The edges in MalaCards are defined based on searches within MalaCards, highlighting three types of interconnections: (i) textual co-occurrence, e.g. in the 'Summaries' and 'Publications' sections, (ii) symptoms/phenotypes, and (iii) gene sharing, as manifested in the related diseases section derived from GeneDecks gene set analysis.
AGRA uses finding-associated concepts with text analysis (FACTA), an online text search engine for MEDLINE abstracts that can quickly compute the association strengths between a query and different types of biomedical concepts based on their textual co-occurrence statistics (Tsuruoka et al., 2008).
These have all been used previously in information retrieval to model information about the occurrences of textual keywords, but have been modified here to model information about the occurrences of substructural fragments.
For example, by simply searching co-occurrences of textual terms belonging to a disorder class and to a gene class it is possible to extract potential disease gene associations from text, although a more complex strategy would likely improve performance.
For a set of texts, each n-gram may be characterized by textual frequency of n-gram occurrence (f_{T} left( {T_{i} } right))—total number of n-gram occurrences within a text (T_{i}) and by absolute frequency of occurrence (f_{A} = mathop sum limits_{i} f_{A} left( {T_{i} } right))—total number of n-gram occurrences.
contains a collection of texts from different time periods (in our research, several different events from the EuropaCat research conference were used), the analysis of textual and absolute frequencies of occurrence will allow to follow up the "life cycle" of each term-like phrase on the quantitative level (term usage increasing, decreasing and so on).
Finally, the application does not contextualize concepts found in textual variables based on their occurrence timeline and does not perform sustained semantic analysis.
In our approach, known entity activities represent entity co-occurrences in the textual collection.
Interactions are initially established in a network by entity co-occurrences in a textual collection.
We determine the interaction level based on the VSM when we look for the entity co-occurrences throughout the textual collection.
