Dwilliams week 4 assignment

1. Gene sequence string

cat infA-E.coli-K12.txt | sed "s/cat[at]at/ <minus10box>&<\/minus10box> /g" | 
sed -r "s/.{17} <minus10box/<\/minus35box> &/g" | sed "s/tt[gt]ac[at]<\/minus35box> / <minus35box>&/g" | 
sed -r "s/\/minus10box> .{6}/&<\/tss> /g" | sed "s/.<\/tss> / <tss>&/g" | sed "s/gagg/ <rbs>&<\/rbs>/g" | 
sed "s/<\/rbs>/&\n/g" | sed "2s/atg/ <start_codon>&<\/start_codon> /1" | 
sed -r "2s/<\/start_codon> .{3}*t[ag][ag]/&<\/stop_codon> /g" | sed "s/...<\/stop_codon> / <stop_codon>&/g" | 
sed "2s/aaaaggt/ <terminator>&/g" | sed "2s/gcctttt/&<\/terminator> /g"

1. mRNA transcribed sequence

cat infA-E.coli-K12.txt | sed "s/cat[at]at/ <minus10box>&<\/minus10box> /g" | sed -r "s/.{17} <minus10box/<\/minus35box> &/g" | 
sed "s/tt[gt]ac[at]<\/minus35box> / <minus35box>&/g" | sed -r "s/\/minus10box> .{6}/&<\/tss> /g" | sed "s/.<\/tss> / <tss>&/g" | 
sed "s/gagg/ <rbs>&<\/rbs>/g" | sed "s/<\/rbs>/&\n/g" | sed "2s/atg/\n&/1" | sed -r "3s/^.{3}*t[ag][ag]/&\n/g" | sed "3s/t/u/g" | 
sed "3s/.../& /g"

1. mRNA translation sequence determining code

cat infA-E.coli-K12.txt | sed "s/cat[at]at/ <minus10box>&<\/minus10box> /g" | sed -r "s/.{17} <minus10box/<\/minus35box> &/g" | 
sed "s/tt[gt]ac[at]<\/minus35box> / <minus35box>&/g" | sed -r "s/\/minus10box> .{6}/&<\/tss> /g" | sed "s/.<\/tss> / <tss>&/g" | 
sed "s/gagg/ <rbs>&<\/rbs>/g" | sed "s/<\/rbs>/&\n/g" | sed "2s/atg/\n&/1" | sed -r "3s/^.{3}*t[ag][ag]/&\n/g" | sed "3s/t/u/g" | 
sed "3s/.../& /g" | sed -f genetic-code.sed