Search

Motivated by the observation that network-based methods for the automatic prediction of protein functions can greatly benefit from exploiting both the similarity between proteins and the similarity between functional classes (as encoded, e.g., in the Gene Ontology), in this paper we propose a novel approach to the problem, based on the notion of a “graph transduction game.” We envisage a (non-cooperative) game, played over a graph, where the players (graph vertices) represent proteins, the functional classes correspond to the (pure) strategies, and protein- and function-level similarities are combined into a suitable payoff function. Within this formulation, Nash equilibria turn out to provide consistent functional labelings of proteins, and we use classical replicator dynamics from evolutionary game theory to find them. To test the effectiveness of our approach we conducted experiments on five different organisms and three ontologies, and the results obtained show that our method compares favorably with state-of-the-art algorithms.

Several problems in computational biology and medicine are modelled as learning problems in graphs, where nodes represent the biological entities to be studied, e.g. proteins, and connections dierent kinds of relationships among them, e.g. protein-protein interactions. In this context, classes are usually characterized by a high imbalance, i.e. positive examples for a class are much less than those negative. Although several works studied this problem, no graphbased software designed to explicitly take into account the label imbalance in biological networks is available. We propose COSNet, an R package to serve this purpose. COSNet deals with the label imbalance problem by implementing a novel parametric model of Hopeld Network (HN), whose output levels and activation thresholds of neurons are parameters to be automatically learnt. Due to the quasi linear time complexity, COSNet nicely scales when the number of instances is large, and application examples to challenging problems in biomedicine show the eciency and the accuracy of the proposed library.

Several solutions have been proposed to exploit the availability of heterogeneous sources of biomolecular data for gene function prediction, but few attention has been dedicated to the evaluation of the potential improvement in functional classification results that could be achieved through data fusion realized by means of ensemble-based techniques. In this contribution we test the performance of several ensembles of support vector machine (SVM) classifiers, in which each component learner has been trained on different types of bio-molecular data, and then combined to obtain a consensus prediction using different aggregation techniques. Experimental results using data obtained with different high-throughput biotechnologies show that simple ensemble methods outperform both learning machines trained on single homogeneous types of bio-molecular data, and vector space integration methods.

The analysis of non-coding DNA regulatory regions is one of the most challenging open problems in computational biology. In this paper we investigate whether we can predict functional information about genes by using information extracted from their sequences together with expression data. We formalize this problem as a classification problem, and we apply Support Vector Machines (SVMs) with non-linear kernels to predict classes of co-expressed genes obtained from clustering procedures. SVMs are trained using information about selected motifs extracted from DNA regulatory regions through combinatorial and statistical methods. In our experiments, we show that functional classes of genes can be predicted from biological sequence data in Saccharomices cerevisiae, achieving results competitive with those recently presented in the literature.

Objective:: Clustering algorithms may be applied to the analysis of DNA microarray data to identify novel subgroups that may lead to new taxonomies of diseases defined at bio-molecular level. A major problem related to the identification of biologically meaningful clusters is the assessment of their reliability, since clustering algorithms may find clusters even if no structure is present. Methodology:: Recently, methods based on random ''perturbations'' of the data, such as bootstrapping, noise injections techniques and random subspace methods have been applied to the problem of cluster validity estimation. In this framework, we propose stability measures that exploits the high dimensionality of DNA microarray data and the redundancy of information stored in microarray chips. To this end we randomly project the original gene expression data into lower dimensional subspaces, approximately preserving the distance between the examples according to the Johnson-Lindenstrauss (JL) theory. The stability of the clusters discovered in the original high dimensional space is estimated by comparing them with the clusters discovered in randomly projected lower dimensional subspaces. The proposed cluster-stability measures may be applied to validate and to quantitatively assess the reliability of the clusters obtained by a large class of clustering algorithms. Results and conclusion:: We tested the effectiveness of our approach with high dimensional synthetic data, whose distribution is a priori known, showing that the stability measures based on randomized maps correctly predict the number of clusters and the reliability of each individual cluster. Then we showed how to apply the proposed measures to the analysis of DNA microarray data, whose underlying distribution is unknown. We evaluated the validity of clusters discovered by hierarchical clustering algorithms in diffuse large B-cell lymphoma (DLBCL) and malignant melanoma patients, showing that the proposed reliability measures can support bio-medical researchers in the identification of stable clusters of patients and in the discovery of new subtypes of diseases characterized at bio-molecular level.

Support vector machines (SVMs), and other supervised learning techniques have been experimented for the bio-molecular diagnosis of malignancies, using also feature selection methods. The classification task is particularly difficult because of the high dimensionality and low cardinality of gene expression data. In this paper we investigate a different approach based on random subspace ensembles of SVMs: a set of base learners is trained and aggregated using subsets of features randomly drawn from the available DNA microarray data. Experimental results on the colon adenocarcinoma diagnosis and medulloblastoma clinical outcome prediction show the effectiveness of the proposed approach.

