Interaction prediction in structure-based virtual screening using deep learning.

Journal: Computers in biology and medicine
Published Date:

Abstract

We introduce a deep learning architecture for structure-based virtual screening that generates fixed-sized fingerprints of proteins and small molecules by applying learnable atom convolution and softmax operations to each molecule separately. These fingerprints are further non-linearly transformed, their inner product is calculated and used to predict the binding potential. Moreover, we show that widely used benchmark datasets may be insufficient for testing structure-based virtual screening methods that utilize machine learning. Therefore, we introduce a new benchmark dataset, which we constructed based on DUD-E, MUV and PDBBind databases.

Authors

  • Adam Gonczarek
    Department of Computer Science, Wrocław University of Science and Technology, Poland; Alphamoon, Wrocław, Poland. Electronic address: adam.gonczarek@pwr.edu.pl.
  • Jakub M Tomczak
    Department of Computer Science, Wrocław University of Science and Technology, Poland.
  • Szymon Zaręba
    Department of Computer Science, Wrocław University of Science and Technology, Poland; Alphamoon, Wrocław, Poland.
  • Joanna Kaczmar
    Department of Computer Science, Wrocław University of Science and Technology, Poland.
  • Piotr Dąbrowski
    Department of Computer Science, Wrocław University of Science and Technology, Poland; Indata SA, Wrocław, Poland.
  • Michał J Walczak
    Alphamoon, Wrocław, Poland.