U ñad¨vã @sddlZddlZddlZddlZddlmZddlmZej  ej  ej  ej  e ¡¡¡¡Z dZej e e¡ZdZddgZdZd Ze ¡d kr”d Zne ¡dd krªd ZndZdZdZdZdZdZdZdZdZdZ dZ!dZ"dZ#dZ$dZ%dZ&dZ'da(dZ)dZ*dZ+dZ,dZ-dZ.dZ/dZ0dZ1dZ2dZ3dZ4dZ5dZ6dZ7dZ8dZ9dZ:dZ;dZdZ?dZ@dZAdZBdZCdZDdZEdZFdZGdZHdZIdZJdZKdZLdZMdZNdZOd ZPd!ZQdZRdZSdZTdZUd"ZVd#ZWd$ej X¡ Yd%¡ZZdZ[d&Z\d'Z]d(Z^d)Z_d*Z`d+Zad,Zbd-Zcd.Zdd/Zed0Zfd1Zgd2Zhd3Zid4Zjd5Zkd6Zld7Zmd8Znd9ZodZpdZqd:Zrd;dZtd?ZudZvdZwd@ZxdZydZzdAZ{dZ|dBZ}dCZ~dDZdEZ€dFZdGZ‚dHZƒdIZ„dJZ…dKZ†dLZ‡dMZˆdNZ‰dOZŠdPZ‹d@ZŒdQZdRZŽdQZd.__next_versionrú-ú+éÿÿÿÿz Python%s: %sz and higherTzERROR! Python version z is not supported! zSupported versions are ú, Ú r ) Úsysr$rÚSUPPORTED_PYTHON_VERSIONSÚendswithÚappendÚreplacerÚstderrÚwriter#Úexit)r(Zcurrent_versionZsupported_versions_msgZsupported_versionsÚmajorZmin_incZmax_incZmax_excr&r&r'Úcheck_python_versions, $ÿÿÿr7c Cshtdkrdzddl}td| ¡dƒaWn&ttfk rL| d¡taYnX| dt tƒd¡dS)Nrr rz&Failed to determine the number of CPUsz$Maximum number of threads is set to z* (use --threads option to set it manually)) Ú max_threadsÚmultiprocessingÚmaxÚ cpu_countÚ ImportErrorÚNotImplementedErrorZwarningÚDEFAULT_MAX_THREADSZnoticer!)Zloggerr9r&r&r'Úset_max_threads.s  ÿr?cCs–d}zddlm}|j}|j}Wn\tk r|ttj t d¡ƒ}|  ¡  ¡  d¡}|  ¡|d}t|ƒdkrx|d}YnX|rŽ|d|S|SdS)Nr)r$z VERSION.txtr-r r,)rr$Ú __version__Z__git_revision__r<ÚopenÚosÚpathr#Ú QUAST_HOMEÚreadÚstriprÚcloser)Zrevisionr$ZversZ version_fileÚlinesr&r&r'Ú quast_version;s    rIcCsD|dkrtjd}d}t|ƒ d¡r*d}nt|ƒ d¡s| d¡| d¡| d¡| d¡|dkrÒ| d¡| d¡| d¡| d tttf¡| d!¡| d"t ¡| d#¡|dkr | d$¡n |dkr | d%¡n | d&¡|s:| d'¡| d(¡| d)¡| d*t¡| d+¡| d,¡| d-¡|sŒ| d.¡n,| d/¡| d0t¡| d1¡| d2¡| d3t¡| d4t¡|rä| d5¡| d6¡| d7¡| d8|¡| d9|¡| d:¡| d;t¡| d<¡| d=¡| d>t¡|rl| d?¡| d@t¡| dA¡| dB¡| dC¡| dD|¡| dE¡| dFt¡| dG¡| dHt¡| dI¡| dJt¡| dK¡| dL¡| dM¡| dN¡| dOt¡| dP¡| dQ¡| dR¡| dSttf¡| dTt¡| dU¡| dVt¡| dWdX t¡¡| dY¡| dZ¡| d[¡| d\¡| d]¡| d^¡| d_¡| d`¡| da¡| db¡| dc¡| dd¡| de¡| df¡| dg¡| dh¡| di¡| dj¡| dk¡| dl¡| d ¡| dm¡| dn¡| do¡| dp¡| dq¡| dr¡| ds¡| dt¡| du¡| dv¡|r| d ¡| dw¡| dx¡| dy¡| dz¡| d{¡|r| d|¡| d}¡| d~¡| d ¡| d¡| d€¡|rj| d¡| d‚¡| dƒ¡| d„¡n| d…¡| d†¡| d‡¡| dˆ¡| d‰¡|r¬| dŠ¡| d ¡| d‹¡| ¡dS)ŒNrrKTFz=MetaQUAST: Quality Assessment Tool for Metagenome Assemblies rLz>QUAST-LG: Quality Assessment Tool for Large Genome Assemblies z5QUAST: Quality Assessment Tool for Genome Assemblies z Version: r-zUsage: python rz [options] z Options: zr-o --output-dir Directory to store all result files [default: quast_results/results_] zp-r Comma-separated list of reference genomes or directory with reference genomes zj--references-list Text file with list of reference genome names for downloading from NCBI zr-g --features [type:] File with genomic feature coordinates in the references (GFF, BED, NCBI or TXT) zx Optional 'type' can be specified for extracting only a specific feature type from GFF z8-r Reference genome file zq-g --features [type:] File with genomic feature coordinates in the reference (GFF, BED, NCBI or TXT) zR-m --min-contig Lower threshold for contig length [default: %d] zS-t --threads Maximum number of threads [default: 25% of CPUs] z:These are basic options. To see the full list, use --help zAdvanced options: z-s --split-scaffolds Split assemblies by continuous fragments of N's and add such "contigs" to