Transfer Learning Approach to Develop Natural Molecules with Specific Flavor Requirements

• Tipo: Artigo em Revista Científica Internacional
• Data: 2023

Autores

Queiroz, LP (Autor) Outra; Rebello, CM (Autor) Outra; Costa, EA (Autor) Outra; Santana, VV (Autor) Outra; Rodrigues, BCL (Autor) Outra; Rodrigues, AE (Autor) Outra; Ana M. Ribeiro (Autor) FEUP; Nogueira, IBR (Autor) Outra

Revista

Título: Industrial & Engineering Chemistry Research

Vol. 62

Páginas: 9062-9076

ISSN: 0888-5885

Editora: American Chemical Society

Indexação

ISI Web of Knowledge - 0 Citações

Scopus - 0 Citações

Projetos Associados

LA LSRE-LCM - Financiamento Plurianual 2020-2023 para a Unidade LA LSRE-LCM Laboratório de Processos de Separação e Reacção - Laboratório de Catálise e Materiais

Outras Informações

ID Authenticus: P-00Y-M6A

DOI: 10.1021/acs.iecr.3c00722

Abstract (EN): In the past decades, the flavor industry's investmentinresearch and development has increased to take innovative steps. Meanwhile,the lack of information regarding the flavored molecules and specificflavoring properties is an obstacle to advances in this sector. Inthis context, this work presents the implementation of three scientificmachine learning techniques as an innovative methodology to designnew natural flavor molecules with specific desired properties to productdevelopment. The transfer learning technique is presented to tacklethe lack of data available when analyzing flavor molecules. Nine flavordescriptors were studied along this work, and all of them presentedmore than 50% of molecules generated within the outstanding resultsconsidered for the evaluation metric, natural product-likeness scoreand synthetic accessibility score. Finally, a discussion of the resultsis constructed based on the data availability, the presence in nature,and the multisensorial flavor component impact for the specific flavors'results.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 15