Legacy Bioinformatics Toolkit

Text2Knowledge

A compact archive of text-mining tools built around Medline, GenBank, OMIM, and taxonomy data. The interface has been refreshed, but the project still keeps its original workflow: direct search, immediate results, and lightweight exploration.

400k+ acronym entries
2.4M+ gene-name records
80k+ supported species

What It Is

Text mining tools from an earlier web, kept practical

Text2Knowledge aims to turn biomedical text into structured lookup data. The project extracts patterns from large text sources and exposes them through narrow, task-specific tools instead of one heavy application.

The current archive keeps the original tools online while modernizing the interface and hardening the public pages.

Core Tools

Pick a focused workflow

Acronym Finder

Look up a medical acronym or reverse-search a long form, then rate the candidate mappings.

400,000+ acronyms release 1.0

GeneQuery

Retrieve gene and protein interaction statements extracted from literature and ranked by confidence.

interaction lookup beta

Synonym Finder

Search a gene symbol and retrieve synonyms, accessions, taxonomy IDs, and linked phenotype identifiers.

2.4M+ names 80k+ species

Gene Mapper

Traverse the same gene index with a broader query surface, including synonym expansion and accession mapping.

mapping workflow release 1.0

Gene Tagger

Paste text and label detected genes with taxonomy and accession context, with precision and recall controls.

text annotation release 1.0

GO Digger

An archival placeholder for GO term exploration and clustering work that never fully shipped.

archive coming soon

Data Sources

Medline, GenBank, OMIM, taxonomy

The tools combine automatically extracted data with limited curated input. Expect uneven coverage, but quick, useful recall for exploratory work.

Support

Need background or citations?

Use the help page for workflow notes, or visit the contact page for project details.