GPCRTree:online hierarchical classification of GPCR function

G protein-coupled receptors (GPCRs) play important physiological roles transducing extracellular signals into intracellular responses. Approximately 50% of all marketed drugs target a GPCR. There remains considerable interest in effectively predicting the function of a GPCR from its primary sequence.

Efficient training of RBF networks for classification.

Radial Basis Function networks with linear outputs are often used in regression problems because they can be substantially faster to train than Multi-layer Perceptrons. For classification problems, the use of linear outputs is less appropriate as the outputs are not guaranteed to represent probabilities. We show how RBFs with logistic and softmax outputs can be trained efficiently using the Fisher scoring algorithm. This approach can be used with any model which consists of a generalised linear output function applied to a model which is linear in its parameters. We compare this approach with standard non-linear optimisation algorithms on a number of datasets.

Bayesian classification with Gaussian processes

We consider the problem of assigning an input vector bfx to one of m classes by predicting P(c|bfx) for c = 1, ldots, m. For a two-class problem, the probability of class 1 given bfx is estimated by s(y(bfx)), where s(y) = 1/(1 + e^-y). A Gaussian process prior is placed on y(bfx), and is combined with the training data to obtain predictions for new bfx points. We provide a Bayesian treatment, integrating over uncertainty in y and in the parameters that control the Gaussian process prior; the necessary integration over y is carried out using Laplace's approximation. The method is generalized to multi-class problems (m >2) using the softmax function. We demonstrate the effectiveness of the method on a number of datasets.

Efficient training of RBF networks for classification

Radial Basis Function networks with linear outputs are often used in regression problems because they can be substantially faster to train than Multi-layer Perceptrons. For classification problems, the use of linear outputs is less appropriate as the outputs are not guaranteed to represent probabilities. In this paper we show how RBFs with logistic and softmax outputs can be trained efficiently using algorithms derived from Generalised Linear Models. This approach is compared with standard non-linear optimisation algorithms on a number of datasets.

Bayesian classification with Gaussian processes

We consider the problem of assigning an input vector to one of m classes by predicting P(c|x) for c=1,...,m. For a two-class problem, the probability of class one given x is estimated by s(y(x)), where s(y)=1/(1+e-y). A Gaussian process prior is placed on y(x), and is combined with the training data to obtain predictions for new x points. We provide a Bayesian treatment, integrating over uncertainty in y and in the parameters that control the Gaussian process prior the necessary integration over y is carried out using Laplace's approximation. The method is generalized to multiclass problems (m>2) using the softmax function. We demonstrate the effectiveness of the method on a number of datasets.

Sensing and control of adipocyte function

Obesity has become a global epidemic. Approximately 15% of the world population is either overweight or obese. This figure rises to 75% in many westernised countries including the United Kingdom. Health costs in the UK to treat obesity and associated disease are conservatively estimated at 6% of the National Health Service (NHS) budget equating to 3.33 billion Euros. Excess adiposity, especially in visceral depots, increases the risk of type 2 diabetes, cardiovascular disease, gall stones, hypertension and cancer. Type 2 diabetes mellitus accounts for >90% of all cases of diabetes of which the majority can be attributed to increased adiposity, and approximately 70% of cardiovascular disease has been attributed to obesity in the US. Weight loss reduces risk of these complications and in some cases can eliminate the condition. However, weight loss by conventional non-medicated methods is often unsuccessful or promptly followed by weight regain. This thesis has investigated adipocytes development and adipokine signalling with a view to enhance the understanding of tissue functionality and to identify possible targets or pathways for therapeutic intervention. Adipocyte isolation from human tissue samples was undertaken for these investigative studies, and the methodology was optimised. The resulting isolates of pre-adipocytes and mature adipocytes were characterised and evaluated. Major findings from these studies indicate that mature adipocytes undergo cell division post terminal differentiation. Gene studies indicated that subcutaneous adipose tissue exuded greater concentrations and fluctuations of adipokine levels than visceral adipose tissue, indicating an important adiposensing role of subcutaneous adipose tissue. It was subsequently postulated that the subcutaneous depot may provide the major focus for control of overall energy balance and by extension weight control. One potential therapeutic target, 11ß-hydrosteroid dehydrogenase (11ß-HSD1) was investigated, and prospective inhibitors of its action were considered (BVT1, BVT2 and AZ121). Selective reduction of adiposity of the visceral depot was desired due to its correlation with the detrimental effects of obesity. However, studies indicated that although the visceral depot tissue was not unaffected, the subcutaneous depot was more susceptible to therapeutic inhibition by these compounds. This was determined to be a potentially valuable therapeutic intervention in light of previous postulations regarding long-term energy control via the subcutaneous tissue depot.

Hierarchical classification of G-protein-coupled receptors with data-driven selection of attributes and classifiers

We address the important bioinformatics problem of predicting protein function from a protein's primary sequence. We consider the functional classification of G-Protein-Coupled Receptors (GPCRs), whose functions are specified in a class hierarchy. We tackle this task using a novel top-down hierarchical classification system where, for each node in the class hierarchy, the predictor attributes to be used in that node and the classifier to be applied to the selected attributes are chosen in a data-driven manner. Compared with a previous hierarchical classification system selecting classifiers only, our new system significantly reduced processing time without significantly sacrificing predictive accuracy.

On the hierarchical classification of G protein-coupled receptors

MOTIVATION: G protein-coupled receptors (GPCRs) play an important role in many physiological systems by transducing an extracellular signal into an intracellular response. Over 50% of all marketed drugs are targeted towards a GPCR. There is considerable interest in developing an algorithm that could effectively predict the function of a GPCR from its primary sequence. Such an algorithm is useful not only in identifying novel GPCR sequences but in characterizing the interrelationships between known GPCRs. RESULTS: An alignment-free approach to GPCR classification has been developed using techniques drawn from data mining and proteochemometrics. A dataset of over 8000 sequences was constructed to train the algorithm. This represents one of the largest GPCR datasets currently available. A predictive algorithm was developed based upon the simplest reasonable numerical representation of the protein's physicochemical properties. A selective top-down approach was developed, which used a hierarchical classifier to assign sequences to subdivisions within the GPCR hierarchy. The predictive performance of the algorithm was assessed against several standard data mining classifiers and further validated against Support Vector Machine-based GPCR prediction servers. The selective top-down approach achieves significantly higher accuracy than standard data mining methods in almost all cases.