skip to main content
Idioma:

Predicting protein condensate formation using machine learning

van Mierlo, Guido ; Jansen, Jurriaan R.G. ; Wang, Jie ; Poser, Ina ; van Heeringen, Simon J. ; Vermeulen, Michiel

Cell reports (Cambridge), 2021-02, Vol.34 (5), p.108705-108705, Article 108705 [Periódico revisado por pares]

United States: Elsevier Inc

Texto completo disponível

Citações Citado por
  • Título:
    Predicting protein condensate formation using machine learning
  • Autor: van Mierlo, Guido ; Jansen, Jurriaan R.G. ; Wang, Jie ; Poser, Ina ; van Heeringen, Simon J. ; Vermeulen, Michiel
  • Assuntos: Biomolecular Condensates - genetics ; Humans ; Machine Learning - standards ; phase separation, machine learning, condensate formation ; Protein Biosynthesis - genetics
  • É parte de: Cell reports (Cambridge), 2021-02, Vol.34 (5), p.108705-108705, Article 108705
  • Notas: ObjectType-Article-1
    SourceType-Scholarly Journals-1
    ObjectType-Feature-2
    content type line 23
  • Descrição: Membraneless organelles are liquid condensates, which form through liquid-liquid phase separation. Recent advances show that phase separation is essential for cellular homeostasis by regulating basic cellular processes, including transcription and signal transduction. The reported number of proteins with the capacity to mediate protein phase separation (PPS) is continuously growing. While computational tools for predicting PPS have been developed, obtaining a proteome-wide overview of PPS probabilities has remained challenging. Here, we present a phase separation analysis and prediction (PSAP) machine-learning classifier that, based solely on the amino acid content of a training set of known PPS proteins, can determine the phase separation likelihood for each protein in a given proteome. Through comparison with PPS databases, existing predictors, and experimental evidence, we demonstrate the validity and advantages of the PSAP classifier. We anticipate that the PSAP predictor provides a useful tool for future research aimed at identifying phase separating proteins in health and disease. [Display omitted] •An overview of amino acid features associated with condensate-forming (PPS) proteins•Development of a machine learning classifier (PSAP) to predict candidate PPS proteins•PSAP enabled the discovery of new PPS proteins, including DAZAP1 and CPEB3 van Mierlo et al. curate human PPS proteins to identify a range of specific amino acid features that are associated with protein condensate formation. By using these features in machine learning, they develop a classifier that can predict candidate proteins with phase separation capacities in a given proteome.
  • Editor: United States: Elsevier Inc
  • Idioma: Inglês
Links
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.