Maria Luisa Ganadu

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%.

Synthesis and characterization of gold(III) complexes of 1,4-benzodiazepin-2-ones. Crystal structure of trichloro-[7-chloro-1-(cyclopropylmethyl)-1,3-dihydro-5-phenyl-2H-1,4-benzodiazepin-2-one]gold(III)

Abstract The reaction of gold(III) chloride with several 1,4-benzodiazepin-2-ones, L, gives 1:1 adducts, (L)AuCl3*, which were characterized by IR, Raman and 1H NMR spectroscopy. In the title compound the coordination of the ligand, ascertained through a X-ray structure determination, was shown to occur through the 4-nitrogen atom.

Validation of protein models by a neural network approach

BackgroundThe development and improvement of reliable computational methods designed to evaluate the quality of protein models is relevant in the context of protein structure refinement, which has been recently identified as one of the bottlenecks limiting the quality and usefulness of protein structure prediction.ResultsIn this contribution, we present a computational method (Artificial Intelligence Decoys Evaluator: AIDE) which is able to consistently discriminate between correct and incorrect protein models. In particular, the method is based on neural networks that use as input 15 structural parameters, which include energy, solvent accessible surface, hydrophobic contacts and secondary structure content. The results obtained with AIDE on a set of decoy structures were evaluated using statistical indicators such as Pearson correlation coefficients, Znat, fraction enrichment, as well as ROC plots. It turned out that AIDE performances are comparable and often complementary to available state-of-the-art learning-based methods.ConclusionIn light of the results obtained with AIDE, as well as its comparison with available learning-based methods, it can be concluded that AIDE can be successfully used to evaluate the quality of protein structures. The use of AIDE in combination with other evaluation tools is expected to further enhance protein refinement efforts.

A POTENTIOMETRIC, SPECTROPHOTOMETRIC AND 1H NMR STUDY ON THE INTERACTION OF CIMETIDINE, FAMOTIDINE AND RANITIDINE WITH PLATINUM(II) AND PALLADIUM(II) METAL IONS

Abstract Spectrophotometric, potentiometric and 1H NMR results on the M-L systems [M = PdII or PtII and L = cimetidine, famotidine or ranitidine] are clearly indicative of the strong chelating ability of these antiulcerative drugs towares metal ions. In view of the great biological interest in these two metals, their coordination to such drugs should have significant implications.

Adducts and cyclometallated derivatives of palladium(II) with some 1,4-benzodiazepin-2-ones: crystal and molecular structure of trans -dichlorobis[7-chloro-1-(cyclopropylmethyl)-1,3-dihydro-5-phenyl-2H-1,4-benzodiazepin-2-one] palladium(II)

Abstract The adducts trans-L2PdCl2 (1, L = Diazepam = 7- chloro-1,3-dihydro-1-methyl-5-phenyl-2H-1,4-benzodiazepin -2-one; 5, L = Prazepam = 7-chloro-1-(cyclopropylmethyl)- 1,3-dihydro-5-phenyl-2H-1,4-benzodiazepin-2-one) were prepared by reaction of PdCl2 or (PhCN)2PdCl2 with Diazepam and Prazepam, respectively. In the adducts, the benzodiazepines act as monodentate ligands through the 4-nitrogen atom, as shown by the structure of compound 5, determined by X-ray diffraction. Two crystalline modifications have been characterized: 5a, trans-(Prazepam)2PdCl2/CHCl3 1/1, monoclinic, space group P21/n, a = 11.996(4), b = 13.678(5), c = 12.717(3) A, β = 98.83(2), Z = 2, R = 0.032; 5b, trans-(Prazepam)2PdCl2/CH2Cl2 1/1, monoclinic, space group P21/c, a = 14.074(3), b = 14.622(7), c = 19.360(10) A, β = 100.04(3), Z = 4, R = 0.076. Cyclometallated derivatives [(LH)PdCl]2, 2, L = Diazepam and 6, L = Prazepam, involving both C- and N-intramolecular coordination of the deprotonated ligands, have been obtained by reaction with Na2[PdCl4] in ethanol solution. In the dimeric species 2 and 6, the halide-bridge is easily split by reaction with Ph3P or Tl(acac), to give [(LH)·(Ph3P)PdCl], (3, 7) and [(LH)Pd(acac)] (4, 8) respectively.

Famotidine, the new antiulcero-genic agent, a potent ligand for metal ions

Potentiometric, polarographic, and spectroscopic results obtained for Cu2+ and Ni(2+)-famotidine systems clearly indicated that this anti-ulcerogenic drug is a very potent chelating agent able to coordinate cupric ion that was at pH below 2. This drug exhibits excellent histamine H2 receptor blocking effects and its effective coordination to metal ions may have significant biological implications. Famotidine is found to be a very effective ligand for Ni2+ ions also.

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.

METAL COMPLEXES OF CIMETIDINE. SYNTHESIS, X-RAY STRUCTURE DETERMINATION AND SEMIEMPIRICAL CALCULATIONS ON THE CIMETIDINATECOPPER(II)+ CATION

Abstract The addition of a methanolic solution of cimetidine (1) to a methanolic solution of M2+ cations (M = Co, NJ, Cu, Zn) affords the cationic complexes [M(1)2]2+. In the case of M = Cu the addition of KOH in the reaction medium at 60 °C gives the [Cu(2′)]+ cation, where 2′ is an anionic ligand resulting from deprotonation of a cimetidine molecule modified by methanolic solvolysis of the nitrilic function. The X-ray structure characterization of [Cu(2′)]X·0.5H2O has been performed for X = ClO4− (5) and I− (6). Compound 5 is monoclinic, space group C2/c with a=20.732(8), b=7.471(3), c=23.734(5) A, β 100.76(3)°, Z=8, R=0.034, Rw=0.045 for 1767 reflections with I>3σ(I). Compound 6 is monoclinic, space group C2/c with a=20.736(3), b=7.426(3), c=22.786(2) A, β=99.65(1)°, Z=8, R=0.029, Rw=0.045 for 2498 reflections with I>3σ(I). In both compounds the 2′ anion acts as a tetradentate ligand coiled around the almost square planar metal center. Quantomechanical semiempirical calculations (CNDO/ 2) have been carried out on simple models of 2′, 5 and 6.

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.

An 1H NMR and potentiometric study of the interaction between platinum(II) and cimetidine

Abstract The platinum(II)-cimetidine system was studied in aqueous solutions by potentiometric and 1H NMR methods. Evidence is given of the formation of 1:1 and 1:2 platinum(II)-ligand complexes, with different degrees of protonation. A bonding scheme is proposed on the basis of NMR spectra.