De novo design of anticancer peptides by ensemble artificial neural networks

Francesca Grisoni; Claudia S. Neuhaus; Miyabi Hishinuma; Gisela Gabernet; Jan A. Hiss; Masaaki Kotera; Gisbert Schneider

doi:10.1007/s00894-019-4007-6

De novo design of anticancer peptides by ensemble artificial neural networks

Francesca Grisoni, Claudia S. Neuhaus, Miyabi Hishinuma, Gisela Gabernet, Jan A. Hiss, Masaaki Kotera, Gisbert Schneider

Research output: Contribution to journal › Article › Academic › peer-review

53 Citations (Scopus)

Abstract

Membranolytic anticancer peptides (ACPs) are drawing increasing attention as potential future therapeutics against cancer, due to their ability to hinder the development of cellular resistance and their potential to overcome common hurdles of chemotherapy, e.g., side effects and cytotoxicity. In this work, we present an ensemble machine learning model to design potent ACPs. Four counter-propagation artificial neural-networks were trained to identify peptides that kill breast and/or lung cancer cells. For prospective application of the ensemble model, we selected 14 peptides from a total of 1000 de novo designs, for synthesis and testing in vitro on breast cancer (MCF7) and lung cancer (A549) cell lines. Six de novo designs showed anticancer activity in vitro, five of which against both MCF7 and A549 cell lines. The novel active peptides populate uncharted regions of ACP sequence space.

Original language	English
Article number	112
Journal	Journal of Molecular Modeling
Volume	25
Issue number	5
DOIs	https://doi.org/10.1007/s00894-019-4007-6
Publication status	Published - 5 Apr 2019
Externally published	Yes

Bibliographical note

Funding Information:
Acknowledgments The authors thank Sarah Haller for technical support. This research was financially supported by the Swiss National Science Foundation (grants no. CRSII2_160699, no. 200021_157190 and no. IZSEZ0_177477). M.H. was financially supported by BTobitate! (Leap for tomorrow)^ study abroad initiative (Japan’s Ministry of Education, Culture, Sports, Science, and Technology [MEXT]).

Publisher Copyright:
© 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

Funding

Acknowledgments The authors thank Sarah Haller for technical support. This research was financially supported by the Swiss National Science Foundation (grants no. CRSII2_160699, no. 200021_157190 and no. IZSEZ0_177477). M.H. was financially supported by BTobitate! (Leap for tomorrow)^ study abroad initiative (Japan’s Ministry of Education, Culture, Sports, Science, and Technology [MEXT]).

Keywords

Artificial intelligence
Cancer
Counterpropagation
Machine learning
Membranolysis
Peptide design
A549 Cells
Neural Networks, Computer
Humans
Peptides/chemistry
Models, Molecular
Neoplasms/drug therapy
Antineoplastic Agents/chemistry
Machine Learning
MCF-7 Cells
Cell Proliferation/drug effects

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/s00894-019-4007-6

Cite this

@article{891b0cbc5c9d44fca6aa5a2dba19967b,

title = "De novo design of anticancer peptides by ensemble artificial neural networks",

abstract = "Membranolytic anticancer peptides (ACPs) are drawing increasing attention as potential future therapeutics against cancer, due to their ability to hinder the development of cellular resistance and their potential to overcome common hurdles of chemotherapy, e.g., side effects and cytotoxicity. In this work, we present an ensemble machine learning model to design potent ACPs. Four counter-propagation artificial neural-networks were trained to identify peptides that kill breast and/or lung cancer cells. For prospective application of the ensemble model, we selected 14 peptides from a total of 1000 de novo designs, for synthesis and testing in vitro on breast cancer (MCF7) and lung cancer (A549) cell lines. Six de novo designs showed anticancer activity in vitro, five of which against both MCF7 and A549 cell lines. The novel active peptides populate uncharted regions of ACP sequence space.",

keywords = "Artificial intelligence, Cancer, Counterpropagation, Machine learning, Membranolysis, Peptide design, A549 Cells, Neural Networks, Computer, Humans, Peptides/chemistry, Models, Molecular, Neoplasms/drug therapy, Antineoplastic Agents/chemistry, Machine Learning, MCF-7 Cells, Cell Proliferation/drug effects",

