DUfKfddlZddlZddlZddlZddlZddlZddlZddlmZddl m Z ddl Z ddl Z ddlZn #e$rdZYnwxYw ddlZn #e$rdZYnwxYwddlmZddlmZddlmZmZgd Zdd Z ddZddZ d dZddZddZGddZ d!dZ!d"dZ"d"dZ#d#dZ$d$dZ%dS)%N) OrderedDict)closing) argnatsort) parse_region) BAM_FIELDSSCHEMAS) read_tableread_chromsizes read_tabix read_pairixread_bam load_fasta read_bigwig to_bigwig read_bigbed to_bigbedFc |dd|dd|ddt|tr+|dr|dd |x |d t|nU#t t f$rAt|trtd |d |d |YnwxYwtj |fi|}|rM| d d k rtd|S)a; Read a tab-delimited file into a data frame. Equivalent to :func:`pandas.read_table` but supports an additional `schema` argument to populate column names for common genomic formats. Parameters ---------- filepath_or : str, path object or file-like object Any valid string path is acceptable. The string could be a URL schema : str Schema to use for table column names. schema_is_strict : bool Whether to check if columns are filled with NAs. Returns ------- df : pandas.DataFrame of intervals sep headerN index_colF.gz compressiongzipnameszTSV schema not found: ''raxiszvone or more columns are all NA, check agreement between number of fields in schema and number of columns in input file) setdefault isinstancestrendswithr KeyError TypeError ValueErrorpdread_csvnotnasumany) filepath_orschemaschema_is_strictkwargsdfs P/var/www/html/software/conda/lib/python3.11/site-packages/bioframe/io/fileops.pyr r *s* eT""" h%%% k5)))+s##1 (<(.chrom.sizes`` or ``.chromInfo.txt`` file from the UCSC database, where ``db`` is a genome assembly name, as a `pandas.Series`. Parameters ---------- filepath_or : str or file-like Path or url to text file, or buffer. filter_chroms : bool, optional Filter for chromosome names given in ``chrom_patterns``. chrom_patterns : sequence, optional Sequence of regular expressions to capture desired sequence names. natsort : bool, optional Sort each captured group of names in natural order. Default is True. as_bed : bool, optional If True, return chromsizes as an interval dataframe (chrom, start, end). **kwargs : Passed to :func:`pandas.read_csv` Returns ------- Series of integer bp lengths indexed by sequence name or an interval dataframe. Notes ----- Mention name patterns See also -------- * UCSC assembly terminology: * NCBI assembly terminology: rrrrrrnamelength)rusecolsrdtyperstart)r5r9r6chromend)r5r6columnsT)drop)r"r#r$r!r(r)lencontainsilocrappendconcatrename reset_indexvaluesindex) r- filter_chromschrom_patternsnatsortas_bedr0 chromtablepartspatternparts r2r r VsR+s##1 (<( >                    IsA)BB #B c ddl}ddl} |i}| |d} | } t | r|d| } d| vrQ|Od| dD} t | r.|,t d| D\}}tj||}d | vr*(| d d d dt||\}}}|t||\}}}n|||}}}| ||||||}|fd |Dfd |D}|n|}tj | }LD]I}||vr%||||||<+tj||d||<J|S)z4 Read a pairix-indexed file into DataFrame. rNrc8|ddS)N:rsplit)xs r2zread_pairix..s QrOz #chromsizecFg|]}|ddS)rNr_).0lines r2 zread_pairix..s)NNN$TZZ\\!""%NNNrOc3PK|]!}|dt|dfV"dS)rrN)int)rditems r2 zread_pairix..s5&Q&Q4QT!W'>&Q&Q&Q&Q&Q&QrO)rFdataz#columnsrc:g|]}|S)rF)rdcolr<s r2rfzread_pairix..s%<<..s'22!F1I222222rOrm)rdrr argusecolss @r2rfzread_pairix..s/DDDv2222z222DDDrOr<ignore)cytoolzpypairixopen get_headerr>groupbyzipr(Seriesr`rquery2D DataFrame from_recordsastype to_numeric)rYregion1region2 chromsizesr<r7dtypesr0toolzrwrZr header_groupsitemsrlengthschrom1start1end1chrom2start2end2itrecordsr1rnrss ` @r2rrs!OOO ~ b#A \\^^F 6{{? &?