Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311005208> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4311005208 abstract "Chromatin structural domains, or topologically associated domains (TADs), are a general organizing principle in chromatin biology. RNA polymerase II (RNAPII) mediates multiple chromatin interactive loops, tethering together as RNAPII-associated chromatin interaction domains (RAIDs) to offer a framework for gene regulation. RAID and TAD alterations have been found to be associated with diseases. They can be further dissected as micro-domains (micro-TADs and micro-RAIDs) by clustering single-molecule chromatin-interactive complexes from next-generation three-dimensional (3D) genome techniques, such as ChIA-Drop. Currently, there are few tools available for micro-domain boundary identification. In this work, we developed the MCI-frcnn deep learning method to train a Faster Region-based Convolutional Neural Network (Faster R-CNN) for micro-domain boundary detection. At the training phase in MCI-frcnn, 50 images of RAIDs from Drosophila RNAPII ChIA-Drop data, containing 261 micro-RAIDs with ground truth boundaries, were trained for 7 days. Using this well-trained MCI-frcnn, we detected micro-RAID boundaries for the input new images, with a fast speed (5.26 fps), high recognition accuracy (AUROC = 0.85, mAP = 0.69), and high boundary region quantification (genomic IoU = 76%). We further applied MCI-frcnn to detect human micro-TADs boundaries using human GM12878 SPRITE data and obtained a high region quantification score (mean gIoU = 85%). In all, the MCI-frcnn deep learning method which we developed in this work is a general tool for micro-domain boundary detection." @default.
- W4311005208 created "2022-12-22" @default.
- W4311005208 creator A5017315241 @default.
- W4311005208 creator A5036766419 @default.
- W4311005208 creator A5040720352 @default.
- W4311005208 creator A5047886547 @default.
- W4311005208 creator A5049692788 @default.
- W4311005208 creator A5064943988 @default.
- W4311005208 creator A5066867952 @default.
- W4311005208 creator A5074947920 @default.
- W4311005208 creator A5087492673 @default.
- W4311005208 date "2022-11-30" @default.
- W4311005208 modified "2023-10-02" @default.
- W4311005208 title "MCI-frcnn: A deep learning method for topological micro-domain boundary detection" @default.
- W4311005208 cites W1985621639 @default.
- W4311005208 cites W2011463791 @default.
- W4311005208 cites W2070021921 @default.
- W4311005208 cites W2090037139 @default.
- W4311005208 cites W2161212572 @default.
- W4311005208 cites W2181886201 @default.
- W4311005208 cites W2195190137 @default.
- W4311005208 cites W2551092411 @default.
- W4311005208 cites W2806123558 @default.
- W4311005208 cites W2904120442 @default.
- W4311005208 cites W2911835695 @default.
- W4311005208 cites W2945655181 @default.
- W4311005208 cites W3028224764 @default.
- W4311005208 cites W3049062131 @default.
- W4311005208 cites W4295242280 @default.
- W4311005208 cites W639708223 @default.
- W4311005208 doi "https://doi.org/10.3389/fcell.2022.1050769" @default.
- W4311005208 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36531953" @default.
- W4311005208 hasPublicationYear "2022" @default.
- W4311005208 type Work @default.
- W4311005208 citedByCount "0" @default.
- W4311005208 crossrefType "journal-article" @default.
- W4311005208 hasAuthorship W4311005208A5017315241 @default.
- W4311005208 hasAuthorship W4311005208A5036766419 @default.
- W4311005208 hasAuthorship W4311005208A5040720352 @default.
- W4311005208 hasAuthorship W4311005208A5047886547 @default.
- W4311005208 hasAuthorship W4311005208A5049692788 @default.
- W4311005208 hasAuthorship W4311005208A5064943988 @default.
- W4311005208 hasAuthorship W4311005208A5066867952 @default.
- W4311005208 hasAuthorship W4311005208A5074947920 @default.
- W4311005208 hasAuthorship W4311005208A5087492673 @default.
- W4311005208 hasBestOaLocation W43110052081 @default.
- W4311005208 hasConcept C104317684 @default.
- W4311005208 hasConcept C108583219 @default.
- W4311005208 hasConcept C134306372 @default.
- W4311005208 hasConcept C153180895 @default.
- W4311005208 hasConcept C154945302 @default.
- W4311005208 hasConcept C33923547 @default.
- W4311005208 hasConcept C36503486 @default.
- W4311005208 hasConcept C41008148 @default.
- W4311005208 hasConcept C54355233 @default.
- W4311005208 hasConcept C62354387 @default.
- W4311005208 hasConcept C70721500 @default.
- W4311005208 hasConcept C81363708 @default.
- W4311005208 hasConcept C83640560 @default.
- W4311005208 hasConcept C86803240 @default.
- W4311005208 hasConceptScore W4311005208C104317684 @default.
- W4311005208 hasConceptScore W4311005208C108583219 @default.
- W4311005208 hasConceptScore W4311005208C134306372 @default.
- W4311005208 hasConceptScore W4311005208C153180895 @default.
- W4311005208 hasConceptScore W4311005208C154945302 @default.
- W4311005208 hasConceptScore W4311005208C33923547 @default.
- W4311005208 hasConceptScore W4311005208C36503486 @default.
- W4311005208 hasConceptScore W4311005208C41008148 @default.
- W4311005208 hasConceptScore W4311005208C54355233 @default.
- W4311005208 hasConceptScore W4311005208C62354387 @default.
- W4311005208 hasConceptScore W4311005208C70721500 @default.
- W4311005208 hasConceptScore W4311005208C81363708 @default.
- W4311005208 hasConceptScore W4311005208C83640560 @default.
- W4311005208 hasConceptScore W4311005208C86803240 @default.
- W4311005208 hasLocation W43110052081 @default.
- W4311005208 hasLocation W43110052082 @default.
- W4311005208 hasLocation W43110052083 @default.
- W4311005208 hasLocation W43110052084 @default.
- W4311005208 hasOpenAccess W4311005208 @default.
- W4311005208 hasPrimaryLocation W43110052081 @default.
- W4311005208 hasRelatedWork W2731899572 @default.
- W4311005208 hasRelatedWork W2999805992 @default.
- W4311005208 hasRelatedWork W3011074480 @default.
- W4311005208 hasRelatedWork W3116150086 @default.
- W4311005208 hasRelatedWork W3133861977 @default.
- W4311005208 hasRelatedWork W3192840557 @default.
- W4311005208 hasRelatedWork W4200173597 @default.
- W4311005208 hasRelatedWork W4291897433 @default.
- W4311005208 hasRelatedWork W4312417841 @default.
- W4311005208 hasRelatedWork W4321369474 @default.
- W4311005208 hasVolume "10" @default.
- W4311005208 isParatext "false" @default.
- W4311005208 isRetracted "false" @default.
- W4311005208 workType "article" @default.