Machine Learning Models Identify Inhibitors of SARS-CoV-2

Autor(es):Mostrar menos -

Gawriljuk, Victor O. ^[1] ; Zin, Phyo Phyo Kyaw ^[2] ; Puhl, Ana C. ^[2] ; Zorn, Kimberley M. ^[2] ; Foil, Daniel H. ^[2] ; Lane, Thomas R. ^[2] ; Hurst, Brett ^{[3, 4]} ; Tavella, Tatyana Almeida ^[5] ; Maranhao Costa, Fabio Trindade ^[5] ; Lakshmanane, Premkumar ^[6] ; Bernatchez, Jean ^[7] ; Godoy, Andre S. ^[1] ; Oliva, Glaucius ^[1] ; Siqueira-Neto, Jair L. ^[7] ; Madrid, Peter B. ^[8] ; Ekins, Sean ^[2]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Sao Carlos Inst Phys, BR-13563120 Sao Carlos, SP - Brazil

^[2] Collaborat Pharmaceut Inc, Raleigh, NC 27606 - USA

^[3] Utah State Univ, Inst Antiviral Res, Logan, UT 84322 - USA

^[4] Utah State Univ, Dept Anim Dairy & Vet Sci, Logan, UT 84322 - USA

^[5] Univ Campinas UNICAMP, Dept Genet Evolut Microbiol & Immunol, Lab Trop Dis Prof Dr Luiz Jacinto da Silva, Campinas, SP - Brazil

^[6] Univ N Carolina, Sch Med, Dept Microbiol & Immunol, Chapel Hill, NC 27599 - USA

^[7] Univ Calif San Diego, Skaggs Sch Pharm & Pharmaceut Sci, San Diego, CA 92093 - USA

^[8] SRI Int, 333 Ravenswood Ave, Menlo Pk, CA 94025 - USA

• Tipo de documento: Artigo Científico
• Fonte: JOURNAL OF CHEMICAL INFORMATION AND MODELING; v. 61, n. 9, p. 4224-4235, SEP 27 2021.
• Citações Web of Science: 0

Resumo

With the rapidly evolving SARS-CoV-2 variants of concern, there is an urgent need for the discovery of further treatments for the coronavirus disease (COVID-19). Drug repurposing is one of the most rapid strategies for addressing this need, and numerous compounds have already been selected for in vitro testing by several groups. These have led to a growing database of molecules with in vitro activity against the virus. Machine learning models can assist drug discovery through prediction of the best compounds based on previously published data. Herein, we have implemented several machine learning methods to develop predictive models from recent SARS-CoV-2 in vitro inhibition data and used them to prioritize additional FDA-approved compounds for in vitro testing selected from our in-house compound library. From the compounds predicted with a Bayesian machine learning model, lumefantrine, an antimalarial was selected for testing and showed limited antiviral activity in cell-based assays while demonstrating binding (K-d 259 nM) to the spike protein using microscale thermophoresis. Several other compounds which we prioritized have since been tested by others and were also found to be active in vitro. This combined machine learning and in vitro testing approach can be expanded to virtually screen available molecules with predicted activity against SARS-CoV-2 reference WIVO4 strain and circulating variants of concern. In the process of this work, we have created multiple iterations of machine learning models that can be used as a prioritization tool for SARS-CoV-2 antiviral drug discovery programs. The very latest model for SARS-CoV-2 with over 500 compounds is now freely available at www.assaycentrai.org. (AU)

• Processo FAPESP: 20/05369-6 - Estratégia acelerada por inteligência artificial para reposicionamento de fármacos contra COVID-19
• Beneficiário: Fabio Trindade Maranhão Costa
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 19/27626-3 - Identificação de novos tratamentos antimaláricos através de uma abordagem de "reposicionamento de fármacos" centrada no alvo
• Beneficiário: Tatyana Almeida Tavella
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 19/25407-2 - Desenvolvimento de modelos de aprendizado de máquina para a descoberta de novos compostos antivirais contra o vírus da febre amarela
• Beneficiário: Victor Gawriljuk Ferraro Oliveira
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Mestrado