ó ?îec@sŒddlZddlmZd„Zd„Zd„Zd„Zd„Zd„Zd „Z d „Z d „Z d „Z d „Z d„ZdS(iÿÿÿÿN(t __version__c Cs2|j}|dkr7ddlm}dGH||ƒn÷|dkr¾ddlm}|jd"kr†|jd"kr†dGHtj dƒn|jd"k r¬|jd"k r¬d GHnd GH||ƒnp|d krìdd l m }d GH||ƒnB|dkrddl m }dGH||ƒn|dkrHddlm}dGH||ƒnæ|dkrvddlm}dGH||ƒn¸|dkr¤ddlm}dGH||ƒnŠ|dkrÒddlm} dGH| |ƒn\|dkrddlm} dGH| |ƒn.|dkr.dd lm} d!GH| |ƒnd"S(#s*The Main function for calling pyatac tvplotiÿÿÿÿ(t make_vplotsP---------Making VPlot-----------------------------------------------------------t bias_vplot(tmake_bias_vplots. Must input either --bg or --fasta! Exiting...isYWarning-- both --bg and --fasta provided-- will us --bg for bias track and inrore --fastasP---------Making Bias VPlot------------------------------------------------------tsignal(t get_signalsP---------Getting signal around sites--------------------------------------------tins(tget_inssP---------Getting insertions to make track---------------------------------------tcov(tget_covt nucleotide(tget_nucleotidesJ---------Getting nucleotide content---------------------------------------tbias(tmake_bias_tracksE---------Making Tn5 Bias Track---------------------------------------tpwm(tget_pwmsC---------Making PWM from bam---------------------------------------tsizes(t get_sizessF---------Getting fragment sizes---------------------------------------tcounts(t get_countssG---------Getting fragment counts---------------------------------------N(tcalltpyatac.make_vplotRtpyatac.make_bias_vplotRtbgtNonetfastatsystexittpyatac.signal_around_sitesRtpyatac.get_insRtpyatac.get_covR tpyatac.get_nucleotideR tpyatac.make_bias_trackRtpyatac.get_pwmRtpyatac.get_sizesRtpyatac.get_countsR( targsRRRRRR R RRRR((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyt pyatac_mains\                    cCs¯tjddddƒ}|jdddddtƒ|jd d ƒ}t|ƒt|ƒt|ƒt|ƒt |ƒt |ƒt |ƒt |ƒt |ƒt|ƒ|S( sPrepares argparse object t descriptions3%(prog)s -- Utilitis for working with ATAC-Seq datatepilogsCFor command line options for each command, type %(prog)s COMMAND -hs --versiontactiontversions %(prog)s tdestR(targparsetArgumentParsert add_argumentRtadd_subparserstadd_nucleotide_parsertadd_vplot_parsertadd_bias_vplot_parsertadd_pwm_parsertadd_signal_parsertadd_ins_parsertadd_cov_parsertadd_bias_parsertadd_sizes_parsertadd_counts_parser(t argparsert subparsers((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyt pyatac_parser;s           c Cs|jdddƒ}|jddƒ}|jddddd d tƒ|jd dd d tdd ƒ|jddƒ}|jdddddƒ|jddddddtddƒ|jddƒ}|jdddddddd tƒ|jd!dddd"dd#d tƒd$S(%s0Add argument parsers for the sizes utility Rthelps8pyatac function-- compute fragment counts within windowstRequiredsNecessary argumentss--bamtmetavartbam_files Aligned readstrequireds--bedtbed_files"Windows in which to compute countstOptionssOptional settingss--outtoutput_basenamesBasename for outputs --not_atacR)t store_falseR+tatactdefaultsDon't use atac offsetssFragment size bounds optionsUpper and lower limitss--lowertints0lower limit on insert size. Default is 0ittypes--uppers3upper limit