According to Moya-Angeler’s report, published in 2008, the Spanish pharmaceutical industry invested 844 million euros in research in 2006, out of which a 17% was invested in basic research. In Europe, the pharmaceutical sector leads the reinvestment of sales into research with a 15.3% (2007 data), surpassing even the IT sector. In Spain, this reinvestment percentage falls to a meager 6.6%, mostly due to the comparatively small size of companies and the atomization of the sector. In this context, external research centers, including universities, could play a key complementary role. Arguably, drug research has contributed more to the progress of medicine during the past decades than any other scientific factor. One of the main areas of drug research is related to the analysis of proteins. The world of pharmacology is becoming increasingly dependent on the advances in the fields of genomics and proteomics. This dependency brings about the challenge of finding robust methods to analyze the complex data they generate. Such challenge invites us to go one step further than traditional statistics and resort to approaches under the conceptual umbrella of artificial intelligence, including machine learning, statistical pattern recognition and soft computing methods. Sound statistical principles are essential to trust the evidence base built through the use of such approaches. Statistical machine learning methods will thus be at the core of the current project. More than 50% of drugs target only four key protein families, from which almost a 30% correspond to the G-Protein Coupled Receptors (GPCR) superfamily. This superfamily regulates the function of most cells in living organisms and will be the goal of the current project. No much is known about the 3D structure of these proteins. Fortunately, plenty of information regarding their amino acid sequences is readily available. The automatic grouping and classification of GPCRs into families and these into subtypes based on sequence analysis may significantly contribute to ascertain the pharmaceutically relevant properties of this protein superfamily. There is no biologically-relevant manner of representing the symbolic sequences describing proteins using real-valued vectors. This does not preclude the possibility of analyzing them using principled methods. These may come, amongst others, from the field of statistical machine learning. Particularly, kernel methods can be used to this purpose. Moreover, the visualization of high-dimensional protein sequence data can be a key exploratory tool for finding meaningful information that might be obscured by their intrinsic complexity. Overall, thus, the central objective of this proposed project is dual: on one side, the design of adequate artificial intelligence-based methods for the analysis of GPCR sequential data. On the other side, and given that this research has the ultimate goal of being useful in helping drug design and the understanding of the molecular processes involved, we aim to apply the developed methods in relevant pharmacoproteomic problems such as GPCR subtyping, receptor heteromerization and deorphanization, and protein alignment-free analysis. For this objective, we have the key expert support of the Systems Pharmacology and Bioinformatics research group at Universitat Autònoma de Barcelona (UAB), endorsed by the Esteve pharmaceutical company, as well as the back-up of two relevant biomedical companies in Barcelona, namely Sabirmedical and Intelligent Pharma.
Scope
Adm. Estat
Plan
Plan Nacional de Investigación Científica, Desarrollo e Innovación Tecnológica 2008-2011
Call year
2012
Funcding program
Tecnologías Informáticas
Funding call
Proyectos de investigación y acciones complementarias-TIN
Grant institution
Gobierno De España. Ministerio De Economía Y Competitividad, Mineco
Koenig, C.; Cardenas, M.; Giraldo, J.; Alquezar, R.; Vellido, A. BMC bioinformatics Vol. 16:314, p. 1-14 DOI: 10.1186/s12859-015-0731-9 Date of publication: 2015-09-29 Journal article
Cardenas, M.; Vellido, A.; König, C.; Alquezar, R.; Giraldo, J. Genomics and computational biology Vol. 1, num. 1, p. e19- DOI: 10.18547/gcb.2015.vol1.iss1.e19 Date of publication: 2015-09-18 Journal article
Cruz, R.; Vellido, A.; Giraldo, J. Medical and biological engineering and computing Vol. 53, num. 2, p. 137-149 DOI: 10.1007/s11517-014-1218-y Date of publication: 2015-02-01 Journal article
König, C.; Alquezar, R.; Vellido, A.; Giraldo, J. Journal of integrative bioinformatics Vol. 11, num. 3, p. Paper 254- DOI: 10.2390/biecoll-jib-2014-254 Date of publication: 2014-10-23 Journal article
Arizmendi, C.; Sierra, D.A.; Vellido, A.; Romero, E. Expert systems with applications Vol. 41, num. 11, p. 5296-5307 DOI: 10.1016/j.eswa.2014.02.031 Date of publication: 2014-09 Journal article
Cardenas, M.; Vellido, A.; Giraldo, J. IEEE-EMBS International Conferences on Biomedical and Health Informatics p. 764-767 DOI: 10.1109/BHI.2014.6864476 Presentation's date: 2014-06-01 Presentation of work at congresses
Vilamala, A.; Belanche, Ll.; Vellido, A. International Workshop on Pattern Recognition in Neuroimaging p. 6858550-1-6858550-4 DOI: 10.1109/PRNI.2014.6858550 Presentation's date: 2014-06 Presentation of work at congresses
Buchaca, D.; Romero, E.; Mazzanti, F.; Delgado, J. International Conference on Learning Representations Presentation's date: 2014-04-15 Presentation of work at congresses