available to predict the functional consequences of missense mutations. However, many of these methods break down if either one of the two types of data are missing. Furthermore, there is a lack of rigorous assessment of how important the different factors are to prediction. RESULTS: Here we use Bayesian networks to predict whether or not a missense mutation will affect the function of the protein. Bayesian networks provide a concise representation for inferring models from data, and are known to generalise well to new data. More importantly, they can handle the noisy, incomplete and uncertain nature of biological data. Our Bayesian network achieved comparable performance with previous machine learning methods. The predictive performance of learned model structures was no better than a naïve Bayes classifier. However, analysis of the posterior distribution of model structures allows biologically meaningful interpretation of relationships between the input variables. CONCLUSION: The ability of the Bayesian network to make predictions when only structural or evolutionary data was observed allowed us to conclude that structural information is a significantly better predictor of the functional consequences of a missense mutation than evolutionary information, for the dataset used. Analysis of the posterior distribution of model structures revealed that the top three strongest connections with the class node all involved structural nodes. With this in mind, we derived a simplified Bayesian network that used just these three structural descriptors, with comparable performance to that of an all node network.

Algorithms↗
PubMed2006

Discovering semantic features in the literature: a foundation for building functional associations.

BACKGROUND: Experimental techniques such as DNA microarray, serial analysis of gene expression (SAGE) and mass spectrometry proteomics, among others, are generating large amounts of data related to genes and proteins at different levels. As in any other experimental approach, it is necessary to analyze these data in the context of previously known information about the biological entities under study. The literature is a particularly valuable source of information for experiment validation and interpretation. Therefore, the development of automated text mining tools to assist in such interpretation is one of the main challenges in current bioinformatics research. RESULTS: We present a method to create literature profiles for large sets of genes or proteins based on common semantic features extracted from a corpus of relevant documents. These profiles can be used to establish pair-wise similarities among genes, utilized in gene/protein classification or can be even combined with experimental measurements. Semantic features can be used by researchers to facilitate the understanding of the commonalities indicated by experimental results. Our approach is based on non-negative matrix factorization (NMF), a machine-learning algorithm for data analysis, capable of identifying local patterns that characterize a subset of the data. The literature is thus used to establish putative relationships among subsets of genes or proteins and to provide coherent justification for this clustering into subsets. We demonstrate the utility of the method by applying it to two independent and vastly different sets of genes. CONCLUSION: The presented method can create literature profiles from documents relevant to sets of genes. The representation of genes as additive linear combinations of semantic features allows for the exploration of functional associations as well as for clustering, suggesting a valuable methodology for the validation and interpretation of high-throughput experimental data.

Abstracting and Indexing↗
PubMed2006

STAR: predicting recombination sites from amino acid sequence.

BACKGROUND: Designing novel proteins with site-directed recombination has enormous prospects. By locating effective recombination sites for swapping sequence parts, the probability that hybrid sequences have the desired properties is increased dramatically. The prohibitive requirements for applying current tools led us to investigate machine learning to assist in finding useful recombination sites from amino acid sequence alone. RESULTS: We present STAR, Site Targeted Amino acid Recombination predictor, which produces a score indicating the structural disruption caused by recombination, for each position in an amino acid sequence. Example predictions contrasted with those of alternative tools, illustrate STAR'S utility to assist in determining useful recombination sites. Overall, the correlation coefficient between the output of the experimentally validated protein design algorithm SCHEMA and the prediction of STAR is very high (0.89). CONCLUSION: STAR allows the user to explore useful recombination sites in amino acid sequences with unknown structure and unknown evolutionary origin. The predictor service is available from http://pprowler.itee.uq.edu.au/star.

Algorithms↗
PubMed2006

SNP-PHAGE--High throughput SNP discovery pipeline.

