ART A machine learning Automated Recommendation Tool for synthetic biology
➤ Gửi thông báo lỗi ⚠️ Báo cáo tài liệu vi phạmNội dung chi tiết: ART A machine learning Automated Recommendation Tool for synthetic biology
ART A machine learning Automated Recommendation Tool for synthetic biology
arXiv: 1911.11091 v2 Iq-bio.QM] 28 Feb 2020ART: A machine learning Automated Recommendation Tool for synthetic biologyTijana RadivojevkJ-’ Zak Costell ART A machine learning Automated Recommendation Tool for synthetic biologylo Kenneth Workman,and Hector Garcia\DOE Agile BioFoundry, Emeryville, CA. USA.^Biological Systems and Engineering Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA.Ì Biofuels and Bioproducts Division. DOE Joint BioEnergy Institute. Emerytrilie, CA, USA. ^Department of Bioengineerin ART A machine learning Automated Recommendation Tool for synthetic biologyg, University of California, Berkeley. CA. USA ||ZÍ(7j4A/, Basque Center for Applied Ma thermitICS, Bilbao, Spain.E-mail: hgmartin@lbl gov1AbstractSynART A machine learning Automated Recommendation Tool for synthetic biology
thetic biology allows ILS to bioengineer cells to synthesize novel valuable molecules such as renewable biofuels or anticancer drugs- However, traditiarXiv: 1911.11091 v2 Iq-bio.QM] 28 Feb 2020ART: A machine learning Automated Recommendation Tool for synthetic biologyTijana RadivojevkJ-’ Zak Costell ART A machine learning Automated Recommendation Tool for synthetic biologyation Tool (ART), a tool that leverages machine learning and probabilistic modeling techniques to guide synthetic biology in a systematic fashion, without the need for a full mechanistic understanding of the biological system. Using sampling-based optimization, ART provides a set of recommended stra ART A machine learning Automated Recommendation Tool for synthetic biologyins to be built in the next engineering cycle, alongside probabilistic predictions of their production levels. We demonstrate the capabilities of ARTART A machine learning Automated Recommendation Tool for synthetic biology
on simulated data sets, as well as experimental data from real metabolic engineering projects producing renewable biofuels, hoppy flavored beer withouarXiv: 1911.11091 v2 Iq-bio.QM] 28 Feb 2020ART: A machine learning Automated Recommendation Tool for synthetic biologyTijana RadivojevkJ-’ Zak Costell ART A machine learning Automated Recommendation Tool for synthetic biologyIntroductionMetabolic engineering1 enables US to bioengineer cells to synthesize novel valuable molecules such as renewable biofuels2'3 or anticancer drugs.1 The prospects of metabolic engineering to have a positive impact in society are on the rise, as it was considered one of the “Top Ten Emerging ART A machine learning Automated Recommendation Tool for synthetic biology Technologies” by the World Economic Forum in 2016/’ Furthermore, an incoming industrialized biology is expected to improve most human activities: froART A machine learning Automated Recommendation Tool for synthetic biology
m creating renewable bioproducts and materials, to improving crops and enabling new biomedical applications.6However, the practice of metabolic enginearXiv: 1911.11091 v2 Iq-bio.QM] 28 Feb 2020ART: A machine learning Automated Recommendation Tool for synthetic biologyTijana RadivojevkJ-’ Zak Costell ART A machine learning Automated Recommendation Tool for synthetic biologymonstrations rather than a systematic practice based on generalizable methods. This limitation has resulted in very long development times: for example, it took 150 person-years of effort to produce the antimalarial precursor artemisinin by AmyrLs; and 575 person-years of effort for Dupont to genera ART A machine learning Automated Recommendation Tool for synthetic biologyte propanediol,* which is the base for their commercially available Sorona fabric.9Synthetic biology10 aims to improve genetic and metabolic engineeriART A machine learning Automated Recommendation Tool for synthetic biology
ng by applying systematic engineering principles to achieve a previously specified goal. Synthetic biology encompasses, and goes beyond, metabolic engarXiv: 1911.11091 v2 Iq-bio.QM] 28 Feb 2020ART: A machine learning Automated Recommendation Tool for synthetic biologyTijana RadivojevkJ-’ Zak Costell ART A machine learning Automated Recommendation Tool for synthetic biologyce fertilizers.12 This discipline is enjoying an exponential growth, as it heavily benefits from the byproducts of the genomic revolution: high-throughput multi-omics phenotyp-ing,13,14 accelerating DNA sequencing15 and synthesis capabilities,16 and CRISPR-enabled genetic editing.17 This exponential ART A machine learning Automated Recommendation Tool for synthetic biology growth Is reflected in the private investment in the field, which has totalled ~$12B in the 20(19-2018 period and is rapidly accelerating (~$2B in 20ART A machine learning Automated Recommendation Tool for synthetic biology
17 to ~$4B in 2018).18One of t he synt hetic biology engineering principles used to improve metabolic engineering is the Design-Build-Test-Learn (D13TarXiv: 1911.11091 v2 Iq-bio.QM] 28 Feb 2020ART: A machine learning Automated Recommendation Tool for synthetic biologyTijana RadivojevkJ-’ Zak Costell ART A machine learning Automated Recommendation Tool for synthetic biologyps://khothuvien.cori!net). The DBTL cycle’s first step is to design (D) a biological system expected to meet the desired outcome. That design is built (B) in the next phase from DNA parts into an appropriate microbial chassis using synthetic biology tools. The next phase involves testing (T) whether ART A machine learning Automated Recommendation Tool for synthetic biology t he built biological system indeed works as desired in the original design, via a variety of assays: e.g. measurement of production or, and ‘omics (ART A machine learning Automated Recommendation Tool for synthetic biology
