Commit 9df31e3c authored by psimion's avatar psimion
Browse files

minor correction of profiles sorting

parent db585d44
......@@ -27,7 +27,7 @@ for f in $out"/"*".all"
cat $f > $out"/"$ff".profile_tmp"
sed 's/inf/30/g' $out"/"$ff".profile_tmp" > $out"/"$ff".profile_tmp2"
echo -e "$ff" > $out"/"$ff".profile"
cat $out"/"$ff".profile_tmp2" | cut -f$col_ratio | sed '1d' | sed "s/\./,/g" | sort -g >> $out"/"$ff".profile"
cat $out"/"$ff".profile_tmp2" | cut -f$col_ratio | sed '1d' | sed "s/\./,/g" | sort -g | sed "s/,/\./g" >> $out"/"$ff".profile"
rm -f $out"/"$ff".profile_tmp" $out"/"$ff".profile_tmp2"
done
paste $out"/"*".profile" > $out"/CroCo_profiles"
......
### OUTPUT : basic statistics (cross_contamination_summary and cross_contamination_profiles files)
# removing unnecessary files
rm -f $out/ALL_transcripts.all
rm -f $out/ALL_transcripts.fasta_suspect
# computing stats for every sample
echo -e "\nWriting decontamination summary\n\tCroCo_summary\n\tCroCo_profiles"
col_ratio=$((`ls $out/*.fasta_suspect | wc -l`+3))
echo -e "species\ttotal_contigs\tnever_suspected\tnb_suspects\tnb_clean\tnb_lowcov\tnb_overexp\tnb_dubious\tnb_contam\tclean_percent\tlow_cov_percent\toverexp_percent\tdubious_percent\tcontam_percent" > $out"/CroCo_summary"
for f in $out"/"*".all"
do ff=`basename $f .all`
tot_ctgs=`grep -c '>' $INDIR/$ff.fasta`
tot_suspects=`grep -c '>' $out/$ff.fasta_suspect`
never_suspected=$(($tot_ctgs-$tot_suspects))
clean_ctgs=`grep -c -w 'clean' $f`
clean_percent=`echo "scale=2; ($clean_ctgs + ($tot_ctgs-$tot_suspects) ) * 100 / $tot_ctgs " | bc -l | awk '{printf "%.2f", $0}'`
contam_ctgs=`grep -c -w 'contam' $f`
contam_percent=`echo "scale=2; $contam_ctgs * 100 / $tot_ctgs " | bc -l | awk '{printf "%.2f", $0}'`
dubious_ctgs=`grep -c -w 'dubious' $f`
dubious_percent=`echo "scale=2; $dubious_ctgs * 100 / $tot_ctgs " | bc -l | awk '{printf "%.2f", $0}'`
lowcov_ctgs=`grep -c -w 'lowcov' $f`
lowcov_percent=`echo "scale=2; $lowcov_ctgs * 100 / $tot_ctgs " | bc -l | awk '{printf "%.2f", $0}'`
overexp_ctgs=`grep -c -w 'overexp' $f`
overexp_percent=`echo "scale=2; $overexp_ctgs * 100 / $tot_ctgs " | bc -l | awk '{printf "%.2f", $0}'`
echo -e "$ff\t"$tot_ctgs"\t"$never_suspected"\t"$tot_suspects"\t"$clean_ctgs"\t"$lowcov_ctgs"\t"$overexp_ctgs"\t"$dubious_ctgs"\t"$contam_ctgs"\t"$clean_percent"\t"$lowcov_percent"\t"$overexp_percent"\t"$dubious_percent"\t"$contam_percent >> $out"/CroCo_summary"
cat $f > $out"/"$ff".profile_tmp"
sed 's/inf/30/g' $out"/"$ff".profile_tmp" > $out"/"$ff".profile_tmp2"
echo -e "$ff" > $out"/"$ff".profile"
cat $out"/"$ff".profile_tmp2" | cut -f$col_ratio | sed '1d' | sed "s/\./,/g" | sort -g | sed "s/,/\./g" >> $out"/"$ff".profile"
rm -f $out"/"$ff".profile_tmp" $out"/"$ff".profile_tmp2"
done
paste $out"/"*".profile" > $out"/CroCo_profiles"
rm -f $out"/"*".profile"
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment