DUf!RddlZddlmZddlmZddlmZddlZddl Z ddl m Z ddl mZmZddlmZgd Zd d d d d ddededededededee je jffdZ d de jdede jfdZde jde jfdZd!dedede jfdZGddZdS)"N)partial)Union)urljoin) assembly_info)read_chromsizes read_table)SCHEMAS)fetch_chromsizesfetch_centromeres UCSCClientlocalFTz ^chr[0-9]+$z ^chr[XY]$z^chrM$)provideras_bed filter_chromschrom_patternsnatsortdbrrrrrreturnc |dkr9t|}|r!|jgdS|jS|dkrt |jd||||d|St d|d) a Fetch chromsizes from local storage or the UCSC database. Parameters ---------- db : str Assembly name. provider : str, optional [default: "local"] The provider of chromsizes. Either "local" for local storage or "ucsc". as_bed : bool, optional If True, return chromsizes as an interval DataFrame (chrom, start, end) instead of a Series. The remaining options only apply to provider="ucsc". 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. **kwargs : Passed to :func:`pandas.read_csv` Returns ------- Series of integer bp lengths indexed by sequence name or BED3 DataFrame. Notes ----- For more fine-grained control over the chromsizes from local storage, use :func:`bioframe.assembly_info`. Examples -------- >>> fetch_chromsizes("hg38") name chr1 248956422 chr2 242193529 chr3 198295559 ... ... chrX 156040895 chrY 57227415 chrM 16569 Name: length, dtype: int64 >>> fetch_chromsizes("hg38", as_bed=True) chrom start end 0 chr1 0 248956422 1 chr2 0 242193529 2 chr3 0 198295559 ... ... 21 chrX 0 156040895 22 chrY 0 57227415 23 chrM 0 16569 See also -------- bioframe.assembly_info bioframe.UCSCClient r)chromstartenducscrrrrUnknown provider ''N)r viewframecopy chromsizesr r ValueError)rrrrrrkwargsassemblys R/var/www/html/software/conda/lib/python3.11/site-packages/bioframe/io/resources.pyr r sN7 $$  '%&?&?&?@EEGG G& & V  .z"~~. ')       9h999:::gieStaincybband_colc |||dk}|dd}g}|D]\}}t|dks"td|dt||d}|||jd d|jd d |jd d d t j|S) a Extract chromosomal origin positions separating chromosome arms from cytological band data. Takes the cytological origin, i.e. the boundary between the two bands labeled 'acen'. Parameters ---------- cyb : pandas.DataFrame DataFrame with cytoband data. Returns ------- pandas.DataFrame A dataframe with columns 'chrom', 'start', 'end', 'mid'. acenrF)sortzExpected 2 'acen' bands for z, found rrrrrrrmid) groupbylenr# sort_valuesappendilocpd DataFrame from_records)r)r*groupedcensrgroupacenss r&_origins_from_cytobandr=ms$ c(mv% &Ckk'k..G D   u5zzQWEWW3u::WWXX X!!'** Aw/z!}U+z!}U+        < $ $T * **r'r:c8|dtjtjd}|d|dzdz|d<|gddd }|S) a Extract chromosomal origin positions from UCSC centromeres.txt table describing centromere model sequences. Takes the midpoint of all modeled centromere sequences. Parameters ---------- cens : pandas.DataFrame DataFrame with centromeres.txt data. Returns ------- pandas.DataFrame A dataframe with columns 'chrom', 'start', 'end', 'mid'. r)rrrrr.r0r/T)drop)r1aggnpminmax reset_indexr3)r:s r&_origins_from_ucsccentromeresrEs << $ $rvbf%E%E F F R R T TD=4;.14DK - - -. W   $   Kr'c|dkr>m>v>>>r'c Pt|jd}t|fdgdd|S)Nzdatabase/gap.txt.gzgap)rrrlengthtypebridge)rRusecolsr`ras r& fetch_gapszUCSCClient.fetch_gapssIdl$9::  III      r'rIc ~|rt|jd}nt|jd}t|dS)Nzdatabase/cytoBandIdeo.txt.gzzdatabase/cytoBand.txt.gzrH)rRr`)r[rIr$r^s r&rLzUCSCClient.fetch_cytobandsD  D$,(FGGCC$,(BCCC#j1111r'c `t|jd}t|fdtdi|S)Nzdatabase/all_mrna.txt.gzrRall_mrna)rrZr r ras r& fetch_mrnazUCSCClient.fetch_mrna"sEdl$>??   :&    r'N)TrTF)F)__name__ __module__ __qualname__rYstrr\booltuplerr6Seriesr7r r rhrLrlrr'r&r r s1HC3CCCC # I          ry",& '    $?R\????   2242bl2222 bl      r'r )r()r)rM functoolsrtypingr urllib.parsernumpyrApandasr6r%rfileopsrr schemasr __all__rprqrrrsr7r r=rEr r rr'r&r|s  ######00000000   EV;V;V; V;V;  V;  V;  V;V; 29bl "#V;V;V;V;t(2!+!+ !+!$!+\!+!+!+!+H 4G;G;#G;G;2<G;G;G;G;T3 3 3 3 3 3 3 3 3 3 r'