Machine Learning Optimization of Evolvable Artificial Cells

Bidragets oversatte titel: Machine Learning Optimization of Evolvable Artificial Cells

F. Caschera, S. Rasmussen, M. Hanczyc

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingBidrag til bog/antologiForskningpeer review

Resumé

An evolvable artificial cell is a chemical or biological complex system assembled in laboratory. The system is rationally designed to show life-like properties. In order to achieve an optimal design for the emergence of minimal life, a high dimensional space of possible experimental combinations can be explored. A machine learning approach (Evo-DoE) could be applied to explore this experimental space and define optimal interactions according to a specific fitness function. Herein an implementation of an evolutionary design of experiments to optimize chemical and biochemical systems based on a machine learning process is presented. The optimization proceeds over generations of experiments in iterative loop until optimal compositions are discovered. The fitness function is experimentally measured every time the loop is closed. Two examples of complex systems, namely a liposomal drug formulation and an in vitro cell-free expression system are presented as examples of optimization of molecular interactions in high dimensional space of compositions [1,4]. These represent, for instance, the modules or subsystems that could be optimized by "mixing the protocols" to achieve the high level of sophistication that artificial cells requires. In addition a replication cycle of oil in water emulsions is presented. They represent the container for the artificial cells. (C) Selection and peer-review under responsibility of FET11 conference organizers and published by Elsevier B.V.
OriginalsprogEngelsk
TitelProceedings of the 2nd European Future Technologies Conference and Exhibition 2011
RedaktørerE. Giacobino, R. Pfeifer
Antal sider3
Vol/bind7
ForlagElsevier
Publikationsdato2011
Sider187-189
DOI
StatusUdgivet - 2011
NavnProcedia Computer Science

Bibliografisk note

Caschera, Filippo Rasmussen, Steen Hanczyc, Martin FET 11 2nd European Future Technologies Conference and Exhibition (FET) MAY 04-06, 2011 Budapest, HUNGARY European Commiss Future & Emerging Technol (FET), European Res Consortium Informat & Mathemat (ERCIM), Hungarian Acad Sci, Hungarian Presidency European Un

Citer dette

Caschera, F., Rasmussen, S., & Hanczyc, M. (2011). Machine Learning Optimization of Evolvable Artificial Cells. I E. Giacobino, & R. Pfeifer (red.), Proceedings of the 2nd European Future Technologies Conference and Exhibition 2011 (Bind 7, s. 187-189). Elsevier. Procedia Computer Science https://doi.org/10.1016/j.procs.2011.09.057
Caschera, F. ; Rasmussen, S. ; Hanczyc, M. / Machine Learning Optimization of Evolvable Artificial Cells. Proceedings of the 2nd European Future Technologies Conference and Exhibition 2011. red. / E. Giacobino ; R. Pfeifer. Bind 7 Elsevier, 2011. s. 187-189 (Procedia Computer Science).
@inbook{5f78fbedc18440138374f26092cccdf1,
title = "Machine Learning Optimization of Evolvable Artificial Cells",
abstract = "An evolvable artificial cell is a chemical or biological complex system assembled in laboratory. The system is rationally designed to show life-like properties. In order to achieve an optimal design for the emergence of minimal life, a high dimensional space of possible experimental combinations can be explored. A machine learning approach (Evo-DoE) could be applied to explore this experimental space and define optimal interactions according to a specific fitness function. Herein an implementation of an evolutionary design of experiments to optimize chemical and biochemical systems based on a machine learning process is presented. The optimization proceeds over generations of experiments in iterative loop until optimal compositions are discovered. The fitness function is experimentally measured every time the loop is closed. Two examples of complex systems, namely a liposomal drug formulation and an in vitro cell-free expression system are presented as examples of optimization of molecular interactions in high dimensional space of compositions [1,4]. These represent, for instance, the modules or subsystems that could be optimized by {"}mixing the protocols{"} to achieve the high level of sophistication that artificial cells requires. In addition a replication cycle of oil in water emulsions is presented. They represent the container for the artificial cells. (C) Selection and peer-review under responsibility of FET11 conference organizers and published by Elsevier B.V.",
author = "F. Caschera and S. Rasmussen and M. Hanczyc",
note = "Caschera, Filippo Rasmussen, Steen Hanczyc, Martin FET 11 2nd European Future Technologies Conference and Exhibition (FET) MAY 04-06, 2011 Budapest, HUNGARY European Commiss Future & Emerging Technol (FET), European Res Consortium Informat & Mathemat (ERCIM), Hungarian Acad Sci, Hungarian Presidency European Un",
year = "2011",
doi = "10.1016/j.procs.2011.09.057",
language = "English",
volume = "7",
series = "Procedia Computer Science",
pages = "187--189",
editor = "E. Giacobino and R. Pfeifer",
booktitle = "Proceedings of the 2nd European Future Technologies Conference and Exhibition 2011",
publisher = "Elsevier",
address = "Netherlands",