the comparison z|-l --labels "label, label, ..." Names of assemblies to use in reports, comma-separated. If contain spaces, use quotes z\-L Take assembly names from their parent directory names z_-e --eukaryote Genome is eukaryotic (primarily affects gene prediction) z[ --fungus Genome is fungal (primarily affects gene prediction) z] --large Use optimal parameters for evaluation of large genomes zq In particular, imposes '-e -m %d -i %d -x %d' (can be overridden manually) zÝ-k --k-mer-stats Compute k-mer-based quality metrics (recommended for large genomes) This may significantly increase memory and time consumption on large genomes zT --k-mer-size Size of k used in --k-mer-stats [default: %d] z7 --circos Draw Circos plot zG-f --gene-finding Predict genes using MetaGeneMark zF-f --gene-finding Predict genes using GeneMark-ES zˆ-f --gene-finding Predict genes using GeneMarkS (prokaryotes, default) or GeneMark-ES (eukaryotes, use --eukaryote) zv --mgm Use MetaGeneMark for gene prediction (instead of the default finder, see above) zt --glimmer Use GlimmerHMM for gene prediction (instead of the default finder, see above) z| --gene-thresholds Comma-separated list of threshold lengths of genes to search with Gene Finding module z4 [default: %s] zP --rna-finding Predict ribosomal RNA genes using Barrnap z\-b --conserved-genes-finding Count conserved orthologs using BUSCO (only on Linux) zl --operons File with operon coordinates in the reference (GFF, BED, NCBI or TXT) zo --est-ref-size Estimated reference size (for computing NGx metrics without a reference) z„ --max-ref-number Maximum number of references (per each assembly) to download after looking in SILVA database. zZ Set 0 for not looking in SILVA at all [default: %s] z… --blast-db Custom BLAST database (.nsq file). By default, MetaQUAST searches references in SILVA database z --use-input-ref-order Use provided order of references in MetaQUAST summary plots (default order: by the best average value) ze --contig-thresholds Comma-separated list of contig length thresholds [default: %s] zˆ --x-for-Nx Value of 'x' for Nx, Lx, etc metrics reported in addition to N50, L50, etc (0, 100) [default: %s] z{ --reuse-combined-alignments Reuse the alignments from the combined_reference stage on runs_per_reference stages. zg-u --use-all-alignments Compute genome fraction, # genes, # operons in QUAST v1.* style. zl By default, QUAST filters Minimap's alignments to keep only best ones zQ-i --min-alignment The minimum alignment length [default: %s] zc --min-identity The minimum alignment identity (80.0, 100.0) [default: %.1f] zd-a --ambiguity-usage Use none, one, or all alignments of a contig when all of them zd are almost equally good (see --ambiguity-score) [default: %s] z‚ --ambiguity-score Score S for defining equally good alignments of a single contig. All alignments are sorted z by decreasing LEN * IDY% value. All alignments with LEN * IDY% < S * best(LEN * IDY%) are za discarded. S should be between 0.8 and 1.0 [default: %.2f] zd --unique-mapping Disable --ambiguity-usage=all for the combined reference run, zk i.e. use user-specified or default ('%s') value of --ambiguity-usage zh --strict-NA Break contigs in any misassembly event when compute