1-20 of 8576
Sort by
Journal Article
Database, Volume 2024, 2024, baae110, https://doi.org/10.1093/database/baae110
Published: 01 October 2024
Journal Article
Oluwamayowa O Amusat and others
Database, Volume 2024, 2024, baae093, https://doi.org/10.1093/database/baae093
Published: 27 September 2024
Image
Published: 27 September 2024
Figure 4. Flowchart of the artifact linkage process for label generation
Image
Published: 27 September 2024
Figure 1. Knowledge patterns in CPMKG. (a) Side effects refer to side effects or complications that occur during the use of medication. Example: association between olanzapine and metabolic syndrome risk in schizophrenia patients. (b) Drug sensitivity refers to an individual’s propensity to exhibit a heighten
Image
Published: 27 September 2024
Figure 3. Knowledge exploration in CPMKG. (a) Precision medicine knowledge list. A list centered on “warfarin,” comprising four distinct patterns. (b) Knowledge unit details. Illustrated by “warfarin treatment side effects,” it includes graphical representation, established conditions, evidence sources, and e
Journal Article
Jiaxin Yang and others
Database, Volume 2024, 2024, baae102, https://doi.org/10.1093/database/baae102
Published: 27 September 2024
Image
Published: 27 September 2024
Figure 2. “SciKey’s” metadata generation pipeline and submodules.
Image
Published: 27 September 2024
Figure 5. Flowchart of the ontology-based process for label generation
Image
Published: 27 September 2024
Figure 6. Distribution of derived labels.
Image
Published: 27 September 2024
Image
Published: 27 September 2024
Figure 2. Conditional knowledge-based schema of CPMKG. This schema includes foundational elements such as drugs, diseases, phenotypes, genes, and variations. “Drugs” cover pharmacological substances, “diseases” encompass pathological conditions, “variations” refer to differences in the human genome, “phenotyp
Image
Published: 27 September 2024
Figure 4. Advanced application of CPMKG. (a) Personalized drug suggestion offers tailored medical advice based on diagnostic outcomes and genetic backgrounds. Example: crucial factors for prescribing medication to breast cancer patients with the NC_000002.12:g.38071060G>A,C variant. (b) Pharmacogenomics
Image
Published: 27 September 2024
Figure 1. Potential approaches for validating ML-generated keywords for unlabeled texts when human labels are unavailable; our proposed approaches are shown in green.
Image
Published: 27 September 2024
Figure 3. Overview of the automated labeling and metadata generation process. Built on top of the “SciKey” module, the automated label generation process (shown in the rounded rectangle) takes in a text blob containing semantic information and a set of labels that are used for ML-generated keyword validation.
Image
Published: 27 September 2024
Figure 7. Co-occurrence plot for all publication-derived labels. Most of the labels either do not co-occur at all (white space) or co-occur once (small orange circles).
Journal Article
Sara Zareei and others
Database, Volume 2024, 2024, baae092, https://doi.org/10.1093/database/baae092
Published: 20 September 2024
Image
Published: 20 September 2024
Figure 1. Peptide-Based Strategies for Cancer Treatment.
Image
Published: 20 September 2024
Figure 6. Amino acids physicochemical classes based on which grouped features are categorized in PeptiHub.
Image
Published: 20 September 2024
Figure 2. The overall content of PeptiHub.
Image
Published: 20 September 2024
Figure 3. The overall components and utilities of PeptiHub.