STDERR.puts "Analyzing sequences ... "
system(
- "read_fastq -i #{seq_file} |
+ "read_fastq -e illumina1.8 -i #{seq_file} |
progress_meter |
analyze_vals -k SEQ -o #{analyze_vals_file} |
trim_seq -l 3 -m 25 |
- grab -e 'SEQ_LEN > 0' |
+ grab -e 'SEQ_LEN > 20' |
analyze_vals -k SEQ -o #{analyze_vals_trim_file} |
- find_adaptor -c 12 -l 6 -L 6 -f ACACGACGCTCTTCCGATCT -r AGATCGGAAGAGCACACGTC |
+ find_adaptor -l 6 -L 6 -f ACACGACGCTCTTCCGATCT -r AGATCGGAAGAGCACACGTC |
clip_adaptor |
grab -e 'SEQ_LEN > 0' |
analyze_vals -k SEQ -o #{analyze_vals_trim_noadapt_file} |
plot_distribution -k SEQ_LEN -T 'Sequence length distribution' -X 'Sequence length' -t png -o #{lendist_file} |
plot_scores -c -t png -o #{scores_file} |
- plot_nucleotide_distribution -t png -o #{nucdist_file} |
+ plot_nucleotide_distribution -c -t png -o #{nucdist_file} |
bin_vals -k SEQ_LEN -b 25 |
plot_distribution -T '25 bases bin sequence length distribution' -X 'Sequence length' -k SEQ_LEN_BIN -t png -o #{lendist_bin_file} |
mean_scores |