author = "Francesca Grisoni and Neuhaus, {Claudia S.} and Miyabi Hishinuma and Gisela Gabernet and Hiss, {Jan A.} and Masaaki Kotera and Gisbert Schneider",

note = "Funding Information: Acknowledgments The authors thank Sarah Haller for technical support. This research was financially supported by the Swiss National Science Foundation (grants no. CRSII2_160699, no. 200021_157190 and no. IZSEZ0_177477). M.H. was financially supported by BTobitate! (Leap for tomorrow)^ study abroad initiative (Japan{\textquoteright}s Ministry of Education, Culture, Sports, Science, and Technology [MEXT]). Publisher Copyright: {\textcopyright} 2019, Springer-Verlag GmbH Germany, part of Springer Nature.",

year = "2019",

month = apr,

day = "5",

doi = "10.1007/s00894-019-4007-6",

language = "English",

volume = "25",

journal = "Journal of Molecular Modeling",

issn = "1610-2940",

publisher = "Springer",

number = "5",

}

TY - JOUR

T1 - De novo design of anticancer peptides by ensemble artificial neural networks

AU - Grisoni, Francesca

AU - Neuhaus, Claudia S.

AU - Hishinuma, Miyabi

AU - Gabernet, Gisela

AU - Hiss, Jan A.

AU - Kotera, Masaaki

AU - Schneider, Gisbert

N1 - Funding Information: Acknowledgments The authors thank Sarah Haller for technical support. This research was financially supported by the Swiss National Science Foundation (grants no. CRSII2_160699, no. 200021_157190 and no. IZSEZ0_177477). M.H. was financially supported by BTobitate! (Leap for tomorrow)^ study abroad initiative (Japan’s Ministry of Education, Culture, Sports, Science, and Technology [MEXT]). Publisher Copyright: © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

PY - 2019/4/5

Y1 - 2019/4/5

N2 - Membranolytic anticancer peptides (ACPs) are drawing increasing attention as potential future therapeutics against cancer, due to their ability to hinder the development of cellular resistance and their potential to overcome common hurdles of chemotherapy, e.g., side effects and cytotoxicity. In this work, we present an ensemble machine learning model to design potent ACPs. Four counter-propagation artificial neural-networks were trained to identify peptides that kill breast and/or lung cancer cells. For prospective application of the ensemble model, we selected 14 peptides from a total of 1000 de novo designs, for synthesis and testing in vitro on breast cancer (MCF7) and lung cancer (A549) cell lines. Six de novo designs showed anticancer activity in vitro, five of which against both MCF7 and A549 cell lines. The novel active peptides populate uncharted regions of ACP sequence space.

AB - Membranolytic anticancer peptides (ACPs) are drawing increasing attention as potential future therapeutics against cancer, due to their ability to hinder the development of cellular resistance and their potential to overcome common hurdles of chemotherapy, e.g., side effects and cytotoxicity. In this work, we present an ensemble machine learning model to design potent ACPs. Four counter-propagation artificial neural-networks were trained to identify peptides that kill breast and/or lung cancer cells. For prospective application of the ensemble model, we selected 14 peptides from a total of 1000 de novo designs, for synthesis and testing in vitro on breast cancer (MCF7) and lung cancer (A549) cell lines. Six de novo designs showed anticancer activity in vitro, five of which against both MCF7 and A549 cell lines. The novel active peptides populate uncharted regions of ACP sequence space.

KW - Artificial intelligence

KW - Cancer

KW - Counterpropagation

KW - Machine learning

KW - Membranolysis

KW - Peptide design

KW - A549 Cells

KW - Neural Networks, Computer

KW - Humans

KW - Peptides/chemistry

KW - Models, Molecular

KW - Neoplasms/drug therapy

KW - Antineoplastic Agents/chemistry

KW - Machine Learning

KW - MCF-7 Cells

KW - Cell Proliferation/drug effects

UR - http://www.scopus.com/inward/record.url?scp=85064040116&partnerID=8YFLogxK

U2 - 10.1007/s00894-019-4007-6

DO - 10.1007/s00894-019-4007-6

M3 - Article

C2 - 30953170

AN - SCOPUS:85064040116

SN - 1610-2940

VL - 25

JO - Journal of Molecular Modeling

JF - Journal of Molecular Modeling

IS - 5

M1 - 112

ER -

De novo design of anticancer peptides by ensemble artificial neural networks

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this