Premium
Front Cover: Designing Anticancer Peptides by Constructive Machine Learning (ChemMedChem 13/2018)
Author(s) -
Grisoni Francesca,
Neuhaus Claudia S.,
Gabernet Gisela,
Müller Alex T.,
Hiss Jan A.,
Schneider Gisbert
Publication year - 2018
Publication title -
chemmedchem
Language(s) - English
Resource type - Reports
SCImago Journal Rank - 0.817
H-Index - 100
eISSN - 1860-7187
pISSN - 1860-7179
DOI - 10.1002/cmdc.201800415
Subject(s) - front cover , constructive , cover (algebra) , artificial neural network , peptide , artificial intelligence , chemistry , computational biology , computer science , biology , biochemistry , engineering , mechanical engineering , process (computing) , operating system
The Front Cover illustrates the membranolytic action of an anticancer peptide (ACP) that was designed de novo by constructive machine learning. A recurrent neural network model was developed for pattern recognition in the sequences of α‐helical cationic amphipathic peptides and then fine‐tuned on known ACPs by transfer learning. Novel ACPs were automatically generated by this constructive network model. Twelve de novo peptides were synthesized and tested for their activity on MCF7 human breast adenocarcinoma cells and selectivity against human erythrocytes. Ten of these peptides were active against cancer cells, and six had at least threefold selectivity on human erythrocytes. Cover artwork by Dr. Francesca Grisoni. More information can be found in the Communication by Gisbert Schneider et al. on page 1300 in Issue 13, 2018 (DOI: 10.1002/cmdc.201800204).