on insert size. Default is 500iôN(t add_parsertadd_argument_groupR.tTrueRH(R;tparsertgroup0tgroup3tgroup4((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyR9Zs%c CsO|jdddƒ}|jddƒ}|jddddd d tƒ|jd ƒ}|jd dd ddƒ|jddƒ}|jdddddƒ|jddddddtddƒ|jddƒ}|jddddddd d!tƒ|jd"dddd#dd$d!tƒ|jd%d&ƒ}|jd'dd(dtdd)ƒd*S(+s0Add argument parsers for the sizes utility RR=s4pyatac function-- compute fragment size distributionR>sNecessary argumentss--bamR?R@s Aligned readsRAs-Find only fragmentsizes for regions of genomes--bedRBsOOnly compute size distribution for fragment centered within regions in bed fileRCsOptional settingss--outRDsBasename for outputs --not_atacR)RER+RFRGsDon't use atac offsetssFragment sizs bounds optionsUpper and lower limitss--lowerRHs0lower limit on insert size. Default is 0iRIs--uppers3upper limit on insert size. Default is 500iôs Plot optionss Make plots?s --no_plott store_truesDon't plot outputN(RJRKR.RLRHtFalse(R;RMRNtgroup2RORPtgroup5((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyR8os"%c Csó|jdddƒ}|jddƒ}|jddddd d tƒ|jd d ƒ}|jd ddddddƒ|jdƒ}|jdddddƒ|jddƒ}|jdddddƒ|jddddddddtƒd S(!s/Add argument parsers for the bias utility R R=s(pyatac function-- compute Tn5 bias scoreR>sNecessary argumentss--fastaR?t fasta_filesAccepts fasta fileRAs PWM options*Designate PWM file or default will be useds--pwmtTn5_PWMsAPWM descriptor file. Default is Human.PWM.txt included in packageRGtHumans$Find only bias for regions of genomes--bedRBs<Positions around which to get nucleotide frequenciesRCsOptional settingss--outRDsBasename for outputs--coresRHsnumber of cores to useiRIN(RJRKR.RLRH(R;RMRNtgroup1RSRO((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyR7…s c Cs¼|jdddƒ}|jddƒ}|jddddd d tƒ|jd dd dd d tƒ|jddƒ}|jdddddƒ|jddƒ}|jddddddtƒ|jddddddddtƒ|jddddd dd!dtƒ|jd"dddd#dd$dtƒ|jd%dd&d'd(dtdd)ƒ|jd*dd&d'd+dtdd,ƒ|jd-dd.dd/ƒ|jd0dddd1dd2dtƒd3S(4s5Add argument parsers for the nucleotide utility RR=sHpyatac function-- get nucleotide (or di-nucleotide) content around sitesR>sNecessary argumentss--fastaR?RUsAccepts fasta fileRAs--bamR@s)Reads around which to get nucleotide freqs Input sitessQIf bed provided, find nucleotide frequencies around read starts within bed regions--bedRBsRegions from which to use readsRCsOptional settingss--dinucleotideR)RQs=Compute dinucleotide frequencies instead of single nucleotideRGs--flankRHsDBases away from insertion site to get frequencies for. Default is 10i RIs--lowers(lower limit on insert size. default is 0is--uppers+upper limit on insert size. default is 2000iÐs --not_atacRER+RFsDon't use atac offsetss--no_symtsymsDon't symmetrize PWMs--outRDsBasename for outputs--coressnumber of cores to useiN(RJRKR.RLRRRH(R;RMRXRSRO((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyR3™s"%%%%% c Cs`|jdddƒ}|jddƒ}|jddddd d tƒ|jd dd dd d tƒ|jddƒ}|jddddddtƒ|jddddddddtƒ|jddddddddtƒ|jddddddtƒ|jddddd ƒ|jd!dddd"dd#dtƒ|jd$dddtdd%ƒd&S('s5Add argument parsers for the nucleotide utility R R=sHpyatac function-- get nucleotide (or di-nucleotide) content around sitesR>sNecessary argumentss--fastaR?RUsAccepts fasta fileRAs--bedRBs<Positions around which to get nucleotide frequenciesRCsOptional settingss--dinucleotideR)RQs=Compute dinucleotide frequencies instead of single nucleotideRGs--upRHs-Bases upstream of site to get frequencies foriúRIs--downs/Bases downstream of site to get frequencies fors--strands,Column in bedfile with strand info (1-based)s--outRDsBasename for outputs--coressnumber of cores to useis--norms#Normalize by background frequenciesN(RJRKR.RLRRRH(R;RMRXRO((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyR0¯s %% c Cs|jdddƒ}|jddƒ}|jddddd d tƒ|jd dd dd d tƒ|jddƒ}|jdddƒ|jddddddddtƒ|jddƒ}|jddddddddtƒ|jddddddddtƒ|jd dddd!dtddƒ|jd"d#d$dtdd%ƒ|jd&dddtdd'ƒ|jd(dddtdd)ƒ|jd*d#d+d,d-dtdd.ƒ|jd/d0ƒ}|jd1d#d$dtdd2ƒ|jd3d#d$dtdd4ƒd5S(6s0Add argument parsers for the vplot utility RR=spyatac function-- make vplotR>sNecessary argumentss--bedR?RBs0Positions around which to generate VPlotRAs--bamR@sAccepts sorted BAM filesGeneral optionsts--outtbasenames--coresRHRGisNumber of cores to useRIs VMat optionsSize, scaling of VPlots--lowers"lower limit on insert sizeis--uppers"upper limit on insert sizeiús--flanksBhow many bases on each side of site (or center of site) to includes--scaleR)RQsScale each sites--weights.column in which weight information is includeds--strands.column in which strand information is includeds --not_atacRER+RFsDon't use atac offsetss Plot optionss Make plots?s --no_plotsDon't plot outputs --plot_extrasMake some extra plotsN(RJRKR.RLRHRR(R;RMRXRSRORT((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyR1Æs6     %c Cs>|jdddƒ}|jddƒ}|jddddd d tƒ|jd dd dd d tƒ|jddƒ}|jdddddƒ|jdddddƒ|jdddddddƒ|jddƒ}|jdddƒ|jddd dd!dd"d#tƒ|jd$d%ƒ}|jd&dd dd'dd(d#tƒ|jd)dd dd*dd+d#tƒ|jd,dd dd-d#tdd+ƒ|jd.d/d0dtƒ|jd1dd d#tdd2ƒ|jd3dd d#tdd4ƒ|jd5d6ƒ}|jd7d/d0dtdd8ƒ|jd9d/d0dtdd:ƒd;S(<s5Add argument parsers for the bias vplot utility RR=spyatac function-- make vplotR>sNecessary argumentss--bedR?RBs0Positions around which to generate VPlotRAs--sizest sizes_files,Accepts sizes file from pyatac sizes commands Bias OptionssAMust either submit a tabix-indexed bedgraph file or a fasta file.s--bgt bias_filesAccepts tabix indexed files--fastaRUsAccepts indexed fasta files--pwmRVsAPWM descriptor file. Default is Human.PWM.txt included in packageRGRWsGeneral optionsRZs--outR[s--coresRHisNumber of cores to useRIs VMat optionsSize, scaling of VPlots--lowers"lower limit on insert sizeis--uppers"upper limit on insert sizeiús--flanksBhow many bases on each side of site (or center of site) to includes--scaleR)RQs--weights.column in which weight information is includeds--strands.column in which strand information is includeds Plot optionss Make plots?s --no_plotsDon't plot outputs --plot_extrasMake some extra plotsN(RJRKR.RLRHRR(R;RMRNRXRSRORP((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyR2ès@       c CsJ|jdddƒ}|jddƒ}|jddddd d tƒ|jd dd dd d tƒ|jdddd tddƒ|jddƒ}|jdddddƒ|jddddtddddƒ|jddddtddƒ|jd dddtdd!