AutoPeptideML: a study on how to build more trustworthy peptide bioactivity predictors.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: Automated machine learning (AutoML) solutions can bridge the gap between new computational advances and their real-world applications by enabling experimental scientists to build their own custom models. We examine different steps in the development life-cycle of peptide bioactivity binary predictors and identify key steps where automation cannot only result in a more accessible method, but also more robust and interpretable evaluation leading to more trustworthy models.

Authors

  • Raúl Fernández-Díaz
    IBM Research, Dublin, Dublin D15 HN66, Ireland.
  • Rodrigo Cossio-Pérez
    School of Medicine, University College Dublin, Dublin D04 C1P1, Ireland.
  • Clement Agoni
    School of Medicine, University College Dublin, Dublin D04 C1P1, Ireland.
  • Hoang Thanh Lam
    IBM Research, Dublin, Dublin D15 HN66, Ireland.
  • Vanessa Lopez
    IBM Research Ireland, Dublin, Ireland.
  • Denis C Shields
    School of Medicine, University College Dublin, Dublin D04 C1P1, Ireland.