Castrense Savojardo

Ph.D. in Computer Science

Researcher

FaBiT - Department of Pharmacy and Biotechnology

Member of the Bologna Biocomputing Group

savojard AT biocomp.unibo.it

About me

Education and academic positions

My research interest

• Machine Learning, Probabilistic Graphical Models, Neural Networks, Kernel Machines, Ensemble Learning
• Machine-learning methods for beta-barrel discrimination and topology prediction.
• Computational methods for cysteine disulfide connectivity prediction.
• Computational methods for predicting residue contacts in proteins.
• Protein-protein interaction site prediction.
• Prediction of the impact of mutations on protein stability and disease onset in humans.

Software and Web Servers

• BioCRF

  BioCRF is an implementation of Grammatical-Restrained Hidden Conditional Random Fields (GRHCRFs), an extension of linear Hidden-Condtional Random Fields to include prior knowledge about the problem at hand by means of a regular grammar. This results very useful in several Bioinformatics problems where only solution that agree with a regular grammar rules are biologically meaningful.

• DisLocate

  DisLocate is a method based on Grammatical-Restrained Hidden Conditional Random Fields (GRHCRFs) and Support Vector Regression (SVR) for the prediction of cysteine connectivity patterns in a protein chain. The method takes advantage of the protein subcellular localization as predicted by the BaCelLo predictor.

• BetAware

  BetAware is a web server for TransMembrane β-Barrel (TMBB) detection and tooplogy prediction. Both prediction steps are based on advanced machine-learning methods. For TMBB detection, BetAware exploits a new machine learning approach based on N-to-1 Extreme Learning Machines, while TMBB topology prediction is carried-out using a probabilistic model based on Grammatical-Restrained Hidden Conditional Random Fields, a discriminative framework introduced to address sequence labelling tasks in Bioinformatics.

• BCov

  BCov is a software package designed for predicting protein beta-sheet topology from amino acid sequence. BCov is based on the PSICOV residue contact predictor, dynamic-programming algorithm for beta-strand alignments and integer programming for beta-sheet topology prediction.

• TPpred2

  TPpred 2.0 is a web server for MITOCHONDRIAL targeting peptides prediction in proteins. TPpred 2.0 is optimized for the prediction of cleavage sites of mitochondrial targeting peptides.

• TPpred3

  TPpred 3.0 is a web server for organelle targeting peptides prediction and discrimination in proteins. TPpred 3.0 is optimized for the prediction of cleavage sites of both mitochondrial and chloroplastic targeting peptides.

• INPS-MD

  Web server for the prediction of the impact of mutations on protein stability from sequence and structure.

• SChloro

  Web server for the prediction of protein sub-chloroplastic localization. SChloro is able to classify a query protein into six different chloroplastic sub-compartments: inner membrane, outer membrane, stroma, thylokoid lumen, thylakoid membrane and plastoglobule. SChloro also performs multi-label classification.

• ISPRED4

  Web server for the prediction of protein-protein interaction sites on unbound protein chainsn. Starting from protein 3D structure, ISPRED4 identifies those residues located on the chain surface that are likely to be PPI sites.

• DeepSig

  Web server for the prediction of secretory signal peptides from protein sequences.

• BUSCA

  Web server for the prediction of protein subcellular localization.

