CDS

Computational Data Science

within the activities of the CDS-group (formerly CDS-Lab), ICAR-CNR

Objectives

The activity concerns the design of models, algorithms, and software tools to discover, understand, and model scientific phenomena through the analysis of experimental data and/or through the simulation of their generation processes.

Main achievements

Omics Imaging:

- Integrating Imaging and Omics Data [1][4]. See also our companion web page on OmicsImaging.

- Glioma Grade Classification via Omics Imaging [6],[10], Best Paper Award at the 7th International Conference on Bioimaging (BIOIMAGING2020).

- Classifying Alzheimer's Disease Using MRIs and Transcriptomic Data [20].

Network Analysis:

- Clustering [2],[8] and classification [3],[5],[7] of metabolic networks. See also our poster on Supervised and Unsupervised Learning on Biological Networks (2019).

- Network similarities [7],[9].

- Whole-graph embedding [11][12][15][19] and its robustness [13],[14],[16],[17],[18].

- Community detection [21].

Main collaborations

- National Research University Higher School of Economics, Lab LATNA, Russia

- Stazione Zoologica “Anton Dohrn”, Naples, Italy

- University of Cassino and Southern Lazio, Italy

- University of Florida, U.S.A.

- University of Naples "L'Orientale", Naples, Italy

Useful/downloadable material

Software:

- MetabolitesGraphs: R package to integrate gene expression data into a metabolic model and extract metabolites-based graphs, as used in [3],[5],[9]

- GraphDistances: R package to compute distribution-based distance measures between directed and undirected graphs/networks, as used in [3],[5],[9]

- Netpro2vec: Python code for the neural embedding framework proposed in [11]

Web pages:

- OmicsImaging: Compendium of [4] Publications and Communications on Computational Data Science

[21] I. Manipur, M. Giordano, M. Piccirillo, S. Parashuraman and L. Maddalena, Community Detection in Protein-Protein Interaction Networks and Applications, IEEE/ACM Transactions on Computational Biology and Bioinformatics, doi: 10.1109/TCBB.2021.3138142.

[20] L. Maddalena, I. Granata, M. Giordano, M. Manzo, M.R. Guarracino, and for the Alzheimer's Disease Neuroimaging Initiative, Classifying Alzheimer's Disease Using MRIs and Transcriptomic Data, 9th International Conference on Bioimaging (BIOIMAGING2022), online, February 9-11, 2022.

[19] I. Manipur, M. Manzo, I. Granata, M. Giordano, L. Maddalena, and M.R. Guarracino, Netpro2vec: a Graph Embedding Framework for Biomedical Applications, GNCS-INdAM Research Day on Computational Intelligence Methods for Digital Health, Vietri sul Mare (SA) and online, December 21, 2021.

[18] M. Giordano, L. Maddalena, M. Manzo, and M.R. Guarracino, Adversarial Attacks on Graph Embedding: Applications in Computational Biology and Bioinformatics, Bioinformatics and Computational Biology Conference (BBCC 2021), online, December 1-3, 2021.

[17] M. Giordano, L. Maddalena, M. Manzo, and M.R. Guarracino, Whole-Graph Embedding and Adversarial Attacks for Life Sciences, invited presentation at BIOMAT 2021 International Symposium, online, November 1-5, 2021.

[16] M.R. Guarracino, M. Manzo, M. Giordano, L. Maddalena, On Resiliency and Robustness of Whole Graph Embedding, 11th International Conference on Network Analysis (NET 2021), online, October 18-20, 2021.

[15] M. Giordano, I. Granata, M.R. Guarracino, L. Maddalena, M. Manzo, Graph Embedding for Biological Networks, Workshop How can Scientific Computing help to study Life Sciences?, Napoli and online, September 13, 2021.

[14] M. Manzo, M. Giordano, L. Maddalena, and M.R. Guarracino, Whole Graph Embedding: Robustness and Vulnerability, Workshop How can Scientific Computing help to study Life Sciences?, Napoli and online, September 13, 2021.

[13] M. Manzo, M. Giordano, L. Maddalena, and M.R. Guarracino, Performance Evaluation of Adversarial Attacks on Whole-Graph Embedding Models, In: D.E. Simos, P.M. Pardalos, and I.S. Kotsireas (Eds), Learning and Intelligent Optimization. Springer International Publishing, Lecture Notes in Computer Science vol. 12931, DOI: 10.1007/978-3-030-92121-7_19, ISBN: 978-3-030-92121-7, 219-236, 2021.

