sequences : header sequence(s) header : seq_count app_number seq_count : "<160> NUMBER OF SEQ ID NOS:" /\d+/ app_number : "<140> CURRENT APPLICATION NUMBER:" /[\w\/,]+/ sequence : seq_id seq_length seq_type organism feat_token(s?) seq seq_id : "<210> SEQ ID NO" /\d+/ seq_length : "<211> LENGTH:" /\d+/ seq_type : "<212> TYPE:" type type : "DNA" | "PRT" organism : "<213> ORGANISM:" /\w+ \w+/ feat_token : feature | name_key | location | other feature : "<220> FEATURE:" /[\w\s]*/ name_key : "<221> NAME/KEY:" /\w+/ location : "<222> LOCATION:" /[\d\.\(\)]+/ other : "<223> OTHER INFORMATION:" /[^<]+/ seq : "<400> SEQUENCE:" /\d+/ /[\w\s]+/