o RŀgQ'@sZdZddlmZddlmZddlmZGdddeZedkr+ddlmZed Sd S) zFCommand line wrapper for the multiple alignment program Clustal Omega.)_Option)_Switch)AbstractCommandlinec@seZdZdZdddZdS)ClustalOmegaCommandlineuCommand line wrapper for clustal omega. http://www.clustal.org/omega Notes ----- Last checked against version: 1.2.0 References ---------- Sievers F, Wilm A, Dineen DG, Gibson TJ, Karplus K, Li W, Lopez R, McWilliam H, Remmert M, Söding J, Thompson JD, Higgins DG (2011). Fast, scalable generation of high-quality protein multiple sequence alignments using Clustal Omega. Molecular Systems Biology 7:539 https://doi.org/10.1038/msb.2011.75 Examples -------- >>> from Bio.Align.Applications import ClustalOmegaCommandline >>> in_file = "unaligned.fasta" >>> out_file = "aligned.fasta" >>> clustalomega_cline = ClustalOmegaCommandline(infile=in_file, outfile=out_file, verbose=True, auto=True) >>> print(clustalomega_cline) clustalo -i unaligned.fasta -o aligned.fasta --auto -v You would typically run the command line with clustalomega_cline() or via the Python subprocess module, as described in the Biopython tutorial. clustalocKsgtgdddddtgdddddtdd gd tgd d dddtgd d dddtgddddddtddgdtddgdddddtddgddddtddgddddtd d!gd"dddtd#d$gd%dddtd&d'gd(td)d*gd+td,d-gd.d/dd0td1d2gd3dd4td5d6gd7td8d9gd:tgd;dgd?dd@ddtgdAdBtdCdDgdEdFdd0tdGdHgdIdJdd0tgdKdLddMddtdNdOgdPddQddtdRdSgdTddUddtdVdWgdXddYddtdZd[gd\dd]ddtd^d_gd`tdadbgdcdddddtgdedfdddtgdgdhtgdidjtdkdlgdmtdndogdptdqdrgds|_tj||fi|dtS)uzInitialize the class.)z-iz--inz--infileinfilezMultiple sequence input fileTF)filenameequate)z--hmm-inz HMM input hmm_inputzHMM input filesz --dealigndealignzDealign input sequences)z --profile1z--p1profile1zFPre-aligned multiple sequence file (aligned columns will be kept fix).)z --profile2z--p2profile2)z-tz --seqtypeseqtypez:{Protein, RNA, DNA} Force a sequence type (default: auto).cS|dvS)N)proteinrnadnaProteinRNADNAPROTEINxrrX/var/www/html/myenv/lib/python3.10/site-packages/Bio/Align/Applications/_ClustalOmega.pyPz2ClustalOmegaCommandline.__init__..)r checker_functionz --is-profile isprofilez4disable check if profile, force profile (default no)z--infmtinfmtzForced sequence input file format (default: auto) Allowed values: a2m, fa[sta], clu[stal], msf, phy[lip], selex, st[ockholm], vie[nna] cSrN) a2mfafastacluclustalmsfphyphylipselexst stockholmvieviennarrrrrr^rz --distmat-in distmat_inzAPairwise distance matrix input file (skips distance computation).z --distmat-out distmat_outz%Pairwise distance matrix output file.z--guidetree-in guidetree_inzRGuide tree input file (skips distance computation and guide-tree clustering step).z--guidetree-out guidetree_outzGuide tree output file.z--full distmat_fullzKUse full distance matrix for guide-tree calculation (slow; mBed is default)z --full-iterdistmat_full_iterzVUse full distance matrix for guide-tree calculation during iteration (mBed is default)z--cluster-size clustersizez)soft maximum of sequences in sub-clusterscS t|tSN isinstanceintrrrrr )rz--clustering-out clusteringoutzClustering output file)rz --use-kimura usekimurazAuse Kimura distance correction for aligned sequences (default no)z --percent-id percentidz6convert distances into percent identities (default no))z-oz--outz --outfileoutfilez:Multiple sequence alignment output file (default: stdout).z--outfmtoutfmtzgMSA output file format: a2m=fa[sta],clu[stal],msf,phy[lip],selex,st[ockholm],vie[nna] (default: fasta).cSrr rrrrrrr)z--residuenumberz--resno residuenumberz4in Clustal format print residue numbers (default no)z--wrapwrapz-number of residues before line-wrap in outputcSr5r6r7rrrrrr:z--output-order outputorderz)MSA output order like in input/guide-treecSr)N)z input-orderz tree-orderrrrrrrs)z --iterationsz--iter iterationsz.Number of (combined guide-tree/HMM) iterationscSr5r6r7rrrrrr:z--max-guidetree-iterationsmax_guidetree_iterationsz&Maximum number of guidetree iterationscSr5r6r7rrrrrr:z--max-hmm-iterationsmax_hmm_iterationsz Maximum number of HMM iterationscSr5r6r7rrrrrr:z --maxnumseq maxnumseqz#Maximum allowed number of sequencescSr5r6r7rrrrrr:z --maxseqlen maxseqlenzMaximum allowed sequence lengthcSr5r6r7rrrrrr:z--autoautoz@Set options automatically (might overwrite some of your options)z --threadsthreadszNumber of processors to usecSr5r6r7rrrrrr:)z-lz--loglogz*Log all non-essential output to this file.)z-hz--helphelpzPrint help and exit.)z-vz --verboseverbosezVerbose outputz --versionversionz"Print version information and exitz--long-version long_versionz'Print long version information and exitz--forceforcezForce file overwriting.N)rr parametersr__init__)selfcmdkwargsrrrrQ.s "&?EKQW[_dimrx%+28?CI O P QR VXz ClustalOmegaCommandline.__init__N)r)__name__ __module__ __qualname____doc__rQrrrrrsr__main__) run_doctestN) rXBio.ApplicationrrrrrU Bio._utilsrZrrrrs   }