International Journal of Neural Systems

We model dependencies between m multivariate continuous-valued information sources by a combination of (i) a generalized canonical correlations analysis (gCCA) to reduce dimensionality while preserving dependencies in m - 1 of them, and (ii) summarizing dependencies with the remaining one by associative clustering. This new combination of methods avoids multiway associative clustering which would require a multiway contingency table and hence suffer from curse of dimensionality of the table. The method is applied to summarizing properties of yeast stress by searching for dependencies (commonalities) between expression of genes of baker's yeast Saccharomyces cerevisiae in various stressful treatments, and summarizing stress regulation by finally adding data about transcription factor binding sites.

We focus on the problem of prediction with confidence and describe a recently developed learning algorithm called transductive confidence machine for making qualified region predictions. Its main advantage, in comparison with other classifiers, is that it is well-calibrated, with number of prediction errors strictly controlled by a given predefined confidence level. We apply the transductive confidence machine to the problems of acute leukaemia and ovarian cancer prediction using microarray and proteomics pattern diagnostics, respectively. We demonstrate that the algorithm performs well, yielding well-calibrated and informative predictions whilst maintaining a high level of accuracy.

In the study of in silico functional genomics, improving the performance of protein function prediction is the ultimate goal for identifying proteins associated with defined cellular functions. The classical prediction approach is to employ pairwise sequence alignments. However this method often faces difficulties when no statistically significant homologous sequences are identified. An alternative way is to predict protein function from sequence-derived features using machine learning. In this case the choice of possible features which can be derived from the sequence is of vital importance to ensure adequate discrimination to predict function. In this paper we have successfully selected biologically significant features for protein function prediction. This was performed using a new feature selection method (FrankSum) that avoids data distribution assumptions, uses a data independent measurement (p-value) within the feature, identifies redundancy between features and uses an appropiate ranking criterion for feature selection. We have shown that classifiers generated from features selected by FrankSum outperforms classifiers generated from full feature sets, randomly selected features and features selected from the Wrapper method. We have also shown the features are concordant across all species and top ranking features are biologically informative. We conclude that feature selection is vital for successful protein function prediction and FrankSum is one of the feature selection methods that can be applied successfully to such a domain.

Feeling the pulse on the wrist is the regular diagnostic method in traditional Chinese medicine. However it is natural to ask whether there is any difference between feeling the pulse on the wrist or at any other part of the body: such as the fingertips at which it is easily measured by electronic devices. We employ a series of neural networks to model blood pressure propagation from the wrist to the fingertip. In order to avoid the problem of over-fitting we apply information theoretic criterion to determine the optimal model in these networks and then apply surrogate data method to the residuals in this model. We demonstrate the application of this method to recordings of human pulse in six subjects. Our result indicates that there is no significant difference between pulse waveform measure on the lateral arterial artery (wrist) and at the fingertip.

Similarity search for protein 3D structures become complex and computationally expensive due to the fact that the size of protein structure databases continues to grow tremendously. Recently, fast structural similarity search systems have been required to put them into practical use in protein structure classification whilst existing comparison systems do not provide comparison results on time.

Our approach uses multi-step processing that composes of a preprocessing step to represent geometry of protein structures with spatial objects, a filter step to generate a small candidate set using approximate topological string matching, and a refinement step to compute a structural alignment. This paper describes the preprocessing and filtering for fast similarity search using the discovery of topological patterns of secondary structure elements based on spatial relations. Our system is fully implemented by using Oracle 8i spatial. We have previously shown¹ that our approach has the advantage of speed of performance compared with other approach such as DALI. This work shows that the discovery of topological relations of secondary structure elements in protein structures by using spatial relations of spatial databases is practical for fast structural similarity search for proteins.

Reconstruction of genetic regulatory networks from time series data of gene expression patterns is an important research topic in bioinformatics. Probabilistic Boolean Networks (PBNs) have been proposed as an effective model for gene regulatory networks. PBNs are able to cope with uncertainty, corporate rule-based dependencies between genes and discover the sensitivity of genes in their interactions with other genes. However, PBNs are unlikely to use directly in practice because of huge amount of computational cost for obtaining predictors and their corresponding probabilities. In this paper, we propose a multivariate Markov model for approximating PBNs and describing the dynamics of a genetic network for gene expression sequences. The main contribution of the new model is to preserve the strength of PBNs and reduce the complexity of the networks. The number of parameters of our proposed model is O(n²) where n is the number of genes involved. We also develop efficient estimation methods for solving the model parameters. Numerical examples on synthetic data sets and practical yeast data sequences are given to demonstrate the effectiveness of the proposed model.

In this paper a novel approach is introduced for modeling and clustering gene expression time-series. The radial basis function neural networks have been used to produce a generalized and smooth characterization of the expression time-series. A co-expression coefficient is defined to evaluate the similarities of the models based on their temporal shapes and the distribution of the time points. The profiles are grouped using a fuzzy clustering algorithm incorporated with the proposed co-expression coefficient metric. The results on artificial and real data are presented to illustrate the advantages of the metric and method in grouping temporal profiles. The proposed metric has also been compared with the commonly used correlation coefficient under the same procedures and the results show that the proposed method produces better biologicaly relevant clusters.