ƒ|jd"d#ƒ}|jd$dddd%dtdd&ƒ|jd'dddd(dtdd&ƒ|jd)dddtdd7dd*ƒ|jd+dddtdd7dd,ƒ|jd-d.ƒ}|jd/dddtdd0ƒ|jd1dddtdd2ƒ|jd3dddtdd4ƒ|jd5dddtdd6ƒd7S(8s1Add argument parsers for the signal utility RR=s)pyatac function-- get signal around sitesR>sNecessary argumentss--bedR?RBs0Positions around which to generate VPlotRAs--bgtbg_files+Accepts bedgraph file that is tabix indexeds--sizestgenome_sizes_files3File with chromosome names in 1st col, sizes in 2ndsGeneral optionsRZs--outR[sbasename for outputs--coresRHRIRGisNumber of cores to uses--allR)RQsOoutput csv file (gzipped) with signal track around all sitess--no_aggs7Don't make a plot of aggregate or write up of aggregates Bed optionss Options related to bed intervalss--upsbases upstream of site to lookiús--downsbases dowstream site to looks--weightsXColumn with weight information. Signal for interval will be weighted by value in columns--strandsFColumn in which strand information is included if strand is to be usedsSignal optionssOptions related to signals--expstake exponent of values --positivesOnly include positive signals--scalesDscale each individual track by total signal values--norms0normalize aggregate track by number of intervalsN(RJRKR.RLRHRRR(R;RMRXRSRORP((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyR4sB   c CsM|jdddƒ}|jddƒ}|jddddd d tƒ|jd d ƒ}|jd ddddƒ|jdddƒ|jddddddddtƒ|jddƒ}|jddddddddtƒ|jddddddddtƒ|jd dddtdd!ƒ|jd"d#d$d%d&dtdd'ƒd(S()s.Add argument parsers for the ins utility RR=s pyatac function-- get insertionsR>sNecessary argumentss--bamR?R@sAccepts sorted BAM fileRAsGeneral optionsRZs--bedRBs"Regions in which to get insertionss--outR[s--coresRHRGisNumber of cores to useRIsinsertion optionsSize range, smoothings--lowers"lower limit on insert sizeis--uppers"upper limit on insert sizeiÐs--smoothsAsmoothing window for guassian smoothing. default is no smoothings --not_atacR)RER+RFsDon't use atac offsetsN(RJRKR.RLRH(R;RMRXRSRO((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyR56s" %c Csx|jdddƒ}|jddƒ}|jddddd d tƒ|jd d ƒ}|jd ddddƒ|jdddƒ|jddddddddtƒ|jddƒ}|jddddddddtƒ|jddddddddtƒ|jd dddtdd!dd"ƒ|jd#dd$dtdd%dd&ƒ|jd'd(d)d*d+dtdd,ƒd-S(.s.Add argument parsers for the cov utility R R=spyatac function-- get coverageR>sNecessary argumentss--bamR?R@sAccepts sorted BAM fileRAsGeneral optionsRZs--bedRBs"Regions in which to get insertionss--outR[s--coresRHRGisNumber of cores to useRIsinsertion optionsSize range, smoothings--lowers"lower limit on insert sizeis--uppers"upper limit on insert sizeiÐs--windowiysEwindow for flat smoothing of coverage. default is 121, should be odds--scaletfloati s‡scaling value. default is 10, corresponding to signal corresponding to # of fragment centers per 10 bp. Use 1 for fragments per 1 bp.s --not_atacR)RER+RFsDon't use atac offsetsN(RJRKR.RLRHR`(R;RMRXRSRO((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyR6Ms& %(R,tpyatacRR&R<R9R8R7R3R0R1R2R4R5R6(((s0/tmp/pip-install-bGcd2k/NucleoATAC/pyatac/cli.pyts  7       " & (