├── Sort.sh
├── check_rpack.r
├── check_pypack.py
├── test.opt.tbl
├── heliano_bcheck.R
├── Flanking_seq.R
├── configure.sh
├── SplitJoint.R
├── tclcv.txt
├── heliano_cons.py
├── heliano_fisher.R
├── readme.md
├── LICENSE.txt
└── heliano.py
/Sort.sh:
--------------------------------------------------------------------------------
1 | inputfile=${1}
2 | CPU_num=${2}
3 |
4 | sort -k1,1 -k2,2n --parallel=${CPU_num} ${inputfile} > ${inputfile}.tmp
5 |
6 | mv ${inputfile}.tmp ${inputfile}
7 |
--------------------------------------------------------------------------------
/check_rpack.r:
--------------------------------------------------------------------------------
1 |
2 | tryCatch({library('seqinr')}, error=function(e){print("R package seqinr not installed!")})
3 | tryCatch({library('bedtoolsr')}, error=function(e){print("R package bedtoolsr not installed!")})
4 |
--------------------------------------------------------------------------------
/check_pypack.py:
--------------------------------------------------------------------------------
1 |
2 | try:
3 | from Bio import SeqIO
4 | except:
5 | print("python package biopython was not installed!\n")
6 | try:
7 | import pybedtools as BT
8 | except:
9 | print("python package pybedtools was not installed!")
10 |
11 |
--------------------------------------------------------------------------------
/test.opt.tbl:
--------------------------------------------------------------------------------
1 | CP128282.1 53617 59046 HLE2_left_18-HLE2_right_18 7 - 6.3390e-07 60 HLE2 auto insertion_HLE2_auto_1
2 | CP128282.1 83425 88824 HLE2_left_18-HLE2_right_18 7 - 6.3390e-07 60 HLE2 auto insertion_HLE2_auto_2
3 | CP128282.1 94525 99924 HLE2_left_18-HLE2_right_18 7 + 6.3390e-07 60 HLE2 auto insertion_HLE2_auto_3
4 | CP128282.1 306838 312276 HLE2_left_18-HLE2_right_18 7 + 6.3390e-07 60 HLE2 auto insertion_HLE2_auto_4
5 | CP128282.1 665681 668554 HLE2_left_33-HLE2_right_32 3 - 1.3547e-05 60 HLE2 nonauto insertion_HLE2_nonauto_1
6 | CP128282.1 668719 671599 HLE2_left_33-HLE2_right_32 3 + 1.3547e-05 60 HLE2 nonauto insertion_HLE2_nonauto_2
7 | CP128282.1 855863 858738 HLE2_left_33-HLE2_right_32 3 + 1.3547e-05 60 HLE2 nonauto insertion_HLE2_nonauto_3
8 | CP128282.1 855863 880806 HLE2_left_33-HLE2_right_32 3 + 1.3547e-05 60 HLE2 auto insertion_HLE2_auto_5
9 | CP128282.1 926221 928267 CP128282.1-926221-928267 1 - 1 0 HLE2 orfonly insertion_HLE2_orfonly_1
10 | CP128282.1 963556 968985 HLE2_left_18-HLE2_right_18 7 + 6.3390e-07 60 HLE2 auto insertion_HLE2_auto_6
11 | CP128282.1 1107206 1112635 HLE2_left_18-HLE2_right_18 7 + 6.3390e-07 60 HLE2 auto insertion_HLE2_auto_7
12 | CP128282.1 1259412 1264991 HLE2_left_18-HLE2_right_18 7 - 6.3390e-07 60 HLE2 auto insertion_HLE2_auto_8
13 |
--------------------------------------------------------------------------------
/heliano_bcheck.R:
--------------------------------------------------------------------------------
1 | library(seqinr)
2 |
3 | args=commandArgs(T)
4 |
5 | wkdir = args[1]
6 | OPTFILE = args[2]
7 |
8 | setwd(wkdir)
9 |
10 | file_list = list.files('./')
11 |
12 | aln_list = file_list[sapply(file_list, function(x){endsWith(x, '.fa.aln')})]
13 |
14 | calculate_distance = function(x){
15 | aln = read.alignment(x, format = 'fasta')
16 | distance = as.vector(dist.alignment(aln))
17 | ## means only one sequence
18 | if(length(distance)==0){
19 | distance = 1
20 | }
21 | ## na means the two sequences have very low identity.
22 | distance[is.na(distance)] = 1
23 | identity =1 - distance**2
24 | string_vector = strsplit(x, split = '\\.')[[1]]
25 | name = string_vector[1]
26 | direction = string_vector[2]
27 | return(c(name, direction, mean(identity)))
28 | }
29 |
30 |
31 | if(length(aln_list)>=2){
32 | identity_df = as.data.frame(do.call('rbind', lapply(aln_list, function(x){calculate_distance(x)})), stringsAsFactors = F)
33 | colnames(identity_df)=c('pairname', 'direction', 'identity')
34 | # identity_df = tidyr::spread(identity_df, key = direction, value = identity)
35 | # identity_df[which(is.na(identity_df$left)), 'left'] = 0
36 | # identity_df[which(is.na(identity_df$right)), 'right'] = 0
37 |
38 | write.table(identity_df, file = OPTFILE, sep = '\t', quote = F, col.names = T, row.names = F)
39 | }
40 |
41 |
--------------------------------------------------------------------------------
/Flanking_seq.R:
--------------------------------------------------------------------------------
1 | library(bedtoolsr)
2 | library(parallel)
3 |
4 | ###set argument#####
5 | args=commandArgs(T)
6 | bedtools_path = args[1]
7 | bed_fisher_dir=args[2]
8 | boundary_dir = args[3]
9 | Genome_path=args[4]
10 | Genome_size = args[5]
11 | MAX_CPU_num = detectCores() -1
12 | CPU_num=as.numeric(args[6])
13 | CPU_num = ifelse(CPU_num < MAX_CPU_num, CPU_num, MAX_CPU_num)
14 | CPU_num = ifelse(CPU_num<1, 1, CPU_num)
15 | options(bedtools.path = bedtools_path)
16 |
17 | ##################### To output sequences ####################
18 | Genome_size_df=read.csv2(Genome_size, stringsAsFactors = F, header = F, sep = '\t')
19 | colnames(Genome_size_df)=c('chr', 'length')
20 | fisher_file_list = list.files(bed_fisher_dir, full.names = T, pattern = '.bed')
21 |
22 | cl = makeCluster(CPU_num)
23 | clusterExport(cl, c('bedtools_path', 'Genome_path', 'Genome_size_df'), envir = .GlobalEnv)
24 | clusterEvalQ(cl, list(library(bedtoolsr), options(bedtools.path = bedtools_path)))
25 |
26 | parSapply(cl, fisher_file_list, function(x){
27 | pairname=gsub('\\.bed', '', basename(x))
28 | candidate_bed=bt.sort(x)
29 | merged_candidate = bt.merge(d=100, c = '4,5,6', o='first,mean,first')
30 | merged_candidate = merged_candidate[order(merged_candidate$V5, decreacing=T), ]
31 | row_count = nrow(merged_candidate)
32 | if(row_count>=2){
33 | row_count = ifelse(row_count>20, 20, row_count)
34 | merged_candidate = merged_candidate[1:row_count, c(1:6)]
35 | colnames(merged_candidate)=c('chr', 'start', 'stop', 'family', 'copy', 'strand')
36 | ### To output 100 bp terminal flanking
37 | terminal_flank = merged_candidate
38 | terminal_flank$start=terminal_flank$start-101
39 | terminal_flank$stop=terminal_flank$stop+99
40 | terminal_flank = merge(terminal_flank, Genome_size_df)
41 | terminal_flank$start = ifelse(terminal_flank$start<0, 0, terminal_flank$start)
42 | terminal_flank$stop = ifelse(terminal_flank$stop>terminal_flank$length, terminal_flank$length, terminal_flank$stop)
43 | terminal_flank = terminal_flank[which(terminal_flank$stop - terminal_flank$start >200), ]
44 | }
45 |
46 | })
47 |
48 | stopCluster (cl)
--------------------------------------------------------------------------------
/configure.sh:
--------------------------------------------------------------------------------
1 | ## check dependencies
2 |
3 | dependency_stat=1
4 |
5 | gt=`which gt`
6 | if [[ ${gt} == '' ]];then echo "Dependency genometools was not installed!";dependency_stat=0;fi
7 |
8 | hmmsearch=`which hmmsearch`
9 | if [[ ${hmmsearch} == '' ]];then echo "Dependency hmmsearch was not installed!";dependency_stat=0;fi
10 |
11 | cdhit=`which cd-hit-est`
12 | if [[ ${cdhit} == '' ]];then echo "Dependency cd-hit-est was not installed!";dependency_stat=0;fi
13 |
14 | mafft=`which mafft`
15 | if [[ ${mafft} == '' ]];then echo "Dependency mafft was not installed!";dependency_stat=0;fi
16 |
17 | blast=`which blastn`
18 | if [[ ${blast} == '' ]];then echo "Dependency blastn was not installed!";dependency_stat=0;fi
19 |
20 | bedtools=`which bedtools`
21 | if [[ ${bedtools} == '' ]];then echo "Dependency bedtools was not installed!";dependency_stat=0;fi
22 |
23 | dialign2=`which dialign2-2`
24 | if [[ ${dialign2} == '' ]];then echo "Dependency dialign2 was not installed!";dependency_stat=0;fi
25 |
26 | rnabob=`which rnabob`
27 | if [[ ${rnabob} == '' ]];then echo "Dependency rnabob was not installed!";dependency_stat=0;fi
28 |
29 | getorf=`which getorf`
30 | if [[ ${getorf} == '' ]];then echo "Dependency getorf was not installed!";dependency_stat=0;fi
31 |
32 | ## check R packages
33 | R_path=`which R`
34 | if [[ ${R_path} == '' ]];
35 | then
36 | echo "R was not installed!"
37 | dependency_stat=0
38 | else
39 | rpack_stat=`Rscript check_rpack.r|grep "installed"`
40 | echo -e ${rpack_stat}
41 | if [[ ${rpack_stat} != '' ]];then dependency_stat=0;fi
42 | fi
43 |
44 | ## check python packages
45 | myPYTHON_PATH=`which python3`
46 | if [[ ${myPYTHON_PATH} == '' ]];
47 | then
48 | echo "python3 was not installed!"
49 | dependency_stat=0
50 | else
51 | pypack_stat=`python3 check_pypack.py|grep "installed"`
52 | echo -e ${pypack_stat}
53 | if [[ ${pypack_stat} != '' ]];then dependency_stat=0;fi
54 | fi
55 |
56 | ## To summary dependecny status
57 | if [[ ${dependency_stat} == 0 ]];
58 | then
59 | echo "Please make sure that these dependencies installed!"
60 | exit 0
61 | fi
62 |
63 | ## set pathes for heliano
64 | SCRIT_DIR_PATH=`pwd`
65 |
66 | BCHECK=${SCRIT_DIR_PATH}/heliano_bcheck.R
67 | FISHER=${SCRIT_DIR_PATH}/heliano_fisher.R
68 | HMMmodel=${SCRIT_DIR_PATH}/RepHel.hmm
69 | Headermodel=${SCRIT_DIR_PATH}/tclcv.txt
70 | SPLIT=${SCRIT_DIR_PATH}/SplitJoint.R
71 | SORT=${SCRIT_DIR_PATH}/Sort.sh
72 |
73 | cp heliano.py heliano
74 |
75 | sed -i "s|_INTERPRETERPYTHON_PATH_|${myPYTHON_PATH}|" heliano
76 |
77 | sed -i "s|_HMM_|${HMMmodel}|" heliano
78 |
79 | sed -i "s|_HEADER_|${Headermodel}|" heliano
80 |
81 | sed -i "s|_FISHER_|${FISHER}|" heliano
82 |
83 | sed -i "s|_BOUNDARY_|${BCHECK}|" heliano
84 |
85 | sed -i "s|_SPLIT_JOINT_|${SPLIT}|" heliano
86 |
87 | sed -i "s|_SORTPRO_|${SORT}|" heliano
88 |
89 | chmod 755 heliano
90 |
91 | ## set pathes for heliano_cons
92 |
93 | cp heliano_cons.py heliano_cons
94 | sed -i "s|_INTERPRETERPYTHON_PATH_|${myPYTHON_PATH}|" heliano_cons
95 | chmod 755 heliano_cons
96 |
97 | if [ ! -d "bin" ];then mkdir bin;fi
98 | mv heliano heliano_cons bin/
99 |
100 | echo "Succeed! Please find programs in bin/ directory."
101 |
102 |
103 |
104 |
--------------------------------------------------------------------------------
/SplitJoint.R:
--------------------------------------------------------------------------------
1 | ## This script was used to split big bed file into small bed files.
2 | library(bedtoolsr)
3 | library(parallel)
4 |
5 | ###set argument
6 | options(scipen = 200)
7 |
8 | args=commandArgs(T)
9 | left_beddir=args[1]
10 | right_beddir=args[2]
11 | combinid_file=args[3]
12 | subed_dir=args[4]
13 | Genome_size_file = args[5]
14 | HALF_DIST = as.numeric(args[6])
15 | bedtools_path = args[7]
16 | # Set bedtools option
17 | options(bedtools.path = bedtools_path)
18 |
19 | ## multiple processing
20 | MAX_CPU_num = detectCores() -1
21 | CPU_num=as.numeric(args[8])
22 | CPU_num = ifelse(CPU_num < MAX_CPU_num, CPU_num, MAX_CPU_num)
23 | CPU_num = ifelse(CPU_num<1, 1, CPU_num)
24 |
25 |
26 | if(F){
27 | setwd('~/remote2/Helitron/Supplementary_material/TEverify/XL_is1020_sim90_s30_dn6k_heliano16_up0620/HLE1/')
28 | left_beddir='SubBlastnBed/HLE1_left/'
29 | right_beddir='SubBlastnBed/HLE1_right/'
30 | combinid_file='HLE1.combinid.txt'
31 | subed_dir='HLE1_Windowing'
32 | Genome_size_file = '../../Genome.size'
33 | HALF_DIST = 15000
34 | bedtools_path = '/home/zhenli/bioinfo/bedtools2/bin/'
35 | options(bedtools.path = bedtools_path)
36 |
37 | CPU_num=10
38 | }
39 |
40 | ## To make directory
41 | if(dir.exists(subed_dir)){
42 | unlink(subed_dir,recursive = TRUE)
43 | }
44 |
45 | left_flank_dir=paste(subed_dir, 'leftflank', sep = '/')
46 | dir.create(left_flank_dir, recursive = TRUE)
47 | right_flank_dir=paste(subed_dir, 'rightflank', sep = '/')
48 | dir.create(right_flank_dir, recursive = TRUE)
49 |
50 | ## read genome size
51 | genome_size_df = read.csv2(Genome_size_file, sep = '\t', header = F, stringsAsFactors = F)
52 | colnames(genome_size_df)=c('chrmid', 'length')
53 |
54 | #### Output left bed file ####
55 | left_bedfile_list = list.files(left_beddir, full.names = T)
56 |
57 | cl = makeCluster(CPU_num)
58 | clusterExport(cl, c('left_flank_dir', 'genome_size_df', 'bedtools_path', 'HALF_DIST'), envir = .GlobalEnv)
59 | clusterEvalQ(cl, list(library(bedtoolsr), options(bedtools.path = bedtools_path, scipen = 200)))
60 |
61 | parSapply(cl, left_bedfile_list, function(x){
62 | sub_leftbed = bt.sort(x)
63 | sub_leftbed = bt.merge(sub_leftbed, s=TRUE, d = 100, c="4,5,6", o="first,max,first")
64 |
65 | # To backup the real start point
66 | sub_leftbed$bk=ifelse(sub_leftbed$V6=='+', sub_leftbed$V2, sub_leftbed$V3)
67 |
68 | ## To extend bed files, but remove the terminal region.
69 | sub_leftbed$stop=ifelse(sub_leftbed$V6=='+', sub_leftbed$V3+HALF_DIST, sub_leftbed$V2)
70 | sub_leftbed$start=ifelse(sub_leftbed$V6=='+', sub_leftbed$V3, sub_leftbed$V2-HALF_DIST)
71 | sub_leftbed$start=ifelse(sub_leftbed$start<=0, 1, sub_leftbed$start)
72 | sub_leftbed=sub_leftbed[, c('V1', 'start', 'stop', 'V4', 'V5', 'V6', 'bk')]
73 |
74 | colnames(sub_leftbed)=c('chrmid', 'start', 'stop', 'name', 'score', 'strand', 'bk')
75 | sub_leftbed = merge(sub_leftbed, genome_size_df)
76 | sub_leftbed$stop = ifelse(sub_leftbed$stop <= sub_leftbed$length, sub_leftbed$stop, sub_leftbed$length)
77 | sub_leftbed = sub_leftbed[, c('chrmid', 'start', 'stop', 'name', 'score', 'strand', 'bk')]
78 | ## To output
79 | bnm=basename(x)
80 | sub_leftfile = paste(left_flank_dir, '/', bnm, sep = '')
81 | bt.sort(sub_leftbed, output = sub_leftfile)
82 | })
83 | stopCluster (cl)
84 |
85 | #### Output right bed file####
86 | right_bedfile_list = list.files(right_beddir, full.names = T)
87 | ## multiple processing
88 | cl = makeCluster(CPU_num)
89 | clusterExport(cl, c('right_flank_dir', 'genome_size_df', 'bedtools_path', 'HALF_DIST'), envir = .GlobalEnv)
90 | clusterEvalQ(cl, list(library(bedtoolsr), options(bedtools.path = bedtools_path, scipen = 200)))
91 |
92 | parSapply(cl, right_bedfile_list, function(x){
93 | sub_rightbed = bt.sort(x)
94 | sub_rightbed = bt.merge(sub_rightbed, s=TRUE, d = 100, c="4,5,6", o="first,max,first")
95 |
96 | # To backup the real start point
97 | sub_rightbed$bk=ifelse(sub_rightbed$V6=='+', sub_rightbed$V3, sub_rightbed$V2)
98 |
99 | ## To extend bed files, but remove the original terminal regions
100 | sub_rightbed$stop=ifelse(sub_rightbed$V6=='+', sub_rightbed$V2, sub_rightbed$V3+HALF_DIST)
101 | sub_rightbed$start=ifelse(sub_rightbed$V6=='+', sub_rightbed$V2-HALF_DIST, sub_rightbed$V3)
102 | sub_rightbed$start=ifelse(sub_rightbed$start<=0, 1, sub_rightbed$start)
103 | sub_rightbed=sub_rightbed[, c('V1', 'start', 'stop', 'V4', 'V5', 'V6', 'bk')]
104 |
105 | colnames(sub_rightbed)=c('chrmid', 'start', 'stop', 'name', 'score', 'strand', 'bk')
106 | sub_rightbed = merge(sub_rightbed, genome_size_df, by='chrmid')
107 | sub_rightbed$stop = ifelse(sub_rightbed$stop <= sub_rightbed$length, sub_rightbed$stop, sub_rightbed$length)
108 |
109 | ## To output
110 | sub_rightbed = sub_rightbed[, c('chrmid', 'start', 'stop', 'name', 'score', 'strand', 'bk')]
111 | bnm=basename(x)
112 | sub_rightfile = paste(right_flank_dir, '/', bnm, sep = '')
113 | bt.sort(sub_rightbed, output = sub_rightfile)
114 | })
115 |
116 | stopCluster (cl)
117 | ### To create file path file ####
118 |
119 | ## read combined id file
120 | leftname_list = sapply(left_bedfile_list, function(x){strsplit(basename(x), split = '\\.')[[1]][1]})
121 | rightname_list = sapply(right_bedfile_list, function(x){strsplit(basename(x), split = '\\.')[[1]][1]})
122 | combine_id=read.csv2(combinid_file, stringsAsFactors = F, header = F, sep = '\t')
123 | colnames(combine_id)=c('leftname', 'rightname')
124 | combine_id=combine_id[which(combine_id$leftname %in% leftname_list & combine_id$rightname %in% rightname_list), ]
125 |
126 | combine_id$leftname=paste(subed_dir, '/leftflank/', combine_id$leftname, '.bed',sep = '')
127 | combine_id$rightname=paste(subed_dir, '/rightflank/', combine_id$rightname, '.bed', sep = '')
128 | head(combine_id)
129 | write.table(combine_id, file = paste(subed_dir, '/', 'left_right.path.join', sep = ''),
130 | quote = F, sep="\t", col.names = F, row.names = F)
--------------------------------------------------------------------------------
/tclcv.txt:
--------------------------------------------------------------------------------
1 | TCTCTACTA
2 | TCT.TACTA.T
3 | TCT.TACTAC
4 | TC.{2}TACTACT
5 | TCT.TAC.ACT
6 | TCT.TA.TACT
7 | TCT.TACT.CT
8 | TCT.T.CTACT
9 | TC.{1}CTACTA.T
10 | TC.{9}TATTAAG
11 | TC.{1}CTACTAC
12 | TCTCTA.TA.T
13 | TCTCTAC.AC
14 | TCTC.ACTA.T
15 | TCTCTA.TAC
16 | TCTC.AC.ACT
17 | TCT.TA.TATA
18 | TC.{5}TA.CTAT.A
19 | TC.{5}TA.C.ATTA
20 | TC.{8}CTAT.AAG
21 | TCT.TACTAA
22 | TC.{5}TATA.T.AA
23 | TCTCTA.TAA
24 | TCT.TA.TA.CT
25 | TC.{2}TA.TA.C.AT
26 | TC.{0,4}TA.TATAT
27 | TC.{6}TAT.TAT.A
28 | TC.{0,4}TATTAT.T
29 | TC.{0,4}TATTATA
30 | TC.{0,5}TATA.TAA
31 | TC.{0,3}TAT.TA.TA
32 | TCTAT.ATAT
33 | TC.{0,1}T.TTATAT
34 | TC.{5,8}T.TA.TAA.A
35 | TC.{0,5}TATA.TA.A
36 | TC.{0,2}T.TATTAT
37 | TC.{4,5}TA.T.TAT.A
38 | TCTAT.T.TA.A
39 | TC.{6}TAT.TATA
40 | TC.{3,5}CTAT.TAT
41 | TC.{0,2}T.TATCT.T
42 | TC.{2,7}TA.TAAAA
43 | TCTA.AT.TA.A
44 | TC.{5,9}TA.TAT.AA
45 | TC.{4,7}AT.TA.TAA
46 | TCTATATAT
47 | TCTATCTAT
48 | TCT.TATA.A.A
49 | TC.{7,8}ACTAAAA
50 | TC.{0,2}T.T.TCTAT
51 | TC.{2,3}TATATAC
52 | TC.{0,5}TATAC.AA
53 | TC.{1,6}ATA.TAAA
54 | TC.{3,5}TAC.A.T.AA
55 | TC.{3,4}A.AA.TAA.A
56 | TC.{4,9}AC.A.T.AAA
57 | TC.{5}C.A.T.AAAA
58 | TC.{0,3}TA.A.CTAA
59 | TC.{2,3}TA.A.CTA.A
60 | TC.{3,5}TA.AA.T.AA
61 | TC.{5,6}TA.TATA.A
62 | TC.{4,9}TATA.A.TT
63 | TC.{5}C.A.TAA.AA
64 | TC.{5,6}AA.TAAAA
65 | TC.{3,4}A.AA.TA.AA
66 | TC.{4,7}AC.A.TAAA
67 | TC.{6}T.TTATA.A
68 | TC.{12,17}AAA.A.TAA
69 | TC.{12,17}A.A.A.TAAA
70 | TC.{2,6}TA.TA.TA.A
71 | TC.{6}AT.AAA.TT
72 | TC.{2,7}CTA.AA.T.A
73 | TC.{1,5}TA.A.AT.AA
74 | TC.{1,5}T.T.TATA.A
75 | TCTCTAT.T.T
76 | TC.{7,9}TAT.TAT.A
77 | TC.{15,18}TATT.TA.A
78 | TC.{9,12}TATA.A.A.A
79 | TC.{22,26}AA.A.ATAA
80 | TC.{12,13}A.T.AAAA.A
81 | TC.{2,4}TA.TATTA
82 | TC.{7,12}T.T.TAT.AA
83 | TC.{9,11}TAT.T.AAA
84 | TC.{2,5}TA.T.AAA.A
85 | TC.{4,6}TA.ATT.TT
86 | TC.{5}TA.A.TT.AA
87 | TC.{2}TA.TA.TT.A
88 | TC.{36}TAATTTT
89 | TC.{10}AAA.C.CA.T
90 | TC.{8,13}T.TTATTA
91 | TC.{4,9}TT.T.CCTA
92 | TC.{24,28}ATTTTAA
93 | TC.{35}AT.TAT.T.T
94 | TC.{10,12}TTATA.TT
95 | TC.{21}ATTTTT.T
96 | TC.{19}AC.A.A.GAA
97 | TC.{35,37}TC.TT.GG.C
98 | TC.{1}CTAC.ACT
99 | TCTCTAC.A.T
100 | TC.{1}CTACT.CT
101 | TCTCT.CTA.T
102 | TC.{1}CTA.TACT
103 | TCTCT.C.ACT
104 | TCTCTACTA
105 | TC.{9}TATTAAG
106 | TCT.TACTAT
107 | TCT.TACTA.A
108 | TC.{5}TA.C.A.TAA
109 | TC.{8}CTATTAA
110 | TC.{2}TA.TATA.T
111 | TCT.TACTA.C
112 | TC.{3}A.TA.C.ATT
113 | TCTCTA.TAT
114 | TCTA.TATA.A
115 | TC.{0,2}TA.TAT.TA
116 | TCT.TTATA.A
117 | TC.{0,4}TATT.TAT
118 | TC.{1,4}AT.TA.TA.A
119 | TCTAT.ATA.A
120 | TC.{6}T.T.TATA.A
121 | TC.{0,4}TATTA.AT
122 | TC.{1,5}ATTATAT
123 | TCTATA.TA.T
124 | TC.{6}TAT.TA.A.A
125 | TC.{0,2}T.TA.TAT.T
126 | TC.{8}TCTATTA
127 | TC.{2,3}TTATATA
128 | TC.{8,10}TATTAA.A
129 | TC.{0,5}T.TA.TAAA
130 | TC.{5,6}T.T.TAT.AA
131 | TC.{2,5}T.AT.TA.TA
132 | TCTAT.AT.TA
133 | TCTAT.T.T.TA
134 | TC.{1}AT.TATTA
135 | TCTA.A.ATA.A
136 | TCTAT.TAT.T
137 | TC.{5}C.ACT.A.AA
138 | TC.{4}A.A.CTAAA
139 | TC.{3,4}A.AA.T.AAA
140 | TC.{7}A.T.AAAA.A
141 | TC.{2,3}TA.A.CT.AA
142 | TC.{8}CTA.AAAG
143 | TC.{7}A.TA.AAA.A
144 | TC.{3,5}TAC.A.TA.A
145 | TC.{3,5}TAC.A.TAA
146 | TC.{6}T.CTATA.A
147 | TC.{6,7}ACTA.AAA
148 | TC.{5}C.A.TA.AAA
149 | TC.{5,6}TA.TAT.AA
150 | TC.{8}CT.AAAA.A
151 | TC.{0,3}TAC.ACTA
152 | TC.{4,9}AC.A.TA.AA
153 | TC.{9}TATAAAG
