Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Artículo científico (JournalArticle)

Unravelling cyclic peptide membrane permeability prediction: a study on data augmentation, architecture choices, and representation schemes

  • Cabezón Vizoso, Alfonso
  • Otović, Erik
  • Kalafatovic, Daniela
  • Piñeiro Guillén, Ángel
  • García Fandiño, Rebeca
  • Mauša, Goran
Cyclic peptides have emerged as promising candidates for drug development due to their unique structural properties and potential therapeutic benefits. However, clinical applications are limited by their low membrane permeability, which is difficult to predict. This study explores the impact of data augmentation and the inclusion of cyclic structure information in ML modeling to enhance the prediction of membrane permeability of cyclic peptides from their amino acid sequence. Various peptide representation strategies in combination with data augmentation techniques based on amino acid mutations and cyclic permutations were investigated to address the limited availability of experimental data. Moreover, cyclic convolutional layers were explored to explicitly model the cyclic nature of the peptides. The results indicated that combining sequential and peptide properties demonstrated superior performance across multiple metrics. The model performance is highly sensitive to the number and degree of similarity of amino acids involved in mutations. Cyclic permutations improved model performance, particularly in a larger and more diverse dataset and standard architectures captured most of the relevant cyclic information. Highlighting the complexity of peptide-membrane interactions, these results lay a foundation for future improvements in computational methods for the design of cyclic peptide drugs and offer practical guidelines for researchers in this field. The best-performing model was integrated into a user-friendly web-based tool, CYCLOPS: CYCLOpeptide Permeability Simulator (available at http://cyclopep.com/cyclops), to facilitate wider accessibility and application in drug discovery community. This tool allows for rapid predictions of the membrane permeability for cyclic peptides with a classification accuracy score of 0.824 and a regression mean absolute error of 0.477.
Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Artículo científico (JournalArticle)

A comprehensive nomenclature system for cyclodextrins

  • Anderson, Amelia M.
  • O'Connor, Matthew S.
  • Pipkin, James
  • Malanga, Milo
  • Sohajda, Tamas
  • Loftsson, Thorsteinn
  • Szente, Lajos
  • García Fandiño, Rebeca
  • Piñeiro Guillén, Ángel
Modified cyclodextrins (CDs) are cyclic oligosaccharides with many applications in drug delivery, catalysis, and as active pharmaceutical ingredients. In general, they exist as distributions of structurally diverse molecules rather than single-isomer compounds. Their performance depends on the number of glucopyranose units (GPUs), and the type, number, and position of chemical substitutions in their hydroxyl groups. Effectively targeting individual species within these distributions is essential for optimizing CDs for specific applications. Computational techniques can generate large datasets to AI-driven structural optimization, but the absence of a standardized nomenclature system for modified CDs presents a major barrier to progress in this direction. This lack of consensus limits effective communication, data sharing, automation, and collaboration. To address this, a clear and extensible nomenclature for modified CDs is proposed. In this framework, GPUs are treated like amino-acid residues, with unsubstituted GPUs as reference building-blocks and substituted ones considered as mutations. This approach precisely defines substitution types and patterns, resolves cyclic permutation ambiguities, and offers versatility for both simple and complex modifications, including chiral center alterations and covalently linked CD oligomers. By introducing this standardized nomenclature, we aim to enhance molecular design, improve reproducibility, and streamline both experimental and computational research in the CD field.