BioTextRetriever: A Tool to Retrieve Relevant Papers.

Whenever new sequences of DNA or proteins have been decoded it is almost compulsory to look at similarsequences and papers describing those sequences in order to both collect relevant information concerningthe function and activity of the new sequences and/or know what is known already about similar sequences.In current web sites and data bases of sequences there are, usually, a set of curated paper references linkedto each sequence. Those links are a good starting point to look for relevant information related to a set ofsequences. One way to implement such approach is to do a blast with the new decoded sequences, and collectsimilar sequences. Then one looks at the papers linked with the similar sequences. Most often the numberof retrieved papers is small and one has to search large data bases for relevant papers. This paper proposesa process of generating a classifier based on the initially set of relevant papers. First, the authors collectsimilar sequences using an alignment algorithm like Blast. Then, the authors use the enlarges set of papersto construct a classifier. Finally a classifier is used to automatically enlarge the set of relevant papers bysearching the MEDLINE using the automatically constructed classifier