PaperBLAST builds a database of protein sequences that are linked to scientific articles. These links come from automated text searches against the articles in EuropePMC and from manually-curated information from GeneRIF, UniProtKB/Swiss-Prot, BRENDA, CAZy (as made available by dbCAN), CharProtDB, MetaCyc, EcoCyc, REBASE, and the Fitness Browser. Given this database and a protein sequence query, PaperBLAST uses protein-protein BLAST to find similar sequences with E < 0.001.
This should be the first step to be done when working a new gene. It allows to extract papers on several members of a protein family. It is important however to check the links manually. Searches also will miss some references that are not open access and have not mentioned the protein Locus_tag in the abstract/title.
No specific help, but very easy to use and self-explanatory. The search using family ids not sequence is not totally intutive to find.