Project Summary
"The scientific literature of biomedicine, genomics, and other biosciences is a rich, complex, and continually growing resource. With appropriate search tools, bioscience researchers can use the contents of the literature to further their research goals. For example, buried within the literature are important clues that can be applied to the construction and verification of genetic pathways. A key search goal for many such researchers is to narrow or refine the results of queries in useful ways. These narrowing methods include restricting results according to entities (such as type of organism, tissue type, protein type, or process type) and - more desirable still - selecting abstracts only if they describe particular relations between these entities (such as binds-to, treatment-for, and mutation-of). Another useful narrowing approach is to restrict according to certain types of publications and time spans, e.g., only articles that appeared in the last six months in high-quality journals of molecular biology. "
BioText Software for Download
Downloading is free, but please acknowledge us by citing this paper if you use the code in research:
- A Simple Algorithm for Identifying Abbreviation Definitions in Biomedical Text, Ariel Schwartz and Marti Hearst, in the proceedings of the Pacific Symposium on Biocomputing (PSB 2003) Kauai, Jan 2003. pdf
| Java sourcecode | ExtractAbbrev.java |
| Java Documentation | ExtractAbbrev.html |
| Sample input file | test.txt |
| Sample testing file | pairs.txt |
Software to parse and load MEDLINE into a RDBMS
Downloading is free, but acknowledge source if you use the code:
- Tools for loading Medline into a local relational database Diane E. Oliver, Gaurav Bhalotia, Ariel S. Schwartz, Russ B. Altman, Marti A. Hearst, BMC Bioinformatics 2004, (7Oct2004) Available at BioMedCentral
MedlineParser java code. Applicable to MEDLINE 2004. gzipped tar file zip file
MedlineParser perl code. Applicable to MEDLINE 2003. parsemedline.pl medline-schema-perl-oracle.sql