One of the main factors a3ecting the e3ectiveness of error correcting output coding (ECOC) methods for classi4cation is the dependence among the errors of the computed codeword bits. We present an extensive experimental work for evaluating the dependence among output errors of the decomposition unit in ECOC learning machines. In particular, we apply measures based on mutual information to compare the dependence of ECOC multi-layer perceptron (ECOC MLP), made up by a single multi-input multi-output MLP, and ECOC ensembles made up by a set of independent and parallel dichotomizers (ECOC PND). Moreover, the experimentation analyzes the relationship between the architecture, the dependence among output errors and the performances of ECOC learning machines. The results show that the dependence among computed codeword bits is signi4cantly smaller for ECOC PND, pointing out that ensembles of independent parallel dichotomizers are better suited for implementing ECOC classi4cation methods. The experimental results suggest new architectures of ECOC learning machines to improve the independence among output errors and the diversity between base learners. c

The classification of 242 measurements in 14 classes is attempted using two different classification approaches. Measurements have been performed with a commercial electronic nose (EN) comprising 11 chemical sensors on extra-virgin olive oils of 14 different geographical provenances. As we deal with a relatively small data set and a big number of classes, the classification task is quite demanding. We first tackled the global classification task using a single multilayer perceptron (MLP), which gave a misclassification rate of 25%. In order to improve the performance, we studied two different approaches based on ensembles of learning machines, which decompose the classification in subtasks. In the first approach, a classification tree was constructed using a priori knowledge (geographical origin) for the formation of sensible superclasses (union of single classes). At each classification node we both used MLPs and SIMCA (soft independent modeling of class analogy). The second approach applies a learning machine called parallel nonlinear dichotomizers (PND) that is based on the decomposition of a K-class classification problem in a set of two-class tasks. A binary codeword is assigned to each class and each bit is learned by a dichotomizer (implemented by a dedicated MLP). In the reconstruction stage, a pattern is assigned to the class whose codeword is most similar (e.g. in L1 norm) to the output of the set of dichotomizers. We achieved the best results (misclassification error rate of about 10%) using a decomposition based on error correcting output codes (ECOC).

Dioxygen adducts of bis(2-hydroxy-1-naphthyl-ideneimine-3-propyl)amine cobalt(II) complexes, in which either a hydrogen atom or a methyl group are present on the amino nitrogen atom of the ligand, were obtained and studied by EPR spectroscopy. The study shows an unexpectedly strong effect of the solvent(toluene or dimethylsulfoxide) on the stability of the adducts. The EPR study carried out at room and lower temperatures gave indications that an intramolecular process plays a major role in the decay of the cobaltoxygen species.

The reactivity of RhCl(PCy 3 ) 2 in the solid state towards O 2 , CO, and H 2 was investigated by ESR and IR spectroscopies and compared with that in solution. The ‘decomposition’ reaction occuring upon exposure to air produces superoxo species by dioxygen coordination. This leads to auto-oxidation of the coordinated PCy 3 , which is partially dissociated from the complex. This behaviour is quite different from that in solution, where a dioxygen adduct is formed. The ability of the complex in activating O 2 in the solid state has been related to the existence of polynuclear species. No substantial difference has been found for the reactivity of the complex in solution and in the solid state towards CO and H 2 , except that the treatment with CO allowed to evidence Rh(II) impurities contained in the product.

Several Rh(I) compounds used in homogeneous hydrogenation and isomerization catalysis and some of their heterogenized derivatives have been investigated by the X-ray photoelectron spectroscopy (XPS) technique. XPS measurements both on polymer-bound rhodium complexes and on mononuclear Rh(I) complexes with monomeric ligands taken as reference compounds and used as precursors in the preparation of heterogenized catalysts, as well as some other Rh complexes structurally similar to such precursors, show, from Rh 3d spectra, the presence of several oxidation states of rhodium (i.e., +1 and higher), the higher oxidized being generally the major component in the surface layers. The extent of the oxidation phenomenon increased with time and was dependent on the structure and nature of ligands (e.g., RhCl(CO)(PPh3)2 being the most stable toward surface oxidation).

The behaviour of RhCl(PCy 3 ) 2 in the solid state towards O 2 , Co, and H 2 was investigated. Whereas no reaction occurred with dioxygen and dihydrogen, treatment with carbon monoxide led to the formation of RhCl 2 (CO)(PCy 3 ) 2 , which is the first example of a paramagnetic carbonyl Rh(II) derivative. The product is rather labile but the life-time in the solid state was long enough to allow the spectroscopic study of the decay process. ESR and IR spectra indicated a disproportionation reaction to Rh(I) and Rh(II) carbonyl species.

The role and the effect of iodide promoters on the catalytic activity and selectivity of the ruthenium-catalyzed homologation of methyl acetate to ethyl acetate was studied. A significant cation effect in determining the distribution of the reaction products was observed. Alkaline cations and ammonium or tetraalkylammonium cations favour the simple carbonylation reaction rather than the homologation, improving the selectivity to acetic acid but also decreasing the formation of secondary products. The water formed in the homologation reaction is mostly consumed in the water-gas shift reaction, which is also favoured by the presence of alkaline or ammonium cations.