&?HH = ( (Z-?NN- 2MNNNE5zz Bj0!$&Q&Q5&Q&Q&Q!RwYUAAA  & &7?#J/288::122>G'<<FFD+GZ@@%vt 664 > >B<<<.s?XXXAQd1gg&<&< !DXXXrOrt)rRospathsplitextr'r AlignmentFilerXtagsrAqnameflagreference_nameposmapq cigarstringnpnanrnextpnexttlenseqqualjsondumpsdictr(r~r ) rYr:r9r;rRextmoderZrsrr1s r2read_alignmentrsLLL '  2  q !C f}}  C===>>> $$R.. / /71s++  AXXQRQWXXXD NNGF$EF%&Vq[[AMMbfGGFEFJtDzz**      \': 6 6 6+777777777777777, Is:CEE!$E!c&t||||S)zU Deprecated: use `read_alignment` instead. Read bam file into dataframe, )r)rYr:r9r;s r2rrs "eUC 0 00rOceZdZdZdZdS)PysamFastaRecordc`||_||jvrtd|d|d||_dS)NzReference name 'z' not found in 'r)ff referencesr%ref)selfrrs r2__init__zPysamFastaRecord.__init__sC bm # #HcHH2HHHII IrOct|tr|j|j}}n|}|dz}|j|j||S)Nr)r"slicer9stoprrXr)rkeyr9rs r2 __getitem__zPysamFastaRecord.__getitem__#sK c5 ! ! )SX4EEE7Dw}}TXud333rON)__name__ __module__ __qualname__rrrmrOr2rrs2 44444rOrrRc t|t }t}|}|dkr ddl}n#t $rt dwxYw|r4|D]0}|j|fi|}|jd}t||||<1n|j|fi|}|jD]}t||||<n|dkr ddl } n#t $rt dwxYw|rM|D]I}| j |fi|}tt| }||||<Jn@| j |fi|}| D] }||||<ntd|S)a Load lazy fasta sequences from an indexed fasta file (optionally compressed) or from a collection of uncompressed fasta files. Parameters ---------- filepath_or : str or iterable If a string, a filepath to a single `.fa` or `.fa.gz` file. Assumed to be accompanied by a `.fai` index file. Depending on the engine, the index may be created on the fly, and some compression formats may not be supported. If not a string, an iterable of fasta file paths each assumed to contain a single sequence. engine : {'pysam', 'pyfaidx'}, optional Module to use for loading sequences. kwargs : optional Options to pass to ``pysam.FastaFile`` or ``pyfaidx.Fasta``. Returns ------- OrderedDict of (lazy) fasta records. Notes ----- * pysam/samtools can read .fai and .gzi indexed files, I think. * pyfaidx can handle uncompressed and bgzf compressed files. rRrNz'pysam is required to use engine='pysam'pyfaidxz+pyfaidx is required to use engine='pyfaidx'z#engine must be 'pysam' or 'pyfaidx')r"r#rlowerrR ImportError FastaFilerrrFastanextiterkeysr') r-enginer0 is_multifilerrRonefilerr5rs r2rr,s8"+s333LmmG \\^^F  I LLLL I I IGHH H I  ;& ; ;$U_W7777}Q' 0T : :  ; !7777B  ; ; 0T : :  ; 9   M NNNN M M MKLL L M  )& ) )"W]755f55DOO,, "4  ) {55f55B  ) ) "4  )>??? NsAA CC*autocT|}|dkr)tttdtd}nd}|dvrM|d}|d}tj|5}|||| }dddn #1swxYwYn|dkr{tj|}|d}|||}||||}tj |gd  }| dd |ntd ||S)a~ Read intervals from a bigWig file. Parameters ---------- path : str Path or URL to a bigWig file chrom : str start, end : int, optional Start and end coordinates. Defaults to 0 and chromosome length. engine : {"auto", "pybbi", "pybigwig"} Library to use for querying the bigWig file. Returns ------- DataFrame rNz9read_bigwig requires either the pybbi or pyBigWig packagepybbipybigwigrbbirr9r;)r9r;valuertr:2engine must be 'auto', 'pybbi' or 'pybigwig'; got ) rrpyBigWigrrxfetch_intervalschroms intervalsr(r~insertr'rr:r9r;rrZr1ivalss r2rrss&\\^^F  ;8+K _FFF !!! =E ;C Xd^^ @q""53"??B @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ :   M$   =E ;((**U#C E5#.. \%)B)B)B C C C !We$$$$VfVVWWW I$B  B B cT|}|dkr)tttdtd}nd}|dvrM|d}|d}tj|5}|||| }dddn #1swxYwYn|dkr{tj|}|d}|||}||||}tj |gd  }| dd |ntd ||S)a~ Read intervals from a bigBed file. Parameters ---------- path : str Path or URL to a bigBed file chrom : str