Interaction prediction in structure-based virtual screening using deep learning

Adam Gonczarek*, Jakub M. Tomczak, Szymon Zaręba, Joanna Kaczmar, Piotr Dąbrowski, Michał J. Walczak

*Corresponding author for this work

Research output: Contribution to JournalArticleAcademicpeer-review

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.

Original languageEnglish
Pages (from-to)253-258
Number of pages6
JournalComputers in Biology and Medicine
Volume100
DOIs
Publication statusPublished - 1 Sept 2018
Externally publishedYes

Funding

The work conducted in this paper is partially co-financed by European Regional Development Fund within the framework of the Smart Growth Operational Programme 2014-2020 , grant No. POIR.01.01.01-00-1083/15 .

FundersFunder number
European Regional Development FundPOIR.01.01.01-00-1083/15

    Keywords

    • Deep learning
    • DUD-E
    • Graph convolution
    • MUV
    • Neural fingerprint
    • PDBBind
    • Virtual screening

    Fingerprint

    Dive into the research topics of 'Interaction prediction in structure-based virtual screening using deep learning'. Together they form a unique fingerprint.

    Cite this