BACKGROUND: Single nucleotide polymorphisms (SNPs) as defined here are single base sequence changes or short insertion/deletions between or within individuals of a given species. As a result of their abundance and the availability of high throughput analysis technologies SNP markers have begun to replace other traditional markers such as restriction fragment length polymorphisms (RFLPs), amplified fragment length polymorphisms (AFLPs) and simple sequence repeats (SSRs or microsatellite) markers for fine mapping and association studies in several species. For SNP discovery from chromatogram data, several bioinformatics programs have to be combined to generate an analysis pipeline. Results have to be stored in a relational database to facilitate interrogation through queries or to generate data for further analyses such as determination of linkage disequilibrium and identification of common haplotypes. Although these tasks are routinely performed by several groups, an integrated open source SNP discovery pipeline that can be easily adapted by new groups interested in SNP marker development is currently unavailable. RESULTS: We developed SNP-PHAGE (SNP discovery Pipeline with additional features for identification of common haplotypes within a sequence tagged site (Haplotype Analysis) and GenBank (-dbSNP) submissions. This tool was applied for analyzing sequence traces from diverse soybean genotypes to discover over 10,000 SNPs. This package was developed on UNIX/Linux platform, written in Perl and uses a MySQL database. Scripts to generate a user-friendly web interface are also provided with common queries for preliminary data analysis. A machine learning tool developed by this group for increasing the efficiency of SNP discovery is integrated as a part of this package as an optional feature. The SNP-PHAGE package is being made available open source at http://bfgl.anri.barc.usda.gov/ML/snp-phage/. CONCLUSION: SNP-PHAGE provides a bioinformatics solution for high throughput SNP discovery, identification of common haplotypes within an amplicon, and GenBank (dbSNP) submissions. SNP selection and visualization are aided through a user-friendly web interface. This tool is useful for analyzing sequence tagged sites (STSs) of genomic sequences, and this software can serve as a starting point for groups interested in developing SNP markers.

Base Sequence↗
PubMed2006

Using the nucleotide substitution rate matrix to detect horizontal gene transfer.

BACKGROUND: Horizontal gene transfer (HGT) has allowed bacteria to evolve many new capabilities. Because transferred genes perform many medically important functions, such as conferring antibiotic resistance, improved detection of horizontally transferred genes from sequence data would be an important advance. Existing sequence-based methods for detecting HGT focus on changes in nucleotide composition or on differences between gene and genome phylogenies; these methods have high error rates. RESULTS: First, we introduce a new class of methods for detecting HGT based on the changes in nucleotide substitution rates that occur when a gene is transferred to a new organism. Our new methods discriminate simulated HGT events with an error rate up to 10 times lower than does GC content. Use of models that are not time-reversible is crucial for detecting HGT. Second, we show that using combinations of multiple predictors of HGT offers substantial improvements over using any single predictor, yielding as much as a factor of 18 improvement in performance (a maximum reduction in error rate from 38% to about 3%). Multiple predictors were combined by using the random forests machine learning algorithm to identify optimal classifiers that separate HGT from non-HGT trees. CONCLUSION: The new class of HGT-detection methods introduced here combines advantages of phylogenetic and compositional HGT-detection techniques. These new techniques offer order-of-magnitude improvements over compositional methods because they are better able to discriminate HGT from non-HGT trees under a wide range of simulated conditions. We also found that combining multiple measures of HGT is essential for detecting a wide range of HGT events. These novel indicators of horizontal transfer will be widely useful in detecting HGT events linked to the evolution of important bacterial traits, such as antibiotic resistance and pathogenicity.

Computational Biology↗
PubMed2006

Prediction of protein continuum secondary structure with probabilistic models based on NMR solved structures.

BACKGROUND: The structure of proteins may change as a result of the inherent flexibility of some protein regions. We develop and explore probabilistic machine learning methods for predicting a continuum secondary structure, i.e. assigning probabilities to the conformational states of a residue. We train our methods using data derived from high-quality NMR models. RESULTS: Several probabilistic models not only successfully estimate the continuum secondary structure, but also provide a categorical output on par with models directly trained on categorical data. Importantly, models trained on the continuum secondary structure are also better than their categorical counterparts at identifying the conformational state for structurally ambivalent residues. CONCLUSION: Cascaded probabilistic neural networks trained on the continuum secondary structure exhibit better accuracy in structurally ambivalent regions of proteins, while sustaining an overall classification accuracy on par with standard, categorical prediction methods.

Algorithms↗
PubMed2006

Protein ranking by semi-supervised network propagation.