start, end : int, optional Start and end coordinates. Defaults to 0 and chromosome length. engine : {"auto", "pybbi", "pybigwig"} Library to use for querying the bigBed file. Returns ------- DataFrame rNz9read_bigbed requires either the pybbi or pyBigWig packagerrrrrr)r9r;restrtr:r) rrrrrxrrentriesr(r~rr'rs r2rrs&\\^^F  ;8+K _FFF !!! =E ;C Xd^^ @q""53"??B @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ :   M$   =E ;((**U#C %,, \%)A)A)A B B B !We$$$$VfVVWWW Irc |7d} tj|Jn#t$rtdwxYw|drTt j|s2t j|t j rtd|d|}nqt j |d}t j|s2t j|t j rtd|dd}dD] }||j vrd }t|j d krd }|std |j | |j d }d dd|g}|| } | d t| d <| gd} t#jd5} t#jdd5} || dd | | | jd|d d dt-j|| j| j|gd} dddn #1swxYwYdddn #1swxYwY| S)m Save a bedGraph-like dataframe as a binary BigWig track. Parameters ---------- df : pandas.DataFrame Data frame with columns 'chrom', 'start', 'end' and one or more value columns chromsizes : pandas.Series Series indexed by chromosome name mapping to their lengths in bp outpath : str The output BigWig file path value_field : str, optional Select the column label of the data frame to generate the track. Default is to use the fourth column. path_to_binary : str, optional Provide system path to the bedGraphToBigWig binary. NbedGraphToBigWigzbedGraphToBigWig is not present in the current environment. Pass it as 'path_to_binary' parameter to bioframe.to_bigwig or install it with, for example, conda install -y -c bioconda ucsc-bedgraphtobigwig zHbedGraphToBigWig is absent in the provided path or cannot be fexecuted: . zGbedGraphToBigWig is absent in the provided path or cannot be executed: Tr:r9r;Fz+A bedGraph-like DataFrame is required, got r:r9r;z.bgsuffixwt .chrom.sizesrrrrrr<rFrna_repcapture_outputshutilwhich Exceptionr'r$rrisfileaccessX_OKrWr<r>copyrr# sort_valuestempfileNamedTemporaryFileto_csvflushr5 subprocessrun) r1routpath value_fieldpath_to_binarycmd is_bedgraphrnr<bgrZcsps r2rrs]*  <$$0000   )    !3 4 4 w~~n-- ")NBG2T2T 1,111 gll>+=>>w~~c"" rybg'>'> 0+000  K(   bj K 2: USrzSSTTTjm  4G G    BW+$$S))BwK 111 2 2B  $E 2 2 2  a  $T. A A A  EG"$u555   FgU5QV     N !&"'7 +                                   Hs?7J.A1I+ J+I/ /J2I/ 3JJ Jbed6c |7d} tj|Jn#t$rtdwxYw|drTt j|s2t j|t j rtd|d|}nqt j |d}t j|s2t j|t j rtd|dd}dD] }||j vrd }t|j d krd }|std |j gd}|| } | d t| d <| gd } t#jd5} t#jdd5} || dd | | | jd|d d dt-j|d|| j| j|gd} dddn #1swxYwYdddn #1swxYwY| S)rN bedToBigBedzbedToBigBed is not present in the current environment. Pass it as 'path_to_binary' parameter to bioframe.to_bigbed or install it with, for example, conda install -y -c bioconda ucsc-bedtobigbed zBbedToBigBed is absent in the provided path or cannot be executed: rrT)r:r9r;r5scorestrandFz'A bed6-like DataFrame is required, got r:rz.bedrrrrrrrz-type=rr) r1rrr.rris_bed6rnr<bedrZr r s r2rr2sY* <$$0000   $     / / w~~n-- ")NBG2T2T 0+000 gll>+=>>w~~c"" rybg'>'> 0+000  GC bj G 2: QO2:OOPPPBBBG W+    Cw<&&s++CL //333 4 4C  $F 3 3 3  q(:U ^;;;  "$u555   FgU5QV     N #6##QVRWg >                                   Hs?7I5A5I I5I" "I5%I" &I55I9<I9)NF)Tr3TF)NNN)NNNNN)rR)NNr)NN)r N)&rrUrrrrr collectionsr contextlibrnumpyrpandasr(rrr core.arropsrcore.stringopsrschemasr r __all__r r r rrrrrrrrrrmrOr2rs ######JJJJ CCCOOOOHHH%$$$$$))))))((((((((   ))))\<   JJJJZ(    4444n&&&&R1111 4 4 4 4 4 4 4 4 DDDDN4444n4444nN N N N bL L L L L L s!7AAA AA