biblio_i06.bib

@ARTICLE{depitta05gene,
  AUTHOR = {C. De Pitt\`{a} and L. Tombolan and G. Albiero and F. Sartori and C. Romualdi and G. Jurman and M. Carli and C. Furlanello and G. Lanfranchi and A. Rosolen},
  TITLE = {{Gene expression profiling identifies potential relevant genes in alveolar rhabdomyosarcoma pathogenesis and discriminates PAX3-FKHR positive and negative tumors}},
  JOURNAL = {Int. J. Cancer},
  YEAR = {2006},
  VOLUME = {118},
  NUMBER = {11},
  PAGES = {2772--2781},
  ABSTRACT = {We analyzed the expression signatures of 14 tumor biopsies from children affected by alveolar
rhabdomyosarcoma (ARMS) to identify genes correlating to biological features of
this tumor.
Seven of these patients were positive for the PAX3-FKHR fusion gene and seven were negative. We
used a cDNA platform containing a large majority of probes derived from muscle tissues.

The comparison of transcription profiles of tumor samples with fetal skeletal muscle identified
171 differentially expressed genes common to all ARMS patients. The functional classification
analysis of altered genes led to the identification of a group of transcripts (BCOR, LGALS1, BIN1)
that may be relevant for the tumorigenic processes.

The muscle-specific microarray platform was able to distinguish PAX3-FKHR positive and
negative ARMS through the expression pattern of a limited number of genes (RAC1, CFL1,
CCND1, IGFBP2) that might be biologically relevant for the different clinical behavior and
aggressiveness of the two ARMS subtypes. Expression levels for selected candidate genes were
validated by quantitative real-time reverse-transcription PCR.
}
}

@INPROCEEDINGS{merler06Strategies,
  AUTHOR = {S. Merler and G. Jurman and C. Furlanello and C. Rizzo and A. Bella and M. Massari and M.L. Ciofi degli Atti},
  TITLE = {Strategies for containing an influenza pandemic: the case of Italy},
  BOOKTITLE = {Proceedings of Bionetics, Trento, Italy, December 13-17, 2006},
  YEAR = {2006},
  ABSTRACT = {In this paper we introduce an individual based model for simulating
the spread of an emerging influenza pandemic in Italy and testing the
effectiveness of some containing strategies including vaccination,
antiviral prophylaxis and quarantine measures to increase social
distances. Our results show that while the probability of interrupting
a large outbreak is negligible, a combination of the control measures
can be effective in reducing the incidence of infection. In
particular, in the worst case, an incidence reduction from about 50\%
to about 10\% can be hopefully achieved.
}
}

@INPROCEEDINGS{Jolma2006_GFOSS,
  AUTHOR = {A. Jolma and D.P. Ames and N. Horning and M. Neteler and A. Racicot and T. Sutton},
  TITLE = {Free and {O}pen {S}ource Geospatial Tools for Environmental
   Modeling and Management},
  BOOKTITLE = {Proc. iEMSs 2006, Session W13, July 9-13, 2006, Burlington,
   Vermont, USA},
  CITEULIKE-ARTICLE-ID = {747897},
  YEAR = {2006},
  EDITOR = {Voinov, A.},
  KEYWORDS = {geo gis grass java perl postgis python qgis r-stats},
  URL = {http://www.iemss.org/iemss2006/papers/w13/pp.pdf},
  ABSTRACT = {Geospatial software tools (GIS) are used for creating,
  viewing, managing, analyzing, and utilizing geospatial
  data. Geospatial data can include socio-economic, environmental,
  geophysical, and technical data about the Earth and societal
  infrastructure and it is pivotal in environmental modeling and
  management (EMM). Desktop, web-based, and embedded geospatial tools
  and systems have become an essential part of EMM. Environmental
  simulation models often require pre- or post-processing of
  geospatial data, or they can be tightly linked to a GIS, using it as
  a graphical user interface (GUI). Many local, regional, national,
  and international efforts are underway to create geospatial data
  infrastructures and tools for viewing and using geospatial
  data. When environmental attribute data is linked to these
  infrastructures, powerful tools for environmental management are
  instantly created. The growing culture of free and open source
  software (FOSS) provides an alternative approach to software
  development also in the field of GIS (FOSS4G). For a systematic look
  at FOSS4G for EMM platforms, software stacks, and EMM workflows need
  to be analyzed. Platform is a service abstraction on which software
  stacks are built. A software stack for FOSS4G comprises system
  software, data processing tools, data serving tools, user interface
  tools, and end-user applications. Digital map creation, support for
  numerical modeling, and geospatial information systems are main
  areas of use for FOSS4G in EMM. The dividing line between FOSS and
  proprietary software is fuzzy, partly because it is in the interest
  of developers of proprietary software to make it fuzzy and partly
  because the end-users are getting reluctant to buy software. In the
  FOSS world the barriers to interoperability are low and thus the
  software stack tends to be thicker than in the proprietary
  platform. The FOSS4G world thrives on the evolution of software
  stacks and platforms. Our examples show that it is possible to build
  software stacks from current FOSS4G to support EMM workflows. In the
  examples we mention for example how a particular funding agency has
  chosen FOSS4G solutions because of the opportunities to redistribute
  resulting modeling tools freely to end-users and to support general
  goals of openness and transparency with respect to modeling tools.}
}

