What is Text2Knowledge?
Text2Knowledge (T2K) is aiming to provide text mining tools to analyze medical texts.
It utilizes natural language processing techniques to extract patterns from text
and convert them into knowledge.
T2K currently maintains the following databases:
- Medical Acronym Database
- Gene Interaction Database
- Gene Synonym Database
- Gene ID Database
- Go Digger Database (alpha)
T2K is providing a series of web tools to interface the above databases: 
| Tools | Description | Statistics | Status |
| Retrieve acronym or full name | 400,000+ acronyms | release 1.0 | |
| Retrieve gene/protein interaction | limited entries | beta | |
| Find a gene's synonyms with Accession number, NCBI Taxonomy ID and phenotype information | 2,400,000+ gene name entries for 80,000+ species | release 1.0 | |
| same as above + query on function, protein product and phenotype | same as above | release 1.0 | |
| Gene Tagger | Label your text with GENE Tags with Taxonomy and Accession number information. | similar as above | release 1.0 |
| Label your text with GO terms. Cluster texts based on GO terms | coming soon |
If you are interested in T2K databases and tools, contact me for details.
Text2Knowledge ... Yong Huang 2005