Premium
Cover Feature: Identification of Synthetic Activators of Cancer Cell Migration by Hybrid Deep Learning (ChemBioChem 4/2020)
Author(s) -
Bruns Dominique,
Gawehn Erik,
Kumar Karthiga Santhana,
Schneider Petra,
Baumgartner Martin,
Schneider Gisbert
Publication year - 2020
Publication title -
chembiochem
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.05
H-Index - 126
eISSN - 1439-7633
pISSN - 1439-4227
DOI - 10.1002/cbic.202000041
Subject(s) - feature (linguistics) , cover (algebra) , convolutional neural network , identification (biology) , computational biology , chemistry , focus (optics) , deep learning , molecule , artificial intelligence , computer science , combinatorial chemistry , biology , physics , engineering , mechanical engineering , organic chemistry , philosophy , linguistics , botany , optics
The cover feature picture shows at the bottom the pharmacophoric map of a molecule. This map was used as input for a convolutional neural network that was previously trained on known bioactive molecules, with a focus on compounds with annotated CXCR4 activity. The network associates the mapped molecules (top left) with an activity pseudo‐probability. These predictions were confirmed in a spheroid invasion assay, showing the migration of cells (top right). More information can be found in the full paper by G. Schneider et al. on page 500 in Issue 4, 2020 (DOI: 10.1002/cbic.201900346).