Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312222866> ?p ?o ?g. }
- W4312222866 abstract "Abstract Synthetic biology often involves engineering microbial strains to express high-value proteins. Thanks to progress in rapid DNA synthesis and sequencing, deep learning has emerged as a promising approach to build sequence-to-expression models for strain optimization. But such models need large and costly training data that create steep entry barriers for many laboratories. Here we study the relation between accuracy and data efficiency in an atlas of machine learning models trained on datasets of varied size and sequence diversity. We show that deep learning can achieve good prediction accuracy with much smaller datasets than previously thought. We demonstrate that controlled sequence diversity leads to substantial gains in data efficiency and employed Explainable AI to show that convolutional neural networks can finely discriminate between input DNA sequences. Our results provide guidelines for designing genotype-phenotype screens that balance cost and quality of training data, thus helping promote the wider adoption of deep learning in the biotechnology sector." @default.
- W4312222866 created "2023-01-04" @default.
- W4312222866 creator A5016017194 @default.
- W4312222866 creator A5016689070 @default.
- W4312222866 creator A5029579606 @default.
- W4312222866 creator A5061509713 @default.
- W4312222866 creator A5063600180 @default.
- W4312222866 date "2022-12-15" @default.
- W4312222866 modified "2023-10-11" @default.
- W4312222866 title "Accuracy and data efficiency in deep learning models of protein expression" @default.
- W4312222866 cites W1019830208 @default.
- W4312222866 cites W1539868719 @default.
- W4312222866 cites W2017526934 @default.
- W4312222866 cites W2018645639 @default.
- W4312222866 cites W2047360542 @default.
- W4312222866 cites W2051242197 @default.
- W4312222866 cites W2054173531 @default.
- W4312222866 cites W2145674897 @default.
- W4312222866 cites W2157815481 @default.
- W4312222866 cites W2159933659 @default.
- W4312222866 cites W2170211552 @default.
- W4312222866 cites W2198606573 @default.
- W4312222866 cites W2345512687 @default.
- W4312222866 cites W2550783271 @default.
- W4312222866 cites W2746247987 @default.
- W4312222866 cites W2766736793 @default.
- W4312222866 cites W2787894218 @default.
- W4312222866 cites W2805310212 @default.
- W4312222866 cites W2889326414 @default.
- W4312222866 cites W2892180666 @default.
- W4312222866 cites W2900987595 @default.
- W4312222866 cites W2911964244 @default.
- W4312222866 cites W2951203227 @default.
- W4312222866 cites W2951934944 @default.
- W4312222866 cites W2955231772 @default.
- W4312222866 cites W2990395719 @default.
- W4312222866 cites W3000716014 @default.
- W4312222866 cites W3023962428 @default.
- W4312222866 cites W3028645112 @default.
- W4312222866 cites W3037592148 @default.
- W4312222866 cites W3043211404 @default.
- W4312222866 cites W3092146751 @default.
- W4312222866 cites W3092434764 @default.
- W4312222866 cites W3111071374 @default.
- W4312222866 cites W3144239152 @default.
- W4312222866 cites W3146944767 @default.
- W4312222866 cites W3189576964 @default.
- W4312222866 cites W3194729882 @default.
- W4312222866 cites W3203588026 @default.
- W4312222866 cites W4221128536 @default.
- W4312222866 cites W4225332093 @default.
- W4312222866 cites W4225691151 @default.
- W4312222866 cites W4293569212 @default.
- W4312222866 cites W4312222866 @default.
- W4312222866 doi "https://doi.org/10.1038/s41467-022-34902-5" @default.
- W4312222866 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36517468" @default.
- W4312222866 hasPublicationYear "2022" @default.
- W4312222866 type Work @default.
- W4312222866 citedByCount "11" @default.
- W4312222866 countsByYear W43122228662022 @default.
- W4312222866 countsByYear W43122228662023 @default.
- W4312222866 crossrefType "journal-article" @default.
- W4312222866 hasAuthorship W4312222866A5016017194 @default.
- W4312222866 hasAuthorship W4312222866A5016689070 @default.
- W4312222866 hasAuthorship W4312222866A5029579606 @default.
- W4312222866 hasAuthorship W4312222866A5061509713 @default.
- W4312222866 hasAuthorship W4312222866A5063600180 @default.
- W4312222866 hasBestOaLocation W43122228661 @default.
- W4312222866 hasConcept C104317684 @default.
- W4312222866 hasConcept C108583219 @default.
- W4312222866 hasConcept C119857082 @default.
- W4312222866 hasConcept C132917006 @default.
- W4312222866 hasConcept C141231307 @default.
- W4312222866 hasConcept C154945302 @default.
- W4312222866 hasConcept C2778112365 @default.
- W4312222866 hasConcept C41008148 @default.
- W4312222866 hasConcept C51679486 @default.
- W4312222866 hasConcept C54355233 @default.
- W4312222866 hasConcept C552990157 @default.
- W4312222866 hasConcept C70721500 @default.
- W4312222866 hasConcept C81363708 @default.
- W4312222866 hasConcept C86803240 @default.
- W4312222866 hasConceptScore W4312222866C104317684 @default.
- W4312222866 hasConceptScore W4312222866C108583219 @default.
- W4312222866 hasConceptScore W4312222866C119857082 @default.
- W4312222866 hasConceptScore W4312222866C132917006 @default.
- W4312222866 hasConceptScore W4312222866C141231307 @default.
- W4312222866 hasConceptScore W4312222866C154945302 @default.
- W4312222866 hasConceptScore W4312222866C2778112365 @default.
- W4312222866 hasConceptScore W4312222866C41008148 @default.
- W4312222866 hasConceptScore W4312222866C51679486 @default.
- W4312222866 hasConceptScore W4312222866C54355233 @default.
- W4312222866 hasConceptScore W4312222866C552990157 @default.
- W4312222866 hasConceptScore W4312222866C70721500 @default.
- W4312222866 hasConceptScore W4312222866C81363708 @default.
- W4312222866 hasConceptScore W4312222866C86803240 @default.
- W4312222866 hasFunder F4320331788 @default.
- W4312222866 hasIssue "1" @default.
- W4312222866 hasLocation W43122228661 @default.
- W4312222866 hasLocation W43122228662 @default.