Giovanni Maria Mura

A comparative study of K-Nearest Neighbour, Support Vector Machine and Multi-Layer Perceptron for Thalassemia screening

In this paper, we investigate the feasibility of two typical techniques of Pattern Recognition in the classification for Thalassemia screening. They are the Support Vector Machine (SVM) and the K-Nearest Neighbour (KNN). We compare SVM and KNN with a Multi-Layer Perceptron (MLP) classifier. We propose a two-classifier system based on SVM. The first layer is used to differentiate between pathological and non-pathological cases while the second layer is used to discriminate between two different pathologies (α-thalassemia carrier against β-thalassemia carrier) from the first output layer (pathological cases). Using the parameters sensitivity (percentage of pathologic cases correctly classified) and specificity (percentage of non-pathologic cases correctly classified), the results obtained with this analysis show that the MLP classifier gives slightly better results than SVM although the amount of data available is limited. Both techniques enable thalassemia carriers to be discriminated from healthy subjects with 95% specificity, although the sensitivity of MLP is 92% while that of SVM is 83%.

A Real-Time Classification System of Thalassemic Pathologies Based on Artificial Neural Networks

Thalassemias are pathologies that derive from genetic defects of the globin genes. The most common defects among the population affect the genes that are involved in the synthesis of α and β chains. The main aspects of these pathologies are well explained from a biochemical and genetic point of view. The diagnosis is fundamentally based on hematologic and genetic tests. A genetic analysis is particularly important to determine the carriers of α-thalassemia, whose identification by means of the hematologic parameters is more difficult in comparison with heterozygotes for β-thalassemia. This work investigates the use of artificial neural networks (ANNs) for the classification of thalassemic pathologies using the hematologic parameters resulting from hemochromocytometric analysis only. Different combinations of ANNs are reported, which allow thalassemia carriers to be discriminated from normals with 94% classification accuracy, 92% sensitivity, and 95% specificity. On the basis of these results, an automated system that allows real-time support for diagnoses is proposed. The automated system interfaces a hemochromo analyzer to a simple PC.

Glucose oxidase catalyses the reduction of O2 to H2O2 in the presence of irradiated TiO2 and isopropyl alcohol

Catalytic amounts of glucose oxidase from Aspergillus niger (GO) are active in the reduction of O2 to H2O2 in the presence of irradiated suspensions of TiO2 and isopropyl alcohol as electron donor. An explanation of this behaviour is given on the basis of the ability of the enzyme to capture electrons from the photoexcited TiO2 instead of its natural substrate, glucose. This process has a marked positive effect on both the oxidation of isopropyl alcohol to acetone and the formation of radical intermediates, which have been detected, for the first time, by EPR-spin trapping investigation.

Photodegradation of Organic Waste Coupling Hydrogenase and Titanium Dioxide

In this work the results of the study on the degradation of dairy waste and lactose with use of titanium dioxide (TiO2), as photocatalyst, are presented. The ability of TiO2 to degrade dairy waste is compared either in the presence of molecular oxygen or of a bacterial hydrogenase as electron acceptor. The enzyme-mediated H2 production rates or the O2 consumption rates are used to measure electron donor degradation. The results obtained clearly indicate that dairy waste can be degraded by the TiO2 photocatalyst. Proteins present in the dairy waste have a strong inhibitory effect on the degradation process. Indeed lactose alone can easily be degraded. When the protein extract obtained from the dairy waste was added to the lactose solution, the reaction for both electron acceptors, hydrogenase and oxygen, was inhibited. When the dairy waste solutions were diluted, there was a positive effect on the reaction rate. This was particularly true in the case of hydrogenase, and to a lesser extent in the case of oxygen acceptor. The reduction of the pH from 8 to 6 also increased H2 production when the enzyme was used.

Dissociation of human alphaB-crystallin aggregates by thiocyanate is structurally and functionally reversible

Conformational modifications and changes in the aggregation state of human αB-crystallin were investigated at different concentrations of SDS, KBr, urea, and NH4SCN and at different temperatures. Intrinsic fluorescence measurements indicated complete and reversible unfolding of the protein at 2 M NH4SCN, whereas the concentration of urea required for complete and irreversible unfolding was 6 M. Gel permeation chromatography indicated almost complete dissociation of the micelle-like aggregate of αB-crystallin in 2 M NH4SCN, but only partial dissociation into large-sized aggregates in 6 M urea. Thiocyanate-treated αB-crystallin recovered its chaperone-like activity upon dilution of the dissociating agent, whereas the urea-treated protein did not.