BACKGROUND: Biologists regularly search DNA or protein databases for sequences that share an evolutionary or functional relationship with a given query sequence. Traditional search methods, such as BLAST and PSI-BLAST, focus on detecting statistically significant pairwise sequence alignments and often miss more subtle sequence similarity. Recent work in the machine learning community has shown that exploiting the global structure of the network defined by these pairwise similarities can help detect more remote relationships than a purely local measure. METHODS: We review RankProp, a ranking algorithm that exploits the global network structure of similarity relationships among proteins in a database by performing a diffusion operation on a protein similarity network with weighted edges. The original RankProp algorithm is unsupervised. Here, we describe a semi-supervised version of the algorithm that uses labeled examples. Three possible ways of incorporating label information are considered: (i) as a validation set for model selection, (ii) to learn a new network, by choosing which transfer function to use for a given query, and (iii) to estimate edge weights, which measure the probability of inferring structural similarity. RESULTS: Benchmarked on a human-curated database of protein structures, the original RankProp algorithm provides significant improvement over local network search algorithms such as PSI-BLAST. Furthermore, we show here that labeled data can be used to learn a network without any need for estimating parameters of the transfer function, and that diffusion on this learned network produces better results than the original RankProp algorithm with a fixed network. CONCLUSION: In order to gain maximal information from a network, labeled and unlabeled data should be used to extract both local and global structure.

Algorithms↗
PubMed2006

Automatic recognition of topic-classified relations between prostate cancer and genes using MEDLINE abstracts.

BACKGROUND: Automatic recognition of relations between a specific disease term and its relevant genes or protein terms is an important practice of bioinformatics. Considering the utility of the results of this approach, we identified prostate cancer and gene terms with the ID tags of public biomedical databases. Moreover, considering that genetics experts will use our results, we classified them based on six topics that can be used to analyze the type of prostate cancers, genes, and their relations. METHODS: We developed a maximum entropy-based named entity recognizer and a relation recognizer and applied them to a corpus-based approach. We collected prostate cancer-related abstracts from MEDLINE, and constructed an annotated corpus of gene and prostate cancer relations based on six topics by biologists. We used it to train the maximum entropy-based named entity recognizer and relation recognizer. RESULTS: Topic-classified relation recognition achieved 92.1% precision for the relation (an increase of 11.0% from that obtained in a baseline experiment). For all topics, the precision was between 67.6 and 88.1%. CONCLUSION: A series of experimental results revealed two important findings: a carefully designed relation recognition system using named entity recognition can improve the performance of relation recognition, and topic-classified relation recognition can be effectively addressed through a corpus-based approach using manual annotation and machine learning techniques.

Abstracting and Indexing↗
PubMed2006

Evaluation of clustering algorithms for gene expression data.

BACKGROUND: Cluster analysis is an integral part of high dimensional data analysis. In the context of large scale gene expression data, a filtered set of genes are grouped together according to their expression profiles using one of numerous clustering algorithms that exist in the statistics and machine learning literature. A closely related problem is that of selecting a clustering algorithm that is "optimal" in some sense from a rather impressive list of clustering algorithms that currently exist. RESULTS: In this paper, we propose two validation measures each with two parts: one measuring the statistical consistency (stability) of the clusters produced and the other representing their biological functional congruence. Smaller values of these indices indicate better performance for a clustering algorithm. We illustrate this approach using two case studies with publicly available gene expression data sets: one involving a SAGE data of breast cancer patients and the other involving a time course cDNA microarray data on yeast. Six well known clustering algorithms UPGMA, K-Means, Diana, Fanny, Model-Based and SOM were evaluated. CONCLUSION: No single clustering algorithm may be best suited for clustering genes into functional groups via expression profiles for all data sets. The validation measures introduced in this paper can aid in the selection of an optimal algorithm, for a given data set, from a collection of available clustering algorithms.

Algorithms↗
PubMed2005

Boosting alternating decision trees modeling of disease trait information.

We applied the alternating decision trees (ADTrees) method to the last 3 replicates from the Aipotu, Danacca, Karangar, and NYC populations in the Problem 2 simulated Genetic Analysis Workshop dataset. Using information from the 12 binary phenotypes and sex as input and Kofendrerd Personality Disorder disease status as the outcome of ADTrees-based classifiers, we obtained a new quantitative trait based on average prediction scores, which was then used for genome-wide quantitative trait linkage (QTL) analysis. ADTrees are machine learning methods that combine boosting and decision trees algorithms to generate smaller and easier-to-interpret classification rules. In this application, we compared four modeling strategies from the combinations of two boosting iterations (log or exponential loss functions) coupled with two choices of tree generation types (a full alternating decision tree or a classic boosting decision tree). These four different strategies were applied to the founders in each population to construct four classifiers, which were then applied to each study participant. To compute average prediction score for each subject with a specific trait profile, such a process was repeated with 10 runs of 10-fold cross validation, and standardized prediction scores obtained from the 10 runs were averaged and used in subsequent expectation-maximization Haseman-Elston QTL analyses (implemented in GENEHUNTER) with the approximate 900 SNPs in Hardy-Weinberg equilibrium provided for each population. Our QTL analyses on the basis of four models (a full alternating decision tree and a classic boosting decision tree paired with either log or exponential loss function) detected evidence for linkage (Z >or= 1.96, p < 0.01) on chromosomes 1, 3, 5, and 9. Moreover, using average iteration and abundance scores for the 12 phenotypes and sex as their relevancy measurements, we found all relevant phenotypes for all four populations except phenotype b for the Karangar population, with suggested subgroup structure consistent with latent traits used in the model. In conclusion, our findings suggest that the ADTrees method may offer a more accurate representation of the disease status that allows for better detection of linkage evidence.

