polito.it
Politecnico di Torino (logo)

Application of Face Recognition Methodologies to the Classification of Proteins

Touseef Sadiq

Application of Face Recognition Methodologies to the Classification of Proteins.

Rel. Federica Marcolin, Jacek Adam Tuszynski. Politecnico di Torino, Corso di laurea magistrale in Communications And Computer Networks Engineering (Ingegneria Telematica E Delle Comunicazioni), 2020

Abstract:

The characterization of proteins is necessary as proteins perform certain functions by interacting with other proteins (protein-protein interaction) or with small molecules (protein-ligand interaction). Active sites are the pocket regions in proteins where protein-ligand interaction takes place and to know the geometrical characteristics of these binding sites helps us in drug design discovery and many other biological processes. In this thesis, we have computed geometrical features that come from differential geometry on the main protease MPro surface to identify cavities and attractive sites that could be the best match in binding with other protein molecules. These geometrical descriptors from differential geometry have already experimented on 3D face surfaces for face recognition methodologies with considerable results. SARS-CoV-2 is the virus originally responsible for the COVID-19 pandemic around the globe. So far, there are not pointed therapeutic agents for the cure of this disease. Here we have explained the analysis that could be useful for drug-design discovery against this disease. It has been focused on the drugs that may target (M Pro) the main protease of SARS-CoV-2 which is responsible for the disease. MPro is a leading enzyme of Coronaviruses and plays a vital role in transcription and replication that shows an important drug target for SARS-CoV-2. The process starts with the generation of protein dataset frames by running molecular dynamic simulations for small-time units which shows an analytical representation of the molecular surface protein. After that, derived geometrical descriptors are computed protein datasets by using primary geometrical descriptors such as mean, Gaussian, principal curvatures, shape index, curvedness, and fundamental forms coefficients. After the features extraction computation, protein classification is performed. Classification of several candidate Inhibitors of MPro active compounds with targeted main protease based on these features and classification. Our results achieve the efficiency that can help us to understand better the function of protein-ligand interaction and drug-design discovery process.

Relatori: Federica Marcolin, Jacek Adam Tuszynski
Anno accademico: 2020/21
Tipo di pubblicazione: Elettronica
Numero di pagine: 67
Informazioni aggiuntive: Tesi secretata. Fulltext non presente
Soggetti:
Corso di laurea: Corso di laurea magistrale in Communications And Computer Networks Engineering (Ingegneria Telematica E Delle Comunicazioni)
Classe di laurea: Nuovo ordinamento > Laurea magistrale > LM-27 - INGEGNERIA DELLE TELECOMUNICAZIONI
Aziende collaboratrici: NON SPECIFICATO
URI: http://webthesis.biblio.polito.it/id/eprint/15854
Modifica (riservato agli operatori) Modifica (riservato agli operatori)