}

Caschera, F, Rasmussen, S & Hanczyc, M 2011, Machine Learning Optimization of Evolvable Artificial Cells. i E Giacobino & R Pfeifer (red), Proceedings of the 2nd European Future Technologies Conference and Exhibition 2011. bind 7, Elsevier, Procedia Computer Science, s. 187-189. https://doi.org/10.1016/j.procs.2011.09.057

Machine Learning Optimization of Evolvable Artificial Cells. / Caschera, F.; Rasmussen, S.; Hanczyc, M.

Proceedings of the 2nd European Future Technologies Conference and Exhibition 2011. red. / E. Giacobino; R. Pfeifer. Bind 7 Elsevier, 2011. s. 187-189 (Procedia Computer Science).

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingBidrag til bog/antologiForskningpeer review

TY - CHAP

T1 - Machine Learning Optimization of Evolvable Artificial Cells

AU - Caschera, F.

AU - Rasmussen, S.

AU - Hanczyc, M.

N1 - Caschera, Filippo Rasmussen, Steen Hanczyc, Martin FET 11 2nd European Future Technologies Conference and Exhibition (FET) MAY 04-06, 2011 Budapest, HUNGARY European Commiss Future & Emerging Technol (FET), European Res Consortium Informat & Mathemat (ERCIM), Hungarian Acad Sci, Hungarian Presidency European Un

PY - 2011

Y1 - 2011

N2 - An evolvable artificial cell is a chemical or biological complex system assembled in laboratory. The system is rationally designed to show life-like properties. In order to achieve an optimal design for the emergence of minimal life, a high dimensional space of possible experimental combinations can be explored. A machine learning approach (Evo-DoE) could be applied to explore this experimental space and define optimal interactions according to a specific fitness function. Herein an implementation of an evolutionary design of experiments to optimize chemical and biochemical systems based on a machine learning process is presented. The optimization proceeds over generations of experiments in iterative loop until optimal compositions are discovered. The fitness function is experimentally measured every time the loop is closed. Two examples of complex systems, namely a liposomal drug formulation and an in vitro cell-free expression system are presented as examples of optimization of molecular interactions in high dimensional space of compositions [1,4]. These represent, for instance, the modules or subsystems that could be optimized by "mixing the protocols" to achieve the high level of sophistication that artificial cells requires. In addition a replication cycle of oil in water emulsions is presented. They represent the container for the artificial cells. (C) Selection and peer-review under responsibility of FET11 conference organizers and published by Elsevier B.V.

AB - An evolvable artificial cell is a chemical or biological complex system assembled in laboratory. The system is rationally designed to show life-like properties. In order to achieve an optimal design for the emergence of minimal life, a high dimensional space of possible experimental combinations can be explored. A machine learning approach (Evo-DoE) could be applied to explore this experimental space and define optimal interactions according to a specific fitness function. Herein an implementation of an evolutionary design of experiments to optimize chemical and biochemical systems based on a machine learning process is presented. The optimization proceeds over generations of experiments in iterative loop until optimal compositions are discovered. The fitness function is experimentally measured every time the loop is closed. Two examples of complex systems, namely a liposomal drug formulation and an in vitro cell-free expression system are presented as examples of optimization of molecular interactions in high dimensional space of compositions [1,4]. These represent, for instance, the modules or subsystems that could be optimized by "mixing the protocols" to achieve the high level of sophistication that artificial cells requires. In addition a replication cycle of oil in water emulsions is presented. They represent the container for the artificial cells. (C) Selection and peer-review under responsibility of FET11 conference organizers and published by Elsevier B.V.

U2 - 10.1016/j.procs.2011.09.057

DO - 10.1016/j.procs.2011.09.057

M3 - Book chapter

VL - 7

T3 - Procedia Computer Science

SP - 187

EP - 189

BT - Proceedings of the 2nd European Future Technologies Conference and Exhibition 2011

A2 - Giacobino, E.

A2 - Pfeifer, R.

PB - Elsevier

ER -

Caschera F, Rasmussen S, Hanczyc M. Machine Learning Optimization of Evolvable Artificial Cells. I Giacobino E, Pfeifer R, red., Proceedings of the 2nd European Future Technologies Conference and Exhibition 2011. Bind 7. Elsevier. 2011. s. 187-189. (Procedia Computer Science). https://doi.org/10.1016/j.procs.2011.09.057