1-20 of 11777
Select how you would like to sort the search results
Image
Published: 08 July 2025
Figure 1. Architecture of the PLoV database. Each rectangular shape corresponds to a separate table in the database. Key fields have the ‘ID’ suffix and are connected using arrows.
Image
Published: 08 July 2025
Figure 2. Summary statistics of the entries in the PLoV database. Pie charts showing the proportions of cases with different numbers of PLs (A) or outcomes (B). Pie charts showing the numbers and proportions of genetic variants in the indicated variant pathogenicity (C) or confidence (D) categories. (E) A bar
Journal Article
Evgeniia M Maksiutenko and others
Published: 08 July 2025
Image
Published: 08 July 2025
Figure 3. Main elements of the user interface of the PLoV database. The top screenshot shows the Variants page and functionality of the database (location of extended information panels, filtration, and data submission options). The bottom screenshot shows the detailed variant view with corresponding informat
Journal Article
Fang-Yi Su and others
Database, Volume 2025, 2025, baaf025, https://doi.org/10.1093/database/baaf025
Published: 03 July 2025
Image
Published: 03 July 2025
Figure 1. (a) Results of generated data using traditional data augmentation approaches. (b) Results of generated data using our method. Text enclosed in rounded rectangles represents entity tags or components that should be preserved (corresponding to the highlighted text). Text that should have been preserve
Image
Published: 03 July 2025
Figure 9. Constrained Augmentor applied in code completion task.
Image
Published: 03 July 2025
Figure 4. (a) The template for Constrained Augmentor. (b) Details of how Constrained Augmentor is applied in the BioRED dataset.
Image
Published: 03 July 2025
Figure 5. Template for SemQ filter.
Image
Published: 03 July 2025
Figure 6. Constrained Augmentor applied in information retrieval task.
Image
Published: 03 July 2025
Figure 7. Example of generated data in BioRED with semantic score. Highlights indicate modifications that preserve the same semantic meaning. Underlines denote the entities with unique tags around them.
Image
Published: 03 July 2025
Figure 2. (a) An example of a biomedical relation extraction task for a “Positive Correlation” relation between two types of entity, Gene and Chemical, being wrapped in entity type tagging. There will be a source entity (with “Src” tags) and a Target entity (with “Tgt” tag). The specific tags @/EntityType$
Image
Published: 03 July 2025
Figure 3. Overall flow of the framework.
Image
Published: 03 July 2025
Figure 8. Example of generated data in Code Completion with semantic score. Highlights indicate modifications that preserve the same semantic meaning. Underlines denote the entities with unique tags around them. Bold text represents modifications that alter the semantic meaning.
Journal Article
Published: 26 June 2025
Image
Published: 30 May 2025
Figure 2. Research methodology.
Image
Published: 30 May 2025
Figure 1. Artificial Intelligence Driven Predictive Framework for Analyzing Protein Sequences Across Diverse Bioinformatics Tasks.
Image
Published: 30 May 2025
Figure 3. Precise classification of unique protein sequence analysis tasks in 11 major biological goals.
Image
Published: 30 May 2025
Figure 4. A comprehensive methodical categorization of protein sequence analysis tasks into regression, binary classification, multi-class classification, multi-label classification, and clustering.
Image
Published: 30 May 2025
Figure 6. Utilization of 15 different LLMs in diverse protein sequence analysis pipelines based on a variety of machine and deep learning algorithms