MarkerInfoFinder: Data Flow Chart
Natural Language Processing modules Invoke literautre queries Further filter literature sets Return literature results Integrate text mining results with biological database Integrate and clearn up multiple databases Integrate multiple biological databases ProbeMatchDB (developed in our group) HapMap II database Entrez Gene database NCBI Ideogram table NCBI UniSTS database (combined with other resources) NCBI dbSNP database OMIM (disease names) GenBank (gene names and symbols) SwissProt (gene names and symbols) Human Genome Organisation (gene nomenclature) Entrez Gene (LocusLink) (gene names and symbols) MEdical Subject Headings Medline abstracts Applying filters and other criteria Provide specific links to multiple external databases Export citations of seletced publications direct to citation managers Explore literature sets Group literature by MeSH terms Literature sets (Medline abstracts) Scaffolding tools to assist researchers Integrate multiple resources (journal, etc) Conduct text mining algorithms and store results Bayes classifier algorithm Rules and regular expressions, based on development corpus Corpus statistics, for term correlations Frequence profiling Filter out negated disease/marker relationships Extract biological entities (genes, markers, etc) Word Sense Disambiguation Shallow parsing Filter out negated disease/marker relationships Search literature by probes Search SNPs by genomic location Search functional related SNPs Disease (disease names, MeSH terms) Gene probes (sequence IDs, gene names) Genomic locations (Cytogenetic band, chromosome region) Genetic Markers (SNP, STS/Microsatellite)