Semeion Research Center

Rome, Italy

Semeion Research Center

Rome, Italy
Time filter
Source Type

Coppede F.,University of Pisa | Grossi E.,Semeion Research Center | Migheli F.,University of Pisa | Migliore L.,University of Pisa
BMC Medical Genomics | Year: 2010

Background. Studies in mothers of Down syndrome individuals (MDS) point to a role for polymorphisms in folate metabolic genes in increasing chromosome damage and maternal risk for a Down syndrome (DS) pregnancy, suggesting complex gene-gene interactions. This study aimed to analyze a dataset of genetic and cytogenetic data in an Italian group of MDS and mothers of healthy children (control mothers) to assess the predictive capacity of artificial neural networks assembled in TWIST system in distinguish consistently these two different conditions and to identify the variables expressing the maximal amount of relevant information to the condition of being mother of a DS child. The dataset consisted of the following variables: the frequency of chromosome damage in peripheral lymphocytes (BNMN frequency) and the genotype for 7 common polymorphisms in folate metabolic genes (MTHFR 677C>T and 1298A>C, MTRR 66A>G, MTR 2756A>G, RFC1 80G>A and TYMS 28bp repeats and 1494 6bp deletion). Data were analysed using TWIST system in combination with supervised artificial neural networks, and a semantic connectivity map. Results. TWIST system selected 6 variables (BNMN frequency, MTHFR 677TT, RFC1 80AA, TYMS 1494 6bp +/+, TYMS 28bp 3R/3R and MTR 2756AA genotypes) that were subsequently used to discriminate between MDS and control mothers with 90% accuracy. The semantic connectivity map provided important information on the complex biological connections between the studied variables and the two conditions (being MDS or control mother). Conclusions. Overall, the study suggests a link between polymorphisms in folate metabolic genes and DS risk in Italian women. © 2010 Coppedè et al; licensee BioMed Central Ltd.

Tabaton M.,University of Genoa | Odetti P.,University of Genoa | Cammarata S.,Galliera Hospital | Borghi R.,University of Genoa | And 4 more authors.
Journal of Alzheimer's Disease | Year: 2010

The search for markers that are able to predict the conversion of amnestic mild cognitive impairment (aMCI) to Alzheimer's disease (AD) is crucial for early mechanistic therapies. Using artificial neural networks (ANNs), 22 variables that are known risk factors of AD were analyzed in 80 patients with aMCI, for a period spanning at least 2 years. The cases were chosen from 195 aMCI subjects recruited by four Italian Alzheimer's disease units. The parameters of glucose metabolism disorder, female gender, and apolipoprotein E ε3/ε4 genotype were found to be the biological variables with high relevance for predicting the conversion of aMCI. The scores of attention and short term memory tests also were predictors. Surprisingly, the plasma concentration of amyloid-β42 had a low predictive value. The results support the utility of ANN analysis as a new tool in the interpretation of data from heterogeneous and distinct sources. © 2010 - IOS Press and the authors. All rights reserved.

Eller-Vainicher C.,University of Milan | Zhukouskaya V.V.,University of Milan | Zhukouskaya V.V.,Belarusian State Medical University | Tolkachev Y.V.,Republic Clinical Hospital of Medical Rehabilitation | And 6 more authors.
Diabetes Care | Year: 2011

OBJECTIVE - To investigate factors associated with bone mineral density (BMD) in type 1 diabetes by classic statistic and artificial neural networks. RESEARCH DESIGN AND METHODS - A total of 175 eugonadal type 1 diabetic patients (age 32.8 ± 8.4 years) and 151 age- and BMI-matched control subjects (age 32.6 ± 4.5 years) were studied. In all subjects, BMI and BMD (as Z score) at the lumbar spine (LS-BMD) and femur (F-BMD) were measured. Daily insulin dose (DID), age at diagnosis, presence of complications, creatinine clearance (ClCr), and HbA 1c were determined. RESULTS - LS- and F-BMD levels were lower in patients (20.11 ± 1.2 and 20.32 ± 1.4, respectively) than in control subjects (0.59 ± 1, P < 0.0001, and 0.63 ± 1, P < 0.0001, respectively). LS-BMD was independently associated with BMI and DID, whereas F-BMD was associated with BMI and ClCr. The cutoffs for predicting low BMD were as follows: BMI <23.5 kg/m 2, DID >0.67 units/kg, and ClCr <88.8 mL/min. The presence of all of these risk factors had a positive predictive value, and their absence had a negative predictive value for low BMD of 62.9 and 84.2%, respectively. Data were also analyzed using the TWIST system in combination with supervised artificial neural networks and a semantic connectivity map. The TWIST system selected 11 and 12 variables for F-BMD and LS-BMD prediction, which discriminated between high and low BMD with 67 and 66% accuracy, respectively. The connectivity map showed that low BMD at both sites was indirectly connected with HbA1c through chronic diabetes complications. CONCLUSIONS - In type 1 diabetes, low BMD is associated with low BMI and low ClCr and high DID. Chronic complications negatively influence BMD. © 2011 by the American Diabetes Association.