154 | TC.{5,6}AA.TAAA.A
155 | TC.{12}AAAA.TAA
156 | TC.{2,5}CTAC.A.TA
157 | TC.{7,11}A.TAAA.A.A
158 | TC.{5}TT.CTA.A.A
159 | TCT.TATCT.T
160 | TC.{0,1}TCT.TCT.T
161 | TC.{2,6}TA.TA.AAA
162 | TC.{6}TA.T.TAAA
163 | TC.{3,6}TA.TA.T.AA
164 | TC.{5}T.T.AAA.TT
165 | TC.{1}TAT.TAT.A
166 | TC.{4,5}C.ACTA.AA
167 | TC.{2,5}CTA.TA.T.A
168 | TC.{1,5}T.T.TAT.AA
169 | TC.{11,15}A.AA.A.TAA
170 | TC.{2,3}TAC.AC.A.A
171 | TC.{5}TT.CTATA
172 | TC.{5}TT.CT.TA.A
173 | TC.{9,11}AAAAA.TA
174 | TC.{6}T.TTAT.AA
175 | TC.{1}AT.A.AAAA
176 | TC.{1,6}TA.TATAT
177 | TC.{8,9}TATATA.T
178 | TC.{9}TATA.AG.T
179 | TC.{5,9}TA.TATA.A
180 | TCTATA.TA.A
181 | TCTA.AT.TA.A
182 | TC.{1,4}ATA.TA.AA
183 | TC.{4,8}TATA.A.TT
184 | TC.{23}AAA.ATAA
185 | TC.{0,4}T.T.TACTA
186 | TC.{9}TATAT.AA
187 | TC.{2,4}TA.TA.TA.A
188 | TC.{2,4}TA.TAT.A.A
189 | TCTATA.TAA
190 | TC.{5}CT.TTATA
191 | TC.{4}TATA.AT.T
192 | TC.{1}CTAT.T.TA
193 | TC.{2}T.T.TCTA.T
194 | TC.{13}T.TATTAT
195 | TC.{1}ATA.TAA.A
196 | TC.{0,1}T.T.TATA.A
197 | TCTCTATCT
198 | TC.{6}TATTAT.T
199 | TC.{1}ATA.TAAA
200 | TC.{9,14}TATA.AAA
201 | TC.{0,3}TAT.TAT.T
202 | TC.{0,3}TAT.ATA.A
203 | TC.{7}CTTA.AAA
204 | TC.{2,6}CTAT.TAT
205 | TC.{5,9}TATTATA
206 | TC.{2,5}TA.TAT.AA
207 | TC.{6,8}TA.TA.T.AA
208 | TCT.TA.CTCT
209 | TC.{11}T.TCTA.TA
210 | TC.{6}TA.ATTTT
211 | TC.{1}CTATCT.T
212 | TC.{10,14}T.AAAAAA
213 | TC.{9,12}TAT.TA.A.A
214 | TC.{18,23}AAAA.TAA
215 | TC.{1}T.TATA.A.A
216 | TC.{2,4}TAT.ATTA
217 | TC.{1,5}ATA.TATT
218 | TC.{9,11}TAT.TA.TA
219 | TC.{9,10}AC.A.T.AAA
220 | TC.{0,4}T.T.TATCT
221 | TC.{10,15}TAAAAAA
222 | TC.{2,4}TATTAT.A
223 | TC.{10,14}T.T.AAA.TT
224 | TC.{2}TA.TA.TTA
225 | TC.{10,12}ATAT.AAA
226 | TC.{5,8}TATA.T.AA
227 | TC.{3,5}A.TA.T.AAA
228 | TC.{9,10}A.TA.TTA.A
229 | TC.{11,13}T.TATTA.A
230 | TC.{0,2}TA.TA.T.TA
231 | TC.{39}T.AAAAA.T
232 | TC.{2,5}T.A.AAAAT
233 | TC.{25}T.TAAA.A.A
234 | TC.{7,12}T.TAT.T.AA
235 | TC.{6,10}TATAAA.A
236 | TC.{0,1}TATATAC
237 | TCT.TA.CT.TA
238 | TC.{18,23}A.AA.TAA.A
239 | TC.{7,8}ATAT.A.A.A
240 | TC.{22,26}AA.AA.TAA
241 | TC.{9,12}ATAAA.A.A
242 | TC.{5}TATA.TT.A
243 | TC.{0,4}CTA.AA.T.A
244 | TC.{0,5}TA.AA.T.AA
245 | TC.{4}CTA.A.TT.A
246 | TC.{0,5}TA.C.TATA
247 | TC.{14}A.AAT.TCA
248 | TC.{9}TT.TT.CTA
249 | TC.{14,19}A.A.CTAAA
250 | TC.{4}CT.TA.TT.A
251 | TC.{1,2}AC.A.T.AAA
252 | TCT.TATT.AT
253 | TC.{7}AT.TTA.A.T
254 | TC.{23,24}CTAATT.T
255 | TC.{1}CTAAT.TT
256 | TC.{16}TA.AA.TAA
257 | TC.{10,12}AT.TT.TTA
258 | TC.{31}CC.TA.T.TT
259 | TC.{25}A.TA.C.ATT
260 | TC.{5,8}TA.AATT.A
261 | TC.{12,14}AAAG.TAA
262 | TC.{0,5}T.TT.TAAA
263 | TC.{8}T.TAT.T.TC
264 | TC.{2}CA.C.AAA.A
265 | TC.{38}T.T.TCT.TC
266 | TCC.TAAT.T.A
267 | TC.{0,5}TA.ATTT.T
268 | TC.{0,3}A.TA.TTA.A
269 | TC.{5,8}T.TT.TTAT
270 | TCC.TA.TAA.T
271 | TC.{5,10}AT.TT.TT.T
272 | TC.{28,31}CCC.ACTA
273 | TC.{10,11}A.T.TTAT.A
274 | TC.{6,10}TAT.TAT.T
275 | TC.{4,9}TT.TTCCT
276 | TC.{7,10}T.AT.C.CCA
277 | TC.{20}ACA.CTAA
278 | TC.{32}TACTA.AA
279 | TC.{28}CTAC.A.AT
280 | TC.{5,7}T.ATT.AAA
281 | TC.{1,5}A.TAAAAA
282 | TC.{10}TAAA.A.A.C
283 | TC.{22,25}T.ATT.TAA
284 | TC.{0,5}TAATTA.A
285 | TC.{5}TAT.A.A.AA
286 | TC.{28}AC.TAAA.C
287 | TC.{10,15}TAT.T.T.TA
288 | TC.{16}AATT.T.TA
289 | TC.{1,5}ACTA.AA.G
290 | TC.{0,1}TCTT.T.T.C
291 | TC.{24}T.T.TATT.A
292 | TC.{29}TT.TTATA
293 | TC.{6,10}ATAAT.CA
294 | TC.{34}CTAT.TAT
295 | TCCATAATA
296 | TC.{8,10}AC.CTT.TA
297 | TC.{37}AG.G.G.CCA
298 | TC.{21}ATTTTT.T
299 | TC.{35,37}TC.TT.G.CC
300 | TC.{34,37}A.CG.GGC.A
301 | TC.{33,36}ATTT.T.TA
302 | TC.{3,4}AA.A.CGA.T
303 | TC.{32}C.A.TA.CGA
304 | TC.{25}TAAA.A.AA
305 |
--------------------------------------------------------------------------------
/heliano_cons.py:
--------------------------------------------------------------------------------
1 | #!_INTERPRETERPYTHON_PATH_
2 |
3 | import os, re, subprocess, sys, argparse, shutil, random
4 | from Bio import SeqIO
5 | from multiprocessing.pool import ThreadPool
6 | from collections import defaultdict
7 | import pybedtools as BT
8 |
9 | class Consensus_making:
10 | def __init__(self, genome, wkdir, represent_bed, process_num):
11 | self.genome = genome
12 | self.genome_dict = SeqIO.parse(genome, 'fasta')
13 | self.genome_dict = {k.id: k.seq.upper() for k in self.genome_dict}
14 | self.process_num=int(process_num)
15 | self.wkdir = wkdir
16 | self.repsenbed = represent_bed
17 | if not os.path.exists(self.wkdir):
18 | os.mkdir(self.wkdir)
19 | os.chdir(self.wkdir)
20 | else:
21 | os.chdir(self.wkdir)
22 |
23 | self.genome_size = 'Genome.size'
24 | genome_size = [[i, len(self.genome_dict[i])] for i in self.genome_dict]
25 | genome_size = sorted(genome_size, key=lambda x: x[0])
26 | with open(self.genome_size, 'w') as F:
27 | F.writelines([''.join([i[0], '\t', str(i[1]), '\n']) for i in genome_size])
28 |
29 | def cdhitest_clust(self, input_fa):
30 | cons_name = '.'.join([input_fa, 'reduce.temp'])
31 | cluster_file = '.'.join([cons_name, 'clstr'])
32 | run_cluster = subprocess.Popen(
33 | ['cd-hit-est', '-i', input_fa, '-o', cons_name, '-d', '0', '-aS', '0.8', '-aL', '0.8', '-c', '0.8', '-G', '1', '-g',
34 | '1', '-b', '500', '-T', str(self.process_num), '-M', '0'], stdout=subprocess.DEVNULL)
35 | run_cluster.wait()
36 |
37 | cluster_dict = {}
38 | with open(cluster_file, 'r') as F:
39 | for line in F:
40 | if line.startswith('>'):
41 | cluster_name = line.strip('>\n').replace(' ', '_')
42 | else:
43 | insertion_name = line.split('...')[0].split(', >')[1]
44 | cluster_dict[insertion_name] = cluster_name
45 |
46 | if os.path.exists(cons_name):
47 | os.remove(cons_name)
48 | os.remove(cluster_file)
49 | reversed_cluster_dict = defaultdict(list)
50 | [reversed_cluster_dict[cluster_dict[key]].append(key) for key in cluster_dict]
51 | return reversed_cluster_dict
52 |
53 | def consencus(self, mfa):
54 | basename = os.path.basename(mfa).split('.')[0]
55 | ## need to cluster before making consensus
56 | cluster_dict = self.cdhitest_clust(mfa) #{pairname:[insertion1, insertion2, ...]}
57 | mfa_dict = SeqIO.parse(mfa, 'fasta')
58 | mfa_dict = {k.id: k.seq.upper() for k in mfa_dict}
59 |
60 | for pairname in cluster_dict:
61 | insertion_name_list = cluster_dict[pairname]
62 | if len(insertion_name_list) < 2:
63 | conseq = str(mfa_dict[insertion_name_list[0]])
64 | self.consensus_dict[basename].append(conseq)
65 | continue
66 |
67 | submfa = ''.join(['Consensus/', basename, '.mfa'])
68 | subaln = ''.join([submfa, '.fa'])
69 | with open(submfa, 'w') as F:
70 | ## only first five insertions used for consensus making
71 | for insertion in insertion_name_list[:5]:
72 | F.write(''.join(['>', insertion, '\n', str(mfa_dict[insertion]), '\n']))
73 |
74 | mul_aln_run = subprocess.Popen(['dialign2-2', '-n', '-fa', '-mask', submfa],
75 | stdout=subprocess.DEVNULL)
76 | mul_aln_run.wait()
77 |
78 | ## To remove non utf-8 codes
79 | with open(subaln, 'rb') as F:
80 | text = F.read().decode('utf-8', 'ignore')
81 | with open(subaln, 'w') as F:
82 | F.write(text)
83 |
84 | consensus_file = ''.join([submfa, '.con.fa'])
85 | consencus_task = subprocess.Popen(["cons", "-sequence", subaln, '-outseq', consensus_file],
86 | stdout = subprocess.DEVNULL)
87 | consencus_task.wait()
88 |
89 | consencus_seq = {}
90 | with open(consensus_file, 'r') as F:
91 | for line in F:
92 | if line.startswith('>'):
93 | key = line.strip('>\n')
94 | consencus_seq[key] = ''
95 | else:
96 | consencus_seq[key] += line.rstrip()
97 | #os.remove(consensus_file)
98 | #os.remove(subaln)
99 | conseq = list(consencus_seq.values())[0]
100 | conseq = re.findall('[ATCG]{5,}.*[ATCG]{5,}', conseq)[0].replace('n', '').replace('N', '').replace('*', '').replace('x', '') ## delete gap region
101 | self.consensus_dict[basename].append(conseq)
102 |
103 | def extract_seq(self, pairlist):
104 | subwkdir = 'Consensus'
105 | pairname = pairlist[0][3]
106 | pairfa = ''.join([subwkdir, '/', pairname, '.fa'])
107 | ## To extend both ends for 50 bp.
108 | distance = 50
109 | with open(pairfa, 'w') as PF:
110 | for line in pairlist:
111 | chrmid, start, stop, name, score, strand = line[:6]
112 | seq_start = int(start) - distance if int(start) - distance > 0 else 0
113 | seq_stop = int(stop) + distance
114 | seq = self.genome_dict[chrmid][seq_start-1:seq_stop]
115 | if strand == '+':
116 | PF.write(''.join(['>', chrmid, '-', str(seq_start), '-', str(seq_stop), '\n']))
117 | PF.write(str(seq))
118 | PF.write('\n')
119 | else:
120 | PF.write(''.join(['>', chrmid, '-', str(seq_start), '-', str(seq_stop), '\n']))
121 | PF.write(str(seq.reverse_complement()))
122 | PF.write('\n')
123 | self.mfalist.append(pairfa)
124 |
125 | def main(self):
126 | sys.stdout.write('Begin to make consensus sequences.\n')
127 | subwkdir = 'Consensus/'
128 | if not os.path.exists(subwkdir):
129 | os.mkdir(subwkdir)
130 | else:
131 | shutil.rmtree(subwkdir)
132 | os.mkdir(subwkdir)
133 | representative_dict = defaultdict(list)
134 | with open(self.repsenbed, 'r') as F:
135 | for line in F:
136 | splitlines = line.rstrip().split('\t')
137 | representative_dict[splitlines[3]].append(splitlines)
138 | representative_list = [representative_dict[pairname] for pairname in representative_dict]
139 |
140 | ## To output the multiple sequences
141 | self.mfalist = []
142 | planpool = ThreadPool(int(self.process_num))
143 | for pairlist in representative_list:
144 | planpool.apply_async(self.extract_seq, args=(pairlist, ))
145 | planpool.close()
146 | planpool.join()
147 |
148 | self.consensus_dict = defaultdict(list)
149 | ## To make consensus sequences for each subfamily.
150 | planpool = ThreadPool(int(self.process_num))
151 | for mfa in self.mfalist:
152 | opfile=''
153 | planpool.apply_async(self.consencus, args=(mfa, ))
154 | planpool.close()
155 | planpool.join()
156 |
157 | with open('RC.representative.cons.fa', 'w') as F:
158 | for name in self.consensus_dict:
159 | init = 1
160 | for seq in self.consensus_dict[name]:
161 | seqname = ''.join(['>', name, '.', str(init)])
162 | F.write(''.join([seqname, '\n', seq, '\n']))
163 | init += 1
164 | sys.stdout.write('Consensus sequences got constructed!.\n')
165 |
166 |
167 | if __name__ == "__main__":
168 | parser = argparse.ArgumentParser(description="Making consensus for Helitron-like sequences. Please visit https://github.com/Zhenlisme/heliano/ for more information. Email us: zhen.li3@universite-paris-saclay.fr")
169 | parser.add_argument("-g", "--genome", type=str, required=True, help="The genome file in fasta format.")
170 | parser.add_argument("-r", "--repsenbed", type=str, required=True, help="The representative bed file.")
171 | parser.add_argument("-o", "--opdir", type=str, required=True, help="The output directory.")
172 | parser.add_argument("-n", "--process", type=int, default=2, required=False, help="Maximum of threads to be used.")
173 | parser.add_argument("-v", "--version", action='version', version='%(prog)s 1.0.2')
174 | Args = parser.parse_args()
175 | makeconsenus = Consensus_making(os.path.abspath(Args.genome), os.path.abspath(Args.opdir), os.path.abspath(Args.repsenbed), Args.process)
176 | makeconsenus.main()
177 |
178 |
--------------------------------------------------------------------------------
/heliano_fisher.R:
--------------------------------------------------------------------------------
1 | library(bedtoolsr)
2 | library(parallel)
3 |
4 | ###set argument#####
5 | args=commandArgs(T)
6 | bedtools_path = args[1]
7 | Genome_size = args[2]
8 | joint_bedpath_df=args[3]
9 | bed_opt=args[4]
10 | MAX_CPU_num = detectCores() -1
11 | CPU_num=as.numeric(args[5])
12 | CPU_num = ifelse(CPU_num < MAX_CPU_num, CPU_num, MAX_CPU_num)
13 | CPU_num = ifelse(CPU_num<1, 1, CPU_num)
14 | PVALUE=as.numeric(args[6])
15 | ORF_BED=args[7]
16 | Strategy=args[8]
17 | options(bedtools.path = bedtools_path)
18 |
19 | #####################
20 | cluster_intervals <- function(bed_data, min_overlap = 0.8){
21 | add_index = ncol(bed_data)+1
22 | row_number = nrow(bed_data)
23 | if(row_number<2){
24 | bed_data[1,add_index]=1
25 | colnames(bed_data)[add_index]='cluster'
26 | return(bed_data)
27 | }
28 | ## Define overlap function ##
29 | overlap_percentage <- function(a_start, a_end, b_start, b_end) {
30 | overlap <- max(0, min(a_end, b_end) - max(a_start, b_start))
31 | a_length <- a_end - a_start
32 | b_length <- b_end - b_start
33 | return(max(overlap / a_length, overlap / b_length))
34 | }
35 | ## Finish of overlap function ##
36 | prev_interval = unlist(bed_data[1, ])
37 | cluster_id=1
38 | prev_interval[add_index]=cluster_id
39 | clusters <- list(prev_interval)
40 | Merged_result = lapply(2:row_number, function(i){
41 | curr_interval <- unlist(bed_data[i, ])
42 | overlap <- overlap_percentage(as.numeric(prev_interval[2]), as.numeric(prev_interval[3]),
43 | as.numeric(curr_interval[2]), as.numeric(curr_interval[3]))
44 | if (overlap >= min_overlap & curr_interval[1] == prev_interval[1]) {
45 | prev_interval <<- c(curr_interval[1], prev_interval[2],
46 | pmax(as.numeric(prev_interval[3]), as.numeric(curr_interval[3])))
47 | } else {
48 | prev_interval <<- curr_interval
49 | cluster_id <<- cluster_id+1
50 | }
51 | curr_interval[add_index]=cluster_id
52 | return(curr_interval)
53 | })
54 | bed_data = as.data.frame(do.call('rbind', c(clusters, Merged_result)), stringsAsFactors=F)
55 | colnames(bed_data)[add_index]='cluster'
56 | return(bed_data)
57 | }
58 |
59 | Genome_size_df=read.csv2(Genome_size, stringsAsFactors = F, header = F, sep = '\t')
60 | joint_df = read.csv2(joint_bedpath_df, stringsAsFactors = F, header = F, sep = '\t')
61 | colnames(joint_df)=c('left', 'right')
62 |
63 | cl = makeCluster(CPU_num)
64 | clusterExport(cl, c('Genome_size_df', 'bedtools_path'), envir = .GlobalEnv)
65 | clusterEvalQ(cl, list(library(bedtoolsr), options(bedtools.path = bedtools_path)))
66 |
67 | significance_df = parApply(cl, joint_df, MARGIN = 1, function(x){
68 | left_bed = read.csv2(x[1], stringsAsFactors = F, header = F, sep = '\t')
69 | right_bed = read.csv2(x[2], stringsAsFactors = F, header = F, sep = '\t')
70 | fisher_result = bt.fisher(a=left_bed, b=right_bed, g=Genome_size_df, nonamecheck = TRUE, m = TRUE, s = TRUE)
71 | pvalue=fisher_result$right
72 | return(c(x[1], x[2], pvalue))
73 | })
74 |
75 | stopCluster (cl)
76 | significance_df=t(significance_df)
77 | colnames(significance_df)=c('leftpath', 'rightpath', 'pvalue')
78 | significance_df=as.data.frame(significance_df, stringsAsFactors = F)
79 | significance_df$pvalue=as.numeric(significance_df$pvalue)
80 | write.table(significance_df, file = 'RawPvalue.txt', quote = F, sep="\t", col.names = F, row.names = F)
81 |
82 | significance_df=significance_df[which(significance_df$pvalue<=PVALUE), ]
83 |
84 | ## make joint and merge pvalue file
85 | cl = makeCluster(CPU_num)
86 | clusterExport(cl, c('bedtools_path', 'bed_opt', 'ORF_BED', 'cluster_intervals'), envir = .GlobalEnv)
87 | clusterEvalQ(cl, list(library(bedtoolsr), options(bedtools.path = bedtools_path)))
88 |
89 | if(Strategy=='1'){
90 | if(length(rownames(significance_df))){
91 | parApply(cl, significance_df, MARGIN = 1, function(x){
92 | pvalue = x[3]
93 | window_df = bt.intersect(a=x[1], b=x[2], nonamecheck = TRUE, s=TRUE, wo=TRUE)
94 | if(length(rownames(window_df))>0){
95 | Start = ifelse(window_df$V6=='+', window_df$V7, window_df$V14)
96 | Stop = ifelse(window_df$V6=='+', window_df$V14, window_df$V7)
97 | name=paste(window_df$V4, window_df$V11, sep = '-')
98 | Bitscore=(as.numeric(window_df$V5)+as.numeric(window_df$V12))/2
99 | window_df=data.frame(chrm=window_df$V1, start=Start, stop=Stop,
100 | combiname=name, count=1, strand=window_df$V6,
101 | pvalue=1, Bscore=Bitscore, stringsAsFactors=F)
102 | left_name = gsub('.bed', '', basename(x[1]))
103 | right_name = gsub('.bed', '', basename(x[2]))
104 |
105 | window_df = window_df[order(window_df$chrm, as.numeric(window_df$start)), ]
106 | ## Cluster intervals
107 | window_df = cluster_intervals(window_df, min_overlap = 0.8)
108 | ## To select the intervals with highest bitscore
109 | window_df = window_df[ave(window_df$Bscore, window_df$cluster, FUN = max) == window_df$Bscore, ]
110 | cluster_count = length(unique(window_df$cluster))
111 | window_df$pvalue=pvalue
112 | window_df$count=cluster_count
113 | window_df$repalt='rep'
114 | window_df=window_df[, c(1:8, 10)]
115 | ##################### dedup function ############################
116 | dedup_func = function(inpt_fisher_df){
117 | intersection_df = bt.intersect(inpt_fisher_df, inpt_fisher_df, F=1, s=T, wo=T)
118 |
119 | ## To select the one who cover any other lines
120 | intersection_df = intersection_df[which(!(intersection_df$V2==intersection_df$V11 & intersection_df$V3==intersection_df$V12)),
121 | c(1:9)]
122 | intersection_df = unique(intersection_df)
123 | non_overlapped_bed = bt.intersect(inpt_fisher_df, intersection_df, wa=T, f=1, F=1, v=T, s=T)
124 |
125 | if(nrow(intersection_df)>0){
126 | intersection_df$V9='alt'
127 | }
128 | final_opt = rbind(non_overlapped_bed, intersection_df)
129 | return(final_opt)
130 | }
131 | ################## Function end ################################
132 | if(file.exists(ORF_BED)){
133 | ORF_fisherpart = bt.intersect(window_df, ORF_BED, F=1, wa=T)
134 | nonauto_fisherpart = bt.intersect(window_df, ORF_BED, F=.5, wa=T, v = T)
135 | Auto_dedup = data.frame()
136 | Nonauto_dedup = data.frame()
137 | if(nrow(ORF_fisherpart)>0){
138 | Auto_dedup = dedup_func(ORF_fisherpart)
139 | }
140 | if(nrow(nonauto_fisherpart>0)){
141 | Nonauto_dedup = dedup_func(nonauto_fisherpart)
142 | }
143 | Dedup_df = rbind(Auto_dedup, Nonauto_dedup)
144 |
145 | }else{
146 | Dedup_df = dedup_func(window_df)
147 | }
148 | filename=paste(bed_opt, '/',left_name, '-', right_name, '.bed', sep = '')
149 | write.table(Dedup_df, file = filename, quote = F, row.names = F, col.names = F, sep = '\t')
150 | }
151 | })
152 |
153 | }
154 | }else{
155 | if(length(rownames(significance_df))){
156 | parApply(cl, significance_df, MARGIN = 1, function(x){
157 | pvalue = x[3]
158 | window_df = bt.intersect(a=x[1], b=x[2], nonamecheck = TRUE, s=TRUE, wo=TRUE)
159 | if(length(rownames(window_df))>0){
160 | Start = ifelse(window_df$V6=='+', window_df$V7, window_df$V14)
161 | Stop = ifelse(window_df$V6=='+', window_df$V14, window_df$V7)
162 | name=paste(window_df$V4, window_df$V11, sep = '-')
163 | Bitscore=(as.numeric(window_df$V5)+as.numeric(window_df$V12))/2
164 | window_df=data.frame(chrm=window_df$V1, start=Start, stop=Stop,
165 | combiname=name, count=1, strand=window_df$V6,
166 | pvalue=1, Bscore=Bitscore, stringsAsFactors=F)
167 | left_name = gsub('.bed', '', basename(x[1]))
168 | right_name = gsub('.bed', '', basename(x[2]))
169 |
170 | window_df = window_df[order(window_df$chrm, as.numeric(window_df$start)), ]
171 | ## Cluster intervals
172 | window_df = cluster_intervals(window_df, min_overlap = 0.8)
173 | ## To select the intervals with highest bitscore for each clusters
174 | window_df = window_df[ave(window_df$Bscore, window_df$cluster, FUN = max) == window_df$Bscore, ]
175 | cluster_count = length(unique(window_df$cluster))
176 | window_df$pvalue=pvalue
177 | window_df$count=cluster_count
178 | window_df$repalt='rep'
179 | window_df=window_df[, c(1:8, 10)]
180 | filename=paste(bed_opt, '/',left_name, '-', right_name, '.bed', sep = '')
181 | write.table(window_df, file = filename, quote = F, row.names = F, col.names = F, sep = '\t')
182 | }
183 | })
184 |
185 | }
186 | }
187 |
188 |
189 | stopCluster (cl)
190 |
191 | ## To filter out pairs whose sequences are similar.
