DeepAllo: allosteric site prediction using protein language model (pLM) with multitask learning.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: Allostery, the process by which binding at one site perturbs a distant site, is being rendered as a key focus in the field of drug development with its substantial impact on protein function. The identification of allosteric pockets (sites) is a challenging task and several techniques have been developed, including Machine Learning to predict allosteric pockets that utilize both static and pocket features.

Authors

  • Moaaz Khokhar
    Department of Computer Engineering, KoƧ University, 34450 Istanbul, Turkey.
  • Ozlem Keskin
    Department of Chemical and Biological Engineering, Koc University, Istanbul, 34450, Turkey. Electronic address: okeskin@ku.edu.tr.
  • Attila Gursoy
    Department of Computer Engineering, Koc University, Istanbul, 34450, Turkey. Electronic address: agursoy@ku.edu.tr.