Ferilli G.,IULM University | Sacco P.L.,IULM University | Teti E.,Bocconi University | Buscema M.,Semeion Research Center | Buscema M.,University of Colorado at Denver
Expert Systems with Applications | Year: 2016

Working on the top 100 Interbrand world corporate brands dataset over the 10-years period 2001–10, we analyze the relative positioning of country brands as derived from the structural characteristics of the corresponding portfolios of top corporate brands. We find that the structural complexity of both sector and country variables are not correlated with brand equity. Moreover, we apply an innovative ANN methodology, AutoCM, to build the Minimum Spanning Tree (MST) of the multi-dimensional similarities among the top corporate brands structures at country level, and carry out a further related analysis in terms of the so called Maximum Regular Graph (MRG). We find that while the USA dominates the ranking of top brands at a global level, it does not have a central positioning in the MST and MRG, whereas Germany and other European and Far-Eastern countries do. We show how these results may have significant implications for the strategic intelligence analysis of country and corporate brands, and of their inter-relatedness. Moreover, we illustrate how AutoCM qualifies as a new computational approach that usefully expands the toolbox of scholars and analysts in corporate and country branding in a relevant, as yet unexplored direction. © 2016 Elsevier Ltd

Buscema M.,Semeion Research Center | Penco S.,Niguarda Ca Granda Hospital | Grossi E.,Bracco SpA
Neurology Research International | Year: 2012

Background. Complex diseases like amyotrophic lateral sclerosis (ALS) implicate phenotypic and genetic heterogeneity. Therefore, multiple genetic traits may show differential association with the disease. The Auto Contractive Map (AutoCM), belonging to the Artificial Neural Network (ANN) architecture, spatializes the correlation among variables by constructing a suitable embedding space where a visually transparent and cognitively natural notion such as closeness among variables reflects accurately their associations. Results. In this pilot case-control study single nucleotide polymorphism (SNP) in several genes has been evaluated with a novel data mining approach based on an AutoCM. We have divided the ALS dataset into two dataset: Cases and Control dataset; we have applied to each one, independently, the AutoCM algorithm. Six genetic variants were identified which differently contributed to the complexity of the system: three of the above genes/SNPs represent protective factors, APOA4, NOS3, and LPL, since their contribution to the whole complexity resulted to be as high as 0.17. On the other hand ADRB3, LIPC, and MMP3, whose hub relevancies contribution resulted to be as high as 0.13, seem to represent susceptibility factors. Conclusion. The biological information available on these six polymorphisms is consistent with possible pathogenetic pathways related to ALS. © 2012 Massimo Buscema et al.

Buscema M.,Semeion Research Center | Buscema M.,University of Colorado at Denver | Sacco P.L.,IULM University | Sacco P.L.,Harvard University
Physica A: Statistical Mechanics and its Applications | Year: 2016

In this paper, we introduce a new methodology for the evaluation of alternative algorithms in capturing the deep statistical structure of datasets of different types and nature, called MST Fitness, and based on the notion of Minimum Spanning Tree (MST). We test this methodology on six different databases, some of which artificial and widely used in similar experimentations, and some related to real world phenomena. Our test set consists of eight different algorithms, including some widely known and used, such as Principal Component Analysis, Linear Correlation, or Euclidean Distance. We moreover consider more sophisticated Artificial Neural Network based algorithms, such as the Self-Organizing Map (SOM) and a relatively new algorithm called Auto-Contractive Map (AutoCM). We find that, for our benchmark of datasets, AutoCM performs consistently better than all other algorithms for all of the datasets, and that its global performance is superior to that of the others of several orders of magnitude. It is to be checked in future research if AutoCM can be considered a truly general-purpose algorithm for the analysis of heterogeneous categories of datasets. © 2016 Elsevier B.V.

Coppede F.,University of Pisa | Grossi E.,Bracco Foundation | Grossi E.,Semeion Research Center | Buscema M.,Semeion Research Center | And 2 more authors.
PLoS ONE | Year: 2013

Folate metabolism, also known as one-carbon metabolism, is required for several cellular processes including DNA synthesis, repair and methylation. Impairments of this pathway have been often linked to Alzheimer's disease (AD). In addition, increasing evidence from large scale case-control studies, genome-wide association studies, and meta-analyses of the literature suggest that polymorphisms of genes involved in one-carbon metabolism influence the levels of folate, homocysteine and vitamin B12, and might be among AD risk factors. We analyzed a dataset of 30 genetic and biochemical variables (folate, homocysteine, vitamin B12, and 27 genotypes generated by nine common biallelic polymorphisms of genes involved in folate metabolism) obtained from 40 late-onset AD patients and 40 matched controls to assess the predictive capacity of Artificial Neural Networks (ANNs) in distinguish consistently these two different conditions and to identify the variables expressing the maximal amount of relevant information to the condition of being affected by dementia of Alzheimer's type. Moreover, we constructed a semantic connectivity map to offer some insight regarding the complex biological connections among the studied variables and the two conditions (being AD or control). TWIST system, an evolutionary algorithm able to remove redundant and noisy information from complex data sets, selected 16 variables that allowed specialized ANNs to discriminate between AD and control subjects with over 90% accuracy. The semantic connectivity map provided important information on the complex biological connections among one-carbon metabolic variables highlighting those most closely linked to the AD condition. © 2013 Coppedè et al.