192 | fisher_bedfilelist = list.files(bed_opt)
193 |
194 | cl = makeCluster(CPU_num)
195 | clusterExport(cl, c('bedtools_path', 'bed_opt'), envir = .GlobalEnv)
196 | clusterEvalQ(cl, list(library(bedtoolsr), options(bedtools.path = bedtools_path)))
197 |
198 | parSapply(cl, fisher_bedfilelist, function(x){
199 | fisherbed_file = paste(bed_opt, '/', x, sep = '')
200 | split_list = strsplit(gsub('.bed', '', x),split = '-')
201 | leftname = split_list[[1]][1]
202 | rightname = split_list[[1]][2]
203 | classname = strsplit(leftname, split = '_left_')[[1]][1]
204 | left_blasnbed = paste('./SubBlastnBed/', classname, '_left/', leftname, '.bed', sep = '')
205 | right_blasnbed = paste('./SubBlastnBed/', classname, '_right/', rightname, '.bed', sep = '')
206 | left_bed = read.csv2(left_blasnbed, stringsAsFactors = F, header = F, sep = '\t')
207 | intersection_df = bt.intersect(a=left_blasnbed, b=right_blasnbed, nonamecheck = FALSE, s=FALSE, f=0.8)
208 | proportion = nrow(unique(intersection_df))/nrow(left_bed)
209 | if(proportion>=0.3){
210 | file.remove(fisherbed_file)
211 | }
212 | })
213 | stopCluster (cl)
214 |
--------------------------------------------------------------------------------
/readme.md:
--------------------------------------------------------------------------------
1 | [](https://anaconda.org/zhenlisme/heliano/)
2 | [](https://anaconda.org/bioconda/heliano)
3 | [](https://anaconda.org/zhenlisme/heliano/)
4 | [](https://anaconda.org/zhenlisme/heliano/)
5 | [](./LICENSE)
6 |
7 | # HELIANO: A fast and accurate tool for detection of Helitron-like elements.
8 | Helitron-like elements (HLE1 and HLE2) are DNA transposons. They have been found in diverse species and seem to play significant roles in the evolution of host genomes. Although known for over twenty years, Helitron sequences are still challenging to identify. Here, we propose HELIANO (Helitron-like elements annotator) as an efficient solution for detecting Helitron-like elements. Please check [wiki](https://github.com/Zhenlisme/heliano/wiki/1.-Home) for detailed usage.
9 |
10 | # Table of contents
11 | - [Update Note](#Update-Note)
12 | - [Dependencies](#dependencies)
13 | - [Installation](#installation)
14 | * [conda](#conda)
15 | * [mamba](#mamba)
16 | * [Manual installation](#manual-installation)
17 | - [Usage](#usage)
18 | - [Test run](#Perform-a-test-run-of-HELIANO)
19 | - [Making Consensus](#Generation-for-consensus-sequences)
20 | - [Dis-denovo prediction](#Dis-denovo-prediction)
21 | - [References](#References)
22 | - [FAQ](#Frequently-asked-questions)
23 | - [Release history](#Release-history)
24 | - [To contact us](#to-contact-us)
25 |
26 | # Update Note:
27 | 1) Since version 1.1.0, HELIANO will use the term HLE1 to refer to the canonical Helitron (called Helitron in v1.0.2) and the term HLE2 to refer to the non-canonical Helitrons (called HLE2 in v1.0.2).
28 | See figure below:
29 |
30 |
31 |
32 | 2) From version 1.1.0, users are allowed to input a pair file as a complementary for LTS-RTS pair information. This will help a lot in searching for HLEs in close species. For more information, see [here](#Dis-denovo-prediction).
33 | # Dependencies
34 | ```
35 | - python = 3.9.0
36 | - r-base = 4.1
37 | - biopython
38 | - pybedtools = 0.9.0 =py39hd65a603_2
39 | - r-bedtoolsr
40 | - r-seqinr = 4.2_16 = r41h06615bd_0
41 | - bedtools = 2.30.0
42 | - dialign2 = 2.2.1
43 | - mafft
44 | - cd-hit = 4.8.1
45 | - blast = 2.2.31
46 | - emboss = 6.6.0
47 | - hmmer = 3.3.2
48 | - genometools-genometools = 1.6.2 = py39h58cc16e_6
49 | - rnabob = 2.2.1
50 | ```
51 | # Installation
52 | ## mamba (Recommendation)
53 | If mamba is not installed on your system, you can install it with the following commands easily.
54 | ```
55 | wget "https://github.com/conda-forge/miniforge/releases/latest/download/Mambaforge-$(uname)-$(uname -m).sh"
56 | bash Mambaforge-$(uname)-$(uname -m).sh -b
57 | ```
58 | Then you can install HELIANO with mamba.
59 | ```
60 | #create the HELIANO environment
61 | mamba create -n HELIANO
62 | #activate the HELIANO environment
63 | mamba activate HELIANO
64 | # install
65 | mamba install zhenlisme::HELIANO -c conda-forge -c bioconda
66 | mamba deactivate
67 | ```
68 | ## conda
69 | ```
70 | #create the HELIANO environment
71 | conda create -n HELIANO
72 | #activate the HELIANO environment
73 | conda activate HELIANO
74 | # installation
75 | conda install zhenlisme::HELIANO -c conda-forge -c bioconda
76 | conda deactivate
77 | ```
78 | ## manual installation
79 | Before installation, you need to be sure that all dependencies have been installed on your computer and that their path are defined in your environmental variables. All dependencies could be installed via conda/mamba.
80 | 1. download the latest HELIANO package.
81 | `git clone https://github.com/Zhenlisme/HELIANO.git`
82 | 2. switch to the source code dorectory that you cloned at the last step.
83 | `cd HELIANO/`
84 | 3. run configure file.
85 | `bash configure.sh`
86 | 4. You can find HELIANO in the bin directory.
87 | # Usage
88 | ### Activate the HELIANO conda environment (for conda/mamba installation)
89 | `conda activate HELIANO`
90 | ### Perform a test run of HELIANO
91 | ##### Here we will use the chromosome 18 of Fusarium oxysporum strain Fo5176 as an example, where you can find it in file test.fa .
92 | Perform the following code:
93 | `heliano -g test.fa -is1 0 -is2 0 -o test_opt -w 15000`
94 | ### HELIANO outputs
95 | You will find two main result files when HELIANO program runs successfully.
96 | 1. RC.representative.bed: the predicted HLE1/HLE2 coordinates in bed format (available in the file test.opt.tbl in this repository).
97 | 2. RC.representative.fa: the predicted HLE1/HLE2 sequences in fasta format.
98 | 3. pairlist.tbl: The file for LTS-RTS pair information.
99 | Other files or directories are intermediate outputs.
100 | 1. TIR_count.tbl: Table for counts of terminal inverted repeats of each HLE subfamily.
101 | 2. Boundary.tbl: Table for the conservation of flanking regions of each HLE subfamily.
102 | 3. HLE1/ or HLE2/: Directory for intermediate files when detecting HLE1/HLE2.
103 | ##### Explanation for RC.representative.bed
104 | There are 11 columns in RC.representative.bed file:
105 | |chrm-id|start|end|subfamily|occurence|strand|pvalue|TS_blastn_identity|variant|type|name|
106 | | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
107 | |CP128282.1|53617|59046|HLE2_left_18-HLE2_right_18|7|-|6.3390e-07|60|HLE2|auto|insertion_HLE2_auto_1|
108 | |CP128282.1|83425|88824|HLE2_left_18-HLE2_right_18|7|-|6.3390e-07|60|HLE2|auto|insertion_HLE2_auto_2|
109 | |CP128282.1|94525|99924|HLE2_left_18-HLE2_right_18|7|+|6.3390e-07|60|HLE2|auto|insertion_HLE2_auto_3|
110 | |CP128282.1|306838|312276|HLE2_left_18-HLE2_right_18|7|+|6.3390e-07|60|HLE2|auto|insertion_HLE2_auto_4|
111 | ##### Detailed explaination for each column.
112 | Notice: The insertions that encode Rep/helicase are considered putative autonomous HLEs.
113 | |Columns|Explaination|
114 | | ---- | ---- |
115 | |chrm-id|chromosome id|
116 | |start|start site of HLE|
117 | |stop|stop site of HLE|
118 | |subfamily|heliano classification|
119 | |occurence|how often this subfamily occurred in genome|
120 | |strand|the insertion is on which strand|
121 | |pvalue|pvalue of fisher's exact test, indicating the significance of the prediction. The lower, the more significant.|
122 | |TS_blastn_identity|the average identity of RTS and LTS to their representative counterparts|
123 | |variant|the insertion is HLE1 or HLE2|
124 | |type|the mobility of HLE, either autonomous (auto) or nonautonomous (nonauto)|
125 | |name|unique identifier for each insertion|
126 | ### Generation for consensus sequences
127 | The HELIANO package also provides a program (heliano_cons) for generating consensus sequences of HLE.
128 | Check the usage of heliano_cons:
129 | `heliano_cons -h`
130 | ```
131 | usage: heliano_cons [-h] -g GENOME -r REPSENBED -o OPDIR [-n PROCESS] [-v]
132 |
133 | Making consensus for Helitron-like sequences. Please visit https://github.com/Zhenlisme/heliano/ for more information. Email us: zhen.li3@universite-paris-saclay.fr
134 |
135 | optional arguments:
136 | -h, --help show this help message and exit
137 | -g GENOME, --genome GENOME
138 | The genome file in fasta format.
139 | -r REPSENBED, --repsenbed REPSENBED
140 | The representative bed file (RC.representative.bed).
141 | -o OPDIR, --opdir OPDIR
142 | The output directory.
143 | -n PROCESS, --process PROCESS
144 | Maximum of threads to be used.
145 | -v, --version show program's version number and exit
146 | ```
147 | ### Dis-denovo prediction
148 | Since version 1.1.0, HELIANO enables prediction of HLEs with the help of pre-identified LTS-RTS pair file.
149 | The `pairlist.tbl` can be either obtained from the main directory of your previous run or user-defined.
150 |
151 | You can skip the denovo prediction of the LTS-RTS pair process (will save a lot of time),
152 | ```
153 | heliano -g test.fa -is1 0 -is2 0 -o test_opt -w 15000 -ts pairlist.tbl --dis_denovo
154 | ```
155 | Or not skip the de novo prediction of the LTS-RTS process
156 | ```
157 | heliano -g test.fa -is1 0 -is2 0 -o test_opt -w 15000 -ts pairlist.tbl
158 | ```
159 | # References
160 | ### If you find HELIANO useful to you, please cite:
161 | Li Z , Gilbert C , Peng H , Pollet N. "Discovery of numerous novel Helitron-like elements in eukaryote genomes using HELIANO." Nucleic Acids Research, 2024. [doi: doi.org/10.1093/nar/gkae679](https://doi.org/10.1093/nar/gkae679).
162 |
163 | Li Z , Pollet N. "HELIANO: a Helitron-like element annotator." Zenodo (2024). [doi: 10.5281/zenodo.10625239](https://doi.org/10.5281/zenodo.10625239)
164 |
165 | # Frequently asked questions
166 | ### 1. How to get fragmented copies of HLEs?
167 | HELIANO is designed to predict complete insertions of Helitron-like elements (HLE), with the limitation that fragmented insertions will not be reported. To identify fragmented insertions, we recommend running RepeatMasker or BLASTN using HELIANO predictions as the query. Before you run RepeatMasker or BLASTN, we suggest masking the HLE query with a trusted non-HLE TE database because other non-HLE TEs might insert into long HLEs, which would inflate sequence length and result in misannotation.
168 | ### 2. How to choose parameters properly?
169 | For a precise and quick search, you can use the stringent parameter '-is1 1 -is2 1 -p 1e-5 -s 30 -pt 1 -sim_tir 100' that considers the preferred insertion sites of HLE. For big or complex genomes (e.g., the maize genome), I just recommend you use the stringent parameter set. But not all HLEs obey their regular preferred insertion sites. If you want to explore more in your interested genome, you can use the loose parameter set, e.g., '-is1 0 -is2 0 -sim_tir 90', and you will have more predictions and a longer execution time. Note that the parameters '-is2' and '-sim_tir' are only for HLE2s, and '-is1' and '-pt' are only for Helitrons.
170 | # Release history
171 | ### [v1.0.1](https://github.com/Zhenlisme/heliano/releases/tag/v1.0.1)
172 | Initial version
173 | ### [v1.0.2](https://github.com/Zhenlisme/heliano/releases/tag/v1.0.2)
174 | Fixed some bugs
175 | ### [v1.1.0](https://github.com/Zhenlisme/heliano/releases/tag/v1.1.0)
176 | 1. Replace the term Helitron with HLE1 and Helentron with HLE2.
177 | 2. Enable to prediction of HLEs based on a pre-identified LTS-RTS pair file. (see -ts and --dis_denovo parameters)
178 | 3. Add a new parameter that allows an auto HLE to have multiple terminal sequences. (see '--multi_ts' parameter)
179 | ### [v1.2.0](https://github.com/Zhenlisme/heliano/releases/tag/v1.2.0)
180 | 1. Add parameter '--nearest' that allows users to find terminal pairs whose LTS and RTS are closest to each other. By default, HELIANO will try to find the furthest pairs.
181 | 2. Add parameter '-dn' that allows users to define the length of nonautonomous HLEs. By default (dn 0), HELIANO will deduce it automatically.
182 | ### [v1.2.1](https://github.com/Zhenlisme/heliano/releases/tag/v1.2.1)
183 | Add the '-flank_sim' parameter, which allows users to set the cut-off to define false positive LTS/RTS. The lower the value, the more stringent. This value was set to 0.7 in previous versions, but it is now set to 0.5 by default.
184 | ### [v1.3.1](https://github.com/Zhenlisme/heliano/releases/tag/v1.3.1)
185 | 1. Resolve the hmmsearch error issue.
186 | 2. Add that "--table" parameter that allows users to adjust the genetic code of test organisms.
187 | 3. Optimize the LTS/RTS selection. When there are alternative terminal sequences on the same autonomous locus, try to use the one with a higher blastn score.
188 |
189 | # To contact us
190 | For any questions, please open an issue in [the issues section](https://github.com/Zhenlisme/heliano/issues) or send me an email to zhen.li3@universite-paris-saclay.fr.
191 |
--------------------------------------------------------------------------------
/LICENSE.txt:
--------------------------------------------------------------------------------
1 | GNU GENERAL PUBLIC LICENSE
2 | Version 3, 29 June 2007
3 |
4 | Copyright (C) 2007 Free Software Foundation, Inc.
5 | Everyone is permitted to copy and distribute verbatim copies
6 | of this license document, but changing it is not allowed.
7 |
8 | Preamble
9 |
10 | The GNU General Public License is a free, copyleft license for
11 | software and other kinds of works.
12 |
13 | The licenses for most software and other practical works are designed
14 | to take away your freedom to share and change the works. By contrast,
15 | the GNU General Public License is intended to guarantee your freedom to
16 | share and change all versions of a program--to make sure it remains free
17 | software for all its users. We, the Free Software Foundation, use the
18 | GNU General Public License for most of our software; it applies also to
19 | any other work released this way by its authors. You can apply it to
20 | your programs, too.
21 |
22 | When we speak of free software, we are referring to freedom, not
23 | price. Our General Public Licenses are designed to make sure that you
24 | have the freedom to distribute copies of free software (and charge for
25 | them if you wish), that you receive source code or can get it if you
26 | want it, that you can change the software or use pieces of it in new
27 | free programs, and that you know you can do these things.
28 |
29 | To protect your rights, we need to prevent others from denying you
30 | these rights or asking you to surrender the rights. Therefore, you have
31 | certain responsibilities if you distribute copies of the software, or if
32 | you modify it: responsibilities to respect the freedom of others.
33 |
34 | For example, if you distribute copies of such a program, whether
35 | gratis or for a fee, you must pass on to the recipients the same
36 | freedoms that you received. You must make sure that they, too, receive
37 | or can get the source code. And you must show them these terms so they
38 | know their rights.
39 |
40 | Developers that use the GNU GPL protect your rights with two steps:
41 | (1) assert copyright on the software, and (2) offer you this License
42 | giving you legal permission to copy, distribute and/or modify it.
43 |
44 | For the developers' and authors' protection, the GPL clearly explains
45 | that there is no warranty for this free software. For both users' and
46 | authors' sake, the GPL requires that modified versions be marked as
47 | changed, so that their problems will not be attributed erroneously to
48 | authors of previous versions.
49 |
50 | Some devices are designed to deny users access to install or run
51 | modified versions of the software inside them, although the manufacturer
52 | can do so. This is fundamentally incompatible with the aim of
53 | protecting users' freedom to change the software. The systematic
54 | pattern of such abuse occurs in the area of products for individuals to
55 | use, which is precisely where it is most unacceptable. Therefore, we
56 | have designed this version of the GPL to prohibit the practice for those
57 | products. If such problems arise substantially in other domains, we
58 | stand ready to extend this provision to those domains in future versions
59 | of the GPL, as needed to protect the freedom of users.
60 |
61 | Finally, every program is threatened constantly by software patents.
62 | States should not allow patents to restrict development and use of
63 | software on general-purpose computers, but in those that do, we wish to
64 | avoid the special danger that patents applied to a free program could
65 | make it effectively proprietary. To prevent this, the GPL assures that
66 | patents cannot be used to render the program non-free.
67 |
68 | The precise terms and conditions for copying, distribution and
69 | modification follow.
70 |
71 | TERMS AND CONDITIONS
72 |
73 | 0. Definitions.
74 |
75 | "This License" refers to version 3 of the GNU General Public License.
76 |
77 | "Copyright" also means copyright-like laws that apply to other kinds of
78 | works, such as semiconductor masks.
79 |
80 | "The Program" refers to any copyrightable work licensed under this
81 | License. Each licensee is addressed as "you". "Licensees" and
82 | "recipients" may be individuals or organizations.
83 |
84 | To "modify" a work means to copy from or adapt all or part of the work
85 | in a fashion requiring copyright permission, other than the making of an
86 | exact copy. The resulting work is called a "modified version" of the
87 | earlier work or a work "based on" the earlier work.
88 |
89 | A "covered work" means either the unmodified Program or a work based
90 | on the Program.
91 |
92 | To "propagate" a work means to do anything with it that, without
93 | permission, would make you directly or secondarily liable for
94 | infringement under applicable copyright law, except executing it on a
95 | computer or modifying a private copy. Propagation includes copying,
96 | distribution (with or without modification), making available to the
97 | public, and in some countries other activities as well.
98 |
99 | To "convey" a work means any kind of propagation that enables other
100 | parties to make or receive copies. Mere interaction with a user through
101 | a computer network, with no transfer of a copy, is not conveying.
102 |
103 | An interactive user interface displays "Appropriate Legal Notices"
104 | to the extent that it includes a convenient and prominently visible
105 | feature that (1) displays an appropriate copyright notice, and (2)
106 | tells the user that there is no warranty for the work (except to the
107 | extent that warranties are provided), that licensees may convey the
108 | work under this License, and how to view a copy of this License. If
109 | the interface presents a list of user commands or options, such as a
110 | menu, a prominent item in the list meets this criterion.
111 |
112 | 1. Source Code.
113 |
114 | The "source code" for a work means the preferred form of the work
115 | for making modifications to it. "Object code" means any non-source
116 | form of a work.
117 |
118 | A "Standard Interface" means an interface that either is an official
119 | standard defined by a recognized standards body, or, in the case of
120 | interfaces specified for a particular programming language, one that
121 | is widely used among developers working in that language.
122 |
123 | The "System Libraries" of an executable work include anything, other
124 | than the work as a whole, that (a) is included in the normal form of
125 | packaging a Major Component, but which is not part of that Major
126 | Component, and (b) serves only to enable use of the work with that
127 | Major Component, or to implement a Standard Interface for which an
128 | implementation is available to the public in source code form. A
129 | "Major Component", in this context, means a major essential component
130 | (kernel, window system, and so on) of the specific operating system
131 | (if any) on which the executable work runs, or a compiler used to
132 | produce the work, or an object code interpreter used to run it.
133 |
134 | The "Corresponding Source" for a work in object code form means all
135 | the source code needed to generate, install, and (for an executable
136 | work) run the object code and to modify the work, including scripts to
137 | control those activities. However, it does not include the work's
138 | System Libraries, or general-purpose tools or generally available free
139 | programs which are used unmodified in performing those activities but
140 | which are not part of the work. For example, Corresponding Source
141 | includes interface definition files associated with source files for
142 | the work, and the source code for shared libraries and dynamically
143 | linked subprograms that the work is specifically designed to require,
144 | such as by intimate data communication or control flow between those
145 | subprograms and other parts of the work.
146 |
147 | The Corresponding Source need not include anything that users
148 | can regenerate automatically from other parts of the Corresponding
149 | Source.
150 |
151 | The Corresponding Source for a work in source code form is that
152 | same work.
153 |
154 | 2. Basic Permissions.
155 |
156 | All rights granted under this License are granted for the term of
157 | copyright on the Program, and are irrevocable provided the stated
158 | conditions are met. This License explicitly affirms your unlimited
159 | permission to run the unmodified Program. The output from running a
160 | covered work is covered by this License only if the output, given its
161 | content, constitutes a covered work. This License acknowledges your
162 | rights of fair use or other equivalent, as provided by copyright law.
163 |
164 | You may make, run and propagate covered works that you do not
165 | convey, without conditions so long as your license otherwise remains
166 | in force. You may convey covered works to others for the sole purpose
167 | of having them make modifications exclusively for you, or provide you
168 | with facilities for running those works, provided that you comply with
169 | the terms of this License in conveying all material for which you do
170 | not control copyright. Those thus making or running the covered works
171 | for you must do so exclusively on your behalf, under your direction
172 | and control, on terms that prohibit them from making any copies of
173 | your copyrighted material outside their relationship with you.
174 |
175 | Conveying under any other circumstances is permitted solely under
176 | the conditions stated below. Sublicensing is not allowed; section 10
177 | makes it unnecessary.
178 |
179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law.
180 |
181 | No covered work shall be deemed part of an effective technological
182 | measure under any applicable law fulfilling obligations under article
183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or
184 | similar laws prohibiting or restricting circumvention of such
185 | measures.
186 |
187 | When you convey a covered work, you waive any legal power to forbid
188 | circumvention of technological measures to the extent such circumvention
189 | is effected by exercising rights under this License with respect to
190 | the covered work, and you disclaim any intention to limit operation or
191 | modification of the work as a means of enforcing, against the work's
192 | users, your or third parties' legal rights to forbid circumvention of
193 | technological measures.
194 |
195 | 4. Conveying Verbatim Copies.
196 |
197 | You may convey verbatim copies of the Program's source code as you
198 | receive it, in any medium, provided that you conspicuously and
199 | appropriately publish on each copy an appropriate copyright notice;
200 | keep intact all notices stating that this License and any
201 | non-permissive terms added in accord with section 7 apply to the code;
202 | keep intact all notices of the absence of any warranty; and give all
203 | recipients a copy of this License along with the Program.
204 |
205 | You may charge any price or no price for each copy that you convey,
206 | and you may offer support or warranty protection for a fee.
207 |
208 | 5. Conveying Modified Source Versions.
209 |
210 | You may convey a work based on the Program, or the modifications to
211 | produce it from the Program, in the form of source code under the
212 | terms of section 4, provided that you also meet all of these conditions:
213 |
214 | a) The work must carry prominent notices stating that you modified
215 | it, and giving a relevant date.
216 |
217 | b) The work must carry prominent notices stating that it is
218 | released under this License and any conditions added under section
219 | 7. This requirement modifies the requirement in section 4 to
220 | "keep intact all notices".