@ARTICLE{furlan06combining,
  AUTHOR = {C. Furlanello and S. Merler and G. Jurman},
  TITLE = {{Combining feature selection and DTW for time-varying functional genomics}},
  JOURNAL = {IEEE Transactions on Signal Processing},
  YEAR = {2006},
  VOLUME = {54},
  NUMBER = {6},
  PAGES = {2436--2443}
}

@INPROCEEDINGS{bouktif2006_clone,
  AUTHOR = {S. Bouktif and G. Antoniol and E. Merlo and M. Neteler},
  TITLE = {A novel approach to optimize clone refactoring activity},
  BOOKTITLE = {GECCO '06: Proceedings of the 8th annual conference on Genetic and evolutionary computation},
  YEAR = {2006},
  ISBN = {1-59593-186-4},
  PAGES = {1885--1892},
  LOCATION = {Seattle, Washington, USA},
  DOI = {http://doi.acm.org/10.1145/1143997.1144312},
  PUBLISHER = {ACM Press},
  ADDRESS = {New York, NY, USA}
}

@INPROCEEDINGS{barla06proteome,
  AUTHOR = {A. Barla and B. Irler and S. Merler and G. Jurman and S. Paoli and C. Furlanello},
  TITLE = {Proteome Profiling without Selection Bias},
  BOOKTITLE = {CBMS '06: Proceedings of the 19th IEEE Symposium on Computer-Based Medical Systems},
  YEAR = {2006},
  PAGES = {941--946},
  PUBLISHER = {IEEE Computer Society},
  ADDRESS = {Washington, DC, USA}
}

@ARTICLE{merler06terminated,
  AUTHOR = {S. Merler and G. Jurman},
  TITLE = {{Terminated Ramp - Support Vector Machine: a nonparametric data dependent kernel}},
  JOURNAL = {Neural Network},
  YEAR = {2006},
  VOLUME = {19},
  PAGES = {1597--1611}
}

@INPROCEEDINGS{cibb05,
  AUTHOR = {S. Paoli and G. Jurman and D. Albanese and S. Merler and C. Furlanello},
  TITLE = {{Semisupervised Profiling of Gene Expressions and Clinical Data}},
  BOOKTITLE = {Fuzzy Logic and Applications: 6th International Workshop, WILF 2005},
  EDITOR = {I. Bloch, A. Petrosino, A.G.B. Tettamanzi},
  YEAR = {2006},
  SERIES = {LNCS},
  PUBLISHER = {Springer},
  PAGES = {284 -- 289},
  NUMBER = {3849},
  ABSTRACT = {We present an application of BioDCV, a computational environment for
  semisupervised profiling with Support Vector Machines, aimed at
  detecting outliers and deriving informative subtypes of patients
  with respect to pathological features. First, a sample-tracking
  curve is extracted for each sample as a by-product of the profiling
  process. The curves are then clustered according to a distance
  derived from Dynamic Time Warping. The procedure allows
  identification of noisy cases, whose removal is shown to improve
  predictive accuracy and the stability of derived gene profiles.
  After removal of outliers, the semisupervised process is repeated
  and subgroups of patients are specified. The procedure is
  demonstrated through the analysis of a liver cancer dataset of $213$
  samples described by $1 993$ genes and by pathological features.
}
}

@ARTICLE{granitto06recursive,
  AUTHOR = {P. Granitto and C. Furlanello and F. Biasioli and F. Gasperi},
  TITLE = {{Recursive Feature Elimination with Random Forest for PTR-MS analysis of agroindustrial products}},
  JOURNAL = {Chemometrics and Intelligent Laboratory Systems},
  YEAR = {2006},
  VOLUME = {83},
  NUMBER = {2},
  PAGES = {83--90}
}

@ARTICLE{marta06predicting,
  AUTHOR = {M. {Benito Garz\'on} and R. Blazek and M. Neteler and R. {S\'anchez de Dios} and H. {Sainz Ollero} and C. Furlanello},
  TITLE = {{Predicting habitat suitability with Machine Learning models: the potential area of {\em {P}inus sylvestris {L}.} in the {I}berian {P}eninsula.}},
  JOURNAL = {Ecological Modelling},
  MONTH = {August},
  NUMBER = {3-4},
  PAGES = {383--393},
  VOLUME = {197},
  YEAR = {2006},
  LINK = {http://www.uam.es/proyectosinv/Mclim/pdf/MBenito_EcoMod.pdf},
  DOI = {http://dx.doi.org/10.1016/j.ecolmodel.2006.03.015},
  ABSTRACT = {We present a modelling framework for predicting forest
  areas. The framework is obtained by integrating a machine learning
  software suite within the GRASS Geographical Information System
  (GIS) and by providing additional methods for predictive habitat
  modelling. Three machine learning techniques (Tree-Based
  Classification, Neural Networks and Random Forest) are available in
  parallel for modelling from climatic and topographic
  variables. Model evaluation and parameter selection are measured by
  sensitivity-specificity ROC analysis, while the final presence and
  absence maps are obtained through maximisation of the kappa
  statistic. The modelling framework is applied at a resolution of 1
  km with Iberian subpopulations of Pinus sylvestris L. forests. For
  this data set, the most accurate algorithm is Breiman's random
  forest, an ensemble method which provides automatic combination of
  tree-classifiers trained on bootstrapped subsamples and randomised
  variable sets. All models show a potential area of P. sylvestris for
  the Iberian Peninsula which is larger than the present one, a result
  corroborated by regional pollen analyses.}
}