Buscema M.,Semeion Research Center
Annual Conference of the North American Fuzzy Information Processing Society - NAFIPS | Year: 2010

An individual patient is not the average representative of the population. Rather he or she is a person with unique characteristics. An intervention may be effective for a population but not necessarily for the individual patient. The recommendation of a guideline may not be right for a particular patient because it is not what he or she wants, and implementing the recommendation will not necessarily mean a favourable outcome. The author describes a reconfiguration of medical thought which originates from non linear dynamics and chaos theory. The coupling of computer science and these new theoretical bases coming from complex systems mathematics allows the creation of "intelligent" agents able to adapt themselves dynamically to problem of high complexity: the Artificial Adaptive Systems, which include Artificial Neural Networks (ANNs) and Evolutionary Algorithms ( EA). ANNs and EA are able to reproduce the dynamical interaction of multiple factors simultaneously, allowing the study of complexity; they can also help medical doctors in making decisions under extreme uncertainty and to draw conclusions on individual basis and not as average trends. © 2010 IEEE.

Grossi E.,Centro Diagnostico Italiano | Podda G.M.,University of Milan | Pugliano M.,University of Milan | Gabba S.,Centro Diagnostico Italiano | And 5 more authors.
Pharmacogenomics | Year: 2014

Background: In recent years, pharmacogenetic algorithms were developed for estimating the appropriate dose of vitamin K antagonists. Aim: To evaluate the performance of new generation artificial neural networks (ANNs) to predict the warfarin maintenance dose. Methods: Demographic, clinical and genetic data (CYP2C9 and VKORC1 polymorphisms) from 377 patients treated with warfarin were used. The final prediction model was based on 23 variables selected by TWIST® system within a bipartite division of the data set (training and testing) protocol. Results: The ANN algorithm reached high accuracy, with an average absolute error of 5.7 mg of the warfarin maintenance dose. In the subset of patients requiring ≤21 mg and 21-49 mg (45 and 51% of the cohort, respectively) the absolute error was 3.86 mg and 5.45 with a high percentage of subjects being correctly identified (71 and 73%, respectively). Conclusion: ANN appears to be a promising tool for vitamin K antagonist maintenance dose prediction. © 2014 Future Medicine Ltd.

Gironi M.,San Raffaele Hospital | Gironi M.,Polidiagnostic Center | Saresella M.,Don Carlo Gnocchi Foundation | Rovaris M.,Don Carlo Gnocchi Foundation | And 4 more authors.
Immunity and Ageing | Year: 2013

Background: Multiple Sclerosis (MS) is a multi-factorial disease, where a single biomarker unlikely can provide comprehensive information. Moreover, due to the non-linearity of biomarkers, traditional statistic is both unsuitable and underpowered to dissect their relationship. Patients affected with primary (PP=14), secondary (SP=33), benign (BB=26), relapsing-remitting (RR=30) MS, and 42 sex and age matched healthy controls were studied. We performed a depth immune-phenotypic and functional analysis of peripheral blood mononuclear cell (PBMCs) by flow-cytometry. Semantic connectivity maps (AutoCM) were applied to find the natural associations among immunological markers. AutoCM is a special kind of Artificial Neural Network able to find consistent trends and associations among variables. The matrix of connections, visualized through minimum spanning tree, keeps non linear associations among variables and captures connection schemes among clusters.Results: Complex immunological relationships were shown to be related to different disease courses. Low CD4IL25+ cells level was strongly related (link strength, ls=0.81) to SP MS. This phenotype was also associated to high CD4ROR+ cells levels (ls=0.56). BB MS was related to high CD4+IL13 cell levels (ls=0.90), as well as to high CD14+IL6 cells percentage (ls=0.80). RR MS was strongly (ls=0.87) related to CD4+IL25 high cell levels, as well indirectly to high percentages of CD4+IL13 cells. In this latter strong (ls=0.92) association could be confirmed the induction activity of the former cells (CD4+IL25) on the latter (CD4+IL13). Another interesting topographic data was the isolation of Th9 cells (CD4IL9) from the main part of the immunological network related to MS, suggesting a possible secondary role of this new described cell phenotype in MS disease.Conclusions: This novel application of non-linear mathematical techniques suggests peculiar immunological signatures for different MS phenotypes. Notably, the immune-network displayed by this new method, rather than a single marker, might be viewed as the right target of immunotherapy. Furthermore, this new statistical technique could be also employed to increase the knowledge of other age-related multifactorial disease in which complex immunological networks play a substantial role. © 2013 Gironi et al.; licensee BioMed Central Ltd.

Loading Semeion Research Center collaborators
Loading Semeion Research Center collaborators