However, the majority of predicted interactions among AvBDs and between AvBDs and other antimicrobial proteins were merely derived from textmining
data and lacks experimental evidence.
MYH3 myosin-3 (1940aa) Your Input Neighborhood Gene Cooccurence Experiments Fusion Database CSB4 Predicted Functional Partners: PPP3C8 * * PPP3CC * * ENSBTAG00000019525 * * PPP3CA * * ATP284 * ATP2B1 * ATP2B2 * A7P2B3 * CNBP * MYH3 * Your Input Textmining
Score [Homology] CSB4 Predicted Functional Partners: PPP3C8 * 0.657 PPP3CC * 0.657 ENSBTAG00000019525 * 0.657 PPP3CA * 0.657 ATP284 * 0.642 ATP2B1 * 0.642 ATP2B2 * 0.642 A7P2B3 * 0.642 CNBP * 0.627 MYH3 * 0.591
A red line indicates the presence of fusion evidence; a green line, neighborhood evidence; a blue line, coocurrence evidence; a purple line, experimental evidence; a yellow line, textmining
evidence; a light blue line, database evidence; and a black line, coexpression evidence.
A potential limitation of the automated textmining
approach is that the search is more specific but less sensitive, sometimes necessitating a manual validation of the literature base to ensure that all relevant publications have been captured.
Nao obstante, alem dos softwares pagos (que se destinam ao textmining
, datamining etc.), as ferramentas de acesso livre da Web 2.0 proporcionam uma tecnologia emergente na opcao para tratar volume de dados para as organizacoes que nao possuem uma robusta facilidade de aquisicao e manutencao de softwares e mecanismos de buscas privados (licencas de uso).
tools may be of great help in this task.
Smith et al., "Evaluation of textmining
systems for biology: overview of the Second BioCreative community challenge," Genome Biology, vol.
Using Autonomy's IDOL (Intelligent Data Operating Layer) engine to take advantage of its robustness, scalability and adaptability, the project incorporated a variety of search and discovery functionality: simple metadata search; full-text indexing of documents and associated digital artefacts; textmining
of full-text documents; automatic subject classification; dynamic clustering and serendipitous browsing; term-based document classification and visualisation approaches to search results.