awk 筛选特定长度的序列

awk '/^>/ {printf("\n%s\t",$0);next;} {printf("%s",$0);} END {printf("\n");}' < assembly.fasta | egrep -v '^$' | tr "\t" "\n" | awk '!/^>/ { next } { getline seq } length(seq) > 200 { print $0 "\n" seq }' > assembly.fas