221 |
222 | c) You must license the entire work, as a whole, under this
223 | License to anyone who comes into possession of a copy. This
224 | License will therefore apply, along with any applicable section 7
225 | additional terms, to the whole of the work, and all its parts,
226 | regardless of how they are packaged. This License gives no
227 | permission to license the work in any other way, but it does not
228 | invalidate such permission if you have separately received it.
229 |
230 | d) If the work has interactive user interfaces, each must display
231 | Appropriate Legal Notices; however, if the Program has interactive
232 | interfaces that do not display Appropriate Legal Notices, your
233 | work need not make them do so.
234 |
235 | A compilation of a covered work with other separate and independent
236 | works, which are not by their nature extensions of the covered work,
237 | and which are not combined with it such as to form a larger program,
238 | in or on a volume of a storage or distribution medium, is called an
239 | "aggregate" if the compilation and its resulting copyright are not
240 | used to limit the access or legal rights of the compilation's users
241 | beyond what the individual works permit. Inclusion of a covered work
242 | in an aggregate does not cause this License to apply to the other
243 | parts of the aggregate.
244 |
245 | 6. Conveying Non-Source Forms.
246 |
247 | You may convey a covered work in object code form under the terms
248 | of sections 4 and 5, provided that you also convey the
249 | machine-readable Corresponding Source under the terms of this License,
250 | in one of these ways:
251 |
252 | a) Convey the object code in, or embodied in, a physical product
253 | (including a physical distribution medium), accompanied by the
254 | Corresponding Source fixed on a durable physical medium
255 | customarily used for software interchange.
256 |
257 | b) Convey the object code in, or embodied in, a physical product
258 | (including a physical distribution medium), accompanied by a
259 | written offer, valid for at least three years and valid for as
260 | long as you offer spare parts or customer support for that product
261 | model, to give anyone who possesses the object code either (1) a
262 | copy of the Corresponding Source for all the software in the
263 | product that is covered by this License, on a durable physical
264 | medium customarily used for software interchange, for a price no
265 | more than your reasonable cost of physically performing this
266 | conveying of source, or (2) access to copy the
267 | Corresponding Source from a network server at no charge.
268 |
269 | c) Convey individual copies of the object code with a copy of the
270 | written offer to provide the Corresponding Source. This
271 | alternative is allowed only occasionally and noncommercially, and
272 | only if you received the object code with such an offer, in accord
273 | with subsection 6b.
274 |
275 | d) Convey the object code by offering access from a designated
276 | place (gratis or for a charge), and offer equivalent access to the
277 | Corresponding Source in the same way through the same place at no
278 | further charge. You need not require recipients to copy the
279 | Corresponding Source along with the object code. If the place to
280 | copy the object code is a network server, the Corresponding Source
281 | may be on a different server (operated by you or a third party)
282 | that supports equivalent copying facilities, provided you maintain
283 | clear directions next to the object code saying where to find the
284 | Corresponding Source. Regardless of what server hosts the
285 | Corresponding Source, you remain obligated to ensure that it is
286 | available for as long as needed to satisfy these requirements.
287 |
288 | e) Convey the object code using peer-to-peer transmission, provided
289 | you inform other peers where the object code and Corresponding
290 | Source of the work are being offered to the general public at no
291 | charge under subsection 6d.
292 |
293 | A separable portion of the object code, whose source code is excluded
294 | from the Corresponding Source as a System Library, need not be
295 | included in conveying the object code work.
296 |
297 | A "User Product" is either (1) a "consumer product", which means any
298 | tangible personal property which is normally used for personal, family,
299 | or household purposes, or (2) anything designed or sold for incorporation
300 | into a dwelling. In determining whether a product is a consumer product,
301 | doubtful cases shall be resolved in favor of coverage. For a particular
302 | product received by a particular user, "normally used" refers to a
303 | typical or common use of that class of product, regardless of the status
304 | of the particular user or of the way in which the particular user
305 | actually uses, or expects or is expected to use, the product. A product
306 | is a consumer product regardless of whether the product has substantial
307 | commercial, industrial or non-consumer uses, unless such uses represent
308 | the only significant mode of use of the product.
309 |
310 | "Installation Information" for a User Product means any methods,
311 | procedures, authorization keys, or other information required to install
312 | and execute modified versions of a covered work in that User Product from
313 | a modified version of its Corresponding Source. The information must
314 | suffice to ensure that the continued functioning of the modified object
315 | code is in no case prevented or interfered with solely because
316 | modification has been made.
317 |
318 | If you convey an object code work under this section in, or with, or
319 | specifically for use in, a User Product, and the conveying occurs as
320 | part of a transaction in which the right of possession and use of the
321 | User Product is transferred to the recipient in perpetuity or for a
322 | fixed term (regardless of how the transaction is characterized), the
323 | Corresponding Source conveyed under this section must be accompanied
324 | by the Installation Information. But this requirement does not apply
325 | if neither you nor any third party retains the ability to install
326 | modified object code on the User Product (for example, the work has
327 | been installed in ROM).
328 |
329 | The requirement to provide Installation Information does not include a
330 | requirement to continue to provide support service, warranty, or updates
331 | for a work that has been modified or installed by the recipient, or for
332 | the User Product in which it has been modified or installed. Access to a
333 | network may be denied when the modification itself materially and
334 | adversely affects the operation of the network or violates the rules and
335 | protocols for communication across the network.
336 |
337 | Corresponding Source conveyed, and Installation Information provided,
338 | in accord with this section must be in a format that is publicly
339 | documented (and with an implementation available to the public in
340 | source code form), and must require no special password or key for
341 | unpacking, reading or copying.
342 |
343 | 7. Additional Terms.
344 |
345 | "Additional permissions" are terms that supplement the terms of this
346 | License by making exceptions from one or more of its conditions.
347 | Additional permissions that are applicable to the entire Program shall
348 | be treated as though they were included in this License, to the extent
349 | that they are valid under applicable law. If additional permissions
350 | apply only to part of the Program, that part may be used separately
351 | under those permissions, but the entire Program remains governed by
352 | this License without regard to the additional permissions.
353 |
354 | When you convey a copy of a covered work, you may at your option
355 | remove any additional permissions from that copy, or from any part of
356 | it. (Additional permissions may be written to require their own
357 | removal in certain cases when you modify the work.) You may place
358 | additional permissions on material, added by you to a covered work,
359 | for which you have or can give appropriate copyright permission.
360 |
361 | Notwithstanding any other provision of this License, for material you
362 | add to a covered work, you may (if authorized by the copyright holders of
363 | that material) supplement the terms of this License with terms:
364 |
365 | a) Disclaiming warranty or limiting liability differently from the
366 | terms of sections 15 and 16 of this License; or
367 |
368 | b) Requiring preservation of specified reasonable legal notices or
369 | author attributions in that material or in the Appropriate Legal
370 | Notices displayed by works containing it; or
371 |
372 | c) Prohibiting misrepresentation of the origin of that material, or
373 | requiring that modified versions of such material be marked in
374 | reasonable ways as different from the original version; or
375 |
376 | d) Limiting the use for publicity purposes of names of licensors or
377 | authors of the material; or
378 |
379 | e) Declining to grant rights under trademark law for use of some
380 | trade names, trademarks, or service marks; or
381 |
382 | f) Requiring indemnification of licensors and authors of that
383 | material by anyone who conveys the material (or modified versions of
384 | it) with contractual assumptions of liability to the recipient, for
385 | any liability that these contractual assumptions directly impose on
386 | those licensors and authors.
387 |
388 | All other non-permissive additional terms are considered "further
389 | restrictions" within the meaning of section 10. If the Program as you
390 | received it, or any part of it, contains a notice stating that it is
391 | governed by this License along with a term that is a further
392 | restriction, you may remove that term. If a license document contains
393 | a further restriction but permits relicensing or conveying under this
394 | License, you may add to a covered work material governed by the terms
395 | of that license document, provided that the further restriction does
396 | not survive such relicensing or conveying.
397 |
398 | If you add terms to a covered work in accord with this section, you
399 | must place, in the relevant source files, a statement of the
400 | additional terms that apply to those files, or a notice indicating
401 | where to find the applicable terms.
402 |
403 | Additional terms, permissive or non-permissive, may be stated in the
404 | form of a separately written license, or stated as exceptions;
405 | the above requirements apply either way.
406 |
407 | 8. Termination.
408 |
409 | You may not propagate or modify a covered work except as expressly
410 | provided under this License. Any attempt otherwise to propagate or
411 | modify it is void, and will automatically terminate your rights under
412 | this License (including any patent licenses granted under the third
413 | paragraph of section 11).
414 |
415 | However, if you cease all violation of this License, then your
416 | license from a particular copyright holder is reinstated (a)
417 | provisionally, unless and until the copyright holder explicitly and
418 | finally terminates your license, and (b) permanently, if the copyright
419 | holder fails to notify you of the violation by some reasonable means
420 | prior to 60 days after the cessation.
421 |
422 | Moreover, your license from a particular copyright holder is
423 | reinstated permanently if the copyright holder notifies you of the
424 | violation by some reasonable means, this is the first time you have
425 | received notice of violation of this License (for any work) from that
426 | copyright holder, and you cure the violation prior to 30 days after
427 | your receipt of the notice.
428 |
429 | Termination of your rights under this section does not terminate the
430 | licenses of parties who have received copies or rights from you under
431 | this License. If your rights have been terminated and not permanently
432 | reinstated, you do not qualify to receive new licenses for the same
433 | material under section 10.
434 |
435 | 9. Acceptance Not Required for Having Copies.
436 |
437 | You are not required to accept this License in order to receive or
438 | run a copy of the Program. Ancillary propagation of a covered work
439 | occurring solely as a consequence of using peer-to-peer transmission
440 | to receive a copy likewise does not require acceptance. However,
441 | nothing other than this License grants you permission to propagate or
442 | modify any covered work. These actions infringe copyright if you do
443 | not accept this License. Therefore, by modifying or propagating a
444 | covered work, you indicate your acceptance of this License to do so.
445 |
446 | 10. Automatic Licensing of Downstream Recipients.
447 |
448 | Each time you convey a covered work, the recipient automatically
449 | receives a license from the original licensors, to run, modify and
450 | propagate that work, subject to this License. You are not responsible
451 | for enforcing compliance by third parties with this License.
452 |
453 | An "entity transaction" is a transaction transferring control of an
454 | organization, or substantially all assets of one, or subdividing an
455 | organization, or merging organizations. If propagation of a covered
456 | work results from an entity transaction, each party to that
457 | transaction who receives a copy of the work also receives whatever
458 | licenses to the work the party's predecessor in interest had or could
459 | give under the previous paragraph, plus a right to possession of the
460 | Corresponding Source of the work from the predecessor in interest, if
461 | the predecessor has it or can get it with reasonable efforts.
462 |
463 | You may not impose any further restrictions on the exercise of the
464 | rights granted or affirmed under this License. For example, you may
465 | not impose a license fee, royalty, or other charge for exercise of
466 | rights granted under this License, and you may not initiate litigation
467 | (including a cross-claim or counterclaim in a lawsuit) alleging that
468 | any patent claim is infringed by making, using, selling, offering for
469 | sale, or importing the Program or any portion of it.
470 |
471 | 11. Patents.
472 |
473 | A "contributor" is a copyright holder who authorizes use under this
474 | License of the Program or a work on which the Program is based. The
475 | work thus licensed is called the contributor's "contributor version".
476 |
477 | A contributor's "essential patent claims" are all patent claims
478 | owned or controlled by the contributor, whether already acquired or
479 | hereafter acquired, that would be infringed by some manner, permitted
480 | by this License, of making, using, or selling its contributor version,
481 | but do not include claims that would be infringed only as a
482 | consequence of further modification of the contributor version. For
483 | purposes of this definition, "control" includes the right to grant
484 | patent sublicenses in a manner consistent with the requirements of
485 | this License.
486 |
487 | Each contributor grants you a non-exclusive, worldwide, royalty-free
488 | patent license under the contributor's essential patent claims, to
489 | make, use, sell, offer for sale, import and otherwise run, modify and
490 | propagate the contents of its contributor version.
491 |
492 | In the following three paragraphs, a "patent license" is any express
493 | agreement or commitment, however denominated, not to enforce a patent
494 | (such as an express permission to practice a patent or covenant not to
495 | sue for patent infringement). To "grant" such a patent license to a
496 | party means to make such an agreement or commitment not to enforce a
497 | patent against the party.
498 |
499 | If you convey a covered work, knowingly relying on a patent license,
500 | and the Corresponding Source of the work is not available for anyone
501 | to copy, free of charge and under the terms of this License, through a
502 | publicly available network server or other readily accessible means,
503 | then you must either (1) cause the Corresponding Source to be so
504 | available, or (2) arrange to deprive yourself of the benefit of the
505 | patent license for this particular work, or (3) arrange, in a manner
506 | consistent with the requirements of this License, to extend the patent
507 | license to downstream recipients. "Knowingly relying" means you have
508 | actual knowledge that, but for the patent license, your conveying the
509 | covered work in a country, or your recipient's use of the covered work
510 | in a country, would infringe one or more identifiable patents in that
511 | country that you have reason to believe are valid.
512 |
513 | If, pursuant to or in connection with a single transaction or
514 | arrangement, you convey, or propagate by procuring conveyance of, a
515 | covered work, and grant a patent license to some of the parties
516 | receiving the covered work authorizing them to use, propagate, modify
517 | or convey a specific copy of the covered work, then the patent license
518 | you grant is automatically extended to all recipients of the covered
519 | work and works based on it.
520 |
521 | A patent license is "discriminatory" if it does not include within
522 | the scope of its coverage, prohibits the exercise of, or is
523 | conditioned on the non-exercise of one or more of the rights that are
524 | specifically granted under this License. You may not convey a covered
525 | work if you are a party to an arrangement with a third party that is
526 | in the business of distributing software, under which you make payment
527 | to the third party based on the extent of your activity of conveying
528 | the work, and under which the third party grants, to any of the
529 | parties who would receive the covered work from you, a discriminatory
530 | patent license (a) in connection with copies of the covered work
531 | conveyed by you (or copies made from those copies), or (b) primarily
532 | for and in connection with specific products or compilations that
533 | contain the covered work, unless you entered into that arrangement,
534 | or that patent license was granted, prior to 28 March 2007.
535 |
536 | Nothing in this License shall be construed as excluding or limiting
537 | any implied license or other defenses to infringement that may
538 | otherwise be available to you under applicable patent law.
539 |
540 | 12. No Surrender of Others' Freedom.
541 |
542 | If conditions are imposed on you (whether by court order, agreement or
543 | otherwise) that contradict the conditions of this License, they do not
544 | excuse you from the conditions of this License. If you cannot convey a
545 | covered work so as to satisfy simultaneously your obligations under this
546 | License and any other pertinent obligations, then as a consequence you may
547 | not convey it at all. For example, if you agree to terms that obligate you
548 | to collect a royalty for further conveying from those to whom you convey
549 | the Program, the only way you could satisfy both those terms and this
550 | License would be to refrain entirely from conveying the Program.
551 |
552 | 13. Use with the GNU Affero General Public License.
553 |
554 | Notwithstanding any other provision of this License, you have
555 | permission to link or combine any covered work with a work licensed
556 | under version 3 of the GNU Affero General Public License into a single
557 | combined work, and to convey the resulting work. The terms of this
558 | License will continue to apply to the part which is the covered work,
559 | but the special requirements of the GNU Affero General Public License,
560 | section 13, concerning interaction through a network will apply to the
561 | combination as such.
562 |
563 | 14. Revised Versions of this License.
564 |
565 | The Free Software Foundation may publish revised and/or new versions of
566 | the GNU General Public License from time to time. Such new versions will
567 | be similar in spirit to the present version, but may differ in detail to
568 | address new problems or concerns.
569 |
570 | Each version is given a distinguishing version number. If the
571 | Program specifies that a certain numbered version of the GNU General
572 | Public License "or any later version" applies to it, you have the
573 | option of following the terms and conditions either of that numbered
574 | version or of any later version published by the Free Software
575 | Foundation. If the Program does not specify a version number of the
576 | GNU General Public License, you may choose any version ever published
577 | by the Free Software Foundation.
578 |
579 | If the Program specifies that a proxy can decide which future
580 | versions of the GNU General Public License can be used, that proxy's
581 | public statement of acceptance of a version permanently authorizes you
582 | to choose that version for the Program.
583 |
584 | Later license versions may give you additional or different
585 | permissions. However, no additional obligations are imposed on any
586 | author or copyright holder as a result of your choosing to follow a
587 | later version.
588 |
589 | 15. Disclaimer of Warranty.
590 |
591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
599 |
600 | 16. Limitation of Liability.
601 |
602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
610 | SUCH DAMAGES.
611 |
612 | 17. Interpretation of Sections 15 and 16.
613 |
614 | If the disclaimer of warranty and limitation of liability provided
615 | above cannot be given local legal effect according to their terms,
616 | reviewing courts shall apply local law that most closely approximates
617 | an absolute waiver of all civil liability in connection with the
618 | Program, unless a warranty or assumption of liability accompanies a
619 | copy of the Program in return for a fee.
620 |
621 | END OF TERMS AND CONDITIONS
622 |
623 | How to Apply These Terms to Your New Programs
624 |
625 | If you develop a new program, and you want it to be of the greatest
626 | possible use to the public, the best way to achieve this is to make it
627 | free software which everyone can redistribute and change under these terms.
628 |
629 | To do so, attach the following notices to the program. It is safest
630 | to attach them to the start of each source file to most effectively
631 | state the exclusion of warranty; and each file should have at least
632 | the "copyright" line and a pointer to where the full notice is found.
633 |
634 |
635 | Copyright (C)
636 |
637 | This program is free software: you can redistribute it and/or modify
638 | it under the terms of the GNU General Public License as published by
639 | the Free Software Foundation, either version 3 of the License, or
640 | (at your option) any later version.
641 |
642 | This program is distributed in the hope that it will be useful,
643 | but WITHOUT ANY WARRANTY; without even the implied warranty of
644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
645 | GNU General Public License for more details.
646 |
647 | You should have received a copy of the GNU General Public License
648 | along with this program. If not, see .
649 |
650 | Also add information on how to contact you by electronic and paper mail.
651 |
652 | If the program does terminal interaction, make it output a short
653 | notice like this when it starts in an interactive mode:
654 |
655 | Copyright (C)
656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
657 | This is free software, and you are welcome to redistribute it
658 | under certain conditions; type `show c' for details.
659 |
660 | The hypothetical commands `show w' and `show c' should show the appropriate
661 | parts of the General Public License. Of course, your program's commands
662 | might be different; for a GUI interface, you would use an "about box".
663 |
664 | You should also get your employer (if you work as a programmer) or school,
665 | if any, to sign a "copyright disclaimer" for the program, if necessary.
666 | For more information on this, and how to apply and follow the GNU GPL, see
667 | .
668 |
669 | The GNU General Public License does not permit incorporating your program
670 | into proprietary programs. If your program is a subroutine library, you
671 | may consider it more useful to permit linking proprietary applications with
672 | the library. If this is what you want to do, use the GNU Lesser General
673 | Public License instead of this License. But first, please read
674 | .
--------------------------------------------------------------------------------
/heliano.py:
--------------------------------------------------------------------------------
1 | #!_INTERPRETERPYTHON_PATH_
2 |
3 | import os, re, subprocess, sys, argparse, shutil, random, gc
4 | from Bio import SeqIO
5 | from multiprocessing.pool import ThreadPool
6 | from collections import defaultdict
7 | import pybedtools as BT
8 |
9 | """
10 | This program is supposed to detect and classify different variants of Helitron-like elements: HLE1 and HLE2. Please follow the homepage of this software for more information: https://github.com/Zhenlisme/heliano.
11 | """
12 |
13 | # define Structure_search class for motif identification, including stem loop and terminal inverted repeats.
14 | class Structure_search:
15 | def __init__(self, genome, START=0):
16 | self.START = int(START)
17 | self.genome = genome
18 | self.genome_dict = SeqIO.parse(genome, 'fasta')
19 | self.genome_dict = {k.id: k.seq.upper() for k in self.genome_dict}
20 | self.maximum_length = sorted([len(self.genome_dict[i]) for i in self.genome_dict])[-1]
21 |
22 | def stem_loop(self, stem_loop_description, minus_tailone=1):
23 | ## Function to find hairpin structures. Start coord is 1 not 0
24 | rnabobopt = ''.join([os.path.basename(self.genome), '.stemloop.txt'])
25 | with open(rnabobopt, 'w') as rnabf:
26 | rnabob_program = subprocess.Popen(["rnabob", "-c", "-q", "-F", "-s", stem_loop_description, self.genome],
27 | stderr=subprocess.DEVNULL, stdout=rnabf)
28 | rnabob_program.wait()
29 | if not os.path.exists(rnabobopt):
30 | return []
31 | stem_loop_loc = []
32 |
33 | complement_dict = {'A': "T", "T": "A", "G": "C", "C": "G",
34 | "K": "M", "M": "K", "Y": "R", "R": "Y", "S": "S", "W": "W",
35 | "B": "V", "V": "B", "H": "D", "D": "H", "N": "N", "X": "X"}
36 |
37 | with open(rnabobopt, 'r') as F:
38 | for line in F:
39 | line = line.strip()
40 | if re.match('\d', line):
41 | splitline = re.split('\s+', line)[:3]
42 | chrid = splitline[2]
43 | ## To avoid rnabob bugs
44 | if int(splitline[1]) < 0:
45 | print(splitline)
46 | continue
47 | ## positive strand
48 | if int(splitline[0]) < int(splitline[1]):
49 | strand = '+'
50 | length = int(splitline[1]) - int(splitline[0]) + 1
51 | start = int(splitline[0]) + self.START
52 | end = start + length - 1
53 | end = end - 1 if minus_tailone else end ## To remove the T nucleotide
54 | ## negative strand
55 | else:
56 | strand = '-'
57 | length = int(splitline[0]) - int(splitline[1]) + 1
58 | start = int(splitline[0]) + self.START - length + 1
59 | end = start + length - 1
60 | start = start + 1 if minus_tailone else start ## To remove the T nucleotide
61 | else:
62 | seq = line.strip('|').split('|')
63 | helix_seq1, loop_seq, helix_seq2, tail_seq = seq
64 | stem_len = len(helix_seq1)
65 | loop_len = len(loop_seq)
66 | ## To revise the rnabob output. rnabob sometimes does not return as long as possible of helix. need to revise it.
67 | midpoint = int(len(loop_seq) / 2)
68 | for i in range(midpoint):
69 | ## if the left nucleotide is reverse-complementary to the right nucleotide
70 | if loop_seq[i] == complement_dict[loop_seq[-i - 1]]:
71 | stem_len += 1
72 | loop_len -= 2
73 | # The loop should exist.
74 | if loop_len >= 1:
75 | stem_loop_loc.append([chrid, str(start), str(end), str(stem_len), str(loop_len), strand])
76 | os.remove(rnabobopt)
77 | stem_loop_loc = sorted(stem_loop_loc, key=lambda x: [x[0], int(x[1])])
78 | return stem_loop_loc
79 |
80 | def regularexpression_match(self, pattern, strand='+'):
81 | ## Use helitronscanner lcv file to detect terminal region of helitron
82 | coord_record = []
83 | for chrm in self.genome_dict: ## start coord is 1 not 0
84 | if strand == '+':
85 | genom_seq = str(self.genome_dict[chrm]).upper()
86 | pCT_start_list = re.finditer(pattern, genom_seq)
87 | for p_coord in pCT_start_list:
88 | start = str(p_coord.start() + self.START + 1)
89 | end = str(p_coord.end() + self.START)
90 | coord_record.append([chrm, start, end])
91 | else:
92 | genom_seq = str(self.genome_dict[chrm].reverse_complement()).upper()
93 | sequence_length = len(genom_seq)
94 | pCT_start_list = re.finditer(pattern, genom_seq)
95 | for p_coord in pCT_start_list:
96 | end = str(sequence_length - p_coord.start() + self.START)
97 | start = str(sequence_length - p_coord.end() + self.START + 1)
98 | coord_record.append([chrm, start, end])
99 | coord_record = sorted(coord_record, key=lambda x: [x[0], int(x[1])])
100 | return coord_record
101 |
102 | def inverted_detection(self, sequencefile, minitirlen, maxtirlen, mintirdist, maxtirdist, seed):
103 | ## start coord is 1 not 0
104 | dbname = ''.join([os.path.basename(sequencefile), '.invdb'])
105 | invttirfile = ''.join([os.path.basename(sequencefile), '.inv.txt'])
106 | ## build database
107 | mkinvdb = subprocess.Popen(
108 | ['gt', 'suffixerator', '-db', sequencefile, '-indexname', dbname, '-mirrored', '-dna', '-suf', '-lcp',
109 | '-bck'], stderr=subprocess.DEVNULL, stdout=subprocess.DEVNULL)
110 | mkinvdb.wait()
111 | ## run tirvish
112 | with open(invttirfile, 'w') as invf:
113 | runinvsearch = subprocess.Popen(
114 | ['gt', 'tirvish', '-index', dbname, '-mintirlen', str(minitirlen), '-maxtirlen', str(maxtirlen),
115 | '-similar', str(Args.simtir), '-mintirdist', str(mintirdist), '-maxtirdist', str(maxtirdist), '-mintsd', '0',
116 | '-seed', str(seed), '-vic', '1', '-overlaps', 'all', '-xdrop', '0'], stderr=subprocess.DEVNULL, stdout=invf)
117 | runinvsearch.wait()
118 | invt_list = []
119 | ## The default output is in gff format, extract coord information and do filteration.
