| spelling |
Douglas Eduardo Valente Pireshttp://lattes.cnpq.br/2675409574553301David Benjamin AscherLucas BleicherRafaela Salgado FerreiraRubens Lima do Monte NetoWandré Nunes de Pinho Velosohttp://lattes.cnpq.br/8174409471999279João Paulo Linhares Velloso2023-05-04T14:46:49Z2023-05-04T14:46:49Z2022-04-27http://hdl.handle.net/1843/52800GPCRs are crucial receptors for many vital physiological processes including control of cell division and proliferation, regulation of ion transport, modulation of neuronal firing, homeostasis, modulation, and modification of cell morphology. They are also involved in many pathological processes, such as in Alzheimer’s and Parkinson’s disease, cardiovascular disorder, asthma, depression and diabetes. Given their biological importance, over a third of FDA approved drugs target GPCRs. Nonetheless, GPCRs lead compound development suffers from high attrition rates, with poor in vivo efficacy being the primary contributor, resulting in only 7% of all drugs (for other receptors as well) in phase I studies being marketed. This thesis focused on the development of machine learning models capable of predicting bioactivity of small molecules when interacting with GPCRs as means to support the discovery of novel leads through ranking compounds on drug discovery investigations, which would enable enriching screening libraries with compounds more likely to be active. The developed models (composing the pdCSM-GPCR tool) rely on deriving a range of molecular signatures from known ligands, associating them to bioactivities, and modelling them as regression problems, making them independent of receptor structural information. Because of this characteristic, the same approach can be used for any GPCRs which already had been screened for ligands, and also other important targets, including kinases, and ligand-gated ion channels. Our models make up the most comprehensive computational resource for prediction of GPCR bioactivity to date, including support for drug development for orphan GPCRs. Our approach achieved Pearson’s correlations of up to 0.89, across 10-fold cross- validation and blind tests. We significantly outperformed previous methods. pdCSM-GPCR was made freely available via a user-friendly web server at http://biosig.unimelb.edu.au/pdcsm_gpcr. We also investigated the properties of small molecules with high affinity for GPCRs in order to identify molecular determinants of recognition. Overall, potent ligands possess nitrogen- containing fragments and aromatic rings, features common in ligands across all classes of GPCRs. The outcomes of this research provide powerful tools for GPCR drug discovery and valuable biological insights into the characteristics that make up GPCR ligands.Os receptores acoplados a proteína G (GPCR) são cruciais para muitos processos fisiológicos vitais, incluindo controle da divisão e proliferação celular, regulação do transporte de íons, modu- lação sinapse nervosa, homeostase, modulação e modificação da morfologia celular. Eles também estão envolvidos em muitos processos patológicos, como Alzheimer e Parkinson, distúrbios cardiovasculares, asma, depressão e diabete. Dada a sua importância biológica, mais de um terço dos medicamentos aprovados pela FDA têm como alvo esses receptores. No entanto, o desenvolvimento de fármacos para GPCRs passa por altas taxas de fracasso, com baixa eficácia in vivo sendo o principal contribuinte nesse processo. Isso resulta em apenas 7% de todos os medicamentos (incluindo outros receptores) em estudos de fase I sendo comercializados. Esta tese se concentrou no desenvolvimento de modelos de aprendizado de máquina capazes de prever a bioatividade de pequenas moléculas ao interagir com GPCRs. Pretendemos com essas ferramentas apoiar a descoberta de novos fármacos. Os modelos desenvolvidos (compõe o servidor web pdCSM-GPCR) baseiam-se em derivar uma série de assinaturas moleculares de ligantes conhecidos, associando essas assinaturas a bioatividade e modelando essas questões como problemas de regressão, sem a necessidade de informação estrutural do receptor. Devido a esta característica, a mesma abordagem pode ser usada para quaisquer GPCRs que já tenham sido avaliadas através triagem para ligantes, e também para outros alvos importantes, incluindo quinases e canais iônicos controlados por ligantes. Nossos modelos compõem o recurso computa- cional mais abrangente para previsão da bioatividade de GPCR até o momento, e inclui também suporte para o desenvolvimento de medicamentos para GPCRs órfãos. Nossa abordagem al- cançou correlações de Pearson de até 0,89, por meio de validação cruzada de 10 vezes e em testes cegos. Superamos significativamente os métodos anteriores. O pdCSM-GPCR foi disponibilizado gratuitamente por meio um servidor web http://biosig.unimelb.edu.au/pdcsm_gpcr. Também investigamos as propriedades de pequenas moléculas com alta afinidade por GPCRs a fim de identificar determinantes moleculares de reconhecimento. Em geral, ligantes potentes possuem fragmentos contendo nitrogênio e anéis aromáticos, características comuns em ligantes em todas as classes de GPCRs. Os resultados desta pesquisa fornecem ferramentas poderosas para a descoberta de fármacos e informações biológicas valiosas sobre as características que compõem os ligantes de GPCR.CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível SuperiorengUniversidade Federal de Minas GeraisPrograma de Pós-Graduação em BioinformaticaUFMGBrasilBioinformáticaAprendizado de MáquinaDesenvolvimento de MedicamentosReceptores Acoplados a Proteínas-GAprendizado de MáquinaDesenvolvimento de MedicamentosReceptores Acoplados a Proteínas GIn silico discovery of GPCR ligands using graph-based signatures and auxiliary featuresinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFMGinstname:Universidade Federal de Minas Gerais (UFMG)instacron:UFMGLICENSElicense.txtlicense.txttext/plain; charset=utf-82118https://repositorio.ufmg.br/bitstream/1843/52800/4/license.txtcda590c95a0b51b4d15f60c9642ca272MD54ORIGINALtese_ficha_ata_ap_joao_velloso_number_key_fixed.pdftese_ficha_ata_ap_joao_velloso_number_key_fixed.pdftese de doutorado Joao Paulo Linhares Vellosoapplication/pdf31263029https://repositorio.ufmg.br/bitstream/1843/52800/3/tese_ficha_ata_ap_joao_velloso_number_key_fixed.pdf2d5db3cd356f631e134142ca0310aacfMD531843/528002023-05-04 11:46:50.229oai:repositorio.ufmg.br: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ório InstitucionalPUBhttps://repositorio.ufmg.br/oaiopendoar:2023-05-04T14:46:50Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG)false
|