INFORMATION RETRIEVAL, EXTRACTION AND VISUALISATION

摘要

The present invention generally provides a method and platform for effective information retrieval, information extraction and information visualisation from scientific and/or technical literatures. Preferred method embodiments comprise: (a) retrieval of scientific and/or technical literatures with effective precision and recall using a comprehensive gene/protein synonym dictionary with textual variants; (b) recognition and tagging of one or more chemical compounds from a scientific and/or technical literatures; (c) recognition and tagging of physical properties related to one or more of those compounds; (d) conversion of one or more of those compounds into a chemical structure; (e) recognition and tagging of one or more chemical reaction descriptions from a scientific and/or technical literatures; (f) extraction of tagged information and storing it in thematic databases; and (g) normalisation, de- duplication and integration of bibliographic, chemical and biological information enabling inter-operability among databases.