120 | with open(invttirfile, 'r') as F:
121 | for line in F:
122 | if line.startswith('#'):
123 | continue
124 | splitlines = line.rstrip().split('\t')
125 | if splitlines[2] == 'repeat_region':
126 | chrmid = splitlines[0]
127 | id = splitlines[8].replace('ID=', '')
128 | t = 1
129 | elif splitlines[2] == 'terminal_inverted_repeat_element':
130 | sim = re.findall('tir_similarity=(\d+\.\d+)', splitlines[8])[0]
131 | elif splitlines[2] == 'terminal_inverted_repeat':
132 | if t == 1:
133 | left_start = str(int(splitlines[3]) + self.START)
134 | left_end = str(int(splitlines[4]) + self.START)
135 | left_expand = '-'.join([left_start, left_end])
136 | invt_length_left = int(splitlines[4]) - int(splitlines[3]) + 1
137 | t += 1
138 | else:
139 | right_start = str(int(splitlines[3]) + self.START)
140 | right_end = str(int(splitlines[4]) + self.START)
141 | right_expand = '-'.join([right_start, right_end])
142 | invt_length_right = int(splitlines[4]) - int(splitlines[3]) + 1
143 | ## length of inverted sequences should be greater than 11 and shorter than 18
144 | if invt_length_left >= 12 and invt_length_right >= 12 and invt_length_left <= 17 and invt_length_right <= 17:
145 | invt_list.append([chrmid, str(left_start), str(right_end), left_expand, right_expand,
146 | (invt_length_right + invt_length_left) / 2, sim])
147 |
148 | invt_list = sorted(invt_list, key=lambda x: int(x[1]))
149 | os.remove(invttirfile)
150 | os.system('rm %s*' % dbname)
151 | return invt_list
152 |
153 | # define Homologous_search class to find Helitron-like transposase domain and theri auto/non-auto relatives
154 | class Homologous_search:
155 | def __init__(self, rep_hel_hmm, genome, wkdir, headerfile, window, distance_domain, distance_na, pvalue, process_num, codetable):
156 | self.rep_hel_hmm = rep_hel_hmm
157 | self.genome = genome
158 | self.genome_dict = SeqIO.parse(genome, 'fasta')
159 | self.genome_dict = {k.id: k.seq.upper() for k in self.genome_dict}
160 | self.process_num = int(process_num)
161 | self.wkdir = wkdir
162 | self.headerpatternfile = headerfile
163 | self.window = window
164 | self.distance_domain = distance_domain
165 | self.distance_na = defaultdict(lambda :int(distance_na))
166 | self.pvalue = float(pvalue)
167 | self.cutoff_flank = float(Args.flank_sim)
168 | if Args.terminal_sequence:
169 | self.pairfile = os.path.abspath(Args.terminal_sequence)
170 | sys.stdout.write('You added the pairfile %s.\n' % self.pairfile)
171 | if not os.path.isfile(self.pairfile):
172 | sys.stderr.write("Error: The pair list file doesn't exist, please check!\n")
173 | exit(0)
174 | # To transform the header file to regular expression.
175 | with open(headerfile, 'r') as F:
176 | headerpattern_list = F.read().rstrip().split('\n')
177 | self.headerpattern = '|'.join(headerpattern_list) if not Args.IS1 else '|'.join([''.join(['A', i]) for i in headerpattern_list])
178 | #self.headerpattern = ''.join(['(?=(', self.headerpattern, '))'])
179 | if not os.path.exists(self.wkdir):
180 | os.mkdir(self.wkdir)
181 | os.chdir(self.wkdir)
182 | else:
183 | sys.stderr.write('Error: Directory %s exists. Please change!\n' % self.wkdir)
184 | exit(0)
185 |
186 | ## To check the pair list file
187 | self.terminalfile_dict = defaultdict(lambda: defaultdict(dict))
188 | self.prepair_dict = defaultdict(list)
189 | if Args.terminal_sequence:
190 | pairdict = defaultdict(list)
191 | with open(self.pairfile, 'r') as F:
192 | for line in F:
193 | splitline = line.rstrip().split('\t')
194 | pairdict[splitline[0]].append(splitline[1:])
195 | pairdir = 'Pre_pair/'
196 | if not os.path.exists(pairdir):
197 | os.mkdir(pairdir)
198 | for classname in pairdict:
199 | leftfile = os.path.abspath(''.join([pairdir, classname, '.left.pre.fa']))
200 | rightfile = os.path.abspath(''.join([pairdir, classname, '.right.pre.fa']))
201 | self.terminalfile_dict[classname]['left'] = leftfile
202 | self.terminalfile_dict[classname]['right'] = rightfile
203 | recorder_dict = {}
204 | with open(leftfile, 'w') as left_w, open(rightfile, 'w') as right_w:
205 | for line in pairdict[classname]:
206 | leftname, leftseq, rightname, rightseq = line
207 | leftname, rightname = ''.join([leftname, 'pre']), ''.join([rightname, 'pre'])
208 | ## To avoid repeatly writing
209 | if leftname not in recorder_dict:
210 | left_w.write(''.join(['>', leftname, '\n', leftseq, '\n']))
211 | if rightname not in recorder_dict:
212 | right_w.write(''.join(['>', rightname, '\n', rightseq, '\n']))
213 | self.prepair_dict[leftname].append(rightname)
214 | recorder_dict[leftname] = 1
215 | recorder_dict[rightname] = 1
216 |
217 | if Args.dis_denovo:
218 | if not self.terminalfile_dict:
219 | sys.stderr.write('Error: The pair list file is either not specified or empty. See parameter "-ts".\n')
220 | exit(0)
221 | else:
222 | sys.stdout.write(
223 | 'You will not search for the terminal structures of HLE in a de-novo way, but by using the pair file: %s.\n' % self.pairfile)
224 | self.bedtoolstmp = os.path.abspath('BedtoolsTMP')
225 | if not os.path.exists(self.bedtoolstmp):
226 | os.mkdir(self.bedtoolstmp)
227 | BT.set_tempdir(self.bedtoolstmp)
228 |
229 | CWD = os.getcwd()
230 | self.genome_size = '%s/Genome.size' % CWD
231 | self.chrm_size = {i:len(self.genome_dict[i]) for i in self.genome_dict}
232 | genome_size = list(self.chrm_size.items())
233 | genome_size = sorted(genome_size, key=lambda x: x[0])
234 | with open(self.genome_size, 'w') as F:
235 | F.writelines([''.join([i[0], '\t', str(i[1]), '\n']) for i in genome_size])
236 |
237 | ## To determine the evalue for short-sequence blastn, set the bit-score cutoff as 30, the evalue cutoff should follow the formula: m*n/(2**30)
238 | sum_genomesize = sum([i[1] for i in genome_size])
239 | self.evalue_blastn = sum_genomesize * 30 / (2 ** int(Args.score))
240 |
241 | # To define stem_loop structure ending with CTRR motif of Helitron
242 | self.CTRR_stem_loop_description = '%s/CTRR_stem_loop.descr' % CWD
243 | CTRR_description = """r1 s1 r1' s2\nr1 1:1 NNNNN[10]:[10]NNNNN TGCA\ns1 0 N[7]\ns2 0 N[15]CTRR%s\n"""
244 | # Add 'T' in the end if user limitted the 'A-T' insertion site for Helitron.
245 | CTRR_description = CTRR_description % 'T' if Args.IS1 else CTRR_description % ''
246 | with open(self.CTRR_stem_loop_description, 'w') as F:
247 | F.write(CTRR_description)
248 |
249 | # To define stem_loop structure of HLE2
250 | self.subtir_description = '%s/subtir_stem_loop.descr' % CWD
251 | # Add 'T' in the end if user limitted the 'T-T' insertion site for HLE2.
252 | if Args.IS2:
253 | subtir_description = """r1 s1 r1' s2\nr1 1:1 NNNNN[10]:[10]NNNNN TGCA\ns1 0 N[15]\ns2 0 NNNNN[10]T\n"""
254 | else:
255 | subtir_description = """r1 s1 r1' s2\nr1 1:1 NNNNN[10]:[10]NNNNN TGCA\ns1 0 N[15]\ns2 0 NNNNNN[2]\n"""
256 | with open(self.subtir_description, 'w') as F:
257 | F.write(subtir_description)
258 |
259 | dbdir = 'GenomeDB/'
260 | if not os.path.exists(dbdir):
261 | os.mkdir(dbdir)
262 | self.genomedb = ''.join([CWD, '/', dbdir, os.path.basename(self.genome), '.blastndb'])
263 | makeblastndb = subprocess.Popen(['makeblastdb', '-dbtype', 'nucl', '-in', self.genome, '-out', self.genomedb],
264 | stderr=subprocess.DEVNULL, stdout=subprocess.DEVNULL)
265 | makeblastndb.wait()
266 |
267 | ## code table
268 | code_table_dict = {0: (0, "Standard"), 1: (6, "Ciliate Macronuclear and Dasycladacean"),
269 | 2: (15, "Blepharisma Macronuclear"), 3: (22, "Scenedesmus obliquus")}
270 | self.codetable = code_table_dict[codetable]
271 | sys.stdout.write('You are using the (%s) code to predict ORFs.\n' % self.codetable[1])
272 | def hmmsearch(self, subgenome):
273 | # Run hmmersearch program to search for Helitron-like transposase
274 | orf_file = ''.join([subgenome, '.orf'])
275 | hmm_opt = ''.join([subgenome, '.hmmsearch.out'])
276 |
277 | #The index of getorf output starts from 1, not 0
278 | # Use getorf to predicte open reading frames for a given genome
279 | get_orf = subprocess.Popen(['getorf', '-sequence', subgenome, '-outseq', orf_file, '-minsize', '100',
280 | '-maxsize', '30000', '-table', str(self.codetable[0])],
281 | stderr=subprocess.DEVNULL)
282 | get_orf.wait()
283 |
284 | Rep_dict, Hel_dict = defaultdict(list), defaultdict(list)
285 | Rep_opline, Hel_opline = [], []
286 | if os.path.getsize(orf_file):
287 | run_hmmsearch = subprocess.Popen(
288 | ['hmmsearch', '--domtblout', hmm_opt, '--noali', '-E', '1e-3', self.rep_hel_hmm, orf_file],
289 | stdout=subprocess.DEVNULL)
290 | run_hmmsearch.wait()
291 | os.remove(orf_file)
292 | else:
293 | return Rep_opline, Hel_opline
294 | if not os.path.exists(hmm_opt):
295 | return Rep_opline, Hel_opline
296 |
297 | # To parser hmmsearch output
298 | with open(hmm_opt, 'r') as F:
299 | for line in F:
300 | if line.startswith('#'):
301 | continue
302 | splitlines = re.split('\s+', line.rstrip())
303 | domain, sub_class = splitlines[3].split('_')
304 | subchrname = "_".join(splitlines[0].split('_')[:-1])
305 | chrm_name, START = subchrname.split('startat')
306 | start, end = re.findall('\[(\d+)\s+-\s+(\d+)\]', line)[0]
307 | start = str(int(start) + int(START))
308 | end = str(int(end) + int(START))
309 |
310 | aa_start, aa_end = splitlines[19:21]
311 | score = splitlines[7]
312 | c_evalue, i_evalue = splitlines[11:13]
313 | if float(c_evalue) > 1e-5 or float(i_evalue) > 1e-5:
314 | continue
315 | ## To transform amino acide coord to nucleotide coord
316 | if int(end) > int(start):
317 | strand = '+'
318 | nuc_start = int(aa_start) * 3 - 3 + int(start)
319 | nuc_end = int(aa_end) * 3 + int(start) - 1
320 | orf_loc = '-'.join([start, end])
321 | else:
322 | nuc_end = int(start) - 3 * int(aa_start) + 3
323 | nuc_start = int(start) - 3 * int(aa_end) + 1
324 | strand = '-'
325 | orf_loc = '-'.join([end, start])
326 | if domain.startswith('Hel'):
327 | Hel_dict[splitlines[0]].append(
328 | [chrm_name, str(nuc_start), str(nuc_end), sub_class, score, strand, orf_loc])
329 | else:
330 | Rep_dict[splitlines[0]].append(
331 | [chrm_name, str(nuc_start), str(nuc_end), sub_class, score, strand, orf_loc])
332 | for key in Hel_dict:
333 | hel_candidate = sorted(Hel_dict[key], key=lambda x: float(x[4]))[-1] ## Select the case with highest score.
334 | Hel_opline.append(hel_candidate)
335 | for key in Rep_dict:
336 | rep_candidate = sorted(Rep_dict[key], key=lambda x: float(x[4]))[-1] ## Select the case with highest score.
337 | Rep_opline.append(rep_candidate)
338 | try:
339 | Hel_bed = BT.BedTool([BT.create_interval_from_list(line) for line in Hel_opline]).sort()
340 | Rep_bed = BT.BedTool([BT.create_interval_from_list(line) for line in Rep_opline]).sort()
341 | return Rep_bed, Hel_bed
342 | except:
343 | return [], []
344 |
345 | def intersect(self, location1, location2, slip=0, lportion=0.0, rportion=0.0, bool_and=1):
346 | # Define intersect function to check if two intervals are intersected or not, similar to bedtools intersect
347 | location1 = sorted([int(i) for i in location1])
348 | location2 = sorted([int(i) for i in location2])
349 | if location1[0] - slip > location2[1] or location1[1] < location2[0] - slip:
350 | return False
351 | else:
352 | total_list = sorted([location1[0], location1[1], location2[0], location2[1]])
353 | portion1 = (total_list[2] - total_list[1] + 1) / (
354 | location1[1] - location1[0] + 1) ## how much proportion the intersected sequence occupiedonseq1
355 | portion2 = (total_list[2] - total_list[1] + 1) / (
356 | location2[1] - location2[0] + 1) ## how much proportion the intersected sequence occupiedonseq2
357 | if bool_and:
358 | if portion1 >= lportion and portion2 >= rportion:
359 | return True
360 | else:
361 | return False
362 | else:
363 | if portion1 >= lportion or portion2 >= rportion:
364 | return True
365 | else:
366 | return False
367 |
368 | def merge_bedfile(self, BedInput, window=1500):
369 | # Define function to merge two distance-close genomic features
370 | cluster_bed = BedInput.cluster(d=window, s=True)
371 | merge_dict = defaultdict(list)
372 | merge_list = []
373 | for line in cluster_bed:
374 | line = list(line)
375 | cluster = line[-1]
376 | merge_dict[cluster].append(line[:-1])
377 |
378 | for cluster in merge_dict:
379 | ## To record the domain location.
380 | coordlist = merge_dict[cluster]
381 | coord_set = [int(i[1]) for i in coordlist]
382 | coord_set.extend([int(i[2]) for i in coordlist])
383 | coord_set = sorted(coord_set)
384 | start = coord_set[0]
385 | stop = coord_set[-1]
386 | strand = coordlist[0][5]
387 | ## To determain sub_class, select the case with highest score
388 | sub_class = sorted(coordlist, key=lambda x: float(x[4]))[-1][3]
389 | ## To merge the ORF location
390 | orf_list = sorted([int(b) for i in coordlist for b in i[-1].split('-')])
391 | orf_coord = '-'.join([str(orf_list[0]), str(orf_list[-1])])
392 | chrm_id = coordlist[0][0]
393 | merge_list.append([chrm_id, str(start), str(stop), sub_class, orf_coord, strand])
394 | # merge_list = sorted(merge_list, key=lambda x: [x[0], int(x[1])])
395 | if merge_list:
396 | merge_bed = BT.BedTool([BT.create_interval_from_list(line) for line in merge_list]).sort()
397 | return merge_bed
398 | else:
399 | return 0
400 |
401 | def parser_hmmsearch(self, Rep_bed, Hel_bed, subgenome):
402 | # To find Rep-Hel structure which might imply a possible Helitron-like transposases.
403 | if not Rep_bed or not Hel_bed:
404 | return []
405 |
406 | ## To merge helicase or rep domain splicing sites (helitron-like transposase contain introns)
407 | merge_hel = self.merge_bedfile(Hel_bed, window=1500)
408 | merge_rep = self.merge_bedfile(Rep_bed, window=1500)
409 | if not merge_hel or not merge_rep: ## Either hel or rep data is null
410 | return []
411 |
412 | ## To find rep and helicase gene pairs that rep is less than self.distance_domain bp upstream of hel
413 | joint_rephel = merge_rep.window(merge_hel, l=0, r=int(self.distance_domain), sm=True, sw=True)
414 | bedlist = []
415 | for line in joint_rephel:
416 | splitlines = list(line)
417 | strand = splitlines[5]
418 | chrm = splitlines[0]
419 | rep_start, rep_end = splitlines[1:3]
420 | hel_start, hel_end = splitlines[7:9]
421 |
422 | # If the helicase and rep domain have a intersection, skip
423 | if self.intersect([int(rep_start), int(rep_end)], [int(hel_start), int(hel_end)], lportion=0.2, rportion=0.2):
424 | continue
425 | rep_orf = splitlines[4].split('-')
426 | hel_orf = splitlines[10].split('-')
427 | loc = sorted([rep_start, rep_end, hel_start, hel_end], key=lambda x: int(x))
428 | start, end = loc[0], loc[-1] ## They are REP and Helicase domain region
429 | bedlist.append((chrm, int(start), int(end), '-'.join([rep_start, rep_end]), '-'.join([hel_start, hel_end]),
430 | strand, splitlines[3], splitlines[9], 'NA'))
431 | bedlist = list(set(bedlist)) ## To avoid duplicates
432 | bedlist = sorted(bedlist, key=lambda x: [x[0], x[1]])
433 | return bedlist
434 |
435 | def heltentron_terminal(self, helentron_bed):
436 | # Define function to try to recover Helentron terminal region (stem-loop structure) which is behind the right part of TIRs
437 | extend_seq = []
438 | opbed_list = []
439 | extend_file = ''.join([helentron_bed, '.fa'])
440 | extend_dict = {}
441 | extend_dict = defaultdict(list)
442 | ## To output all extend rigions into one single file
443 | #init_num = 1
444 | with open(helentron_bed, 'r') as F:
445 | for line in F:
446 | feature = line.rstrip().split('\t')
447 | chrmid, start, stop, name, score, strand, pvalue, Bscore, classname, mobile_type, insertion_name = feature
448 | start, stop = int(start), int(stop)
449 | if float(Bscore) == 0: ## without terminal signals
450 | opbed_list.append([chrmid, str(start), str(stop), name, score, strand, pvalue, Bscore, classname, mobile_type, insertion_name])
451 | continue
452 |
453 | if strand == '+':
454 | extend_id = '-'.join([chrmid, str(start), str(stop), 'p'])
455 | if '.2' not in classname:
456 | detect_seq = str(self.genome_dict[chrmid][stop: stop + 80])
457 | StemStart = stop
458 | else: ## Helentron.2, the stem loop is at 5'end
459 | terminal_start = 0 if start - 80 < 0 else start - 80
460 | detect_seq = str(self.genome_dict[chrmid][terminal_start: start])
461 | StemStart = terminal_start
462 | ## To remove short seequence
463 | if len(detect_seq) < 17:
464 | continue
465 | ## To remove N rich seq
466 | N_count = detect_seq.count('N')
467 | if N_count >= 5:
468 | continue
469 | ## The last element is the initial start for terminal detection region
470 | extend_dict[extend_id].append([chrmid, str(start), str(stop), name, score, strand, pvalue, Bscore,
471 | classname, mobile_type, insertion_name, StemStart])
472 | extend_seq.append(''.join(['>', extend_id, '\n', detect_seq, '\n']))
473 | else:
474 | extend_id = '-'.join([chrmid, str(start), str(stop), 'n'])
475 | if '.2' not in classname:
476 | terminal_start = 0 if start - 80 < 0 else start - 80
477 | detect_seq = str(self.genome_dict[chrmid][terminal_start: start])
478 | StemStart = terminal_start
479 | else: ## Helentron.2, the stem loop is at 3'end
480 | detect_seq = str(self.genome_dict[chrmid][stop: stop + 80])
481 | StemStart = stop
482 | ## To remove short seequence
483 | if len(detect_seq) < 17:
484 | continue
485 | ## To remove N rich seq
486 | N_count = detect_seq.count('N')
487 | if N_count >= 5:
488 | continue
489 | ## The last element is the initial start for terminal detection region
490 | extend_dict[extend_id].append([chrmid, str(start), str(stop), name, score, strand, pvalue, Bscore,
491 | classname, mobile_type, insertion_name, StemStart])
492 | extend_seq.append(''.join(['>', extend_id, '\n', detect_seq, '\n']))
493 | if not extend_seq: ## means empty
494 | return helentron_bed
495 | with open(extend_file, 'w') as F:
496 | F.writelines(extend_seq)
497 | ## stem loop detection
498 | stem_loop_list = Structure_search(extend_file, START=0).stem_loop(self.subtir_description, minus_tailone=int(Args.IS2))
499 | stem_loop_dict = defaultdict(list)
500 | [stem_loop_dict[i[0]].append(i) for i in stem_loop_list]
501 |
502 | ## To select the nearest candidate
503 | for extend_id in stem_loop_dict:
504 | for sublist in extend_dict[extend_id]:
505 | chrmid, start, stop, name, score, strand, pvalue, Bscore, classname, mobile_type, insertion_name, e_start = sublist
506 | if extend_id.endswith('p'):
507 | stem_loop = [i for i in stem_loop_dict[extend_id] if i[5] == '+']
508 | ## order by start position (closer), stem length (longer), loop length (shorter), total length (shorter)
509 | if '.2' not in classname:
510 | stem_loop = sorted(stem_loop, key = lambda x: [x[0], int(x[1]), -int(x[3]), int(x[4]), int(x[2]) - int(x[1])])
511 | if stem_loop:
512 | stem_start, stem_stop = stem_loop[0][1:3]
513 | stem_stop = int(stem_stop) + int(e_start)
514 | opbed_list.append([chrmid, start, str(stem_stop), name, score, strand,
515 | pvalue, Bscore, classname, mobile_type, insertion_name])
516 | else:
517 | stem_loop = sorted(stem_loop, key=lambda x: [x[0], -int(x[2]), -int(x[3]), int(x[4]), int(x[2]) - int(x[1])])
518 | if stem_loop:
519 | stem_start, stem_stop = stem_loop[0][1:3]
520 | stem_start = int(stem_start) + int(e_start)
521 | opbed_list.append([chrmid, str(stem_start), stop, name, score, strand,
522 | pvalue, Bscore, classname, mobile_type, insertion_name])
523 | if not stem_loop:
524 | opbed_list.append([chrmid, start, stop, name, score, strand, pvalue, Bscore, classname, mobile_type, insertion_name])
525 | continue
526 | else:
527 | stem_loop = [i for i in stem_loop_dict[extend_id] if i[5] == '-']
528 | ## order by end position (longer), stem length (longer), loop length (shorter), total length (shorter)
529 | if '.2' not in classname:
530 | stem_loop = sorted(stem_loop, key=lambda x: [x[0], -int(x[2]), -int(x[3]), int(x[4]), int(x[2]) - int(x[1])])
531 | if stem_loop:
532 | stem_start, stem_stop = stem_loop[0][1:3]
533 | stem_start = int(stem_start) + int(e_start)
534 | opbed_list.append([chrmid, str(stem_start), stop, name, score, strand,
535 | pvalue, Bscore, classname, mobile_type, insertion_name])
536 | else:
537 | stem_loop = sorted(stem_loop, key=lambda x: [x[0], int(x[1]), -int(x[3]), int(x[4]),
538 | int(x[2]) - int(x[1])])
539 | if stem_loop:
540 | stem_start, stem_stop = stem_loop[0][1:3]
541 | stem_stop = int(stem_stop) + int(e_start)
542 | opbed_list.append([chrmid, start, str(stem_stop), name, score, strand,
543 | pvalue, Bscore, classname, mobile_type, insertion_name])
544 | if not stem_loop:
545 | opbed_list.append([chrmid, start, stop, name, score, strand, pvalue, Bscore, classname, mobile_type, insertion_name])
546 | continue
547 | ### To complement the candidates whose stem loop signal doesn't exist.
548 | remained_cases = set(extend_dict.keys()) - set(stem_loop_dict.keys())
549 | for key in remained_cases:
550 | for sublist in extend_dict[key]:
551 | opbed_list.append(sublist[:11])
552 | ### To creat bedtools objective
553 | #opbed = BT.BedTool([BT.create_interval_from_list(line) for line in opbed_list])
554 | with open(helentron_bed, 'w') as F:
555 | F.write('\n'.join(['\t'.join(line) for line in opbed_list]))
556 | F.write('\n')
557 | os.remove(extend_file)
558 |
559 | def intergrated_program(self, subgenome):
560 | # This function is used to recover terminal signals of Helitron-like elements (TIRs for HLE2; TC... motif and ...CTRR motif for Helitron)
561 | rep_hmmsearch_opt, hel_hmmsearch_opt = self.hmmsearch(subgenome)
562 | ORF_list = self.parser_hmmsearch(rep_hmmsearch_opt, hel_hmmsearch_opt, subgenome)
563 | sys.stdout.write('Find %s rep-hel blocks in %s.\n' % (str(len(ORF_list)), os.path.basename(subgenome).replace('.fa', '')))
564 | RC_total_candidate = []
565 | for Helitron_candidate in ORF_list:
566 | ORF_chrmid = Helitron_candidate[0]
567 | ORF_start = int(Helitron_candidate[1])
568 | ORF_stop = int(Helitron_candidate[2])
569 | rep_loc = Helitron_candidate[3]
570 | hel_loc = Helitron_candidate[4]
571 | strand = Helitron_candidate[5]
572 | chrm_limit = len(self.genome_dict[ORF_chrmid])
573 | rep_name, hel_name = Helitron_candidate[6:8]
574 |
575 | ## To decide class name
576 | if hel_name == 'HLE1' and rep_name == 'HLE1':
577 | classname = 'HLE1'
578 | elif hel_name == 'HLE2' and rep_name == 'HLE2':
579 | classname = 'HLE2'
580 | else:
581 | classname = '_or_'.join([rep_name, hel_name])
582 | ## To produce orf id which will be used as sole identifier of terminal signals.
583 | ORFID = '-'.join([ORF_chrmid, str(ORF_start), str(ORF_stop)])
584 |
585 | ## To decide to run denovo structural search or not. if not, just save the ORFs
586 | if Args.dis_denovo:
587 | RC_total_candidate.append(
588 | (ORF_chrmid, str(ORF_start), str(ORF_stop), strand, classname, (), (), ORFID))
589 | continue
590 |
591 | temp_name_for_helitron = '-'.join([ORF_chrmid, str(ORF_start), str(ORF_stop)])
592 | expansion_all_seqname = ''.join([temp_name_for_helitron, '.expansion.fa'])
593 | left_seqname = ''.join([temp_name_for_helitron, '.left.fa'])
594 | right_seqname = ''.join([temp_name_for_helitron, '.right.fa'])
595 |
596 | # Define regions to search for terminal signals
597 | left_boundary = ORF_start - self.window
598 | right_boundary = ORF_stop + self.window
599 |
600 | ## left and right boundary should be within chromosome ranges
601 | if left_boundary <= 0:
602 | left_boundary = 1
603 | if right_boundary >= chrm_limit:
604 | right_boundary = chrm_limit
605 |
606 | ## To avoid get big tandem heltron-like elements
607 | Helitron_candidate_index = ORF_list.index(Helitron_candidate)
608 | # Left boundary should not touch last Rep-Hel region
609 | if Helitron_candidate_index >= 1: ## not the fist one
610 | last_candidate = ORF_list[Helitron_candidate_index - 1]
611 | last_stop = last_candidate[2]
612 | left_boundary = last_stop if left_boundary < last_stop else left_boundary
613 | # Right boundary should not touch the next Rep-Hel region
614 | if Helitron_candidate_index < len(ORF_list) - 1: ## not the last one
615 | next_candidate = ORF_list[Helitron_candidate_index + 1]
616 | next_start = next_candidate[1]
617 | right_boundary = next_start if right_boundary > next_start else right_boundary
618 |
619 | # To output extended sequences to fasta files
620 | left_seq = str(self.genome_dict[ORF_chrmid][left_boundary - 1: ORF_start])
621 | right_seq = str(self.genome_dict[ORF_chrmid][ORF_stop: right_boundary])
622 | expansion_all_seq = str(self.genome_dict[ORF_chrmid][left_boundary - 1: right_boundary])
623 | with open(expansion_all_seqname, 'w') as F:
624 | F.write(''.join(['>', ORF_chrmid, '\n', expansion_all_seq, '\n']))
625 | with open(left_seqname, 'w') as F:
626 | F.write(''.join(['>', ORF_chrmid, '\n', left_seq, '\n']))
627 | with open(right_seqname, 'w') as F:
628 | F.write(''.join(['>', ORF_chrmid, '\n', right_seq, '\n']))
629 |
630 | # Candiadte is Helitron, try to search for left terminal signals in left extension and right terminal signals in right extension.
631 | if classname == 'HLE1':
632 | if strand == '+':
633 | # left terminal signals are TC... like
634 | TC_list = Structure_search(genome=left_seqname, START=left_boundary - 1).regularexpression_match(self.headerpattern, '+')
635 | # right terminal signals are stem-loop structures ending with CTRR motif.
636 | Stem_loop_list = Structure_search(genome=right_seqname, START=ORF_stop).stem_loop(
637 | self.CTRR_stem_loop_description, minus_tailone=int(Args.IS1))
638 | Stem_loop_list = [i for i in Stem_loop_list if i[-1] == '+'] ## To select the positive strand motif
639 | # To reduce one if user set 'AT' insertion because the A was added at the begaining of header regular expression
640 | if Args.IS1:
641 | TC_list = [[line[0], str(int(line[1])+1), line[2]] for line in TC_list]
642 | else:
643 | TC_list = Structure_search(genome=right_seqname, START=ORF_stop).regularexpression_match(
644 | self.headerpattern, '-')
645 | Stem_loop_list = Structure_search(genome=left_seqname, START=left_boundary - 1).stem_loop(
646 | self.CTRR_stem_loop_description, minus_tailone=int(Args.IS1))
647 | Stem_loop_list = [i for i in Stem_loop_list if i[-1] == '-'] ## To select the negative strand motif
648 | if Args.IS1:
649 | TC_list = [[line[0], line[1], str(int(line[2]) - 1)] for line in TC_list]
650 | RC_total_candidate.append((
651 | ORF_chrmid, str(ORF_start), str(ORF_stop), strand, classname, tuple(TC_list),
652 | tuple(Stem_loop_list), ORFID))
653 |
654 | # Candidate is HLE2
655 | else:
656 | # Size of terminal inverted sequences should be greater than the size of predicted transposase
657 | mini_dist_tir = ORF_stop - ORF_start
658 | # Size of terminal inverted sequences should be less than the size of extension
659 | max_dist_tir = 2 * int(self.window) + ORF_stop - ORF_start
660 |
661 | invt_list = Structure_search(genome=expansion_all_seqname, START=left_boundary - 1).inverted_detection(
662 | expansion_all_seqname, 9, 20, mini_dist_tir, max_dist_tir, 8)
663 | ## To keep the case that fully covered with ORF region
664 | invt_list = [i for i in invt_list if int(i[3].split('-')[1]) - ORF_start <= 0 and int(i[4].split('-')[0]) - ORF_stop >= 0]
665 | left_list, right_list = [], []
666 | for inv in invt_list:
667 | if strand == '+':
668 | left_loc = inv[3].split('-')
669 | right_loc = inv[4].split('-')
670 | if Args.IS2:
671 | is_start = int(left_loc[0]) - 2 ## To get the insertion site index. The real index starts from 1, need to transform to python index.
672 | is_seq = str(self.genome_dict[ORF_chrmid][is_start:is_start+1]).upper()
673 | if is_seq == 'T':
674 | left_list.append((ORF_chrmid, int(left_loc[0]), int(left_loc[1])))
675 | right_list.append((ORF_chrmid, int(right_loc[0]), int(right_loc[1])))
676 | else:
677 | left_list.append((ORF_chrmid, int(left_loc[0]), int(left_loc[1])))
678 | right_list.append((ORF_chrmid, int(right_loc[0]), int(right_loc[1])))
679 | else:
680 | left_loc = inv[4].split('-')
681 | right_loc = inv[3].split('-')
682 | if Args.IS2:
683 | is_start = int(left_loc[1])
684 | is_seq = str(self.genome_dict[ORF_chrmid][is_start:is_start + 1]).upper()
685 | if is_seq == 'A': ## The complementary of T is A
686 | left_list.append((ORF_chrmid, int(left_loc[0]), int(left_loc[1])))
687 | right_list.append((ORF_chrmid, int(right_loc[0]), int(right_loc[1])))
688 | else:
689 | left_list.append((ORF_chrmid, int(left_loc[0]), int(left_loc[1])))
690 | right_list.append((ORF_chrmid, int(right_loc[0]), int(right_loc[1])))
691 | RC_total_candidate.append((ORF_chrmid, str(ORF_start), str(ORF_stop), strand, classname,
692 | tuple(left_list), tuple(right_list), ORFID))
693 | os.remove(expansion_all_seqname)
694 | os.remove(left_seqname)
695 | os.remove(right_seqname)
696 | return RC_total_candidate
697 |
698 | def cdhitest_clust(self, input_fa, opfile, helitron_type, id=0.8):
699 | # This function is for clustering of highly identity sequences
700 | cons_name = '.'.join([helitron_type, 'reduce.temp'])
701 | cluster_file = '.'.join([cons_name, 'clstr'])
702 | run_cluster = subprocess.Popen(
703 | ['cd-hit-est', '-i', input_fa, '-o', cons_name, '-d', '0', '-aS', '0.8', '-c', str(id), '-G', '1', '-g',
704 | '1', '-b', '500', '-T', str(self.process_num), '-M', '0'], stdout=subprocess.DEVNULL)
705 | run_cluster.wait()
706 |
707 | # To get classification information
708 | cluster_dict = {}
709 | with open(cluster_file, 'r') as F:
710 | for line in F:
711 | if line.startswith('>'):
712 | cluster_name = '_'.join([helitron_type, line.strip('>\n').split(' ')[1]])
713 | else:
714 | insertion_name = line.split('...')[0].split(', >')[1]
715 | cluster_dict[insertion_name] = cluster_name
716 |
717 | opseq = ''
718 | with open(cons_name, 'r') as F:
719 | for line in F:
720 | if line.startswith(">"):
721 | insertion_name = line.strip('>\n')
722 | cluster_name = cluster_dict[insertion_name]
723 | opseq += ''.join(['>', cluster_name, '\n'])
724 | else:
725 | opseq += line
726 | with open(opfile, 'w') as F:
727 | F.write(opseq)
728 | if os.path.exists(cons_name):
729 | os.remove(cons_name)
730 | os.remove(cluster_file)
731 | cluster_file = '.'.join([helitron_type, 'clust.info2'])
732 | with open(cluster_file, 'w') as F:
733 | F.writelines(["".join([k, "\t", cluster_dict[k], '\n']) for k in cluster_dict])
734 | return cluster_dict
735 |
736 | def split_list(self, numbers, num_groups):
737 | # Calculate target sum for each group
738 | total_sum = sum([i[1] for i in numbers])
739 | target_sum = total_sum / num_groups
740 |
741 | # Sort numbers in descending order
742 | numbers = sorted(numbers, key=lambda x: -x[1])
743 | # Split numbers into groups with similar sums
744 | groups = [[] for i in range(num_groups)]
745 | group_sums = [0] * num_groups
746 | for number in numbers:
747 | # Find the group with the smallest current sum and add the number to it
748 | min_sum_index = group_sums.index(min(group_sums))
749 | groups[min_sum_index].append(number)
750 | group_sums[min_sum_index] += number[1]
751 | return groups
752 |
753 | def split_genome(self, chunk_size=200000000, flanking_size=50000, num_groups=2):
754 | # To split big genomes into small chunks
755 | if not os.path.exists('genomes'):
756 | os.mkdir('genomes')
757 | subgenome_list = []
758 | for chrm in self.genome_dict:
759 | seq_len = len(self.genome_dict[chrm])
760 | if seq_len < 1000: ##Skip chrms whose length is shorter than 1000 bp
761 | sys.stdout.write(
762 | "Chrm %s will not be used to detect autonomous HLEs as its length is shorter than 1000 bp\n" % chrm)
763 | continue
764 | subgenome_list.append((chrm, seq_len))
765 |
766 | num_groups = num_groups if num_groups <= len(subgenome_list) else len(subgenome_list)
767 | ### To split the genomes into several files.
768 | # Calculate target sum for each group
769 | total_sum = sum([i[1] for i in subgenome_list])
770 | target_sum = total_sum / num_groups
771 | # Sort numbers in descending order
772 | numbers = sorted(subgenome_list, key=lambda x: -x[1])
773 | # Split numbers into groups with similar sums
774 | groups = [[] for i in range(num_groups)]
775 | group_sums = [0] * num_groups
776 | for number in numbers:
777 | # Find the group with the smallest current sum and add the number to it
778 | min_sum_index = group_sums.index(min(group_sums))
779 | groups[min_sum_index].append(number)
780 | group_sums[min_sum_index] += number[1]
781 |
782 | ## To split big chrms into smaller chunks.
783 | subgenome_list = []
784 | init_num = 1
785 | for subgroup in groups:
786 | subgenome = ''.join(['genomes/subgenome', str(init_num), '.fa'])
787 | init_num += 1
788 | with open(subgenome, 'w') as F:
789 | for chrminfo in subgroup:
790 | chrid = chrminfo[0]
791 | seq = self.genome_dict[chrid]
792 | seq_len = len(seq)
793 | num = seq_len // chunk_size
794 | for i in range(num + 1):
795 | start, stop = i * chunk_size, (i + 1) * chunk_size + flanking_size
796 | if start >= seq_len:
797 | continue
798 | if stop > seq_len:
799 | stop = seq_len
800 | subchrm = 'startat'.join([chrid, str(start)])
801 | chunk_seq = str(self.genome_dict[chrid][start:stop])
802 | F.write(''.join(['>', subchrm, '\n']))
803 | F.write(chunk_seq)
804 | F.write('\n')
805 | subgenome_list.append(subgenome)
806 | return subgenome_list
807 |
808 | def autonomous_detect(self):
809 | # main program to search for transposae and terminal signals.
810 | subgenome_list = self.split_genome(chunk_size=200000000, flanking_size=20000, num_groups=200)
811 | if len(subgenome_list) < self.process_num:
812 | processnum = len(subgenome_list)
813 | else:
814 | processnum = self.process_num
815 | sys.stdout.write('Start to search for HLE rep-hel blocks...\n')
816 | # Use python multiple threading
817 | planpool = ThreadPool(processnum)
818 | #processnum = processnum if self.cpu_count > processnum else self.cpu_count
819 | #planpool = Pool(processnum)
820 | run_result = []
821 | for subgenome in subgenome_list:
822 | run_result.append(planpool.apply_async(self.intergrated_program, args=(subgenome,)))
823 | planpool.close()
824 | planpool.join()
825 | Helitron_list = []
826 | for result in run_result:
827 | result_get = result.get()
828 | if result_get:
829 | Helitron_list.extend(result_get)
830 | Helitron_list = sorted(Helitron_list, key=lambda x: [x[0], int(x[1]), int(x[2])])
831 | return Helitron_list
832 |
833 | def blastn(self, query_file, optdir):
834 | # To search for homologous of given sequences
835 | blastn_opt = ''.join([query_file, '.tbl'])
836 | blastn_pro = subprocess.Popen(
837 | ['blastn', '-db', self.genomedb, '-query', query_file, '-num_threads', str(self.process_num),
838 | '-max_target_seqs', '999999999', '-evalue', str(self.evalue_blastn), '-task', 'blastn-short',
839 | '-outfmt', '6 qseqid sseqid pident qstart qend sstart send evalue qlen bitscore', '-out', blastn_opt])
840 | blastn_pro.wait()
841 | ## if the blastn_opt is empty, return
842 | if not os.path.getsize(blastn_opt):
843 | return 0
844 | ## The blastn output is sorted by queryname. Split blastn outfmt-6 table into bed files.
845 | with open(blastn_opt, 'r') as F:
846 | ## init reading
847 | splitlines = F.readline().rstrip().split('\t')
848 | init_qname = splitlines[0]
849 | chrm, identity, qstart, qend, sstart, send, evalue, qlen, bitscore = splitlines[1:10]
850 | if int(sstart) < int(send):
851 | START = sstart
852 | END = send
853 | strand = '+'
854 | else:
855 | START = send
856 | END = sstart
857 | strand = '-'
858 | deposit_list = [''.join([chrm, '\t', START, '\t', END, '\t', init_qname, '\t', bitscore, '\t', strand, '\n'])]
859 | for line in F:
860 | splitlines = line.rstrip().split('\t')
861 | chrm, identity, qstart, qend, sstart, send, evalue, qlen, bitscore = splitlines[1:10]
862 | if int(sstart) < int(send):
863 | START = sstart
864 | END = send
865 | strand = '+'
866 | else:
867 | START = send
868 | END = sstart
869 | strand = '-'
870 | query_name = splitlines[0]
871 | if query_name == init_qname:
872 | deposit_list.append(''.join([chrm, '\t', START, '\t', END, '\t', init_qname, '\t', bitscore, '\t', strand, '\n']))
873 | else:
874 | subfile = ''.join([optdir, '/', init_qname, '.bed'])
875 | with open(subfile, 'w') as wF:
876 | wF.writelines(deposit_list)
877 | ## reinit
878 | init_qname = query_name
879 | deposit_list = [''.join([chrm, '\t', START, '\t', END, '\t', init_qname, '\t', bitscore, '\t', strand, '\n'])]
880 | ## The last deposit need to be saved manually
881 | subfile = ''.join([optdir, '/', init_qname, '.bed'])
882 | with open(subfile, 'w') as wF:
883 | wF.writelines(deposit_list)
884 | os.remove(blastn_opt)
885 | return 1
886 |
887 | def merge_overlaped_intervals(self, bedinput, represent_bed, alt_optbed, rep_type = True):
888 | # To merge overlaped nonautonomous candidates
889 | True_pair_list = []
890 | with open(bedinput, 'r') as RF, open(represent_bed, 'a') as WFr, open(alt_optbed, 'a') as WFalt:
891 | ### To output alternative insertions and extract first line
892 | EMPTY_DEDUCE=0
893 | for line in RF:
894 | EMPTY_DEDUCE=1
895 | splitlines = line.rstrip().split('\t')
896 | chrmid, start, stop, pairname, count, strand, pvalue, Bscore, classname, mobile_type = splitlines
897 | mobile_type, altype = mobile_type.split('-')
898 | if altype == 'alt' and rep_type:
899 | WFalt.write(line)
900 | continue
901 | else:
902 | break
903 | if not EMPTY_DEDUCE:
904 | return {}
905 | alternative_bedlines = [[chrmid, start, stop, pairname, count, strand, pvalue, Bscore, classname, mobile_type]]
906 | compared_line = (chrmid, start, stop, strand)
907 | blockname_init = 1
908 |
909 | output_recorder = {}
910 | for line in RF:
911 | chrmid, start, stop, pairname, count, strand, pvalue, Bscore, classname, mobile_type = line.rstrip().split('\t')
912 | mobile_type, altype = mobile_type.split('-')
913 | ### To output alternative insertions
914 | if altype == 'alt' and rep_type:
915 | WFalt.write(line)
916 | continue
917 |
918 | newline = [chrmid, start, stop, pairname, count, strand, pvalue, Bscore, classname, mobile_type]
919 | Intersection_deduce = self.intersect(compared_line[1:3], [start, stop], lportion=0.8, rportion=0.8, bool_and=0)
920 | if compared_line[0] == chrmid and Intersection_deduce:
921 | merged_coord = sorted([compared_line[1], compared_line[2], start, stop], key=lambda x: int(x))
922 | compared_line_s, compared_line_e = merged_coord[0], merged_coord[-1]
923 | compared_line = [chrmid, start, compared_line_e, strand]
924 | alternative_bedlines.append(newline)
925 | else:
926 | block_name = '_'.join(['insertion', classname, mobile_type, str(blockname_init)])
927 | output_recorder[block_name]=1
928 | ## Begin to output the former to alternative file
929 | [i.append(block_name) for i in alternative_bedlines]
930 | if mobile_type=='auto':
931 | print('blocks', alternative_bedlines)
932 | ## Try to select a representative from these alternatives.
933 | RC_list = self.filter(alternative_bedlines, classname=classname, mobile_type=mobile_type)
934 | if RC_list:
935 | for line in RC_list:
936 | WFr.write('\t'.join(line))
937 | WFr.write('\n')
938 | True_pair_list.append(line[3])
939 |
940 | blockname_init += 1
941 | alternative_bedlines = [newline]
942 | compared_line = [chrmid, start, stop, strand]
943 |
944 | ## in case the last overlaped series not saved.
945 | block_name = '_'.join(['insertion', classname, mobile_type, str(blockname_init)])
946 | if block_name not in output_recorder:
947 | [i.append(block_name) for i in alternative_bedlines]
948 | RC_list = self.filter(alternative_bedlines, classname=classname, mobile_type=mobile_type)
949 | if RC_list:
950 | for line in RC_list:
951 | WFr.write('\t'.join(line))
952 | WFr.write('\n')
953 | True_pair_list.append(line[3])
954 | return set(True_pair_list)
955 |
956 | def merge_overlaped_autos(self, bedinput, represent_bed, alt_optbed, rep_type = True):
957 | True_pair_list = []
958 |
959 | with open(bedinput, 'r') as RF, open(represent_bed, 'a') as WF, open(alt_optbed, 'a') as WFalt:
960 | ### To output alternative insertions and extract first line
961 | EMPTY_DEDUCE=0
962 | for line in RF:
963 | EMPTY_DEDUCE=1
964 | splitlines = line.rstrip().split('\t')
965 | chrmid, start, stop, pairname, count, strand, pvalue, Bscore, classname, mobile_type = splitlines[6:16]
966 | mobile_type, altype = mobile_type.split('-')
967 | splitlines[15] = mobile_type
968 | if altype == 'alt' and rep_type:
969 | WFalt.write(line)
970 | continue
971 | else:
972 | break
973 | if not EMPTY_DEDUCE:
974 | return {}
975 |
976 | last_orfid = splitlines[3]
977 | alternative_bedlines = [splitlines[6:16]]
978 | blockname_init = 1
979 | output_recorder = {}
980 | for line in RF:
981 | splitlines = line.rstrip().split('\t')
982 | orfid = splitlines[3]
983 | mobile_type=splitlines[15]
984 | mobile_type, altype = mobile_type.split('-')
985 | splitlines[15] = mobile_type
986 | ### To output alternative insertions
987 | if altype == 'alt' and rep_type:
988 | WFalt.write(line)
989 | continue
990 | if orfid == last_orfid:
991 | alternative_bedlines.append(splitlines[6:16])
992 | else:
993 | block_name = '_'.join(['insertion', classname, mobile_type, str(blockname_init)])
994 | output_recorder[block_name] = 1
995 | ## Begin to output the former to alternative file
996 | [i.append(block_name) for i in alternative_bedlines]
997 | ## Try to select a representative from these alternatives.
998 | RC_list = self.filter(alternative_bedlines, classname=classname, mobile_type=mobile_type)
999 | if RC_list:
1000 | for line in RC_list:
1001 | WF.write('\t'.join(line))
1002 | WF.write('\n')
1003 | True_pair_list.append(line[3])
1004 | blockname_init += 1
1005 | last_orfid = orfid
1006 | alternative_bedlines = [splitlines[6:16]]
1007 | ## in case the last overlaped series not saved.
1008 | block_name = '_'.join(['insertion', classname, mobile_type, str(blockname_init)])
1009 | if block_name not in output_recorder:
1010 | [i.append(block_name) for i in alternative_bedlines]
1011 | RC_list = self.filter(alternative_bedlines, classname=classname, mobile_type=mobile_type)
1012 | if RC_list:
1013 | for line in RC_list:
1014 | WF.write('\t'.join(line))
1015 | WF.write('\n')
1016 | True_pair_list.append(line[3])
1017 | return set(True_pair_list)
1018 |
1019 | def add_unique_pre_ts(self, pre_lts_fa, pre_rts_fa, new_lts_fa, new_rts_fa):
1020 | pre_lts_dict = SeqIO.parse(pre_lts_fa, 'fasta')
1021 | pre_rts_dict = SeqIO.parse(pre_rts_fa, 'fasta')
1022 | pre_lts_dict = {k.id: k.seq.upper() for k in pre_lts_dict}
1023 | pre_rts_dict = {k.id: k.seq.upper() for k in pre_rts_dict}
1024 | if os.path.isfile(new_lts_fa) and os.path.isfile(new_rts_fa):
1025 | sum_lts_length = sum([len(pre_lts_dict[i]) for i in pre_lts_dict])
1026 | lts_evalue_blastn = sum_lts_length * 30 / (2 ** 30)
1027 | lts_blastn_opt = 'lts.blastn.tbl'
1028 | lts_blastn_pro = subprocess.Popen(
1029 | ['blastn', '-subject', new_lts_fa, '-query', pre_lts_fa,
1030 | '-max_target_seqs', '5', '-evalue', str(lts_evalue_blastn), '-task', 'blastn-short',
1031 | '-outfmt', '6 qseqid sseqid pident qstart qend sstart send evalue qlen bitscore', '-out', lts_blastn_opt])
1032 | lts_blastn_pro.wait()
1033 |
1034 | sum_rts_length = sum([len(pre_rts_dict[i]) for i in pre_rts_dict])
1035 | rts_evalue_blastn = sum_rts_length * 30 / (2 ** 30)
1036 | rts_blastn_opt = 'rts.blastn.tbl'
1037 | rts_blastn_pro = subprocess.Popen(
1038 | ['blastn', '-subject', new_rts_fa, '-query', pre_rts_fa,
1039 | '-max_target_seqs', '5', '-evalue', str(rts_evalue_blastn), '-task', 'blastn-short',
1040 | '-outfmt', '6 qseqid sseqid pident qstart qend sstart send evalue qlen bitscore', '-out', rts_blastn_opt])
1041 | rts_blastn_pro.wait()
1042 |
1043 | with open(lts_blastn_opt, 'r') as F:
1044 | overlap_lts = {line.split('\t')[0] for line in F}
1045 | with open(rts_blastn_opt, 'r') as F:
1046 | overlap_rts = {line.split('\t')[0] for line in F}
1047 | else: ## the de-novo structural files are empty
1048 | overlap_lts = set()
1049 | overlap_rts = set()
1050 |
1051 | unique_lts = list(set(pre_lts_dict.keys()) - overlap_lts)
1052 | unique_rts = list(set(pre_rts_dict.keys()) - overlap_rts)
1053 |
1054 | ## To find unique pairs
1055 | unique_pair = []
1056 | for lts in unique_lts:
1057 | for rts in self.prepair_dict[lts]:
1058 | if rts in unique_rts:
1059 | unique_pair.append((lts, rts))
1060 | ## To pend
1061 | with open(new_lts_fa, 'a') as lts_w, open(new_rts_fa, 'a') as rts_w:
1062 | for pair in unique_pair:
1063 | left, right = pair
1064 | lts_w.write(''.join(['>', left, '\n', str(pre_lts_dict[left]), '\n']))
1065 | rts_w.write(''.join(['>', right, '\n', str(pre_rts_dict[right]), '\n']))
1066 | return unique_pair
1067 |
1068 | def transform_orfbedfile(self, orffile, classname):
1069 | orf_alternative_file = ''.join([classname, '.orfonly.alternative.bed'])
1070 | with open(orffile, 'r') as F, open(orf_alternative_file, 'w') as wf:
1071 | init = 1
1072 | for line in F:
1073 | splitlines = line.rstrip().split('\t')
1074 | name = ''.join(['insertion_', classname, '_orfonly_', str(init)])
1075 | newline = '\t'.join(
1076 | [splitlines[0], splitlines[1], splitlines[2], splitlines[3], '1', splitlines[5], '1', '0', classname, 'orfonly', name])
1077 | wf.write(newline)
1078 | wf.write('\n')
1079 | init += 1
1080 |
1081 | def prepare_terminal_seq(self, Helitron_list, pair=False, classname='HLE1'):
1082 | if not os.path.exists(classname):
1083 | os.mkdir(classname)
1084 | os.chdir(classname)
1085 |
1086 | left_exist, right_exist = 0, 0
1087 |
1088 | ORF_bedfile = ''.join([classname, '_orf.bed'])
1089 | left_ter_file = ''.join([classname, '_left.fa']) ## the file name will be split by '.' in vsearch function.
