Sofia Mosci
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sofia Mosci has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Alessandro Verri
DISI, Università degli Studi di Genova, Genova, Italy
4 shared publications - Lorenzo Rosasco
Malga -DIBRIS University of Genova IT
3 shared publications - Annalisa Barla
Università di Genova
2 shared publications - Luigi Varesio
Laboratory of Molecular Biology, G. Gaslini Institute, Genoa, Italy
2 shared publications - Paolo Fardin
Laboratory of Molecular Biology, G. Gaslini Institute, Genoa 16147, Italy
2 shared publications - Alessandra Eva
Laboratory of Molecular Biology, IRCCS Istituto Giannina Gaslini, Via Gerolamo Gaslini 5, 16147 Genova, Italy
1 shared publication
Latest Publications
- 1 July 2012
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 45 (16) , 971-976
Is there sparsity beyond additive models?
- 1 July 2012
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 45 (16) , 971-976
Is there sparsity beyond additive models?
- Open Access
- 1 January 2010
- Published by Springer Nature in Molecular Cancer
- Vol. 9 (1) , 185
A biology-driven approach identifies the hypoxia gene signature as a predictor of the outcome of neuroblastoma patients
Hypoxia is a condition of low oxygen tension occurring in the tumor microenvironment and it is related to poor prognosis in human cancer. To examine the relationship between hypoxia and neuroblastoma, we generated and tested an in vitro derived hypoxia gene signature for its ability to predict patients' outcome.
- 1 January 2010
- Published by Springer Nature in Molecular Cancer
- Vol. 9 (1) , 185
Open AccessA biology-driven approach identifies the hypoxia gene signature as a predictor of the outcome of neuroblastoma patients
Hypoxia is a condition of low oxygen tension occurring in the tumor microenvironment and it is related to poor prognosis in human cancer. To examine the relationship between hypoxia and neuroblastoma, we generated and tested an in vitro derived hypoxia gene signature for its ability to predict patients' outcome.
- 1 May 2009
- Published by SAGE Publications in Journal of Computational Biology
- Vol. 16 (5) , 677-690
A Regularized Method for Selecting Nested Groups of Relevant Genes from Microarray Data
Gene expression analysis aims at identifying the genes able to accurately predict biological parameters like, for example, disease subtyping or progression. While accurate prediction can be achieved by means of many different techniques, gene identification, due to gene correlation and the limited number of available samples, is a much more elusive problem. Small changes in the expression values often produce different gene lists, and solutions which are both sparse and stable are difficult to obtain. We propose a two-stage regularization method able to learn linear models characterized by a high prediction performance. By varying a suitable parameter these linear models allow to trade sparsity for the inclusion of correlated genes and to produce gene lists which are almost perfectly nested. Experimental results on synthetic and microarray data confirm the interesting properties of the proposed method and its potential as a starting point for further biological investigations.
- 1 May 2009
- Published by SAGE Publications in Journal of Computational Biology
- Vol. 16 (5) , 677-690
A Regularized Method for Selecting Nested Groups of Relevant Genes from Microarray Data
Gene expression analysis aims at identifying the genes able to accurately predict biological parameters like, for example, disease subtyping or progression. While accurate prediction can be achieved by means of many different techniques, gene identification, due to gene correlation and the limited number of available samples, is a much more elusive problem. Small changes in the expression values often produce different gene lists, and solutions which are both sparse and stable are difficult to obtain. We propose a two-stage regularization method able to learn linear models characterized by a high prediction performance. By varying a suitable parameter these linear models allow to trade sparsity for the inclusion of correlated genes and to produce gene lists which are almost perfectly nested. Experimental results on synthetic and microarray data confirm the interesting properties of the proposed method and its potential as a starting point for further biological investigations.
- Open Access
- 1 January 2009
- Published by Springer Nature in BMC Genomics
- Vol. 10 (1) , 474
The l1-l2 regularization framework unmasks the hypoxia signature hidden in the transcriptome of a set of heterogeneous neuroblastoma cell lines
Gene expression signatures are clusters of genes discriminating different statuses of the cells and their definition is critical for understanding the molecular bases of diseases. The identification of a gene signature is complicated by the high dimensional nature of the data and by the genetic heterogeneity of the responding cells. The l1-l2 regularization is an embedded feature selection technique that fulfills all the desirable properties of a variable selection algorithm and has the potential to generate a specific signature even in biologically complex settings. We studied the application of this algorithm to detect the signature characterizing the transcriptional response of neuroblastoma tumor cell lines to hypoxia, a condition of low oxygen tension that occurs in the tumor microenvironment.
- 1 January 2009
- Published by Springer Nature in BMC Genomics
- Vol. 10 (1) , 474
Open AccessThe l1-l2 regularization framework unmasks the hypoxia signature hidden in the transcriptome of a set of heterogeneous neuroblastoma cell lines
Gene expression signatures are clusters of genes discriminating different statuses of the cells and their definition is critical for understanding the molecular bases of diseases. The identification of a gene signature is complicated by the high dimensional nature of the data and by the genetic heterogeneity of the responding cells. The l1-l2 regularization is an embedded feature selection technique that fulfills all the desirable properties of a variable selection algorithm and has the potential to generate a specific signature even in biologically complex settings. We studied the application of this algorithm to detect the signature characterizing the transcriptional response of neuroblastoma tumor cell lines to hypoxia, a condition of low oxygen tension that occurs in the tumor microenvironment.
- Open Access
A Regularized Method for Selecting Nested Groups of Relevant Genes from Microarray Data
Gene expression analysis aims at identifying the genes able to accurately predict biological parameters like, for example, disease subtyping or progression. While accurate prediction can be achieved by means of many different techniques, gene identification, due to gene correlation and the limited number of available samples, is a much more elusive problem. Small changes in the expression values often produce different gene lists, and solutions which are both sparse and stable are difficult to obtain. We propose a two-stage regularization method able to learn linear models characterized by a high prediction performance. By varying a suitable parameter these linear models allow to trade sparsity for the inclusion of correlated genes and to produce gene lists which are almost perfectly nested. Experimental results on synthetic and microarray data confirm the interesting properties of the proposed method and its potential as a starting point for further biological investigations
Open AccessA Regularized Method for Selecting Nested Groups of Relevant Genes from Microarray Data
Gene expression analysis aims at identifying the genes able to accurately predict biological parameters like, for example, disease subtyping or progression. While accurate prediction can be achieved by means of many different techniques, gene identification, due to gene correlation and the limited number of available samples, is a much more elusive problem. Small changes in the expression values often produce different gene lists, and solutions which are both sparse and stable are difficult to obtain. We propose a two-stage regularization method able to learn linear models characterized by a high prediction performance. By varying a suitable parameter these linear models allow to trade sparsity for the inclusion of correlated genes and to produce gene lists which are almost perfectly nested. Experimental results on synthetic and microarray data confirm the interesting properties of the proposed method and its potential as a starting point for further biological investigations