(?i)like
(?i)associated
(?i)containing
(?i)activated
(?i)family
(?i)subfamily
(?i)interacting
(?i)activity
(?i)similar
(?i)product
(?i)expressed
(?i)predicted
(?i)putative
(?i)uncharacterized
(?i)probable
(?i)protein
(?i)gene
(?i)tair
(?i)\b\w{1,2}\b
\b\d+\b
(?i)fragment
(?i)homolog
(?i)contig
(?i)related
(?i)\b\w?orf(\w?|\d+)\b
(?<![-.\w])([a-zA-Z_]+\d+|\d+[a-zA-Z_]+|\d+[a-zA-Z_]+\d+|[a-zA-Z_]+\d+[a-zA-Z_]+|\.\w*)+(?![-.\w])