Bash/run PHoeNIx at main · janis0616/Bash · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
#!/usr/bin/env bash
#Pipeline for running and organizing output from PHoeNIx

#Make sure PHoeNIx is installed in .../kraken2/phoenix
#Make sure you have the Standard-08 database installed in .../kraken2/Standard-08

#Make a directory called "reads" within your Kraken2 directory
##Within the "reads" directory, make a sub-directory for each sample (the directory name should be the sample name)
##Each sample sub-directory should include ONLY the 2 fastq files (each fastq file should have the sample name before any underscore in the file name)

#Before starting, activate your PHoeNIx Conda environment (i.e. conda activate phoenix or whatever you named it)

#Edit script so paths are correct for your computer:
#home: the location of your kraken2 directory
home=/mnt/data/kraken2/
#samplesheet: the location where your samplesheet will be created and what it will be named
samplesheet=/mnt/data/kraken2/samplesheet.csv
#output: the location where your output file will be created and what it will be named
output=/mnt/data/kraken2/phx_output/output.tsv
#summary: the location where your QC summary file will be created and what it will be named
summary=/mnt/data/kraken2/phx_output/qc_summary.tsv

cd $home

#Create the sample sheet
printf "sample,fastq_1,fastq_2\n" > $samplesheet
cd reads/

#Add each sample to the sample sheet
for dir in */
do
	cd $dir
	echo "$dir" | cut -d/ -f1 | tr -d '\n' >> $samplesheet
	for file in *
	do
		printf "," >> $samplesheet
		realpath ${file} | tr -d '\n' >> $samplesheet
	done
	printf "\n" >> $samplesheet
	cd ..
done

cd $home

#Run PHoeNIx
nextflow run cdcgov/phoenix -profile docker -entry PHOENIX --kraken2db ./Standard-08 --input $samplesheet

#Assemble the output
cd phx_output/
echo "PHoeNIx Output" > $output
for dir2 in */
do
	printf "${dir2}" >> $output
	printf "\n\n" >> $output
	cd ${dir2}
	cat *summaryline.tsv >> $output
	printf "\n\n" >> $output
	cat *synopsis >> $output
	printf "\n\n" >> $output
	cd ANI/
	cat *fastANI.txt >> $output
	printf "\n\n" >> $output
	cd ..
	cd AMRFinder/
	cat *all_genes.tsv >> $output
	printf "\nSummary of AMR Genes of Interest\n" >> $output
	awk -F"\t"  '$0 ~ "KPC" || $0 ~ "kpc" || $0 ~ "NDM" || $0 ~ "ndm" || $0 ~ "OXA" || $0 ~ "oxa" || $0 ~ "VIM" || $0 ~ "vim" || $0 ~ "IMP" || $0 ~ "imp" {printf $0 "\n"}' *all_genes.tsv >> $output
	printf "\n\n\n\n" >> $output
	cd $home
	cd phx_output/
done

#Create QC summary file
cd $home
cd ./phx_output/
for dir in */
do
	if [[ "$dir" != multiqc* ]] && [[ "$dir" != pipeline* ]]; then
		printf "${dir%%_*}\n\n" >> $summary
		cd ${dir}
		if compgen -G *summaryline.tsv > /dev/null; then
			awk -F"\t" '{print $2, "\t", $4, "\t", $5}' *summaryline.tsv >> $summary
		else
			printf "\nPass/Fail\tCoverage\tGenome Length\n" >> $summary
			printf "FAIL\tN/A\tN/A\n"  >> $summary
		fi
		printf "\nQuality Score - take average\n" >> $summary
		if compgen -G *synopsis > /dev/null; then
			awk -F":" 'NR >= 9 && NR <= 10 {print $3}' *synopsis >> $summary
		else
			echo "N/A" >> $summary
		fi
		cd ANI/
		printf "\nANI and Species\n" >> $summary
		if compgen -G *fastANI.txt > /dev/null; then
			awk -F"\t" '{print $3, "\t", $1}' *fastANI.txt >> $summary
		else
			echo "N/A" >> $summary
		fi
		cd ..
		cd AMRFinder/
		printf "\nAMR Genes of Interest\n" >> $summary
		if compgen -G *all_genes.tsv > /dev/null; then
		awk -F"\t"  '$0 ~ "KPC" || $0 ~ "kpc" || $0 ~ "NDM" || $0 ~ "ndm" || $0 ~ "OXA" || $0 ~ "oxa" || $0 ~ "VIM" || $0 ~ "vim" || $0 ~ "IMP" || $0 ~ "imp" {print $6, "\t", $7}' *all_genes.tsv >> $summary
		else
			echo "N/A" >> $summary
		fi
		printf "\n\n\n\n" >> $summary
	fi
	cd $home
	cd ./phx_output/
done