1090 | left_ter_reduce_file = ''.join([classname, '.reduce.left.fa'])
1091 |
1092 | right_ter_file = ''.join([classname, '_right.fa'])
1093 | right_ter_reduce_file = ''.join([classname, '.reduce.right.fa'])
1094 |
1095 | ORF_length_list = []
1096 |
1097 | ## To build container for both left and right pair
1098 | EXTEND=30
1099 | Helitron_pair_list = []
1100 | with open(ORF_bedfile, 'w') as orfF, open(left_ter_file, 'w') as leftF, open(right_ter_file, 'w') as rightF:
1101 | for line in Helitron_list:
1102 | left_ter_name, right_ter_name = [], []
1103 | strand = line[3]
1104 | orfF.write(''.join([line[0], '\t', line[1], '\t', line[2], '\t', line[7], '\t', line[4], '\t', strand, '\n']))
1105 | ORF_length_list.append(int(line[2]) - int(line[1]) + 1)
1106 | left_list = line[5]
1107 | left_seq = []
1108 | init = 0
1109 | for left in left_list:
1110 | left_exist += 1
1111 | id = '.'.join([line[7], 'left', str(init)])
1112 | init += 1
1113 | left_ter_name.append(id)
1114 | if strand == '+':
1115 | loc_s = int(left[1]) - 1
1116 | loc_s = loc_s if loc_s >= 0 else 0
1117 | seq = str(self.genome_dict[line[0]][loc_s:int(left[1]) + EXTEND-1].upper())
1118 | else:
1119 | seq = self.genome_dict[line[0]][int(left[2]) - EXTEND:int(left[2])]
1120 | seq = str(seq.reverse_complement().upper())
1121 | left_seq.append(''.join(['>', id, '\n', seq, '\n']))
1122 |
1123 | right_list = line[6]
1124 | right_seq = []
1125 | init = 0
1126 | for right in right_list:
1127 | right_exist += 1
1128 | id = '.'.join([line[7], 'right', str(init)])
1129 | init += 1
1130 | right_ter_name.append(id)
1131 | if strand == '-':
1132 | loc_s = int(right[1]) - 1
1133 | loc_s = loc_s if loc_s >= 0 else 0
1134 | seq = self.genome_dict[line[0]][loc_s:int(right[1]) + EXTEND-1]
1135 | seq = str(seq.reverse_complement().upper())
1136 | else:
1137 | seq = str(self.genome_dict[line[0]][int(right[2]) - EXTEND:int(right[2])].upper())
1138 | right_seq.append(''.join(['>', id, '\n', seq, '\n']))
1139 |
1140 | if classname == 'HLE1' and pair: ## pair the left and right terminals that ever appears on the same Helitron region.
1141 | [Helitron_pair_list.append((left, tuple(right_ter_name))) for left in left_ter_name] ## all possibilities.
1142 | elif classname != 'HLE1':
1143 | [Helitron_pair_list.append((left_ter_name[i], right_ter_name[i])) for i in range(len(left_ter_name))]
1144 | leftF.writelines(left_seq)
1145 | rightF.writelines(right_seq)
1146 |
1147 | ## if run denovo search for motifs:
1148 | if not Args.dis_denovo:
1149 | if not left_exist or not right_exist: ## means that neither left nor right terminal signals exist, so skip blastn
1150 | self.transform_orfbedfile(ORF_bedfile, classname=classname)
1151 | os.chdir('../')
1152 | return []
1153 | else: ### To redunce redundency via cd-hit-est
1154 | left_cluster_dict = self.cdhitest_clust(left_ter_file, left_ter_reduce_file,
1155 | helitron_type=''.join([classname, '_left']), id=0.9)
1156 | right_cluster_dict = self.cdhitest_clust(right_ter_file, right_ter_reduce_file,
1157 | helitron_type=''.join([classname, '_right']), id=0.9)
1158 | else: ## No need to run de-novo terminal structural detection
1159 | left_cluster_dict = {}
1160 | right_cluster_dict = {}
1161 |
1162 | pre_left_file = self.terminalfile_dict[classname]['left']
1163 | pre_right_file = self.terminalfile_dict[classname]['right']
1164 | unique_pairlist = []
1165 | if pre_left_file: ### To pend unique-pre-ts signals
1166 | unique_pairlist = self.add_unique_pre_ts(pre_left_file, pre_right_file, left_ter_reduce_file, right_ter_reduce_file)
1167 | else:
1168 | if Args.dis_denovo:
1169 | ## This means no terminal structures are avaliable. Just output the orf information.
1170 | self.transform_orfbedfile(ORF_bedfile, classname=classname)
1171 | os.chdir('../')
1172 | return []
1173 | ## To make left-right pairs
1174 | combinid_file = '%s.combinid.txt' % classname
1175 | if pair:
1176 | ### To get the collapsed cluster pairs
1177 | collapsed_pair_dict = defaultdict(list)
1178 | terminal_pair_dict = dict(Helitron_pair_list)
1179 | if classname == 'HLE1': ## pair the left and right terminals that ever appears on the same Helitron region.
1180 | for left_name in terminal_pair_dict:
1181 | right_name_list = terminal_pair_dict[left_name]
1182 | for right_name in right_name_list:
1183 | collapsed_left_clust = left_cluster_dict[left_name]
1184 | collapsed_right_clust = right_cluster_dict[right_name]
1185 | collapsed_pair_dict[collapsed_left_clust].append(collapsed_right_clust)
1186 | else: ## pair inverted repeats
1187 | for left_name in terminal_pair_dict:
1188 | right_name = terminal_pair_dict[left_name]
1189 | collapsed_left_clust = left_cluster_dict[left_name]
1190 | collapsed_right_clust = right_cluster_dict[right_name]
1191 | collapsed_pair_dict[collapsed_left_clust].append(collapsed_right_clust)
1192 | # To reduce redundency
1193 | for key in collapsed_pair_dict:
1194 | collapsed_pair_dict[key] = list(set(collapsed_pair_dict[key]))
1195 | with open(combinid_file, 'w') as F:
1196 | for left in collapsed_pair_dict:
1197 | for right in collapsed_pair_dict[left]:
1198 | F.write(''.join([left, '\t', right, '\n']))
1199 | ## To output unique-pre-ts pairs
1200 | for pair in unique_pairlist:
1201 | F.write(''.join([pair[0], '\t', pair[1], '\n']))
1202 | else:
1203 | ## Just make all possibilities
1204 | left_reduced_list = set(left_cluster_dict.values())
1205 | right_cluster_dict = set(right_cluster_dict.values())
1206 | with open(combinid_file, 'w') as F:
1207 | for left in left_reduced_list:
1208 | for right in right_cluster_dict:
1209 | F.write(''.join([left, '\t', right, '\n']))
1210 | ## To output unique-pre-ts pairs, not mixing.
1211 | for pair in unique_pairlist:
1212 | F.write(''.join([pair[0], '\t', pair[1], '\n']))
1213 |
1214 | ## To evaluate the size range
1215 | max_orf_length = sorted(ORF_length_list)[-1]
1216 | distance_na = int(self.window) * 2 + max_orf_length
1217 | half_distance = int(round(int(distance_na) / 2, 0))
1218 | self.distance_na[classname] = distance_na if not self.distance_na[classname] else self.distance_na[classname] ## If specified, will use the specified one.
1219 | sys.stdout.write('The length of autonomous %s is expected to be shorter than %s.\n' % (classname, str(distance_na + 100)))
1220 | sys.stdout.write('The length of nonautonomous %s is expected to be shorter than %s.\n' % (classname, str(self.distance_na[classname] + 100)))
1221 | ## To run blastn to get homologies
1222 | left_beddir, right_beddir = 'SubBlastnBed/%s_left' % classname, 'SubBlastnBed/%s_right' % classname
1223 | if not os.path.exists(left_beddir):
1224 | os.makedirs(left_beddir)
1225 | if not os.path.exists(right_beddir):
1226 | os.makedirs(right_beddir)
1227 | lblastn_status = self.blastn(left_ter_reduce_file, left_beddir)
1228 | rblastn_status = self.blastn(right_ter_reduce_file, right_beddir)
1229 | ## To report if blastn runs well
1230 | if lblastn_status and rblastn_status:
1231 | sys.stdout.write('blastn runs well!\n')
1232 | else:
1233 | sys.stdout.write('No similar hits found for LTS/RTS for %s!\n' % classname)
1234 | ## Prepare for fisher's exact test (avoid overloading, to split bedfiles )
1235 | sys.stdout.write("Prepare for windowing for %s ...\n" % classname)
1236 | subed_dir = '_'.join([classname, 'Windowing'])
1237 | try:
1238 | split_joint_program = subprocess.Popen(
1239 | ['Rscript', SPLIT_JOINT_PRO, left_beddir, right_beddir, combinid_file, subed_dir,
1240 | self.genome_size, str(half_distance), BEDTOOLS_PATH, str(self.process_num)], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
1241 | split_joint_program.wait()
1242 | joint_filepath_blastn = ''.join([subed_dir, '/', 'left_right.path.join'])
1243 | except:
1244 | sys.stderr.write("Error: Windowing program failed...\n")
1245 | exit(0)
1246 |
1247 | ## To run fisher's exact text to select the co-occured left and right terminal signals
1248 | sys.stdout.write("Begin to run fisher's exact test for %s!\n" % classname)
1249 |
1250 | bed_optdir = '%s_BedFisher' % classname
1251 | if os.path.exists(bed_optdir):
1252 | shutil.rmtree(bed_optdir)
1253 | os.mkdir(bed_optdir)
1254 |
1255 | Strategy = '1' if Args.nearest else '0'
1256 | try:
1257 | fisher_program = subprocess.Popen(
1258 | ['Rscript', FISHER_PRO, BEDTOOLS_PATH, self.genome_size, joint_filepath_blastn, bed_optdir,
1259 | str(self.process_num), str(self.pvalue), ORF_bedfile, Strategy], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
1260 | fisher_program.wait()
1261 | sys.stdout.write("Fisher's exact test finished for %s!\n" % classname)
1262 | except:
1263 | sys.stderr.write("Error: Fisher's exact test failed...\n")
1264 | exit(0)
1265 |
1266 | FisherBed_files = ['/'.join([bed_optdir, file]) for file in os.listdir(bed_optdir)]
1267 |
1268 | ## To merge and sort all Fisher bed files
1269 | fisher_pvalue_file = '%s.joint.pvalue.bed' % classname
1270 | fisher_filelist = [''.join([bed_optdir, '/', file]) for file in os.listdir(bed_optdir) if file.endswith('.bed')]
1271 | with open(fisher_pvalue_file, 'w') as WF:
1272 | for subfisher in fisher_filelist:
1273 | with open(subfisher, 'r') as F:
1274 | content = F.read()
1275 | WF.write(content)
1276 | try:
1277 | sort_pro = subprocess.Popen(
1278 | ['bash', SORT_PRO, fisher_pvalue_file, str(self.process_num)],
1279 | stdout=subprocess.DEVNULL)
1280 | sort_pro.wait()
1281 | sys.stdout.write("Merge and sort fisher result files finished for %s!\n" % classname)
1282 | except:
1283 | sys.stdout.write("Merge and sort fisher result files failed for %s!\n" % classname)
1284 | exit(0)
1285 |
1286 | #############To annotate auto or non-autonomous ############
1287 | ORF_bed = BT.BedTool(ORF_bedfile)
1288 | ## To get autonomous candidates.
1289 | fisher_pvalue_bed = BT.BedTool(fisher_pvalue_file)
1290 | ## candidates whose significant terminal signals are able to be found.
1291 | orf_fisher_bed = fisher_pvalue_bed.intersect(ORF_bed, nonamecheck=True, F=1, wa=True, s=True, c=True).saveas('Fisher_with_ORF.bed')
1292 | ## To select the intervals that contain only one ORF
1293 | auto_alternative_file = ''.join([classname, '.auto.alternative.bed'])
1294 |
1295 | with open(auto_alternative_file, 'w') as WF:
1296 | with open('Fisher_with_ORF.bed', 'r') as f1:
1297 | for line in f1:
1298 | splitlines = line.rstrip().split('\t')
1299 | if int(splitlines[-1])==1:
1300 | splitlines = line.rstrip().split('\t')
1301 | newline = '\t'.join(
1302 | [splitlines[0], splitlines[1], splitlines[2], splitlines[3], splitlines[4], splitlines[5],
1303 | splitlines[6], splitlines[7], classname, 'auto-%s'%splitlines[8]])
1304 | WF.write(newline)
1305 | WF.write('\n')
1306 |
1307 | ## To get non-autonomous candidates
1308 | non_autonomous_bed = fisher_pvalue_bed.intersect(ORF_bed, nonamecheck=True, F=0.5, wa=True, v=True).saveas('Nonauto.bed')
1309 | ## candidates whose significant terminal signals are unable to be found.
1310 | auto_alternative_bed = BT.BedTool(auto_alternative_file)
1311 | ORF_without_ter_bed = ORF_bed.intersect(auto_alternative_bed, nonamecheck=True, v=True, s=True, wa=True).saveas('OnlyORF.bed')
1312 | self.transform_orfbedfile('OnlyORF.bed', classname=classname)
1313 | os.chdir('../')
1314 |
1315 | def malign(self, fafile):
1316 | if os.path.getsize(fafile):
1317 | aln_file = ''.join([fafile, '.aln'])
1318 | with open(aln_file, 'w') as mf:
1319 | mul_aln = subprocess.Popen(["mafft", "--auto", "--quiet", fafile], stdout=mf)
1320 | mul_aln.wait()
1321 |
1322 | def flanking_seq(self, fisherfile):
1323 | subwkdir = 'boundary_align'
1324 | pairname = os.path.basename(fisherfile).replace('.bed', '')
1325 | left_extend_file = ''.join([subwkdir, '/', pairname, '.left.fa'])
1326 | right_extend_file = ''.join([subwkdir, '/', pairname, '.right.fa'])
1327 | terminal_file = ''.join([subwkdir, '/', pairname, '.terminal'])
1328 |
1329 | candidate_bed = BT.BedTool(fisherfile).sort()
1330 | candidate_bed = candidate_bed.merge(d=100, c='4,5,6', o='first,mean,first')
1331 | candidate_list = sorted([list(line) for line in candidate_bed], key=lambda x: -float(x[4]))
1332 | if len(candidate_list) < 2:
1333 | return 0
1334 |
1335 | self.filepath_list.append(left_extend_file)
1336 | self.filepath_list.append(right_extend_file)
1337 | self.filepath_list.append(terminal_file)
1338 |
1339 | selected_list = candidate_list[:20]
1340 | with open(left_extend_file, 'w') as LF, open(right_extend_file, 'w') as RF, open(terminal_file, 'w') as TF:
1341 | for line in selected_list:
1342 | chrmid, start, stop, name, score, strand = line
1343 | TF.write(''.join(['>', chrmid, '-', str(start), '-', str(stop), strand.replace('-', '-n').replace('+', '-p'), '\n']))
1344 | if int(stop) - int(start) > 200:
1345 | left_terminal_seq = str(self.genome_dict[chrmid][int(start):int(start)+100])
1346 | right_terminal_seq = str(self.genome_dict[chrmid][int(stop) -100:int(stop)])
1347 | TF.write(''.join([left_terminal_seq, 'N'*10, right_terminal_seq, '\n']))
1348 | else:
1349 | TF.write(''.join([str(self.genome_dict[chrmid][int(start):int(stop)]), '\n']))
1350 |
1351 | if strand == '+':
1352 | if int(start) - 50 >= 0:
1353 | seq_stop = int(start)
1354 | seq_start = int(start) - 50
1355 | seq = self.genome_dict[chrmid][seq_start:seq_stop]
1356 | LF.write(''.join(['>', chrmid, '-', str(seq_start), '-', str(seq_stop), '\n']))
1357 | LF.write(str(seq))
1358 | LF.write('\n')
1359 |
1360 | if int(stop) + 50 <= self.chrm_size[chrmid]:
1361 | seq_start = int(stop)
1362 | seq_stop = int(stop) + 50
1363 | seq = self.genome_dict[chrmid][seq_start:seq_stop]
1364 | RF.write(''.join(['>', chrmid, '-', str(seq_start), '-', str(seq_stop), '\n']))
1365 | RF.write(str(seq))
1366 | RF.write('\n')
1367 | else:
1368 | if int(stop) + 50 <= self.chrm_size[chrmid]:
1369 | seq_start = int(stop)
1370 | seq_stop = int(stop) + 50
1371 | seq = self.genome_dict[chrmid][seq_start:seq_stop].reverse_complement()
1372 | LF.write(''.join(['>', chrmid, '-', str(seq_start), '-', str(seq_stop), '\n']))
1373 | LF.write(str(seq))
1374 | LF.write('\n')
1375 | if int(start) - 50 >= 0:
1376 | seq_stop = int(start)
1377 | seq_start = int(start) - 50
1378 | seq = self.genome_dict[chrmid][seq_start:seq_stop].reverse_complement()
1379 | RF.write(''.join(['>', chrmid, '-', str(seq_start), '-', str(seq_stop), '\n']))
1380 | RF.write(str(seq))
1381 | RF.write('\n')
1382 |
1383 | def TIR_denection(self, sequencefile):
1384 | sequence_length_dict = SeqIO.parse(sequencefile, 'fasta')
1385 | sequence_length_dict = {k.id: len(k.seq) for k in sequence_length_dict}
1386 | Terminal_dict = defaultdict(lambda :0)
1387 | pairname = os.path.basename(sequencefile).replace('.terminal', '')
1388 | ## start coord is 1 not 0
1389 | dbname = ''.join([os.path.basename(sequencefile), '.invdb'])
1390 | invttirfile = ''.join([os.path.basename(sequencefile), '.inv.txt'])
1391 | ## build database
1392 | mkinvdb = subprocess.Popen(
1393 | ['gt', 'suffixerator', '-db', sequencefile, '-indexname', dbname, '-mirrored', '-dna', '-suf', '-lcp', '-bck'],
1394 | stderr=subprocess.DEVNULL, stdout=subprocess.DEVNULL)
1395 | mkinvdb.wait()
1396 | ## run tirvish
1397 | with open(invttirfile, 'w') as invf:
1398 | runinvsearch = subprocess.Popen(['gt', 'tirvish', '-index', dbname, '-mintirlen', '20', '-maxtirlen', '150',
1399 | '-similar', '85', '-mintirdist', '2', '-maxtirdist', '200', '-mintsd', '0',
1400 | '-seed', '12', '-vic', '1', '-overlaps', 'all', '-xdrop', '0'],
1401 | stderr=subprocess.DEVNULL, stdout=invf)
1402 | runinvsearch.wait()
1403 |
1404 | ## The default output is in gff format, extract coord information and do filteration.
1405 | with open(invttirfile, 'r') as F:
1406 | for line in F:
1407 | if line.startswith('#'):
1408 | continue
1409 | splitlines = line.rstrip().split('\t')
1410 | if splitlines[2] == 'repeat_region':
1411 | chrmid = splitlines[0]
1412 | id = splitlines[8].replace('ID=', '')
1413 | t = 1
1414 | elif splitlines[2] == 'terminal_inverted_repeat':
1415 | if t == 1:
1416 | left_start = str(int(splitlines[3]))
1417 | t += 1
1418 | else:
1419 | right_end = str(int(splitlines[4]))
1420 | if self.intersect([1, int(sequence_length_dict[chrmid])], [left_start, right_end], lportion=0.7):
1421 | ## means long terminal inverted repeats detected
1422 | Terminal_dict[chrmid]+=1
1423 |
1424 | os.remove(invttirfile)
1425 | os.system('rm %s*' % dbname)
1426 | Inv_count = len([i for i in Terminal_dict if Terminal_dict[i]>0])
1427 | Total_num = len(sequence_length_dict.keys())
1428 | self.Terminal_dict[pairname]=Inv_count/Total_num
1429 |
1430 | def MakeSelection(self, FisherFile_pathlist):
1431 | # This function is to filter out the candidates who might insert into other superfamily of transposons.
1432 | sys.stdout.write('Begin to run boundary check program.\n')
1433 | subwkdir = 'boundary_align'
1434 | if not os.path.exists(subwkdir):
1435 | os.mkdir(subwkdir)
1436 | else:
1437 | shutil.rmtree(subwkdir)
1438 | os.mkdir(subwkdir)
1439 | ## To output the flanking sequences
1440 | self.filepath_list = []
1441 |
1442 | planpool = ThreadPool(self.process_num)
1443 | for fisherfile in FisherFile_pathlist:
1444 | planpool.apply_async(self.flanking_seq, args=(fisherfile,))
1445 | planpool.close()
1446 | planpool.join()
1447 | filepath_list = [i for i in self.filepath_list if os.path.getsize(i) and i.endswith('.fa')]
1448 | planpool = ThreadPool(self.process_num)
1449 |
1450 | for fafile in filepath_list:
1451 | planpool.apply_async(self.malign, args=(fafile,))
1452 | planpool.close()
1453 | planpool.join()
1454 | boundary_identity_tbl = 'Boundary.identity.tbl'
1455 | Boundary_check_pro = subprocess.Popen(
1456 | ['Rscript', BOUNDARY_PRO, os.path.abspath(subwkdir), os.path.abspath(boundary_identity_tbl)],
1457 | stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
1458 | Boundary_check_pro.wait()
1459 | sys.stdout.write("Boundary check was finished!\n")
1460 |
1461 | ## insertions that only contain orf regions will automatically pass this filter
1462 |
1463 | if os.path.exists(boundary_identity_tbl):
1464 | with open(boundary_identity_tbl, 'r') as F:
1465 | F.readline() ## Skip header
1466 | for line in F:
1467 | name, direction, iden = line.rstrip().split('\t')
1468 | self.Boundary_iden_dict[name][direction] = float(iden)
1469 |
1470 | ## To filter out the candidates who might contain long tirs.
1471 | terminal_file_list = [i for i in self.filepath_list if os.path.getsize(i) and i.endswith('.terminal')]
1472 | planpool = ThreadPool(self.process_num)
1473 | for terminal_file in terminal_file_list:
1474 | planpool.apply_async(self.TIR_denection, args=(terminal_file,))
1475 | planpool.close()
1476 | planpool.join()
1477 | sys.stdout.write("Inverted repeats detection was finished!\n")
1478 |
1479 | def filter(self, alternative_list, classname, mobile_type):
1480 | ## To do selection for autonomous firstly, because the nonautonomous counterparts will be dertermined by autonomous ones.
1481 | candidate_list = []
1482 | RC_replist = []
1483 | if classname == 'HLE1':
1484 | for line in alternative_list:
1485 | pairname = line[3]
1486 | ## insertions that only contain orf regions will automatically pass this filter, because default value is 0.
1487 | if self.Boundary_iden_dict[pairname]['left'] < self.cutoff_flank and self.Boundary_iden_dict[pairname]['right'] < self.cutoff_flank:
1488 | candidate_list.append(line)
1489 | else: ## means HLE2
1490 | for line in alternative_list:
1491 | pairname = line[3]
1492 | left_iden, right_iden = self.Boundary_iden_dict[pairname]['left'], self.Boundary_iden_dict[pairname]['right']
1493 | if left_iden < self.cutoff_flank:
1494 | ## means regular HLE2, try to find stem-loop terminal markers at 5'end
1495 | candidate_list.append(line)
1496 | elif right_iden < self.cutoff_flank and left_iden >= self.cutoff_flank:
1497 | ## unregular HLE2, try to find stem-loop terminal markers at 3'end
1498 | line[-3] = ''.join([line[-3], '.2'])
1499 | candidate_list.append(line)
1500 | if not candidate_list:
1501 | if mobile_type != 'nonauto':
1502 | ## Might represent a truncated helitron insertion. Just keep the autonomous ones and remove the nonautonomous ones.
1503 | ## Because we are sure that there should be one insertion in autonomous region.
1504 | candidate_list = sorted(alternative_list, key=lambda x: [int(x[2]) - int(x[1]), float(x[6]), -float(x[7])]) ## length (shorter), ## pvalue, then bitscore
1505 | else:
1506 | candidate_list = sorted(candidate_list, key=lambda x: [float(x[6]), int(x[1]) - int(x[2]), -float(x[7])]) ## pvalue, length, then bitscore
1507 | ## To further filter out TIRs
1508 | candidate_list2 = [i for i in candidate_list if self.Terminal_dict[i[3]] <= 0.2]
1509 | if candidate_list2:
1510 | candidate_list = candidate_list2
1511 | else:
1512 | if mobile_type == 'nonauto':
1513 | return []
1514 | if candidate_list:
1515 | RC_replist.append(candidate_list[0])
1516 | return RC_replist
1517 |
1518 | def OutputSequence(self, bedinput, faoutput):
1519 | with open(bedinput, 'r') as RF, open(faoutput, 'w') as WF:
1520 | for line in RF:
1521 | splitlines = line.rstrip().split('\t')
1522 | chrmid, start, stop, pairname, score, strand = splitlines[:6]
1523 | insertion_name = splitlines[-1]
1524 | start = int(start) - 1
1525 | start = 0 if start <0 else start
1526 | seq = self.genome_dict[chrmid][start:int(stop)]
1527 | if strand == '+':
1528 | WF.write(''.join(['>', insertion_name, '\n']))
1529 | WF.write(str(seq))
1530 | WF.write('\n')
1531 | else:
1532 | WF.write(''.join(['>', insertion_name, '\n']))
1533 | WF.write(str(seq.reverse_complement()))
1534 | WF.write('\n')
1535 |
1536 | def Convienced_LTS_RTS(self, RCfile, opfile):
1537 | ## To output convinced pair list which can be used as query in another close species genome.
