small update in doc and regexps

misc-scripts/gene_description/Homo_sapiens.regexps

 # regexp used for filter out useless description for Homo sapiens
 # add more as appropriate, line begining with # are supposed to be comments
 
+^LOC\d+\s*(PROTEIN)?\.?
+^ORF.*
+^PROTEIN C\d+ORF\d+\.*
 \(CLONE \S+\)\s+
 ^BC\d+\_\d+\.?
 ^CGI\-\d+ PROTEIN\.?\;?
@@ -28,8 +31,9 @@ RIKEN CDNA [0-9A-Z]{10}[ \.]
 ^SIMILAR TO (KIAA|LOC).*
 ^SIMILAR TO\s+$
 ^WUGSC:H_.*
-^\s*\(FRAGMENT\)\.?\s*$
-^\s*\(GENE\)\.?\s*$
+^\s*\(?PROTEIN\)?\.?\s*$
+^\s*\(?FRAGMENT\)?\.?\s*$
+^\s*\(?GENE\)?\.?\s*$
 ^\s*\(\s*\)\s*$
 ^\s*\(\d*\)\s*[ \.]$
 

misc-scripts/gene_description/gene-descriptions.pl

@@ -50,7 +50,7 @@ my $usage = "
                                    RefSeq entries in gnp-like format.
                                    and/or
                                    \"consortium\" description file, which format should
-                                   match this regexp /^(\S+)\\t(.*)\$/, making sure that
+                                   match this regexp /^(\\S+)\\t(.*)\$/, making sure that
                                    the mapping includes populating identity_xref table.
 
  OR to load the data from gene-descriptions.tab file to \'gene-description\' table

modules/Bio/EnsEMBL/Slice.pm

@@ -967,7 +967,7 @@ sub get_Chromosome {
   Arg [2]    : int $default_masking_type (optional, default is 0)
                0 hard mask, repeats are replaced by Ns
                1 soft mask, repeats are transformed in lower case  
-  Arg [3]    : hash reference $not_default_masking_cases (optional)
+  Arg [3]    : hash reference $not_default_masking_cases (optional, default is {})
                The values are 0 or 1 with same definition as in Arg [2]
                The keys of the hash should be of 2 forms
                "repeat_class_" . $repeat_consensus->repeat_class,