o Rŀg(@sndZddlZddlmZddlmZddlmZddlmZGdddeZed kr5dd l m Z e dSdS) z;Command line wrapper for the motif finding program XXmotif.N) _Argument)_Option)_Switch)AbstractCommandlinec@seZdZdZdddZdS)XXmotifCommandlineuCommand line wrapper for XXmotif. http://xxmotif.genzentrum.lmu.de/ Notes ----- Last checked against version: 1.3 References ---------- Luehr S, Hartmann H, and Söding J. The XXmotif web server for eXhaustive, weight matriX-based motif discovery in nucleotide sequences, Nucleic Acids Res. 40: W104-W109 (2012). Hartmann H, Guthoehrlein EW, Siebert M., Luehr S, and Söding J. P-value based regulatory motif discovery using positional weight matrices, Genome Res. 23: 181–194 (2013) Examples -------- >>> from Bio.motifs.applications import XXmotifCommandline >>> out_dir = "results" >>> in_file = "sequences.fasta" >>> xxmotif_cline = XXmotifCommandline(outdir=out_dir, seqfile=in_file, revcomp=True) >>> print(xxmotif_cline) XXmotif results sequences.fasta --revcomp You would typically run the command line with xxmotif_cline() or via the Python subprocess module, as described in the Biopython tutorial. XXmotifc s.tdtddgddddddtd d gd ddd ddtgd ddddtgddtgddtgddtgddtgddddddtgddddddtgd d!d"dddtgd#d$d%dddtgd&d'd(dddtgd)d*tgd+d,d-dddtgd.d/tgd0d1d2dddtgd3d4fd5dddtgd6d7d8dddtgd9d:d;dddtgd<d=tgd>d?d@dddtgdAdBfdCdddtgdDdEdddtgdFdGdHdddtgdIdJdKdddtdLdMgdNtdOdPgdQtdRdSgdTg|_tj||fi|dUS)VzInitialize the class.ACGTNXoutdirOUTDIRz output directory for all resultsTcSsd|vS)N xr r T/var/www/html/myenv/lib/python3.10/site-packages/Bio/motifs/applications/_xxmotif.py?z-XXmotifCommandline.__init__..)filename is_requiredchecker_functionseqfileSEQFILEz:file name with sequences from positive set in FASTA formatcSstj|ddkS)Nr)ospathsplitr r r rrGs)z--negSetnegSetNEGSETnegsetz4sequence set which has to be used as a reference setF)requate)z--zoopsZOOPSzoopsz7use zero-or-one occurrence per sequence model (DEFAULT))z--mopsMOPSmopsz*use multiple occurrence per sequence model)z--oopsOOPSoopsz%use one occurrence per sequence model)z --revcompREVCOMPrevcompz?search in reverse complement of sequences as well (DEFAULT: NO))z--background-model-orderzbackground-model-orderzBACKGROUND-MODEL-ORDERbackground_model_orderz;order of background distribution (DEFAULT: 2, 8(--negset) )cS t|tSN isinstanceintr r r rrf )rr)z--pseudoPSEUDOpseudoz-percentage of pseudocounts used (DEFAULT: 10)cSr(r)r*r r r rrlr-)z-gz--gapsGAPSgapsz>maximum number of gaps used for start seeds [0-3] (DEFAULT: 0)cS|dvS)N)r r r r rrrr)z--typeTYPEtypezdefines what kind of start seeds are used (DEFAULT: ALL)possible types: ALL, FIVEMERS, PALINDROME, TANDEM, NOPALINDROME, NOTANDEMcSr2)N) ALLallFIVEMERSfivemers PALINDROME palindromeTANDEMtandem NOPALINDROME nopalindromeNOTANDEMnotandemr r r r rry)z--merge-motif-thresholdzmerge-motif-thresholdzMERGE-MOTIF-THRESHOLDmerge_motif_thresholdzddefines the similarity threshold for merging motifs (DEFAULT: HIGH)possible modes: LOW, MEDIUM, HIGHcSr2)N)LOWlowMEDIUMmediumHIGHhighr r r r rrrB)z--no-pwm-length-optimizationzno-pwm-length-optimizationzNO-PWM-LENGTH-OPTIMIZATIONno_pwm_length_optimizationz=do not optimize length during iterations (runtime advantages))z--max-match-positionszmax-match-positionszMAX-MATCH-POSITIONSmax_match_positionsz^max number of positions per motif (DEFAULT: 17, higher values will lead to very long runtimes)cSr(r)r*r r r rrr-)z--batchBATCHbatchz:suppress progress bars (reduce output size for batch jobs))z--maxPosSetSize maxPosSetSize MAXPOSSETSIZE maxpossetsizezEmaximum number of sequences from the positive set used [DEFAULT: all]cSr(r)r*r r r rrr-)z--trackedMotif trackedMotif TRACKEDMOTIF trackedmotifzEinspect extensions and refinement of a given seed (DEFAULT: not used)ctfdd|DS)Nc3|]}|vVqdSr)r .0c_valid_alphabetr r @XXmotifCommandline.__init__....anyr rYr rr)z--formatFORMATformatzEdefines what kind of format the input sequences have (DEFAULT: FASTA)cSr2)N)FASTAfastaMFASTAmfastar r r r rrr)z--maxMultipleSequencesmaxMultipleSequencesMAXMULTIPLESEQUENCESmaxmultiplesequencesz?maximum number of sequences used in an alignment [DEFAULT: all]cSr(r)r*r r r rrr-)z--localization LOCALIZATION localizationzfuse localization information to calculate combined P-values(sequences should have all the same length))z --downstream DOWNSTREAM downstreamzJnumber of residues in positive set downstream of anchor point (DEFAULT: 0)cSr(r)r*r r r rrr-)z-mz --startMotif startMotif STARTMOTIF startmotifzStart motif (IUPAC characters)crT)Nc3rUr)r rVrYr rr[r\r]r^r rYr rrr`)z-pz --profileFile profileFile PROFILEFILE profilefilez profile file)z --startRegion startRegion STARTREGION startregionzWexpected start position for motif occurrences relative to anchor point (--localization)cSr(r)r*r r r rrr-)z --endRegion endRegion ENDREGION endregionzUexpected end position for motif occurrences relative to anchor point (--localization)cSr(r)r*r r r rrr-z --XXmaskermaskerzImask the input sequences for homology, repeats and low complexity regionsz--XXmasker-pos maskerposzKmask only the positive set for homology, repeats and low complexity regionsz --no-graphics nographicsz$run XXmotif without graphical outputN)setrrr parametersr__init__)selfcmdkwargsr rYrr3s0         KzXXmotifCommandline.__init__N)r)__name__ __module__ __qualname____doc__rr r r rrs r__main__) run_doctest) rrBio.Applicationrrrrrr Bio._utilsrr r r rs    t