Sequence-based prediction of protein secretion success in Aspergillus niger

  • Authors:

  • Bastiaan A. Van Den Berg;Jurgen F. Nijkamp;Marcel J. T. Reinders;Liang Wu;Herman J. Pel;Johannes A. Roubos;Dick De Ridder

  • Affiliations:

  • The Delft Bioinformatics Lab, Delft University of Technology, The Netherlands and Netherlands Bioinformatics Centre, The Netherlands and Kluyver Centre for Genomics of Industrial Fermentation, The ...;The Delft Bioinformatics Lab, Delft University of Technology, The Netherlands and Kluyver Centre for Genomics of Industrial Fermentation, The Netherlands;The Delft Bioinformatics Lab, Delft University of Technology, The Netherlands and Netherlands Bioinformatics Centre, The Netherlands and Kluyver Centre for Genomics of Industrial Fermentation, The ...;DSM Biotechnology Center, The Netherlands;DSM Biotechnology Center, The Netherlands;DSM Biotechnology Center, The Netherlands;The Delft Bioinformatics Lab, Delft University of Technology, The Netherlands and Netherlands Bioinformatics Centre, The Netherlands and Kluyver Centre for Genomics of Industrial Fermentation, The ...

  • Venue:
  • PRIB'10 Proceedings of the 5th IAPR international conference on Pattern recognition in bioinformatics
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The cell-factory A spergillus niger is widely used for industrial enzyme production. To select potential proteins for large-scale production, we developed a sequence-based classifier that predicts if an over-expressed homologous protein will successfully be produced and secreted. A dataset of 638 proteins was used to train and validate a classifier, using a 10-fold cross-validation protocol. Using a linear discriminant classifier, an average accuracy of 0.85 was achieved. Feature selection results indicate what features are mostly defining for successful protein production, which could be an interesting lead to couple sequence characteristics to biological processes involved in protein production and secretion.