1538 | with open(RCfile, 'r') as F:
1539 | pairlist = {line.rstrip().split("\t")[3] for line in F}
1540 | convienced_dict = defaultdict(list)
1541 | for pair in pairlist:
1542 | tirvalue = self.Terminal_dict[pair]
1543 | if float(tirvalue) <= 0.2:
1544 | if pair in self.Boundary_iden_dict:
1545 | left_value = float(self.Boundary_iden_dict[pair]['left'])
1546 | right_value = float(self.Boundary_iden_dict[pair]['right'])
1547 | classname = pair.split('_left')[0]
1548 | if 'HLE2' in pair:
1549 | if left_value < self.cutoff_flank or right_value < self.cutoff_flank:
1550 | convienced_dict[classname].append(pair)
1551 | else: ## means Helitron
1552 | if left_value < self.cutoff_flank and right_value < self.cutoff_flank:
1553 | convienced_dict[classname].append(pair)
1554 |
1555 | oplist = []
1556 | for classname in convienced_dict:
1557 | ## To read the left terminal sequence
1558 | left_terminal_file = ''.join([classname, '/', classname, '.reduce.left.fa'])
1559 | left_terminal_dict = SeqIO.parse(left_terminal_file, 'fasta')
1560 | left_terminal_dict = {k.id: k.seq.upper() for k in left_terminal_dict}
1561 | ## To read the right terminal sequence
1562 | right_terminal_file = ''.join([classname, '/', classname, '.reduce.right.fa'])
1563 | right_terminal_dict = SeqIO.parse(right_terminal_file, 'fasta')
1564 | right_terminal_dict = {k.id: k.seq.upper() for k in right_terminal_dict}
1565 |
1566 | for pair in convienced_dict[classname]:
1567 | left, right = pair.split('-')
1568 | left_seq = str(left_terminal_dict[left])
1569 | right_seq = str(right_terminal_dict[right])
1570 | oplist.append(''.join([classname, '\t', left, '\t', left_seq, '\t', right,'\t', right_seq, '\n']))
1571 | with open(opfile, 'w') as F:
1572 | F.writelines(oplist)
1573 |
1574 | def Pre_ts_solo(self, classname, pre_lts_file, pre_rts_file):
1575 | if not os.path.exists(classname):
1576 | os.mkdir(classname)
1577 | os.chdir(classname)
1578 | ORF_bedfile = ''.join([classname, '_orf.bed'])
1579 | ## To evaluate the size range
1580 | distance_na = int(self.window) * 2
1581 | half_distance = int(round(int(distance_na) / 2, 0))
1582 | self.distance_na[classname] = distance_na if not self.distance_na[classname] else self.distance_na[classname] ## If specified, will use the specified one.
1583 | sys.stdout.write('The length of autonomous %s is expected to be shorter than %s.\n' % (classname, str(distance_na + 100)))
1584 | sys.stdout.write('The length of nonautonomous %s is expected to be shorter than %s.\n' % (classname, str(self.distance_na[classname] + 100)))
1585 | ## To run blastn to get homologies
1586 | left_beddir, right_beddir = 'SubBlastnBed/%s_left' % classname, 'SubBlastnBed/%s_right' % classname
1587 | if not os.path.exists(left_beddir):
1588 | os.makedirs(left_beddir)
1589 | if not os.path.exists(right_beddir):
1590 | os.makedirs(right_beddir)
1591 | self.blastn(pre_lts_file, left_beddir)
1592 | self.blastn(pre_rts_file, right_beddir)
1593 | ## To output combine id
1594 | combinid_file = '%s.combinid.txt' % classname
1595 | with open(combinid_file, 'w') as F:
1596 | F.writelines([''.join([left, '\t', right, '\n']) for left in self.prepair_dict for right in self.prepair_dict[left] if re.match('%s_left'%classname, left)])
1597 |
1598 | ## Prepare for fisher's exact test (avoid overloading, to split bedfiles )
1599 | sys.stdout.write("Prepare for windowing for %s ...\n" % classname)
1600 | subed_dir = '_'.join([classname, 'Windowing'])
1601 | try:
1602 | split_joint_program = subprocess.Popen(
1603 | ['Rscript', SPLIT_JOINT_PRO, left_beddir, right_beddir, combinid_file, subed_dir,
1604 | self.genome_size, str(half_distance), BEDTOOLS_PATH, str(self.process_num)], stdout=subprocess.DEVNULL)
1605 | split_joint_program.wait()
1606 | joint_filepath_blastn = ''.join([subed_dir, '/', 'left_right.path.join'])
1607 | except:
1608 | sys.stderr.write("Error: Windowing program failed...\n")
1609 | exit(0)
1610 |
1611 | ## To run fisher's exact text to select the co-occured left and right terminal signals
1612 | sys.stdout.write("Begin to run fisher's exact test for %s!\n" % classname)
1613 |
1614 | bed_optdir = '%s_BedFisher' % classname
1615 | if os.path.exists(bed_optdir):
1616 | shutil.rmtree(bed_optdir)
1617 | os.mkdir(bed_optdir)
1618 | Strategy = '1' if Args.nearest else '0'
1619 | try:
1620 | fisher_program = subprocess.Popen(
1621 | ['Rscript', FISHER_PRO, BEDTOOLS_PATH, self.genome_size, joint_filepath_blastn, bed_optdir,
1622 | str(self.process_num), str(self.pvalue), ORF_bedfile, Strategy], stdout=subprocess.DEVNULL)
1623 | fisher_program.wait()
1624 | sys.stdout.write("Fisher's exact test finished for %s!\n" % classname)
1625 | except:
1626 | sys.stderr.write("Error: Fisher's exact test failed...\n")
1627 | exit(0)
1628 |
1629 | FisherBed_files = ['/'.join([bed_optdir, file]) for file in os.listdir(bed_optdir)]
1630 |
1631 | ## To merge and sort all Fisher bed files
1632 | fisher_pvalue_file = '%s.joint.pvalue.bed' % classname
1633 | fisher_filelist = [''.join([bed_optdir, '/', file]) for file in os.listdir(bed_optdir) if file.endswith('.bed')]
1634 | with open(fisher_pvalue_file, 'w') as WF:
1635 | for subfisher in fisher_filelist:
1636 | with open(subfisher, 'r') as F:
1637 | content = F.read()
1638 | WF.write(content)
1639 | try:
1640 | sort_pro = subprocess.Popen(
1641 | ['bash', SORT_PRO, fisher_pvalue_file, str(self.process_num)],
1642 | stdout=subprocess.DEVNULL)
1643 | sort_pro.wait()
1644 | sys.stdout.write("Merge and sort fisher result files finished for %s!\n" % classname)
1645 | except:
1646 | sys.stdout.write("Merge and sort fisher result files failed for %s!\n" % classname)
1647 | exit(0)
1648 | fisher_pvalue_bed = BT.BedTool(fisher_pvalue_file).saveas('Nonauto.bed')
1649 | os.chdir('../')
1650 |
1651 | def main(self):
1652 | self.Boundary_iden_dict = defaultdict(lambda: defaultdict(lambda: 1))
1653 | self.Terminal_dict = defaultdict(lambda: 1)
1654 |
1655 | RC_total_candidate_dict = defaultdict(list)
1656 | RC_total_candidate = self.autonomous_detect()
1657 | [RC_total_candidate_dict[line[4]].append(line) for line in RC_total_candidate]
1658 | orf_classname_list = list(RC_total_candidate_dict.keys())
1659 | unique_pre_ts_classname = []
1660 | classname_list = []
1661 | classname_list.extend(orf_classname_list)
1662 | if self.prepair_dict:
1663 | ## means add pre-ts
1664 | unique_pre_ts_classname = list(set(self.terminalfile_dict.keys()) - set(orf_classname_list))
1665 | classname_list.extend(unique_pre_ts_classname)
1666 |
1667 | Repsentative_file_list = []
1668 | Alternative_file_list = []
1669 | ## Loop for each variants.
1670 | for class_name in classname_list:
1671 | op_representative = '%s.representative.bed' % class_name
1672 | opauto_nest_alt = '%s.auto.nest.alt.bed' % class_name
1673 | opnonauto_nest_alt = '%s.nonauto.nest.alt.bed' % class_name
1674 | op_nest_rep = '%s.nest.bed' % class_name
1675 |
1676 | if os.path.exists(op_representative):
1677 | os.remove(op_representative)
1678 | Repsentative_file_list.append(op_representative)
1679 | if os.path.exists(op_nest_rep):
1680 | os.remove(op_nest_rep)
1681 | Alternative_file_list.append(op_nest_rep)
1682 |
1683 | FisherFile_list = []
1684 | Auto_file_list = []
1685 | ORFonly_file_list = []
1686 | RC_list = RC_total_candidate_dict[class_name]
1687 | if RC_list:
1688 | if re.findall('HLE2', class_name): ## need to pair the terminal repeats
1689 | self.prepare_terminal_seq(RC_list, pair=True, classname=class_name)
1690 | else:
1691 | if not Args.pair_helitron:
1692 | self.prepare_terminal_seq(RC_list, pair=False, classname=class_name)
1693 | else:
1694 | self.prepare_terminal_seq(RC_list, pair=True, classname=class_name)
1695 | else:
1696 | self.Pre_ts_solo(classname=class_name, pre_lts_file=self.terminalfile_dict[class_name]['left'],
1697 | pre_rts_file=self.terminalfile_dict[class_name]['right'])
1698 |
1699 | fisher_beddir = ''.join([class_name, '/', class_name, '_BedFisher'])
1700 | if os.path.exists(fisher_beddir):
1701 | FisherFile_list.extend([''.join([fisher_beddir, '/', file]) for file in os.listdir(fisher_beddir)])
1702 | ## To check that if the boundary of each family can be well aligned.
1703 | ## To check that if the families contain long terminal inverted repeats.
1704 | self.MakeSelection(FisherFile_list)
1705 |
1706 | ## To merge autonomous insertions and select representatives
1707 | pairnamelist = set()
1708 | if RC_list:
1709 | ORF_bed = BT.BedTool(''.join([class_name, '/', class_name, '_orf.bed']))
1710 | Auto_fisher_file = ''.join([class_name, '/', '%s.auto.alternative.bed' % class_name])
1711 |
1712 | if os.path.isfile(Auto_fisher_file):
1713 | Auto_fisher_bed = BT.BedTool(Auto_fisher_file)
1714 | else:
1715 | Auto_fisher_bed = BT.BedTool([])
1716 | Auto_ORF_intersect_file = ''.join([class_name, '/', class_name, 'ORFinterAUTO.bed'])
1717 | ORF_bed.intersect(Auto_fisher_bed, nonamecheck=True, f=1, wo=True, s=True).saveas(Auto_ORF_intersect_file)
1718 |
1719 | if os.path.exists(Auto_fisher_file):
1720 | pairnamelist = self.merge_overlaped_autos(Auto_ORF_intersect_file, op_representative, opauto_nest_alt, rep_type=True)
1721 | ## To output alternative nest insertions
1722 | if os.path.exists(opauto_nest_alt):
1723 | self.merge_overlaped_autos(opauto_nest_alt, op_nest_rep, 'tmp.txt', rep_type=False)
1724 |
1725 | ## To get non-autonomous candidates
1726 | nonauto_bedfile = '%s/Nonauto.bed' % class_name
1727 | nonauto_alternative_file = ''.join([class_name, '/', class_name, '.nonauto.alternative.bed'])
1728 | if os.path.exists(nonauto_bedfile):
1729 | with open(nonauto_alternative_file, 'w') as WF, open(nonauto_bedfile, 'r') as RF:
1730 | for line in RF:
1731 | splitlines = line.rstrip().split('\t')
1732 | ## To filter out ultra-large nonautonomous
1733 | if int(splitlines[2]) - int(splitlines[1]) + 1 > self.distance_na[class_name] + 100:
1734 | continue
1735 | ## To limit outputing nonautonomous candidates who shares the same autonomous boundaries.
1736 | if Args.multi_ts:
1737 | newline = '\t'.join(
1738 | [splitlines[0], splitlines[1], splitlines[2], splitlines[3], splitlines[4],
1739 | splitlines[5], splitlines[6], splitlines[7], class_name, 'nonauto-%s'%splitlines[8]])
1740 | WF.write(newline)
1741 | WF.write('\n')
1742 | else:
1743 | if splitlines[3] in pairnamelist or 'pre' in splitlines[3]:
1744 | newline = '\t'.join([splitlines[0], splitlines[1], splitlines[2], splitlines[3], splitlines[4],
1745 | splitlines[5], splitlines[6], splitlines[7], class_name, 'nonauto-%s'%splitlines[8]])
1746 | WF.write(newline)
1747 | WF.write('\n')
1748 |
1749 | ## To merge nonautonomous intervals and do selection.
1750 | if os.path.exists(nonauto_alternative_file):
1751 | self.merge_overlaped_intervals(nonauto_alternative_file, op_representative, opnonauto_nest_alt, rep_type=True)
1752 | ## To output alternative nest insertions
1753 | if os.path.exists(opnonauto_nest_alt):
1754 | self.merge_overlaped_intervals(opnonauto_nest_alt, op_nest_rep, 'tmp.txt', rep_type=False)
1755 | ## To integrate orf file into representative file
1756 | # To obtain orf only insertions
1757 | Orfonly_file = ''.join([class_name, '/', '%s.orfonly.alternative.bed' % class_name])
1758 | if os.path.exists(Orfonly_file):
1759 | with open(op_representative, 'a') as WF, open(Orfonly_file, 'r') as RF:
1760 | WF.write(RF.read())
1761 | ## Remove intermediate files
1762 | if os.path.exists(opauto_nest_alt):
1763 | os.remove(opauto_nest_alt)
1764 | if os.path.exists(opnonauto_nest_alt):
1765 | os.remove(opnonauto_nest_alt)
1766 |
1767 | ## To output boundary check file and tir check file
1768 | with open('Boundary.tbl', 'w') as BF:
1769 | for id in self.Boundary_iden_dict:
1770 | for direction in self.Boundary_iden_dict[id]:
1771 | BF.write(''.join([id, '\t', direction, '\t', str(self.Boundary_iden_dict[id][direction]), '\n']))
1772 | with open('TIR_count.tbl', 'w') as TF:
1773 | for id in self.Terminal_dict:
1774 | TF.write(''.join([id, '\t', str(self.Terminal_dict[id]), '\n']))
1775 |
1776 | ## To add terminal markers for HLE2
1777 | for helen_file in Repsentative_file_list:
1778 | if re.findall('HLE2', helen_file):
1779 | self.heltentron_terminal(helentron_bed=helen_file)
1780 |
1781 | if os.path.exists('tmp.txt'):
1782 | os.remove('tmp.txt')
1783 |
1784 | op_representative = 'RC.representative.bed'
1785 | with open(op_representative, 'w') as wf:
1786 | for file in Repsentative_file_list:
1787 | if os.path.exists(file):
1788 | with open(file, 'r') as rf:
1789 | [wf.write(line) for line in rf]
1790 | os.remove(file)
1791 |
1792 | op_alternative = 'RC.alternative.bed'
1793 | with open(op_alternative, 'w') as wf:
1794 | for file in Alternative_file_list:
1795 | if os.path.exists(file):
1796 | with open(file, 'r') as rf:
1797 | [wf.write(line) for line in rf]
1798 | os.remove(file)
1799 |
1800 | ## To sort big file
1801 | if not os.path.exists(op_representative):
1802 | with open(op_representative, 'w') as F:
1803 | F.write('')
1804 | if not os.path.exists(op_alternative):
1805 | with open(op_alternative, 'w') as F:
1806 | F.write('')
1807 | try:
1808 | sort_pro = subprocess.Popen(['bash', SORT_PRO, op_representative, str(self.process_num)],
1809 | stdout=subprocess.DEVNULL)
1810 | sort_pro.wait()
1811 | sys.stdout.write("Sort representative files finished ...\n")
1812 |
1813 | sort_pro = subprocess.Popen(['bash', SORT_PRO, op_alternative, str(self.process_num)],
1814 | stdout=subprocess.DEVNULL)
1815 | sort_pro.wait()
1816 | sys.stdout.write("Sort alternative files finished ...\n")
1817 |
1818 | except:
1819 | sys.stdout.write("Sort representative files failed ...\n")
1820 | exit(0)
1821 | sequence_fa = 'RC.representative.fa'
1822 | ## Delete alternative file if empty
1823 | if not os.path.getsize(op_alternative):
1824 | os.remove(op_alternative)
1825 | ## To output fasta format file.
1826 | self.OutputSequence(op_representative, sequence_fa)
1827 | ## To output convinced pair list.
1828 | Convinced_pairlist = 'pairlist.tbl'
1829 | self.Convienced_LTS_RTS(op_representative, Convinced_pairlist)
1830 |
1831 | ## To remove tempary files
1832 | os.remove(self.CTRR_stem_loop_description)
1833 | os.remove(self.subtir_description)
1834 | os.remove(self.genome_size)
1835 | shutil.rmtree(self.bedtoolstmp)
1836 | if os.path.exists('GenomeDB'):
1837 | shutil.rmtree('GenomeDB')
1838 | if os.path.exists('genomes'):
1839 | shutil.rmtree('genomes')
1840 | #for class_name in RC_total_candidate_dict:
1841 | # if os.path.exists(class_name):
1842 | # shutil.rmtree(class_name)
1843 | if os.path.exists("boundary_align"):
1844 | shutil.rmtree("boundary_align")
1845 | if os.path.exists('Boundary.identity.tbl'):
1846 | os.remove('Boundary.identity.tbl')
1847 |
1848 | if __name__ == "__main__":
1849 | parser = argparse.ArgumentParser(description="heliano can detect and classify different variants of Helitron-like elements: HLE1 and HLE2. Please visit https://github.com/Zhenlisme/heliano/ for more information. Email us: zhen.li3@universite-paris-saclay.fr")
1850 | parser.add_argument("-g", "--genome", type=str, required=True, help="The genome file in fasta format.")
1851 | parser.add_argument("-w", "--window", type=int, default=10000, required=False,
1852 | help="To check terminal signals within a given window bp upstream and downstream of ORF ends. default is 10 kb.")
1853 | parser.add_argument("-dm", "--distance_domain", type=int, default=2500, required=False,
1854 | help="The distance between HUH and Helicase domain, default is 2500.")
1855 | parser.add_argument("-dn", "--distance_ts", type=int, default=0, required=False,
1856 | help="The maximum distance between LTS and RTS. If not specified, HELIANO will set it as two times window size plus the maximum ORF length.")
1857 | parser.add_argument("-pt", "--pair_helitron", type=int, default=1, required=False, choices=[0, 1],
1858 | help="For HLE1, its 5' and 3' terminal signal pairs should come from the same autonomous helitorn or not. 0: no, 1: yes (default).")
1859 | parser.add_argument("-is1", "--IS1", type=int, default=0, required=False, choices=[0, 1],
1860 | help="Set the insertion site of autonomous HLE1 as A and T. 0: no, 1: yes (default).")
1861 | parser.add_argument("-is2", "--IS2", type=int, default=0, required=False, choices=[0, 1],
1862 | help="Set the insertion site of autonomous HLE2 as T and T. 0: no, 1: yes (default).")
1863 | parser.add_argument("-sim_tir", "--simtir", type=int, default=100, required=False, choices=[100, 90, 80],
1864 | help="Set the simarity between short inverted repeats(TIRs) of HLE2. Default 100.")
1865 | parser.add_argument("-flank_sim", "--flank_sim", type=float, default=0.5, required=False, choices=[0.4, 0.5, 0.6, 0.7],
1866 | help="The cut-off to define false positive LTS/RTS. The lower the value, the more strigent. Default 0.5.")
1867 | parser.add_argument("-p", "--pvalue", type=float, required=False, default=1e-5, help="The p-value for fisher's exact test. default is 1e-5.")
1868 | parser.add_argument("-s", "--score", type=int, required=False, default=32,
1869 | help="The minimum bitscore of blastn for searching for homologous sequences of terminal signals. From 30 to 55, default is 32.")
1870 | parser.add_argument("--nearest", action='store_true', required=False,
1871 | help="If you use this parameter, you will use the reciprocal-nearest LTS-RTS pairs as final candidates. By default, HELIANO will try to use the reciprocal-farthest pairs.")
1872 | parser.add_argument("-ts", "--terminal_sequence", type=str, required=False, default='', help="The terminal sequence file. You can find it in the output of previous run (named as pairlist.tbl).")
1873 | parser.add_argument("--dis_denovo", action='store_true', required=False,
1874 | help="If you use this parameter, you refuse to search for LTS/RTS de novo, instead you will only use the LTS/RTS information described in the terminal sequence file.")
1875 | parser.add_argument("--multi_ts", action='store_true', required=False,
1876 | help="To allow an auto HLE to have multiple terminal sequences. If you enable this, you might find nonauto HLEs coming from the same auto HLE have different terminal sequences.")
1877 | parser.add_argument("-tb", "--table", type=int, required=False, choices=[0, 1, 2, 3], default=0,
1878 | help="""Code to use for the open reading fram prediction. 0: Standard (default); 1: Ciliate Macronuclear and Dasycladacean;
1879 | 2: Blepharisma Macronuclear; 3: Scenedesmus obliquus""")
1880 | parser.add_argument("-o", "--opdir", type=str, required=True, help="The output directory.")
1881 | parser.add_argument("-n", "--process", type=int, default=2, required=False, help="Maximum number of threads to be used.")
1882 | parser.add_argument("-v", "--version", action='version', version='%(prog)s 1.3.1')
1883 | Args = parser.parse_args()
1884 | if int(Args.score) < 30 or int(Args.score) >= 55:
1885 | sys.stderr.write("Error: The bitscore value should be greater than 30 and less than 55.\n")
1886 | exit(0)
1887 | if int(Args.distance_ts) < 0 or int(Args.window) < 0 or int(Args.distance_domain) < 0:
1888 | sys.stderr.write("Error: Parameter value should not be negative.\n")
1889 | exit(0)
1890 | ## To set and check dependency file path
1891 | HMMFILE = '_HMM_'
1892 | HEADERFILE = '_HEADER_'
1893 | FISHER_PRO = '_FISHER_'
1894 | BOUNDARY_PRO = '_BOUNDARY_'
1895 | SPLIT_JOINT_PRO = '_SPLIT_JOINT_'
1896 | SORT_PRO = '_SORTPRO_'
1897 | try:
1898 | BEDTOOLS_PATH = subprocess.check_output("which bedtools", shell=True).decode().rstrip()
1899 | BEDTOOLS_PATH = '/'.join(BEDTOOLS_PATH.split('/')[:-1])
1900 | except:
1901 | print("Could not find bedtools path.")
1902 | exit(0)
1903 | try:
1904 | subprocess.check_output("which rnabob", shell=True)
1905 | except:
1906 | print("Could not find rnabob path.")
1907 | exit(0)
1908 |
1909 | try:
1910 | subprocess.check_output("which cd-hit-est", shell=True)
1911 | except:
1912 | print("Could not find cd-hit-est path.")
1913 | exit(0)
1914 |
1915 | try:
1916 | subprocess.check_output("which mafft", shell=True)
1917 | except:
1918 | print("Could not find mafft path.")
1919 | exit(0)
1920 | try:
1921 | subprocess.check_output("which hmmsearch", shell=True)
1922 | except:
1923 | print("Could not find hmmsearch path.")
1924 | exit(0)
1925 |
1926 | try:
1927 | subprocess.check_output("which getorf", shell=True)
1928 | except:
1929 | print("Could not find getorf path.")
1930 | exit(0)
1931 |
1932 | try:
1933 | subprocess.check_output("which gt", shell=True)
1934 | except:
1935 | print('Could not find genometools path.')
1936 | exit(0)
1937 |
1938 | try:
1939 | subprocess.check_output("which dialign2-2", shell=True)
1940 | except:
1941 | print('Could not find dialign2 path.')
1942 | exit(0)
1943 |
1944 | try:
1945 | subprocess.check_output("which blastn", shell=True)
1946 | except:
1947 | print('Could not find genometools path.')
1948 | exit(0)
1949 |
1950 | if not os.path.exists(HMMFILE):
1951 | print("Hmmer model file not found!")
1952 | exit(0)
1953 | if not os.path.exists(HEADERFILE):
1954 | print('header lcv file not found!')
1955 | exit(0)
1956 | if not os.path.exists(BOUNDARY_PRO):
1957 | print('Boundary check program not found!')
1958 | exit(0)
1959 | if not os.path.exists(FISHER_PRO):
1960 | print("Fisher's exact test program not found!")
1961 | exit(0)
1962 | if not os.path.exists(SPLIT_JOINT_PRO):
1963 | print("Split bed file program not found!")
1964 | exit(0)
1965 |
1966 | HomoSearch = Homologous_search(HMMFILE, os.path.abspath(Args.genome), os.path.abspath(Args.opdir),
1967 | HEADERFILE, Args.window, Args.distance_domain, Args.distance_ts, Args.pvalue,
1968 | Args.process, Args.table)
1969 | HomoSearch.main()
1970 |
1971 |
--------------------------------------------------------------------------------