o Nrf<@@sddlZddlZddlZddlZddlmZmZmZm Z m Z m Z ddl m Z ddZdddZdd Zd d Zdd d ZdddZddZddZGdddeZedkrZedSdS)N)Fasta wrap_sequence FetchError ucsc_split bed_splitget_valid_filename) defaultdictc stjj\}}|r|dd}tjj}jr!fdd}t jj t j j j|jj d}t\}}|sD|}d}|D]}||\} } } | dkrVqHjr{| durf| durf| | } nt|| } jd| kszjd| kr{qHjrddd | | | |fD} t| } t| d }n jrj}ntj}z/jr|sjd kr|d d }|t|| | | nt|| | | D]}||qWnt y}zt t!|dd}~wwjr|"qH|#dS)Ncstj| SN)recompileregexsearch)xargsT/var/www/html/software/conda/envs/catlas/lib/python3.10/site-packages/pyfaidx/cli.pysz write_sequence..) default_seqZ key_functionZ strict_bounds split_char filt_functionZread_long_namesZrebuildFr.css|] }|rt|VqdSr )str).0errr 'sz!write_sequence..w nucleotidez name start end A T C G N others Tz Try setting --lazy. )$ospathsplitextfastar r r rZ invert_matchrrevalZheader_functionZlazy delimiterZ long_namesZ no_rebuild split_regionskeysZ size_rangelenZ split_filesjoinropenoutsysstdout transformwritetransform_sequencefetch_sequencerrclose__exit__)r_extrr"regions_to_fetchsplit_functionheaderregionnamestartendZ sequence_lenfilenameoutfilelinerrrrwrite_sequence sZ  .       r?c csz1|jj|j}|jr)||kr)|dur)|dur)|||d|d}|jj}n||||}WntyItj dj dit YdSw|jrP|j}|jrV|j}|j r[dS|j r_n|sc|rq|jsqdd|jdgVn dd|jdgVt||jD]}|VqdS)Nr z"warning: {name} not found in file > r)faidxindexlenc auto_strandreverse complementKeyErrorr+stderrr.formatlocals no_outputZno_namesZ no_coordsr(Z fancy_namer9rseq)rr"r9r:r;line_lensequencer>rrrr0>s4  r0c Cst|jd|jd}t|\}}|D]I}||\}}}|jrG|r&|r&||}n|s1|s1t||}n t||||}||j||||<q|jrZ||||||||<qdS)NT)mutabler) rr"r$r%mask_with_default_seqr'r mask_by_caseZ lowercase) rr"r5r6r8rnamer:r;spanrrr mask_sequence[s   rVcCs*|jr |j}t}||fS|j}t}||fSr )bedrregionsr)rr5r6rrrr%nsr%csZ|jj|j}||||}|jr|j}|jr|j}|jr dS|jdkr2dj|j|j d|j dS|jdkrAdj|jt |dS|jdkrt | tt}|fd d tD|d d }|d d } |dd } |dd } |dd } ddd |D} djd|j|j |j dtS|jdkrdj|j|j |j t |dSdS)NrWz{name} {start} {end} r )r9r:r; chromsizesz{name} {length} )r9lengthrcsg|] }||fqSr)count)rcssrr sz&transform_sequence..ArTCGN|cSs"g|] \}}d|t|fqS):)r(r)rkvrrrr_s"z5{sname} {sstart} {send} {A} {T} {C} {G} {N} {others} )ZsnameZsstartsend transposedz{name} {start} {end} {seq} )r9r:r;rNr)rCrDrErHrGrMr-rKr9r:r;r'rupperrintupdatesetpopr(itemsrL)rr"r9r:r;rOsZnucsr`rarbrcrdothersrr]rr/xs4           r/c Csddlm}tjddd}|jdtdd|jd td d d |d }|d}|d}|jddtddd|jddtddd|jddtddd|jdddd d!d"|jd#d$dd d%d"|jd&d'dd d(d"|jd)d*tdd+d,| }|jd-d.dd d/d"|jd0d1dd d2d"|jd3d4dd d5d"|jd6d7dd d8d"|jd9d:dd d;d"|jdd,|jd?d@tddAd,|jdBdCtdDdEd,|jdFdGtdHdIdJdK|dL}|jdMdNtdOdPd,|jdQdRdd dSd"| }|jdTdUdd dVd"|jdWdXdd dYd"|jdZdd d[d"|jd\dd d]d"|jd^d_|d`dat t j dbkr7|s7|t dbn |r@||} n|} | jr\| jrRt jdc| jr\t jdd| jsd| jrjt| dSt| dS)eNr) __version__zFetch sequences from FASTA. If no regions are specified, all entries in the input file are returned. Input FASTA file must be consistently line-wrapped, and line wrapping of output is based on input line lengths.zPlease cite: Shirley MD, Ma Z, Pedersen BS, Wheelan SJ. (2015) Efficient "pythonic" access to FASTA files using pyfaidx. PeerJ PrePrints 3:e1196 https://dx.doi.org/10.7287/peerj.preprints.970v1) descriptionepilogr"z FASTA file)typehelprX*z=space separated regions of sequence to fetch e.g. chr1:1-1000)rvnargsrwz input optionszoutput optionszheader optionsz-bz--bedrz1bed file of regions (zero-based start coordinate)z-oz--outrz"output file name (default: stdout)z-iz --transform)rWrYrrjzItransform the requested regions into another format. default: %(default)s)rvchoicesrwz-cz --complement store_trueFz-complement the sequence. default: %(default)s)actiondefaultrwz-rz --reversez*reverse the sequence. default: %(default)sz-yz --auto-strandzQreverse complement the sequence when start > end coordinate. default: %(default)sz-az --size-rangezZselected sequences are in the size range [low, high]. example: 1,1000 default: %(default)s)rvr~rwz-nz --no-namesz5omit sequence names from output. default: %(default)sz-fz --long-nameszpoutput full (long) names from the input fasta headers. default: headers are truncated after the first whitespacez-tz --no-coordszOomit coordinates (e.g. chr:start-end) from output headers. default: %(default)sz-xz --split-fileszEwrite each region to a separate file (names are derived from regions)z-lz--lazyz>fill in --default-seq for missing ranges. default: %(default)sz-sz --default-seqzDdefault base for missing positions and masking. default: %(default)sz-dz --delimiterzjdelimiter for splitting names to multiple values (duplicate names will be discarded). default: %(default)sz-ez--header-functionzlambda x: x.split()[0]z]python function to modify header lines e.g: "lambda x: x.split("|")[0]". default: %(default)sz-uz--duplicates-actionstop)rfirstlastlongestZshortestzQentry to take when duplicate sequence names are encountered. default: %(default)s)rvr~r{rwzmatching argumentsz-gz--regexz.*zNselected sequences are those matching regular expression. default: %(default)sz-vz--invert-matchzRselected sequences are those not matching 'regions' argument. default: %(default)sz-mz--mask-with-default-seqzs&   5 9