Algorithms↗
PubMed2006

Towards the identification of essential genes using targeted genome sequencing and comparative analysis.

BACKGROUND: The identification of genes essential for survival is of theoretical importance in the understanding of the minimal requirements for cellular life, and of practical importance in the identification of potential drug targets in novel pathogens. With the great time and expense required for experimental studies aimed at constructing a catalog of essential genes in a given organism, a computational approach which could identify essential genes with high accuracy would be of great value. RESULTS: We gathered numerous features which could be generated automatically from genome sequence data and assessed their relationship to essentiality, and subsequently utilized machine learning to construct an integrated classifier of essential genes in both S. cerevisiae and E. coli. When looking at single features, phyletic retention, a measure of the number of organisms an ortholog is present in, was the most predictive of essentiality. Furthermore, during construction of our phyletic retention feature we for the first time explored the evolutionary relationship among the set of organisms in which the presence of a gene is most predictive of essentiality. We found that in both E. coli and S. cerevisiae the optimal sets always contain host-associated organisms with small genomes which are closely related to the reference. Using five optimally selected organisms, we were able to improve predictive accuracy as compared to using all available sequenced organisms. We hypothesize the predictive power of these genomes is a consequence of the process of reductive evolution, by which many parasites and symbionts evolved their gene content. In addition, essentiality is measured in rich media, a condition which resembles the environments of these organisms in their hosts where many nutrients are provided. Finally, we demonstrate that integration of our most highly predictive features using a probabilistic classifier resulted in accuracies surpassing any individual feature. CONCLUSION: Using features obtainable directly from sequence data, we were able to construct a classifier which can predict essential genes with high accuracy. Furthermore, our analysis of the set of genomes in which the presence of a gene is most predictive of essentiality may suggest ways in which targeted sequencing can be used in the identification of essential genes. In summary, the methods presented here can aid in the reduction of time and money invested in essential gene identification by targeting those genes for experimentation which are predicted as being essential with a high probability.

Animals↗
PubMed2006

Assessing the number of ancestral alternatively spliced exons in the human genome.

BACKGROUND: It is estimated that between 35% and 74% of all human genes undergo alternative splicing. However, as a gene that undergoes alternative splicing can have between one and dozens of alternative exons, the number of alternatively spliced genes by itself is not informative enough. An additional parameter, which was not addressed so far, is therefore the number of human exons that undergo alternative splicing. We have previously described an accurate machine-learning method allowing the detection of conserved alternatively spliced exons without using ESTs, which relies on specific features of the exon and its genomic vicinity that distinguish alternatively spliced exons from constitutive ones. RESULTS: In this study we use the above-described approach to calculate that 7.2% (+/- 1.1%) of all human exons that are conserved in mouse are alternatively spliced in both species. CONCLUSION: This number is the first estimation for the extent of ancestral alternatively spliced exons in the human genome.

Algorithms↗
PubMed2006

Ethanol sensitivity: a central role for CREB transcription regulation in the cerebellum.

