1-20 of 8687
Journal Article
JTIS: enhancing biomedical document-level relation extraction through joint training with intermediate steps
Database, Volume 2024, 2024, baae125, https://doi.org/10.1093/database/baae125
Published: 19 December 2024
Image
The example, adapted from BioRED, illustrates the division of the training ...
Published: 19 December 2024
Figure 2.
The example, adapted from BioRED, illustrates the division of the training task into four related tasks, from an input document with annotated entity mentions to RE and TNT output.
Image
The overall architecture of our proposed JTIS model.
Published: 19 December 2024
Figure 3.
The overall architecture of our proposed JTIS model.
Image
A case study of our method, showing a portion of entities and sentences, du...
Published: 19 December 2024
Figure 4.
A case study of our method, showing a portion of entities and sentences, due to space constraints.
Image
Example document and a relation triple from BioRED, where “37” and “D019308...
Published: 19 December 2024
Figure 1.
Example document and a relation triple from BioRED, where “37” and “D019308” are unique identifiers corresponding to the color-marked mentions in the text, with Entity 1 and Entity 2 highlighted in colorfully underlined italics and other entities in black underlined italics.
Journal Article
scEccDNAdb: an integrated single-cell eccDNA resource for human and mouse
Database, Volume 2024, 2024, baae126, https://doi.org/10.1093/database/baae126
Published: 18 December 2024
Image
A schematic workflow of scEccDNAdb.
Published: 18 December 2024
Figure 1.
A schematic workflow of scEccDNAdb.
Image
The web interface and usage of scEccDNAdb. (a) The navigation bar of scEccD...
Published: 18 December 2024
Figure 2.
The web interface and usage of scEccDNAdb. (a) The navigation bar of scEccDNAdb. (b) Users can browse eccDNA data by sample and datasets. (c) “Details of eccDNA/ecDNA” includes (i) General information, (ii) Sample information, (iii) Sequence information, (iv) Amplicon structure, (v) Circular schemat
Image
Correlation of genes, co-expression network modules, and traits. (a) Visual...
in
AthRiboNC: an Arabidopsis database for ncRNAs with coding potential revealed from ribosome profiling
Published: 17 December 2024
Figure 3.
Correlation of genes, co-expression network modules, and traits. (a) Visualized heatmap of the TOMsimiliarity between ncRNA genes with coding potential. (b) Visualized heatmap of the correlation between 24 modules. (c) Visualized heatmap of the correlation between genes and traits. (d) Visualized he
Image
The construction workflow of AthRiboNC database. (a) The basic workflow for...
in
AthRiboNC: an Arabidopsis database for ncRNAs with coding potential revealed from ribosome profiling
Published: 17 December 2024
Figure 1.
The construction workflow of AthRiboNC database. (a) The basic workflow for data analysis and processing in AthRiboNC. (b). The basic framework for building the AthRiboNC website. (c) The homepage showcases the main functional modules of AthRiboNC database.
Image
Information on ncRNAs with coding potential. (a) Expression levels of the m...
in
AthRiboNC: an Arabidopsis database for ncRNAs with coding potential revealed from ribosome profiling
Published: 17 December 2024
Figure 2.
Information on ncRNAs with coding potential. (a) Expression levels of the miRNA gene AT3G10745 (MIR158a) in different Ribo-Seq samples across different ages. (b) Expression levels of the miRNA gene AT3G10745 (MIR158a) in different Ribo-Seq samples across different tissues. (c) ORFfinder-identified s
Journal Article
AthRiboNC: an Arabidopsis database for ncRNAs with coding potential revealed from ribosome profiling
Database, Volume 2024, 2024, baae123, https://doi.org/10.1093/database/baae123
Published: 17 December 2024
Image
WGCNA module enrichment analysis results and visualized network topology. (...
in
AthRiboNC: an Arabidopsis database for ncRNAs with coding potential revealed from ribosome profiling
Published: 17 December 2024
Figure 4.
WGCNA module enrichment analysis results and visualized network topology. (a) KEGG pathway enrichment analysis results for hub genes in the MEdarkturquoise module. (b) GO enrichment analysis results for hub genes in the MEdarkturquoise module. (c) Visualization of the network correlation strength be
Image
The hierarchical structure. The ontology was classified into 10 categories:...
Published: 05 December 2024
Figure 1.
The hierarchical structure. The ontology was classified into 10 categories: clinical manifestation, comorbidity, complication, diagnosis, model of atherosclerotic cerebrovascular disease, prevention, rehabilitation, risk factor, and treatment.
Image
Named entity recognition by the ontology. Ten categories in the proposed on...
Published: 05 December 2024
Figure 4.
Named entity recognition by the ontology. Ten categories in the proposed ontology were used to auto-annotate one abstract related to atherosclerotic cerebrovascular disease. Among them, depression, obesity, and diabetes were annotated as comorbidity.
Image
Knowledge fusion case based on the ontology. Partial electronic health reco...
Published: 05 December 2024
Figure 5.
Knowledge fusion case based on the ontology. Partial electronic health record information was extracted through models combined with the ontology such as “bilateral internal carotid artery.” The extracted expression was compared with the ontology based on similarity; the expression with higher simil
Journal Article
Toward clearer recognition and easier usefulness: development of a cross-lingual atherosclerotic cerebrovascular disease ontology
Database, Volume 2024, 2024, baae117, https://doi.org/10.1093/database/baae117
Published: 05 December 2024
Image
The rehabilitation ontology design. The rehabilitation ontology comprised t...
Published: 05 December 2024
Figure 2.
The rehabilitation ontology design. The rehabilitation ontology comprised types of rehabilitation, rehabilitation management, rehabilitation assessment, and rehabilitation equipment.
Image
The ontology statistics on concepts. (a) The numbers of English and Chinese...
Published: 05 December 2024
Figure 3.
The ontology statistics on concepts. (a) The numbers of English and Chinese terms in each category were shown, together with the number of total concepts. (b) The concepts in Level 4 reached the most among all levels. (c) One concept could comprise multiple terms. Nearly 300 concepts contain about f
Image
The application and scenario. The proposed ontology could be used for new t...
Published: 05 December 2024
Figure 6.
The application and scenario. The proposed ontology could be used for new term identification, information retrieval, named entity recognition, and knowledge graph fusion.