Complexes of ruthenium(II) and rhodium(I) with linear polymeric ligands such as poly(acrylic acid), some alternate copolymers of maleic acid with vinyl monomers (ethylene, benzylvinylether, and vinyl alcohol) and poly-β-diketones (polymethacroylacetone) have been prepared starting with RuH2(PPh3)4, RuH2CO(PPh3)3, and RhH(PPh3)4. The coordination of the metal units to the macromolecular matrices occurs with displacement of one hydride group and, on the average, of more than one triphenylphosphine ligand per metal atom. The “coordinatively unsaturated” metal species so formed along the polymeric matrices give to these complexes high catalytic activity in hydrogenation and isomerisation of olefins under mild conditions.

The electrochemical behaviour in aprotic solvent of the complexes {M[bis-(2-hydroxy-l-naphthylideneimine-3-propyl)amine]}, where M = Mn(II), Co(II), Fe(II), Ni(II) and Cu(II) is reported. The complexes were prepared and characterized by elemental analysis, infrared and visible spectroscopy and magnetic susceptibility measurements. In addition the reactivity towards dioxygen of the Mn(II), Fe(II) and Co(II) derivatives was investigated, mainly by cyclic voltammetry and gas-volumetric uptake measurements. The results indicate that the Co(II) complexes are able to add dioxygen reversibly, while Mn(II) and Fe(II) compounds undergo an irreversible oxygenation process. The pathway of the dioxygenation processes is tentatively interpreted on the basis of the electrochemical responses. The results confirm that the location of the oxidation potential allows one to predict whether a compound is able to react with dioxygen, but it is not sufficient to predict whether the dioxygenation reaction proceeds reversibly.

The study of metal complexes able to react with dioxygen has aroused great interest in recent years. t001. Oxidation Potential of the [M(NAPRDPT)] Complexes from Cyclic Voltammetry. Complex E°II′/III/V [Mn(NAPHDPT)] −0.31 [MN(NAPMeDPT)] −0.31 [Fe(NAPHDPT)] −0.32 [Fe(NAPMeDPT)] −0.27 [Co(NAPHDPT)] −0.37 [Co(NAPMeDPT)] −0.23 [Ni(NAPHDPT)] +0.35 [Ni(NAPMeDPT)] +0.40 [Cu(NAPHDPT)] +0.751 Cu(NAPMeDPT)] +0.861 1 Peak potential values at 0.2 V sec−1. Particular attention has been paid to those derivatives which take up dioxygen reversibly because they can mimic biological oxygen carriers [1]. In an attempt to find the parameters able to give some rationalization on the oxygenation reactions we have previously studied the behaviour towards dioxygenation of a series of five-coordinated metal complexes with O2N3 donor set (namely [M(SALRDPT)]) by electrochemical and X-ray diffraction techniques [2–5]. We wish to report here on the behaviour of the complexes [M(NAPRDPT)] having the same O2N3 donor set. M = Mn(II), Fe(II), Co(II), Ni(II), Cu(II) R = H, Me As in the case of SAL derivatives, all the NAP compounds undergo in DMSO solution a quasi-reversible one-electron anodic oxidation, except for copper(II) compounds, which are irreversibly oxidized (Table I). The comparison with SAL complexes shows that NAP derivatives are more easily oxidizable. The reaction with dioxygen in DMSO solution was followed by voltammetric techniques. The results indicate that [Co(NAPRDPT)] compounds are able to add dioxygen reversibly. For the manganese(II) and iron(II) complexes irreversible addition occurs, with formation of different oxygenated products. Copper(II) and nickel(II) complexes do not react with dioxygen The equilibrium constant of the reaction: [Co(NAPMeDPT)] + O2 ⇄ [Co(NAPMeDPT)] · O2 in DMSO at 20 °C resulted (1.0 ± 0.5) × 104 dm3 mol−1. At least for these types of pentadentate complexes it is possible to state that the location of the oxidation potential allows one to predict whether a compound is able to react with dioxygen but it is not sufficient to predict whether the dioxygenation reaction proceeds reversibly. The manganese(II), iron(II) and cobalt(II) complexes were ESR inactive both as powders or in degassed solutions. By exposure to O2 of toluene solutions of the [Co(NAPMeDPT)] or [Co(NAPHDPT)] complexes strong ESR signals were recorded, characterized by g-factor values of 2.022 and 2.037 respectively. The [Co(NAPHDPT)] adduct signal exhibited to Co hyperfine interaction, whereas the [Co(NAPMeDPT)] one did not, due to the rotation of the methyl group in this latter system. The ESR spectra have been related to metal species reversibly coordinating O2 which also showed a different spontaneous decaying process. The IR spectra of solid samples or homogeneous solutions of the different complexes showed significant changes due to O2 coordination. Hypotheses on the nature of the reversibly and irreversibly coordinating O2 species have been made on the basis of the frequencies of the IR absorption.