Matches in SemOpenAlex for { <https://semopenalex.org/work/W3183919511> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3183919511 abstract "Abstract One way to better understand the structure in DNA is by learning to predict the sequence. Here, we train a model to predict the missing base at any given position, given its left and right flanking contexts. Our best-performing model is a neural network that obtains an accuracy close to 54% on the human genome, which is 2% points better than modelling the data using a Markov model. In likelihood-ratio tests, we show that the neural network is significantly better than any of the alternative models by a large margin. We report on where the accuracy is obtained, observing first that the performance appears to be uniform over the chromosomes. The models perform best in repetitive sequences, as expected, although they are far from random performance in the more difficult coding sections, the proportions being ~ 70:40%. Exploring further the sources of the accuracy, Fourier transforming the predictions reveals weak but clear periodic signals. In the human genome the characteristic periods hint at connections to nucleosome positioning. To understand this we find similar periodic signals in GC/AT content in the human genome, which to the best of our knowledge have not been reported before. On other large genomes similarly high accuracy is found, while lower predictive accuracy is observed on smaller genomes. Only in mouse did we see periodic signals in the same range as in human, though weaker and of different type. Interestingly, applying a model trained on the mouse genome to the human genome results in a performance far below that of the human model, except in the difficult coding regions. Despite the clear outcomes of the likelihood ratio tests, there is currently a limited superiority of the neural network methods over the Markov model. We expect, however, that there is great potential for better modelling DNA using different neural network architectures." @default.
- W3183919511 created "2021-08-02" @default.
- W3183919511 creator A5010165733 @default.
- W3183919511 creator A5011484483 @default.
- W3183919511 creator A5028760066 @default.
- W3183919511 creator A5083542637 @default.
- W3183919511 date "2021-07-29" @default.
- W3183919511 modified "2023-10-16" @default.
- W3183919511 title "Prediction of DNA from context using neural networks" @default.
- W3183919511 cites W1830719945 @default.
- W3183919511 cites W2004469916 @default.
- W3183919511 cites W2011480164 @default.
- W3183919511 cites W2051866505 @default.
- W3183919511 cites W2064675550 @default.
- W3183919511 cites W2101926813 @default.
- W3183919511 cites W2112796928 @default.
- W3183919511 cites W2165618847 @default.
- W3183919511 cites W2167764944 @default.
- W3183919511 cites W2167856604 @default.
- W3183919511 cites W2284978990 @default.
- W3183919511 cites W2795625769 @default.
- W3183919511 cites W2808938092 @default.
- W3183919511 cites W2958584774 @default.
- W3183919511 cites W3004985820 @default.
- W3183919511 cites W3186029797 @default.
- W3183919511 doi "https://doi.org/10.1101/2021.07.28.454211" @default.
- W3183919511 hasPublicationYear "2021" @default.
- W3183919511 type Work @default.
- W3183919511 sameAs 3183919511 @default.
- W3183919511 citedByCount "1" @default.
- W3183919511 countsByYear W31839195112022 @default.
- W3183919511 crossrefType "posted-content" @default.
- W3183919511 hasAuthorship W3183919511A5010165733 @default.
- W3183919511 hasAuthorship W3183919511A5011484483 @default.
- W3183919511 hasAuthorship W3183919511A5028760066 @default.
- W3183919511 hasAuthorship W3183919511A5083542637 @default.
- W3183919511 hasBestOaLocation W31839195111 @default.
- W3183919511 hasConcept C104317684 @default.
- W3183919511 hasConcept C105795698 @default.
- W3183919511 hasConcept C119857082 @default.
- W3183919511 hasConcept C141231307 @default.
- W3183919511 hasConcept C151730666 @default.
- W3183919511 hasConcept C153180895 @default.
- W3183919511 hasConcept C154945302 @default.
- W3183919511 hasConcept C179518139 @default.
- W3183919511 hasConcept C197077220 @default.
- W3183919511 hasConcept C23224414 @default.
- W3183919511 hasConcept C2779343474 @default.
- W3183919511 hasConcept C33923547 @default.
- W3183919511 hasConcept C41008148 @default.
- W3183919511 hasConcept C50644808 @default.
- W3183919511 hasConcept C51679486 @default.
- W3183919511 hasConcept C54355233 @default.
- W3183919511 hasConcept C552990157 @default.
- W3183919511 hasConcept C70721500 @default.
- W3183919511 hasConcept C774472 @default.
- W3183919511 hasConcept C86803240 @default.
- W3183919511 hasConcept C98763669 @default.
- W3183919511 hasConceptScore W3183919511C104317684 @default.
- W3183919511 hasConceptScore W3183919511C105795698 @default.
- W3183919511 hasConceptScore W3183919511C119857082 @default.
- W3183919511 hasConceptScore W3183919511C141231307 @default.
- W3183919511 hasConceptScore W3183919511C151730666 @default.
- W3183919511 hasConceptScore W3183919511C153180895 @default.
- W3183919511 hasConceptScore W3183919511C154945302 @default.
- W3183919511 hasConceptScore W3183919511C179518139 @default.
- W3183919511 hasConceptScore W3183919511C197077220 @default.
- W3183919511 hasConceptScore W3183919511C23224414 @default.
- W3183919511 hasConceptScore W3183919511C2779343474 @default.
- W3183919511 hasConceptScore W3183919511C33923547 @default.
- W3183919511 hasConceptScore W3183919511C41008148 @default.
- W3183919511 hasConceptScore W3183919511C50644808 @default.
- W3183919511 hasConceptScore W3183919511C51679486 @default.
- W3183919511 hasConceptScore W3183919511C54355233 @default.
- W3183919511 hasConceptScore W3183919511C552990157 @default.
- W3183919511 hasConceptScore W3183919511C70721500 @default.
- W3183919511 hasConceptScore W3183919511C774472 @default.
- W3183919511 hasConceptScore W3183919511C86803240 @default.
- W3183919511 hasConceptScore W3183919511C98763669 @default.
- W3183919511 hasLocation W31839195111 @default.
- W3183919511 hasOpenAccess W3183919511 @default.
- W3183919511 hasPrimaryLocation W31839195111 @default.
- W3183919511 hasRelatedWork W1548481688 @default.
- W3183919511 hasRelatedWork W2023185280 @default.
- W3183919511 hasRelatedWork W2094335760 @default.
- W3183919511 hasRelatedWork W2477364102 @default.
- W3183919511 hasRelatedWork W2539985974 @default.
- W3183919511 hasRelatedWork W2754684770 @default.
- W3183919511 hasRelatedWork W2926763004 @default.
- W3183919511 hasRelatedWork W3108447880 @default.
- W3183919511 hasRelatedWork W4301681594 @default.
- W3183919511 hasRelatedWork W1629725936 @default.
- W3183919511 isParatext "false" @default.
- W3183919511 isRetracted "false" @default.
- W3183919511 magId "3183919511" @default.
- W3183919511 workType "article" @default.