transcriptomics, proteomics, metabolomics) data profiling. It. is extremely rare that the first design behaves as desired, and further attempts are tyarXiv: 1911.11091 v2 Iq-bio.QM] 28 Feb 2020ART: A machine learning Automated Recommendation Tool for synthetic biologyTijana RadivojevkJ-’ Zak Costell ART A machine learning Automated Recommendation Tool for synthetic biologyconverge to the desired specification faster than t hrough a random search process.The Learn phase of the DB IL cycle has traditionally been the most weakly supported and developed,20 despite its critical importance to accelerate the full cycle. The reasons arc multiple, although their relative impo ART A machine learning Automated Recommendation Tool for synthetic biologyrtance is not entirely clear. Arguably, the main drivers of the lack of emphasis on the L phase are: the lack of predictive power for biological systeART A machine learning Automated Recommendation Tool for synthetic biology
ms behavior.21 the reproducibility problems plaguing biological experiments.3-22 21 and the traditionally moderate emphasis on mathematical trilining arXiv: 1911.11091 v2 Iq-bio.QM] 28 Feb 2020ART: A machine learning Automated Recommendation Tool for synthetic biologyTijana RadivojevkJ-’ Zak Costell ART A machine learning Automated Recommendation Tool for synthetic biologyby emerging high-throughput phenotyping technologies.25 Machine learning has been used to produce driverless cars,26 automate language translation,27 predict sensitive personal attributes from Facebook profiles,w predict pathway dynamics,-"* optimize pathways through translational control.3'* diagno ART A machine learning Automated Recommendation Tool for synthetic biologyse skin cancer,31 detect tumors in breast tissues,32 predict DNA and RNA protein-binding sequences,:n drug side effects31 ami antibiotic mechanisms ofART A machine learning Automated Recommendation Tool for synthetic biology
action.3* However, the practice of machine learning requires statistical and mathematical expertise that is scarce ami highly competed for in other farXiv: 1911.11091 v2 Iq-bio.QM] 28 Feb 2020ART: A machine learning Automated Recommendation Tool for synthetic biologyTijana RadivojevkJ-’ Zak Costell ART A machine learning Automated Recommendation Tool for synthetic biologyT combines thi' widely-used and general-purpose open source scikit-learn library37 with a novel Bayesian38 ensemble ap4proach, in a manner that adapts to the particular needs of synthetic biology projects: e.g. low number of t raining instances, recursive DBTL cycles, and the need for uncertainty qu ART A machine learning Automated Recommendation Tool for synthetic biologyantification. The datasets collected in the synthetic biology field are typically not large enough to allow for the use of deep learning (< 100 instanART A machine learning Automated Recommendation Tool for synthetic biology
ces), but our ensemble model will lx’ able to integrate this approach when high-tlưoughput data generation11 w and automated data collection 111 becomarXiv: 1911.11091 v2 Iq-bio.QM] 28 Feb 2020ART: A machine learning Automated Recommendation Tool for synthetic biologyTijana RadivojevkJ-’ Zak Costell ART A machine learning Automated Recommendation Tool for synthetic biology efforts in an effective way.We showcase the efficacy of ART in guiding synthetic biology by mapping -omics data to production through four different examples: one test case wit h simulated data and three real cases of metabolic engineering. In all these cases we assume that the -omics data (pro-tco ART A machine learning Automated Recommendation Tool for synthetic biologymics in these examples, but it could Im* any other type: transcriptomics, mctabolomics, etc.) can be predictive of the final production (response), anART A machine learning Automated Recommendation Tool for synthetic biology
d that we have enough control over thí' system so as to produce any new recommended input. The test case permits US to explore how the algorithm perfoarXiv: 1911.11091 v2 Iq-bio.QM] 28 Feb 2020ART: A machine learning Automated Recommendation Tool for synthetic biologyTijana RadivojevkJ-’ Zak Costell ART A machine learning Automated Recommendation Tool for synthetic biologys. The real metabolic engineering cases involve data sets from published metabolic engineering projects: renewable biofuel production, yeast bioengineering to recreate the flavor of hops in beer, and fatty alcohols synthesis. These projects illustrate what to expect under different typical metabolic ART A machine learning Automated Recommendation Tool for synthetic biology engineering situations: high, low coupling of the heterologous pathway to host metabolism, complex,, simple pathways, high/low number of condit ions,ART A machine learning Automated Recommendation Tool for synthetic biology
high low difficulty in learning pathway behavior. We find that ART'S ensemble approach can successfully guide t he bioengineering process even in thearXiv: 1911.11091 v2 Iq-bio.QM] 28 Feb 2020ART: A machine learning Automated Recommendation Tool for synthetic biologyTijana RadivojevkJ-’ Zak Costell ART A machine learning Automated Recommendation Tool for synthetic biology ami effectively guide recommendations towards the least known part of the phase space. These experimental metabolic engineering cases also illustrate how applicable the underlying assumptions are, and what, happens when they fail.5https://khothuvien.cori!In Sinn. ART provides a tool specifically ta ART A machine learning Automated Recommendation Tool for synthetic biologyilored to the synthetic biologist's needs in order to leverage t he power of machine learning to enable predictable biology. This combination of synthART A machine learning Automated Recommendation Tool for synthetic biology
etic biology with machine loaming and automation has the potential to revolutionize bioengineering28,41,42 by enabling effective inverse design. ThisGọi ngay
Chat zalo
Facebook