User Tools

Site Tools


genetica:bioinf_process:fastqc:script2

# The second script summarizes data from module 1 that may be of interest at the moment of reporting parameters of data quality in papers, parameters like average sequence quality

# It is located at /bonn_data/Bonn_0_fastq/fastqcRawdata/summarizing_fastqc_1module_2data_mine-bis.sh

#It can be run by typing:

[vifehe@detritus fastqcRawdata]$ ./summarizing_fastqc_1module_2data_mine-bis.sh
summarizing_fastqc_1module_2data_mine-bis.sh
#!/bin/bash
 
##FastQC	0.10.1
#>>Basic Statistics	pass
#Measure	Value	
#Filename	SN7640211_14074_P1A01_MND1014_1_sequence.fq.gz	
#File type	Conventional base calls	
#Encoding	Sanger / Illumina 1.9	
#Total Sequences	44012752	
#Filtered Sequences	0	
#Sequence length	101	
#%GC	49	
#>>END_MODULE
#>>Per base sequence quality	pass
#Base	Mean			Median	Lower Quartile	Upper Quartile	10th Percentile	90th Percentile
#1	31.64506284451379	33.0	31.0	34.0	28.0	34.0
#2	31.880190722906853	34.0	31.0	34.0	28.0	34.0
#3	31.972653289210363	34.0	31.0	34.0	28.0	34.0
#4	35.39369340049448	37.0	35.0	37.0	32.0	37.0
#5	35.09201710449735	37.0	35.0	37.0	32.0	37.0
#6	35.08697933726116	37.0	35.0	37.0	32.0	37.0
#7	35.06162818448617	37.0	35.0	37.0	32.0	37.0
#8	35.052662714660514	37.0	35.0	37.0	32.0	37.0
#9	36.63084601026539	39.0	37.0	39.0	32.0	39.0
#10-14	36.86299192561283	39.2	37.2	39.4	32.0	39.4
#15-19	37.82707197677619	40.0	38.0	41.0	32.0	41.0
#20-24	37.68135608516368	40.0	38.0	41.0	31.0	41.0
#25-29	37.417561642134984	40.0	37.0	41.0	30.4	41.0
#30-34	37.13463264010394	40.0	36.8	41.0	30.0	41.0
#35-39	36.80116996546819	40.0	36.0	41.0	29.4	41.0
#40-44	36.6426807985104	40.0	35.8	41.0	28.8	41.0
#45-49	36.66400877636554	40.0	35.2	41.0	28.6	41.0
#50-54	36.30974728415073	39.2	35.0	41.0	28.0	41.0
#55-59	35.784558657000126	38.6	34.6	41.0	27.2	41.0
#60-64	35.131667385852175	37.2	34.0	40.0	26.0	41.0
#65-69	34.42042487140999	35.8	33.2	39.4	26.0	41.0
#70-74	33.645179519790084	35.0	33.0	38.0	25.4	40.4
#75-79	32.74637153341378	35.0	31.8	36.2	24.2	39.0
#80-84	32.329568739532576	35.0	32.0	35.6	24.0	37.2
#85-89	31.784759544233907	35.0	31.2	35.0	23.2	36.2
#90-94	31.437542837584893	34.8	31.0	35.0	23.0	35.6
#95-99	31.11940442170033	34.0	31.0	35.0	20.6	35.0
#100-101	30.526057039105396	34.0	29.5	35.0	19.0	35.0
 
idir=fastqcRawdata_P5
outfile=${idir}_modules_summary.stats
 
touch $outfile
printf "Sample\taverage_mean\taverage_median\n" > $outfile
 
for x in $idir/*.fq_fastqc/fastqc_data.txt
	do
#	echo $x
        sample=(`echo $x | awk -F "/" {'print $2'} | awk -F"_" {'print $4"-"$5'}`) #this should output L5150-1
#        echo $sample
	basic_stats=${sample}_basic_stats.txt
	touch $basic_stats
	sed -n '14,41p' $x > $basic_stats
	av_mean=0
	av_median=0
	count=0
		while IFS=$"\t" read -r; do 
		mean=(`cat $basic_stats | awk -F"\t" {'print $2'}`)
		median=(`cat $basic_stats | awk -F"\t" {'print $3'}`)
		av_mean=`echo  $av_mean+$mean | bc -l`
		av_median=`echo $av_median+$median | bc -l`
#		mean=$(echo "scale=2;${mean}+${line[0]}" | bc);
		((count ++))
#		echo "${line[1]}"
#		median=$(echo "scale=2;${median}+${line[1]}" | bc);
#		echo "$count"
		done < $basic_stats
	final_mean=`echo $av_mean/$count | bc -l`
#	printf "%s\t%s" "$sample" "scale=2;$final_mean";
#	printf "final_mean="; echo "scale=2; $av_mean/$count" | bc;
	final_median=`echo $av_median/$count | bc -l`
#	printf "final_median= "; echo "scale=2; $av_median/$count" | bc;
#	printf "$sample\t"; echo "scale=2; $av_mean/$count" | bc; echo "scale=2; $av_median/$count" | bc;
	printf "%s\t%5.2f\t%5.2f\n" $sample $final_mean $final_median >> $outfile
	rm $basic_stats;
	done

#and the output looks like this:

[vifehe@detritus fastqcRawdata]$ more fastqcRawdata_P1_modules_summary.stats
Sample	average_mean	average_median
MND1014-2	31.28	33.00
MND116-1	31.54	33.00
MND116-2	31.14	33.00
MND126-1	31.62	33.00
MND126-2	31.23	33.00
MND1405-1	31.62	33.00
MND1405-2	31.26	33.00
MND1493-1	31.56	33.00
MND1493-2	31.19	33.00
MND1725-1	31.58	33.00
MND1725-2	31.23	33.00
MND334-1	31.58	33.00
MND334-2	31.19	33.00
MND413-1	31.60	33.00
MND413-2	31.21	33.00
MND1021-1	31.45	33.00
MND1021-2	31.03	33.00
MND1165-1	31.54	33.00
MND1165-2	31.10	33.00
MND1263-1	31.58	33.00
MND1263-2	31.16	33.00
MND1408-1	31.59	33.00
MND1408-2	31.16	33.00
genetica/bioinf_process/fastqc/script2.txt · Last modified: 2020/08/04 10:58 by 127.0.0.1