BACKGROUND: Lowered sensitivity to the effects of ethanol increases the risk of developing alcoholism. Inbred mouse strains have been useful for the study of the genetic basis of various drug addiction-related phenotypes. Inbred Long-Sleep (ILS) and Inbred Short-Sleep (ISS) mice differentially express a number of genes thought to be implicated in sensitivity to the effects of ethanol. Concomitantly, there is evidence for a mediating role of cAMP/PKA/CREB signalling in aspects of alcoholism modelled in animals. In this report, the extent to which CREB signalling impacts the differential expression of genes in ILS and ISS mouse cerebella is examined. RESULTS: A training dataset for Machine Learning (ML) and Exploratory Data Analyses (EDA) was generated from promoter region sequences of a set of genes known to be targets of CREB transcription regulation and a set of genes whose transcription regulations are potentially CREB-independent. For each promoter sequence, a vector of size 132, with elements characterizing nucleotide composition features was generated. Genes whose expressions have been previously determined to be increased in ILS or ISS cerebella were identified, and their CREB regulation status predicted using the ML scheme C4.5. The C4.5 learning scheme was used because, of four ML schemes evaluated, it had the lowest predicted error rate. On an independent evaluation set of 21 genes of known CREB regulation status, C4.5 correctly classified 81% of instances with F-measures of 0.87 and 0.67 respectively for the CREB-regulated and CREB-independent classes. Additionally, six out of eight genes previously determined by two independent microarray platforms to be up-regulated in the ILS or ISS cerebellum were predicted by C4.5 to be transcriptionally regulated by CREB. Furthermore, 64% and 52% of a cross-section of other up-regulated cerebellar genes in ILS and ISS mice, respectively, were deemed to be CREB-regulated. CONCLUSION: These observations collectively suggest that ethanol sensitivity, as it relates to the cerebellum, may be associated with CREB transcription activity.

Alcoholism↗
PubMed2006

The use of genetic programming in the analysis of quantitative gene expression profiles for identification of nodal status in bladder cancer.

BACKGROUND: Previous studies on bladder cancer have shown nodal involvement to be an independent indicator of prognosis and survival. This study aimed at developing an objective method for detection of nodal metastasis from molecular profiles of primary urothelial carcinoma tissues. METHODS: The study included primary bladder tumor tissues from 60 patients across different stages and 5 control tissues of normal urothelium. The entire cohort was divided into training and validation sets comprised of node positive and node negative subjects. Quantitative expression profiling was performed for a panel of 70 genes using standardized competitive RT-PCR and the expression values of the training set samples were run through an iterative machine learning process called genetic programming that employed an N-fold cross validation technique to generate classifier rules of limited complexity. These were then used in a voting algorithm to classify the validation set samples into those associated with or without nodal metastasis. RESULTS: The generated classifier rules using 70 genes demonstrated 81% accuracy on the validation set when compared to the pathological nodal status. The rules showed a strong predilection for ICAM1, MAP2K6 and KDR resulting in gene expression motifs that cumulatively suggested a pattern ICAM1 > MAP2K6 > KDR for node positive cases. Additionally, the motifs showed CDK8 to be lower relative to ICAM1, and ANXA5 to be relatively high by itself in node positive tumors. Rules generated using only ICAM1, MAP2K6 and KDR were comparably robust, with a single representative rule producing an accuracy of 90% when used by itself on the validation set, suggesting a crucial role for these genes in nodal metastasis. CONCLUSION: Our study demonstrates the use of standardized quantitative gene expression values from primary bladder tumor tissues as inputs in a genetic programming system to generate classifier rules for determining the nodal status. Our method also suggests the involvement of ICAM1, MAP2K6, KDR, CDK8 and ANXA5 in unique mathematical combinations in the progression towards nodal positivity. Further studies are needed to identify more class-specific signatures and confirm the role of these genes in the evolution of nodal metastasis in bladder cancer.

Algorithms↗
PubMed2004

Image fusion for dynamic contrast enhanced magnetic resonance imaging.

BACKGROUND: Multivariate imaging techniques such as dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) have been shown to provide valuable information for medical diagnosis. Even though these techniques provide new information, integrating and evaluating the much wider range of information is a challenging task for the human observer. This task may be assisted with the use of image fusion algorithms. METHODS: In this paper, image fusion based on Kernel Principal Component Analysis (KPCA) is proposed for the first time. It is demonstrated that a priori knowledge about the data domain can be easily incorporated into the parametrisation of the KPCA, leading to task-oriented visualisations of the multivariate data. The results of the fusion process are compared with those of the well-known and established standard linear Principal Component Analysis (PCA) by means of temporal sequences of 3D MRI volumes from six patients who took part in a breast cancer screening study. RESULTS: The PCA and KPCA algorithms are able to integrate information from a sequence of MRI volumes into informative gray value or colour images. By incorporating a priori knowledge, the fusion process can be automated and optimised in order to visualise suspicious lesions with high contrast to normal tissue. CONCLUSION: Our machine learning based image fusion approach maps the full signal space of a temporal DCE-MRI sequence to a single meaningful visualisation with good tissue/lesion contrast and thus supports the radiologist during manual image evaluation.

Algorithms↗