Skip to main content

Resultados relacionados

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

Repositorio Digital de la UPF
Publication Artículo científico (JournalArticle)

iDeepLC: chemical structure information yields improved retention time prediction of peptides with unseen modifications

  • Nameni, Alireza
  • Declercq, Arthur
  • Gabriels, Ralf
  • Devreese, Robbe
  • Degroeve, Sven
  • De Maesschalck, Amélie
  • Dhaenens, Maarten
  • Chiva, Cristina
  • Sabidó Aguadé, Eduard, 1981-
  • Martens, Lennart
  • Bouwmeester, Robbin
Deep learning has notably advanced the field of liquid chromatography¿mass spectrometry-based proteomics. Accurate prediction of peptide retention times significantly enhances our ability to match LC-MS data with the correct peptides and proteins, especially for data-independent acquisition data. While numerous models predict peptide LC retention times with high accuracy, few can accurately predict the retention times of chemically modified peptides, particularly those with modifications not encountered during model training. In our previously developed DeepLC model, accurate predictions could be made for unseen modifications by leveraging the chemical compositions of (modified) residues. Here, however, we present a further enhancement of this model based on the chemical structural information. The resulting model, called iDeepLC, shows overall more accurate predictions and better generalization performance for predicting the retention time of modifications structurally defined as SMILES but unseen during training than DeepLC. iDeepLC is freely available as an open-source software under the Apache2 license and can be found at https://github.com/CompOmics/iDeepLC., A.N. acknowledges funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement N° 956148. S.D. acknowledges funding from the European Union’s Horizon 2020 Programme grant no. H2020-INFRAIA-2018-1. R.D., A.D., R.G., L.M., and R.B. acknowledge funding from the Research Foundation Flanders (FWO) [1SH9O24N, 12B7123N, 1SE3724N, G010023N, G028821N, 12A6L24N]. L.M. acknowledges funding from the Horizon Europe Projects BAXERNA 2.0 [101080544] and COMBINE [101191739], and from the Ghent University Concerted Research Action [BOF21/GOA/033]. L.M. is further supported by the CHIST-ERA project ODEEP-EU [G0GDV23N]. C.C. and E.S. acknowledge support from the Spanish Ministry of Science, Innovation, and Universities (PID2024-157336NB-I00, CEX2020-001049-S), and the Generalitat de Catalunya through the CERCA programme and The Departament de Recerca i Universitats de la Generalitat de Catalunya (2021SGR01225). The CRG/UPF Proteomics Unit is part of the Spanish Infrastructure for Omics Technologies (ICTS OmicsTech).
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

iDeepLC: chemical structure information yields improved retention time prediction of peptides with unseen modifications

  • Nameni, Alireza
  • Declercq, Arthur
  • Gabriels, Ralf
  • Devreese, Robbe
  • Degroeve, Sven
  • De Maesschalck, Amélie
  • Dhaenens, Maarten
  • Chiva, Cristina
  • Sabidó Aguadé, Eduard, 1981-
  • Martens, Lennart
  • Bouwmeester, Robbin
Deep learning has notably advanced the field of liquid chromatography¿mass spectrometry-based proteomics. Accurate prediction of peptide retention times significantly enhances our ability to match LC-MS data with the correct peptides and proteins, especially for data-independent acquisition data. While numerous models predict peptide LC retention times with high accuracy, few can accurately predict the retention times of chemically modified peptides, particularly those with modifications not encountered during model training. In our previously developed DeepLC model, accurate predictions could be made for unseen modifications by leveraging the chemical compositions of (modified) residues. Here, however, we present a further enhancement of this model based on the chemical structural information. The resulting model, called iDeepLC, shows overall more accurate predictions and better generalization performance for predicting the retention time of modifications structurally defined as SMILES but unseen during training than DeepLC. iDeepLC is freely available as an open-source software under the Apache2 license and can be found at https://github.com/CompOmics/iDeepLC., A.N. acknowledges funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement N° 956148. S.D. acknowledges funding from the European Union’s Horizon 2020 Programme grant no. H2020-INFRAIA-2018-1. R.D., A.D., R.G., L.M., and R.B. acknowledge funding from the Research Foundation Flanders (FWO) [1SH9O24N, 12B7123N, 1SE3724N, G010023N, G028821N, 12A6L24N]. L.M. acknowledges funding from the Horizon Europe Projects BAXERNA 2.0 [101080544] and COMBINE [101191739], and from the Ghent University Concerted Research Action [BOF21/GOA/033]. L.M. is further supported by the CHIST-ERA project ODEEP-EU [G0GDV23N]. C.C. and E.S. acknowledge support from the Spanish Ministry of Science, Innovation, and Universities (PID2024-157336NB-I00, CEX2020-001049-S), and the Generalitat de Catalunya through the CERCA programme and The Departament de Recerca i Universitats de la Generalitat de Catalunya (2021SGR01225). The CRG/UPF Proteomics Unit is part of the Spanish Infrastructure for Omics Technologies (ICTS OmicsTech).