It is obvious that existing text-mining systems cannot extract full information about molecular-genetic interactions contained in scientific publications.
A comprehensive yeast molecular interaction network containing 23,153 scored protein-protein and protein-DNA interactions was used [ 5] (personal communications, Dr. Anthony Gitter).
For example IntAct, an open-source, open data molecular interaction database contains approximately 275 000 curated binary interactions extracted from over 5000 publications.
Molecular interactions in InnateDB contain contextual information that meets the standards set forth by the minimum information required for reporting a molecular interaction experiment (MIMIx) standards.
The TimeXNet algorithm uses a large molecular interaction network, preferably containing protein-protein and protein-DNA interactions, along with post-translational modifications, weighted for reliability.
The Yeast-5 Pathway Studio database (Ariadne Genomics) contains molecular interactions extracted by MedScan natural processing technology for all fungal species from over 1,000,000 Pubmed abstracts annotated with Medical Subject Headings (MeSH) term "Yeast OR Fungi" and from more than 100,000 full-length open access articles.
MetaCore identifies networks based on a manually curated database containing known molecular interactions, functions, and disease interrelationships.
The integration of such datasets with comprehensive knowledge bases containing direct and indirect molecular interactions aids in deciphering the most prominent modulated pathways.
IPA-Core analysis integrates experimental data with its knowledge base containing a repository of molecular interactions and functional annotations extracted from selected, manually curated, literature sources and databases.
The corpus contains 9719 manually curated molecular interactions from 1551 publications.
