-
44 | ''')
45 | for k,v in results.items():
46 | print("
- {}
- {} ".format(k,v)) 47 | print ("
13 |
14 | 
15 |
16 |
43 |
44 | <% out << summary.collect{ k,v -> "
47 |
48 |
52 |
53 |
54 |
55 |
--------------------------------------------------------------------------------
/bin/create_IGV_js.sh:
--------------------------------------------------------------------------------
1 | #! /bin/bash
2 | fasta=$1
3 | gtf=$2
4 | merged_peak_file=$3
5 | designfile=$4
6 | echo "Start to generate IGV.js"
7 |
8 | ## setting tmp files' name
9 | bedgraph_tracks_file=tmp.bedgraph.tracks
10 | peaks_tracks_file=tmp.peaks.tracks
11 |
12 | ## combined tracks of bedgraph
13 | sampleinfo_list=$(awk 'BEGIN{FS=","}NR>1{print $1","$4}' $designfile |sort|uniq|awk 'BEGIN{ORS=" "}{print $0}')
14 | for sample_group_id in ${sampleinfo_list}
15 | do
16 | {
17 | sample_id=$(echo ${sample_group_id} | awk 'BEGIN{FS=","}{print $1}')
18 | group_id=$(echo ${sample_group_id} | awk 'BEGIN{FS=","}{print $2}')
19 | bedgraph_input_file=$(ls ${sample_id}.input_*.igv.bedgraph)
20 | bedgraph_ip_file=$(ls ${sample_id}.ip_*.igv.bedgraph)
21 | cat >> ${bedgraph_tracks_file} << EOF
22 | {
23 | url: '${bedgraph_input_file}',
24 | name: '${sample_id}.input',
25 | color: 'rgb(200,0,0)',
26 | type: "wig",
27 | sourceType: "file",
28 | autoscaleGroup: 'group_${group_id}.${sample_id}'
29 | },
30 | {
31 | url: '${bedgraph_ip_file}',
32 | name: '${sample_id}.ip',
33 | type: "wig",
34 | sourceType: "file",
35 | color: 'rgb(200,0,0)',
36 | autoscaleGroup: 'group_${group_id}.${sample_id}'
37 | },
38 | EOF
39 | }
40 | done
41 |
42 | ## combined tracks of merged group peaks
43 | groups_peak_file=$(ls *_merged_group_*igv.bed)
44 | for peak_file in ${groups_peak_file}
45 | do
46 | {
47 | cat >> ${peaks_tracks_file} << EOF
48 | {
49 | type: "annotation",
50 | format: "bed",
51 | url: '${peak_file}',
52 | name: "${peak_file}"
53 | },
54 | EOF
55 | }
56 | done
57 |
58 | ## combined tracks and allpeaks track
59 | cat ${bedgraph_tracks_file} ${peaks_tracks_file} > tmp.tracks
60 | cat >> tmp.tracks << EOF
61 | {
62 | type: "annotation",
63 | format: "bed",
64 | url: '${merged_peak_file}',
65 | name: "${merged_peak_file}"
66 | }
67 | EOF
68 | tracks_js=$(cat tmp.tracks)
69 |
70 | ## combined all info
71 | cat>igv.js<nf-core/meripseqpipe v${version}
17 |Run Name: $runName
18 | 19 | <% if (!success){ 20 | out << """ 21 |
22 |
27 | """
28 | } else {
29 | out << """
30 | nf-core/meripseqpipe execution completed unsuccessfully!
23 |The exit status of the task that caused the workflow execution to fail was: $exitStatus.
The full error message was:
25 |${errorReport}
26 |
31 | nf-core/meripseqpipe execution completed successfully!
32 |
33 | """
34 | }
35 | %>
36 |
37 | The workflow was completed at $dateComplete (duration: $duration)
38 |The command used to launch the workflow was as follows:
39 |$commandLine40 | 41 |
Pipeline Configuration:
42 || $k | $v |
|---|
nf-core/meripseqpipe
49 | 50 | 51 |
75 | """
76 | footer = """
77 |
78 |
79 |
80 | """
81 | return header + contents + footer
82 |
83 |
84 | def parse_args(args=None):
85 | parser = argparse.ArgumentParser()
86 | parser.add_argument('mdfile', type=argparse.FileType('r'), nargs='?',
87 | help='File to convert. Defaults to stdin.')
88 | parser.add_argument('-o', '--out', type=argparse.FileType('w'),
89 | default=sys.stdout,
90 | help='Output file name. Defaults to stdout.')