Publications on Journals

1. Savojardo C., Babbi G., Martelli P.L., Casadio R. Functional and Structural Features of Disease-Related Protein Variants, International Journal of Molecular Sciences (2019) 20(7): 1530.
2. Montanucci L., Savojardo C., Martelli P.L., Casadio R., Fariselli P. On the biases in predictions of protein stability changes upon variations: the INPS test case, Bioinformatics (2019) (35): 2525–2527.
3. Savojardo C., Luchetti, A., Martelli P.L., Casadio R., Mantovani, B. Draft genomes and genomic divergence of two Lepidurus tadpole shrimp species (Crustacea, Branchiopoda, Notostraca), Molecular Ecology Resources (2019) 19(1): 235-244.
4. Savojardo C., Martelli P.L., Fariselli P., Profiti G., Casadio R. BUSCA: an integrative web server to predict subcellular localization of proteins, Nucleic Acids Research (Web Server Issue) (2018) 46(W1): W459-W466.
5. Savojardo C., Martelli P.L., Fariselli P., Casadio R. DeepSig: deep learning improves signal peptide detection in proteins, Bioinformatics (2018) 34(10): 1690-1696.
6. Babbi G., Martelli P.L., Profiti G., Bovo S., Savojardo, C., Casadio R. eDGAR: a database of Disease-Gene Associations with annotated Relationships among genes, BMC Genomics (2017) 18(Suppl. 5): 554.
7. Savojardo C., Fariselli P., Martelli P.L., Casadio R. ISPRED4: Interaction Sites PREDiction in protein structures with a refining grammar model, Bioinformatics (2017) 33(11): 1656-1663.
8. Savojardo C., Martelli P.L., Fariselli P., Casadio R. SChloro: directing Viridiplantae proteins to six chloroplastic sub-compartments, Bioinformatics (2017) 33 (3): 347-353.
9. Martelli P.L., Fariselli P., Savojardo C., Babbi G., Aggazio F. Casadio R. Large scale analysis of protein stability in OMIM disease related human protein variants, BMC Genomics (2016) 17(Suppl 2)(397): 239-247.
10. Savojardo C., Fariselli P., Martelli P.L., Casadio R. INPS-MD: a web server to predict stability of protein variants from sequence and structure, Bioinformatics (2016) 32(16): 2542-2544.
11. Savojardo C., Martelli P.L., Fariselli P., Casadio R. "TPpred3 detects and discriminates mitochondrial and chloroplastic targeting peptides in Eukaryotic proteins", Bioinformatics (2015) 31 (20): 3269-3275
12. Fariselli P., Martelli P.L., Savojardo C., Casadio R. "INPS: predicting the impact of non-synonymous variations on protein stability from sequence", Bioinformatics (2015) 31 (17): 2816-2821.
13. Savojardo C., Martelli P.L., Fariselli P., Casadio R. "TPpred2: improving the prediction of mitochondrial targeting peptide cleavage sites by exploiting sequence motifs", Bioinformatics (2014) 30(20): 2973-2974.
14. Savojardo C., Fariselli P., Martelli P.L., Casadio R. "BCov: a method for predicting β-sheet topology using sparse inverse covariance estimation and integer programming", Bioinformatics (2013) 29(24): 3151-3157.
15. Indio V., Martelli P.L., Savojardo C., Fariselli P., Casadio R. The prediction of organelle targeting peptides in eukaryotic proteins with Grammatical Restrained Hidden Conditional Random Fields, Bioinformatics (2013) 29(8): 981-988.
16. Savojardo C., Fariselli P., Casadio R., "BETAWARE: a machine-learning tool to detect and predict trans-membrane β-barrel proteins in Prokaryotes", Bioinformatics (2013) 29(4): 504-505.
17. Savojardo C., Fariselli P., Martelli P.L., Casadio R., "Prediction of disulfide connectivity in proteins with machine-learning methods and correlated mutations", BMC Bioinformatics (2013) 14(Suppl 1):S10.
18. Savojardo C., Fariselli P., Casadio R., "Improving the detection of transmembrane β-barrel chains with N-to-1 Extreme Learning Machines", Bioinformatics (2011) 27 (22): 3123-3128.
19. Savojardo C., Fariselli P., Alhamdoosh, M., Martelli P.L., Pierleoni A., Casadio R., "Improving the prediction of disulfide bonds in Eukaryotes with machine learning methods and protein subcellular localization", Bioinformatics (2011) 27 (16): 2224-2230.
20. Pierleoni A., Indio V., Savojardo C., Fariselli P., Martelli P.L., Casadio R., "MemPype: a pipeline for the annotation of eukaryotic membrane proteins", Nucleic Acids Research (2011) 39 (suppl 2): W375-W380.
21. Fariselli P., Savojardo C., Martelli P.L., Casadio R., "Grammatical-Restrained Hidden Conditional Random Fields for Bioinformatics Applications", Algorithms for Molecular Biology 2009, 4:13.

Conference papers

1. Savojardo C., Fariselli P., Piovesan D., Martelli P.L., Casadio R., "Machine-learning Methods to Predict Protein Interaction Sites in Folded Proteins", in E. Biganzoli et al.(Eds.): Computational Intelligence Methods for Bioinformatics and Biostatistics (CIBB 2011), LNBI 7548, pp. 127-135, Springer-Verlag Berlin Heidelberg, 2012.
2. Savojardo C., Fariselli P., Martelli P.L., Shukla P., Casadio R., "Prediction of the bonding state of cysteine residues in proteins with machine-learning methods", in R. Rizzo and P.J.G. Lisboa (Eds.): Computational Intelligence Methods for Bioinformatics and Biostatistics (CIBB 2010), LNBI 6685, pp. 98-111, Springer-Verlag Berlin Heidelberg, 2011.
3. Alhamdoosh, M., Savojardo, C., Fariselli, P., Casadio, R., "Disulfide Connectivity Prediction with Extreme Learning Machines", in Marco Pellegrini, Ana L. N. Fred, Joaquim Filipe, Hugo Gamboa (Eds.): BIOINFORMATICS 2011 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms, Rome, Italy, 26-29 January, 2011, pp. 5-14, SciTePress 2011.

Book chapters

1. Martelli P.L., Savojardo C., Profiti G., Casadio R. Transmembrane Domain Prediction, in Encyclopedia of Bioinformatics and Computational Biology, Academic Press, Oxford, Volume 2, pp 46-52, 2018.
2. Martelli P.L., Savojardo C., Fariselli P., Tasco G., Casadio R., "Computer-based prediction of mitochondrial-targeting peptides", in Mitochondrial Medicine, Methods in Molecular Biology(1264), Springer New York, 2015 (978-1-4939-2256-7).