NAx and NGAx. zx By default, QUAST breaks contigs only by extensive misassemblies (not local ones) zy-x --extensive-mis-size Lower threshold for extensive misassembly size. All relocations with inconsistency zt less than extensive-mis-size are counted as local misassemblies [default: %s] zx --local-mis-size Lower threshold on local misassembly size. Local misassemblies with inconsistency zj less than local-mis-size are counted as (long) indels [default: %s] zu --scaffold-gap-max-size Max allowed scaffold gap length difference. All relocations with inconsistency zz less than scaffold-gap-size are counted as scaffold gap misassemblies [default: %s] zy --unaligned-part-size Lower threshold for detecting partially unaligned contigs. Such contig should have ze at least one unaligned fragment >= the threshold [default: %s] zq --skip-unaligned-mis-contigs Do not distinguish contigs with >= 50% unaligned bases as a separate group z] By default, QUAST does not count misassemblies in them zx --fragmented Reference genome may be fragmented into small pieces (e.g. scaffolded reference) zy --fragmented-max-indent Mark translocation as fake if both alignments are located no further than N bases z] from the ends of the reference fragments [default: %s] zC Requires --fragmented option zl --upper-bound-assembly Simulate upper bound assembly based on the reference genome and reads z‚ --upper-bound-min-con Minimal number of 'connecting reads' needed for joining upper bound contigs into a scaffold zY [default: %d for mate-pairs and %d for long reads] zŠ --est-insert-size Use provided insert size in upper bound assembly simulation [default: auto detect from reads or %d] a --report-all-metrics Keep all quality metrics in the main report even if their values are '-' for all assemblies or if they are not applicable (e.g., reference-based metrics in the no-reference mode) zT --plots-format Save plots in specified format [default: %s]. z< Supported formats: %s r,ze --memory-efficient Run everything using one thread, separately per each assembly. zh This may significantly reduce memory consumption on large genomes zŽ --space-efficient Create only reports and plots files. Aux files including .stdout, .stderr, .coords will not be created. zŽ This may significantly reduce space consumption on large genomes. Icarus viewers also will not be built zk-1 --pe1 File with forward paired-end reads (in FASTQ format, may be gzipped) zk-2 --pe2 File with reverse paired-end reads (in FASTQ format, may be gzipped) zƒ --pe12 File with interlaced forward and reverse paired-end reads. (in FASTQ format, may be gzipped) zj --mp1 File with forward mate-pair reads (in FASTQ format, may be gzipped) zj --mp2 File with reverse mate-pair reads (in FASTQ format, may be gzipped) z --mp12 File with interlaced forward and reverse mate-pair reads (in FASTQ format, may be gzipped) zg --single File with unpaired short reads (in FASTQ format, may be gzipped) z_ --pacbio File with PacBio reads (in FASTQ format, may be gzipped) zh --nanopore File with Oxford Nanopore reads (in FASTQ format, may be gzipped) zm --ref-sam SAM alignment file obtained by aligning reads to reference genome file zm --ref-bam BAM alignment file obtained by aligning reads to