[12] L. Maddalena, I. Manipur, M. Manzo, and M.R. Guarracino, On Whole-Graph Embedding Techniques, In: Mondaini R.P. (Ed) Trends in Biomathematics: Chaos and Control in Epidemics, Ecosystems, and Cells. BIOMAT 2020. Springer, Cham, DOI: 10.1007/978-3-030-73241-7_8, 115-131, 2021.

[11] I. Manipur, M. Manzo, I. Granata, M. Giordano, L. Maddalena, and M.R. Guarracino, Netpro2vec: a Graph Embedding Framework for Biomedical Applications , in IEEE/ACM Transactions on Computational Biology and Bioinformatics, DOI: 10.1109/TCBB.2021.3078089, to appear.

[10] L. Maddalena, I. Granata, I. Manipur, M. Manzo, and M.R. Guarracino, A Framework Based on Metabolic Networks and Biomedical Images Data to Discriminate Glioma Grades, in X. Ye et al. (Eds.), Biomedical Engineering Systems and Technologies. BIOSTEC 2020. CCIS 1400, Springer, ISBN: 978-3-030-72379-8, DOI: 10.1007/978-3-030-72379-8_9, 165--189, 2021.

[9] I. Manipur, I. Granata, L. Maddalena, and M.R. Guarracino, Network Distances for Weighted Digraphs, in Y. Kochetov et al. (Eds.), Mathematical Optimization Theory and Operations Research, CCIS 1275, Springer Nature Switzerland, ISBN: 978-3-030-58657-7, DOI: 10.1007/978-3-030-58657-7_31, 389-408, 2020.

[8] I. Manipur, I. Granata, L. Maddalena, and M.R. Guarracino, Clustering Analysis of Tumor Metabolic Networks, BMC Bioinformatics, ISSN: 1471-2105, DOI: 10.1186/s12859-020-03564-9, vol.21, n. 349, 2020.

[7] I. Granata, M.R. Guarracino, L. Maddalena, I. Manipur, and P.M. Pardalos, On Network Similarities and Their Applications, in R.P. Mondaini (Ed.), Trends in Biomathematics: Modeling Cells, Flows, Epidemics, and the Environment: Selected Works from the BIOMAT Consortium Lectures, Szeged, Hungary, 2019, Springer International Publishing, 23-41, ISBN: 978-3-030-46306-9, DOI: 10.1007/978-3-030-46306-9_3, 2020.

[6] L. Maddalena, I. Granata, I. Manipur, M. Manzo, and M.R. Guarracino, Glioma Grade Classification via Omics Imaging, in F. Soares, A. Fred, and H. Gamboa (Eds.), Proceed. 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC2020), Volume 2: BIOIMAGING, ISBN: 978-989-758-398-8, 82-92, 2020 (Best Paper Award).

[5] I. Granata, M.R. Guarracino, V. Kalyagin, L. Maddalena, I. Manipur, and P. Pardalos, Model Simplification for Supervised Classification of Metabolic Networks, Annals of Mathematics and Artificial Intelligence 88, Springer, 91-104, 2020.

[4] L. Antonelli, M. R. Guarracino, L. Maddalena, and M. Sangiovanni, Integrating Imaging and Omics Data: A Review, Biomedical Signal Processing and Control 52, 264–280, 2019.

[3] I. Granata, M.R. Guarracino, V. Kalyagin, L. Maddalena, I. Manipur, and P. Pardalos, Supervised Classification of Metabolic Networks, 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Madrid, Spain, 2688-2693, 2018.

[2] I. Manipur, I. Granata, L. Maddalena, K.P. Tripathi, and M.R.Guarracino, Clustering Analysis of Tumor Metabolic Networks, Bioinformatics and Computational Biology Conference (BBCC2018), Naples, November 2018.

[1] L. Antonelli, M. R. Guarracino, L. Maddalena, and M. Sangiovanni, Integrating Imaging and Omics Data: A Review, 17th International Symposium on Mathematical and Computational Biology - BIOMAT 2017, Moscow (Russia), November 2017.

Last update: December 26, 2021