Ranking the whole MEDLINE database according to a large training set using text indexing.

Brian P Suomela and Miguel A Andrade.
BMC Bioinformatics 2005, 6:75.

Supplementary material.

Additional file 2 . Nouns, adjectives, and verb scores.
A zip compressed file (file2.zip) containing three lists in plain text format (sortednounscores.txt, sortedadjectivescores.txt, sortedverbscores.txt) of the computed scores for 2,256 nouns, 1,193 adjectives, and 748 verbs.

Additional file 3 . Stem Cell MEDLINE reference scores
A zip compressed file (file3.zip) containing lists in plain text format (stemcellpaperscores-adjectives.txt, stemcellpaperscores-nouns.txt, stemcellpaperscores-nounsadjectives.txt, stemcellpaperscores-verbs.txt) of 81,416 PMIDs of stem cell references and their scores according to nouns, adjectives, verbs, and combined nouns/adjectives.

Additional file 4 . Subset of MEDLINE reference scores
A zip compressed file (file4.zip) containing lists in plain text format (paperscores-adjectives.txt, paperscores-nouns.txt, paperscores-nounsadjectives.txt, paperscores-verbs.txt) of 81,416 PMIDs of references randomly selected from MEDLINE and their scores according to nouns, adjectives, verbs, and combined nouns/adjectives.

Additional file 5 . List of 6,923 scored abstracts
A zip compressed file (file5.zip) containing a table in plain text format with tab separated columns (paperscores-nouns-recent.txt) of 6,923 PMIDs of references not included in the training set with their scores, and a human evaluation of their relevance to the topic of stem cells.