reference genome file zÐ --sam Comma-separated list of SAM alignment files obtained by aligning reads to assemblies (use the same order as for files with contigs) zÐ --bam Comma-separated list of BAM alignment files obtained by aligning reads to assemblies (use the same order as for files with contigs) zn Reads (or SAM/BAM file) are used for structural variation detection and zL coverage histogram building in Icarus zX --sv-bedpe File with structural variations (in BEDPE format) zSpeedup options: zt --no-check Do not check and correct input fasta files. Use at your own risk (see manual) z8 --no-plots Do not draw plots zS --no-html Do not build html reports and Icarus viewers zB --no-icarus Do not build Icarus viewers zx --no-snps Do not report SNPs (may significantly reduce memory consumption on large genomes) zM --no-gc Do not compute GC% and GC-distribution zy --no-sv Do not run structural variation detection (make sense only if reads are specified) a„ --no-read-stats Do not align reads to assemblies Reads will be aligned to reference and used for coverage analysis, upper bound assembly simulation, and structural variation detection. Use this option if you do not need read statistics for assemblies. z] --fast A combination of all speedup options except --no-check zHidden options: z0-d --debug Run in a debug mode zI--no-portable-html Do not embed CSS and JS files in HTML report zD-j --save-json Save the output also in the JSON format zF-J --save-json-to Save the JSON output to a particular path z†--read-support Use read coverage specified in contig names (SPAdes/Velvet style) for calculating Avg contig read support zR--cov File with read coverage (for Icarus alignment viewer) zV--phys-cov File with physical coverage (for Icarus alignment viewer) zOther: z} --silent Do not print detailed information about each step to stdout (log file is not affected) zw --test Run MetaQUAST on the data from the test_data folder, output to quast_test_output z‹ --test-no-ref Run MetaQUAST without references on the data from the test_data folder, output to quast_test_output. z€ MetaQUAST will download SILVA 16S rRNA database (~170 Mb) for searching reference genomes zF Internet connection is required zs --test Run QUAST on the data from the test_data folder, output to quast_test_output zz --test-sv Run QUAST with structural variants detection on the data from the test_data folder, zB output to quast_test_output z?-h --help Print full usage message z4-v --version Print version zW --help-hidden Print this usage message with all hidden options z?Online QUAST manual is available at http://quast.sf.net/manual )rQr4rIÚLARGE_MIN_CONTIGÚLARGE_MIN_ALIGNMENTÚLARGE_EXTENSIVE_MIS_THRESHOLDÚDEFAULT_MIN_CONTIGÚDEFAULT_MIN_ALIGNMENTÚDEFAULT_EXT_MIS_SIZEÚ META_MIN_IDYÚDEFAULT_MIN_IDYr.rMÚunique_kmer_lenÚ genes_lengthsÚmax_referencesÚcontig_thresholdsÚx_for_additional_NxÚambiguity_usageÚambiguity_scoreÚlocal_misassembly_min_lengthÚscaffolds_gap_thresholdÚunaligned_part_sizeÚMIN_CONNECT_MPÚMIN_CONNECT_LRÚoptimal_assembly_default_ISÚplot_extensionr#Úsupported_plot_extensionsrS) Z show_hiddenrPZshortÚstreamrKZ m_defaultZ i_defaultZ x_defaultZmin_idy_defaultr&r&r'ÚusagevsL                         