91 | return parser.parse_args(args)
92 |
93 | def main(args=None):
94 | args = parse_args(args)
95 | converted_md = convert_markdown(args.mdfile.name)
96 | html = wrap_html(converted_md)
97 | args.out.write(html)
98 |
99 | if __name__ == '__main__':
100 | sys.exit(main())
101 |
--------------------------------------------------------------------------------
/bin/meyer.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | """
3 | Created on Tue Apr 23 18:53:30 2019
4 |
5 | @author: zky
6 | """
7 | from sys import argv
8 | from math import log
9 | from scipy import stats
10 | input_bin25_file = argv[1]
11 | ip_bin25_file = argv[2]
12 | input_total_reads_count = int(argv[3])
13 | ip_total_reads_count = int(argv[4])
14 | peak_windows_number = int(argv[5])
15 | output_ip_file = argv[6]
16 | def windows_fisher_test(input_count, ip_count, input_total_reads_count, ip_total_reads_count):
17 | """fisher test for the PeakCalling of meyer"""
18 | site_input_rest_reads_count = input_total_reads_count - int(input_count)
19 | site_ip_rest_reads_count = ip_total_reads_count - int(ip_count)
20 | ip_oddsratio, ip_pvalue = stats.fisher_exact([[input_count, ip_count], [input_total_reads_count, ip_total_reads_count]], 'less')
21 | input_oddsratio, input_pvalue = stats.fisher_exact([[input_count, ip_count], [site_input_rest_reads_count, site_ip_rest_reads_count]], 'greater')
22 | return input_pvalue,ip_pvalue
23 |
24 | def cluster_bin( bonferroni_filter_list ):
25 | bonferroni_peak = []
26 | peak_line = []
27 | idx = 0
28 | pre_end_position = 0
29 | for data in bonferroni_filter_list:
30 | distance = data[1] - pre_end_position
31 | if pre_end_position == 0 or distance > 0 :
32 | if peak_line :
33 | peak_region = peak_line[2] - peak_line[1]
34 | if peak_region >= 100 :
35 | bonferroni_peak.append([])
36 | bonferroni_peak[idx] = peak_line
37 | idx += 1
38 | peak_line = []
39 | peak_line = data[:]
40 | pre_end_position = data[2]
41 | else:
42 | peak_line[2] = data[2]
43 | pre_end_position = data[2]
44 | peak_line.append(data[3])
45 | for data in bonferroni_peak:
46 | statistic, pval = stats.combine_pvalues(data[3:len(data)], method='fisher', weights=None)
47 | data[3] = pval
48 | del data[4:len(data)]
49 | return bonferroni_peak
50 |
51 | with open (input_bin25_file) as input_bin25,open (ip_bin25_file) as ip_bin25:
52 | """Generate the list of bonferroni_filter_windows"""
53 | ip_bonferroni_filter_list = []
54 | ip_index = 0
55 | print ("Generate the list of bonferroni_filter_windows")
56 | while True:
57 | input_line = input_bin25.readline().rstrip("\n")
58 | ip_line = ip_bin25.readline().rstrip("\n")
59 | if input_line == '':
60 | break
61 | input_line_list = input_line.split("\t")
62 | ip_line_list = ip_line.split("\t")
63 | input_pvalue,ip_pvalue = windows_fisher_test(input_line_list[-1],ip_line_list[-1],input_total_reads_count,ip_total_reads_count)
64 | if (ip_pvalue < 0.05/peak_windows_number ):
65 | del ip_line_list[-1]
66 | ip_line_list.append(ip_pvalue)
67 | ip_line_list[1] = int(ip_line_list[1])
68 | ip_line_list[2] = int(ip_line_list[2])
69 | ip_bonferroni_filter_list.append([])
70 | ip_bonferroni_filter_list[ip_index] = ip_line_list
71 | ip_index += 1
72 | """Generate the list of bonferroni_filter_peaks"""
73 | print ("Generate the list of bonferroni_filter_peaks")
74 | ip_bonferroni_peak = cluster_bin(ip_bonferroni_filter_list[:])
75 | """Write the list of bonferroni_filter_peaks"""
76 | print ("Write the list of bonferroni_filter_peaks")
77 | with open(output_ip_file,'w') as output_file:
78 | for data in ip_bonferroni_peak:
79 | output_file.write('\t'.join(str(i) for i in data))
80 | output_file.write('\n')
--------------------------------------------------------------------------------
/bin/merge_peaks_by_bedtools.sh:
--------------------------------------------------------------------------------
1 | #!/bin/bash
2 | #$1 argv 1 : designfile
3 | #$2 argv 2 : THREAD_NUM
4 | #$3 argv 3 : flag_peakCallingbygroup
5 | #$4 argv 4 : peakCalling_tools_count
6 | designfile=$1
7 | THREAD_NUM=$2
8 | flag_peakCallingbygroup=$3
9 | peakCalling_tools_count=$4
10 | peakCalling_tools_main=$5
11 |
12 | # Define a multi-threaded run channel
13 | mkfifo tmp
14 | exec 9<>tmp
15 | for ((i=1;i<=${THREAD_NUM:=1};i++))
16 | do
17 | echo >&9
18 | done
19 |
20 | function mergebedByBedtools()
21 | {
22 | prefix_id=$1
23 | out_prefix=$2
24 | peakCalling_tools_main=$3
25 | cat ${peakCalling_tools_main}*${prefix_id}*normalized.bed | sortBed -i - | mergeBed -i - -c 4,5 -o count,mean > tmp.${prefix_id}_allPeaks.bed
26 | ls *${prefix_id}*normalized.bed | grep -v ${peakCalling_tools_main} | xargs -i cat {} | sortBed -i - | mergeBed -i - -c 4,5 -o count,mean > tmp.${prefix_id}_others_allPeaks.bed
27 | intersectBed -a tmp.${prefix_id}_allPeaks.bed -b tmp.${prefix_id}_others_allPeaks.bed -u | awk 'BEGIN{FS="\t";OFS="\t"}{print $1,$2,$3,$1":"$2"-"$3,$5}' > ${out_prefix}.bed
28 | }
29 |
30 | if [ $flag_peakCallingbygroup -gt 0 ]; then
31 | group_list=$(awk 'BEGIN{FS=","}NR>1{print $4}' $designfile |sort|uniq|awk 'BEGIN{ORS=" "}{print $0}')
32 | for group_id in $group_list
33 | do
34 | read -u 9
35 | {
36 | if [ $peakCalling_tools_count -gt 1 ]; then
37 | mergebedByBedtools ${group_id} bedtools_merged_group_${group_id} ${peakCalling_tools_main}
38 | else
39 | awk '{OFS="\t";$5=10^-$5;print }' *${group_id}*.bed | sortBed -i - > bedtools_merged_group_${group_id}.bed
40 | fi
41 | echo >&9
42 | }&
43 | done
44 | wait
45 | if [ $peakCalling_tools_count -gt 1 ]; then
46 | mergebedByBedtools "" bedtools_merged_allpeaks ${peakCalling_tools_main}
47 | else
48 | cat ${peakCalling_tools_main}_*_normalized.bed | sortBed -i - | mergeBed -i - -c 4,5 -o count,mean | awk 'BEGIN{FS="\t";OFS="\t"}{print $1,$2,$3,$1":"$2"-"$3,$5}' > bedtools_merged_allpeaks.bed
49 | fi
50 | else
51 | sampleinfo_list=$(awk 'BEGIN{FS=","}NR>1{print $1","$4}' $designfile |sort|uniq|awk 'BEGIN{ORS=" "}{print $0}')
52 | for sample_group_id in ${sampleinfo_list}
53 | do
54 | read -u 9
55 | {
56 | sample_id=$(echo ${sample_group_id} | awk 'BEGIN{FS=","}{print $1}')
57 | group_id=$(echo ${sample_group_id} | awk 'BEGIN{FS=","}{print $2}')
58 | ## Adding the information of group
59 | for samplefile in *_${sample_id}_normalized.bed
60 | do
61 | mv $samplefile ${samplefile/_normalized.bed/_${group_id}_normalized.bed}
62 | done
63 | echo >&9
64 | }&
65 | done
66 | wait
67 | group_list=$(awk 'BEGIN{FS=","}NR>1{print $4}' $designfile |sort|uniq|awk 'BEGIN{ORS=" "}{print $0}')
68 | for group_id in $group_list
69 | do
70 | read -u 9
71 | {
72 | if [ $peakCalling_tools_count -gt 1 ]; then
73 | mergebedByBedtools ${group_id} bedtools_merged_group_${group_id} ${peakCalling_tools_main}
74 | else
75 | awk '{OFS="\t";$5=10^-$5;print }' *${group_id}*.bed | sortBed -i - > bedtools_merged_group_${group_id}.bed
76 | fi
77 | echo >&9
78 | }&
79 | done
80 | wait
81 | if [ $peakCalling_tools_count -gt 1 ]; then
82 | mergebedByBedtools "" bedtools_merged_allpeaks ${peakCalling_tools_main}
83 | else
84 | cat ${peakCalling_tools_main}_*_normalized.bed | sortBed -i - | mergeBed -i - -c 4,5 -o count,mean | awk 'BEGIN{FS="\t";OFS="\t"}{print $1,$2,$3,$1":"$2"-"$3,$5}' > bedtools_merged_allpeaks.bed
85 | fi
86 | fi
87 | echo "${peakCalling_tools_main} merged peaks done"
--------------------------------------------------------------------------------
/bin/arranged_results.R:
--------------------------------------------------------------------------------
1 | #!/bin/Rscript
2 | ## Rscript arranged_result.R