Tools
permits searching and exporting Author-ity data, it's annotations, imputed features, and links to
grants and patents datases;
has 3 databases: 1) Author-ity (author names in PubMed disambiguated),
2) inventor names in USPTO disambiguated (2 versions:
1975-2009
and
1975-2011), and
3) these two sources linked.
currently linked to NIH grants (1971-present from
ExPORTER
and
CRISP) and NSF grants.
a citation matcher that has been optimized for citations from USPTO patents to PubMed but can take any citation string and give you the most likely PMID (with a match probability). We stuck in DBLP too and are interested in including other complementary citation databases -- let us know if you have one.
does more than just prediction -- for a given name it estimates worldwide proportion of females/males over time.
Use Ethnea (below) for greater coverage and ethnicity-specific gender prediction.
predicts ethnicity based on the geo-temporal distribution of names of authors in PubMed, and Genni 2.0 has
ethnicity-specific gender prediction (e.g., English Andrea -> F; Italian Andrea -> M).
Permits searching for identifiers from several bibliographic databases: PubMed, DBLP, MAG, ADS, NIH, NSF, USPTO.
provides access to (and filtering of) disambiguated geo-political entities and institution types inferred from affiliation strings per paper in PubMed. Geocodes link to Google Maps. For geo-locations in the U.S.A., query results also link to county-level demographic, economic, and MeSH summaries.
has more recent PubMed data but only permits queries by PMID.
experimental (i.e., not yet optimized) tool for predicting MeSH on NIH grants and USPTO patents.
calculates bm25 similarity among pairs of abstracts in PubMed.
helps explore novelty measures for a given paper in PubMed. This site is in its infancy!
displays a temporal profile for a given author. You can find the author id by searching our
Author database. This site is in its infancy!
a utility to find terms that are implicit within authors (across their papers). You can relate journals, MeSH, title words, and affiliations words.
has faceted search of USPTO patents but also provides Python code for downloading, parsing, and loading USPTO patent bulk data into a local MySQL database.
addressed a range of critically
important themes in the various fields that address disambiguation and the managing and analysing of large data sets.
includes tools like Arrowsmith, Author-ity, Anne O'Tate, ADAM. The
main site has some new functionality and tools too.