ÿ                                                                                             rm)N)N)ßZdatetimerBÚplatformr.Zdistutils.versionrÚos.pathrrCÚabspathÚdirnameÚrealpathÚ__file__rDZ PACKAGE_NAMEr#Z LIBS_LOCATIONZ GIT_ROOT_URLr/ZLOGGER_DEFAULT_NAMEZLOGGER_META_NAMEÚsystemZ platform_nameZ architecturer`raZ min_contigrXr^Z ref_fpathZ prokaryoteZ is_fungusZ gene_findingZrna_gene_findingrbrcZmeta_ambiguity_scoreZreuse_combined_alignmentsZalignments_for_reuse_dirpathZuse_all_alignmentsr8Z min_alignmentrYZmin_IDYr\r[Zestimated_reference_sizeZ strict_NAZsplit_scaffoldsZ draw_plotsZ draw_circosZ html_reportZ save_jsonZ metagenemarkÚdebugZ portable_htmlZtestZtest_svZ test_no_refZno_checkZ no_check_metaZunique_mappingZno_gcZno_svZ no_read_statsZ show_snpsZglimmerZis_combined_refZcheck_for_fragmented_refZMAX_REFERENCE_FRAGMENTSrfZunaligned_mis_thresholdZall_labels_from_dirsZ run_buscorOZuse_kmcZreport_all_metricsZoptimal_assemblyZoptimal_assembly_insert_sizeriZoptimal_assembly_min_ISZoptimal_assembly_max_ISZsilentZ is_agb_modeZerror_log_fpathZ save_errorZtest_output_dirnameZdefault_results_root_dirnameZnowÚstrftimeZoutput_dirnameZmake_latest_symlinkZdefault_json_dirnameZcorrected_dirnameZ plots_fnameZ report_prefixZtransposed_report_prefixZ html_aux_dirZcontig_report_fname_patternZicarus_report_fname_patternZ detailed_contigs_reports_dirnameZaligner_output_dirnameZoptimal_assembly_basenameZdownloaded_dirnameZper_ref_dirnameZmeta_summary_dirZnot_aligned_nameZcombined_output_nameZ krona_dirnameZcombined_ref_nameZdownloaded_ref_min_aligned_rateZunique_contigs_fname_patternZcalculate_read_supportZuse_input_ref_orderZreads_stats_dirnameZcoverage_thresholdsZtrivial_deletions_fnameZ sv_bed_fnameZ used_colorsZused_lsZ MAX_PE_ISZ cov_fpathZphys_cov_fpathZ busco_dirnameZcreate_icarus_htmlZicarus_css_nameZicarus_script_nameZicarus_dirnameZicarus_html_fnameZicarus_menu_template_fnameZicarus_viewers_template_fnameZ icarus_linkZcontig_size_viewer_fnameZcontig_size_viewer_nameZcontig_alignment_viewer_nameZone_alignment_viewer_nameZalignment_viewer_part_nameZalignment_viewer_fpathZMAX_SIZE_FOR_COMB_PLOTZICARUS_MAX_CHROMOSOMESZmax_contigs_num_for_size_viewerZmin_contig_for_size_viewerZcontig_len_deltaZmin_similar_contig_sizeZSHORT_INDEL_THRESHOLDZSPLIT_ALIGN_THRESHOLDrdrZZextensive_misassembly_thresholdZfragmented_max_indentrWrUrVZupperbound_min_connectionsrgrhr]ZBSS_MAX_SETS_NUMBERZBSS_critical_number_of_alignsZBSS_EXTENSIVE_PENALTYZBSS_LOCAL_PENALTYr>Zassemblies_numZmemory_efficientZspace_efficientZ analyze_gapsZ min_gap_sizeZmin_gene_overlapZALL_FEATURES_TYPEZ GC_bin_sizeZGC_contig_bin_sizeZGC_window_sizeZGC_window_size_largeZassembly_labels_by_fpathZassemblies_fpathsZ max_pointsZmin_differenceZmax_coverage_binsZpcnt_covered_for_histogramZdict_of_broken_scaffoldsZNs_break_thresholdreZcustom_blast_db_fpathZdownloaded_refsZidentity_thresholdZ min_lengthZ min_bitscorer_rjrkZoutput_dirpathZ referenceZgenesZoperonsÚdictZfeaturesÚlabelsZ sam_fpathsZ bam_fpathsZ reference_samZ reference_bamZbedZ reads_fpathsZ forward_readsZ reverse_readsZmp_forward_readsZmp_reverse_readsZinterlaced_readsZmp_interlaced_readsZ paired_readsZ mate_pairsZunpaired_readsZ pacbio_readsZnanopore_readsZreferences_txtZjson_output_dirpathr7r?rIrQrTrRrmr&r&r&r'Ús¨  $   $