tfZ2ddlZddlZddlZddlZddlmcmZddl m Z m Z ddl m Z dZ d dZdZdZdZ d d Zdd Z d d Zy)N)est_query_size_ixload_bai_index) abs2genomicc\g}d}|j}|j}|j|jz}|D]}|dtjk(r#|j ||zd|df||dz }=|dtj k(r|j ||zd|dfn|dtjk(r#|j ||zd|df||dz }|dtjk(r#|j ||zd|df||dz }|dtjk(s|dtjk(s||dz }t|r|d}|d}|dtjk(r|j ||dz d|df|dtjk(r|j ||dz d |df|dtjk(r|j ||dz d|df|dtjk(r|j |d |df|S) NrXIDNSH) cigartuplespos query_lengthpysamCDIFFappendCINSCDEL CREF_SKIPCEQUALCMATCHlen CSOFT_CLIP CHARD_CLIP) readsubscurr_posr readstartreadendctuple first_ctuple last_ctuples [/var/www/html/software/conda/envs/higlass/lib/python3.12/site-packages/clodius/tiles/bam.pyget_cigar_substitutionsr& s* DH""KIhh***G " !9 # KKX-sF1I> ? q !H AY%** $ KKX-sF1I> ? AY%** $ KKX-sF1I> ? q !H AY%// ) KKX-sF1I> ? q !H AY%,, &&)u||*C q !H " ;"1~ !"o ?e.. . KK\!_4c<?K L ?e.. . KK\!_4c<?K L q>U-- - KK;q>13 AG H q>U-- - KK#{1~6 7 Kc |,g}|jD]\}}||t|ggz }ntj|j} tj|j } t j| } tt| | D cgc] } t| c} }|D cgc]} | d } } tjdtj| f} idgdgdgdgdgd gd gd gd gd gdgdgdgdgdgdg}ddd}t|}d}t| ||D]\}}}|t||||z }d}||kDrddiSt| ||D]\}}}t| |}|t|k\r%||d}|j!|||}|D]D}|j"r d}|j$r|j&rd}|j(rd}|j*|z}|dxx|gz cc<|dxxt|j,|zgz cc<|dxxt|j.|zgz cc<|dxx|j0gz cc<|d xx|gz cc<|d xx|j2gz cc<|dxx|j4gz cc<|j6dkD}|r t9||}nd}|s|j:r |j=ddD cgc]F} || dcxkr|kr6nn3| d .| d j?r| d| d|j:| dfH}} |r tC||||dxx|gz cc<n|dxxgz cc<n|dxx|gz cc<|dxxtE|gz cc<tG|jH}|dxx|jKd!dgz cc<|dxx||jLgz cc< |dxx|jOd"gz cc<G|Scc} wcc} wcc} w#t@$rg}YwxYw#xYw#tP$r|dxxdgz cc<YwxYw)#a Sample reads from the specified region, assuming that the chromosomes are ordered in some fashion. Returns an list of pysam reads Parameters: ----------- samfile: pysam.AlignmentFile A pysam entry into an indexed bam file start_pos: int The start position of the sampled region end_pos: int The end position of the sampled region chromsize: pandas.Series A listing of chromosome sizes. If not provided, the chromosome list will be extracted from the the bam file header cache: An object that implements the `get`, `set` and `exists` methods for caching data Returns ------- reads: [read1, read2...] The list of in the sampled regions NrridfromtomdchrName chrOffsetcigarm1Fromm1Tom2Fromm2Tomapqztags.HPstrandvariantscigars-+)TFgNAerrorz,Tile encompasses too much data: {total_size}_1_2i@T)with_seq matches_onlyHPMD))itemsintnparray referenceslengthsctbw natsortedlistzipr_cumsumrrrrfetch is_unmapped is_pairedis_read1is_read2 query_namereference_start reference_endreference_name cigarstringr4rget_cached_variantsquery_sequenceget_aligned_pairsislower ValueErrorset_cached_variantsr&dicttagsget is_reverseget_tagKeyError)samfile start_posend_pos chromsizesindex_filenamecachechromsizes_listchromsizerGrHlengthrabs_chrom_offsetsresultsstrandsidx total_sizecidstartendMAX_SIZE chr_offsetseq_namereadsr id_suffixread_id use_cacher6r`s r% load_readsr4s5<%++- 4KE4 D 23 3O 4XXg001 ((7??+^^J/ s:'/RF /RST,-qt-G-a7!334 b b b  2  R   "  "   2 " B "!G&%G  (CJ'w 7C>UC'C%== >HHGHH&w 7C_UC*3/0 #o& & %c*1-. hs3W D*:  >>}}$( }}$( //I5 '* C(<(%??!  $,,t"4!55 iW _B NO0S-D( **')H*"   "%  scO=2 PDPP +A P6P 8BPP#P  PPPPP #P>=P>c|d|}|r5|j|r$tj|j|Sy)zTry to get variants from a read we've seen before. This is useful for ONT reads where there's many variants per read and retrieving them takes a while. variants.N)existsjsonloadsra)rjr}cache_ids r%rYrYs9 7)$H h'zz%))H-.. r'c^d|}|r&|j|tj|yy)z$Save a set of variants to the cache.rN)setrdumps)rjr}r6rs r%r^r^s-7)$H  (DJJx01 r'c |Hg}|jD]\}}||t|ggz }t|Dcgc]}|d c}}nt|j}t j |j }t j |j}tt||} tj|}|D cgc]} | |  }} tt||D cgc] } t| c} }d} tjtj|| z tjdz } d}dg|g| d| zz| || |d}|Scc}wcc} wcc} w)at Get the tileset info for a bam file Parameters ---------- tileset: tilesets.models.Tileset object The tileset that the tile ids should be retrieved from Returns ------- tileset_info: {'min_pos': [], 'max_pos': [], 'tile_size': 1024, 'max_zoom': 7 } rr@ir)min_posmax_pos max_width tile_sizerhmax_zoommax_tile_width)rCrDsumrHrErFrGr_rLrIrJrKmathceillog)rerhrkrlrmc total_lengthrGrH ref_lengthsrornrrMAX_TILE_WIDTH tileset_infos r%alignment_tileset_infors["%++- 4KE4 D 23 3O 4/:QAaD:; 7??+ XXg001 ((7??+3z734 ^^J/ +56a;q>66s:'/RF /RSTIyy,":;dhhqkIJHN3 >h.%(L ;;7/Rs E E$)E)c `g}t||}|D]}|jddjd} ttt| dd} |ddt | dzz } |r| |k\r |dd |ifgcSt | d| z} | | z} t || | ||| }|||fgz }|S) a Generate tiles from a bigwig file. Parameters ---------- tileset: tilesets.models.Tileset object The tileset that the tile ids should be retrieved from tile_ids: [str,...] A list of tile_ids (e.g. xyx.0.0) identifying the tiles to be retrieved index_filename: str The name of the file containing the index max_tile_width: int How wide can each tile be before we return no data. This can be used to limit the amount of data returned. cache: An object that implements the `get`, `set` and `exists` methods for caching data Returns ------- tile_list: [(tile_id, tile_data),...] A list of tile_id, tile_data tuples |r.rrr@r:z1Tile too large, no data returned. Max tile size: )rfrgrhrirj)rsplitrKmaprDr)retile_idsrirhrrjgenerated_tilestsinfotile_id tile_id_parts tile_position tile_widthrfrg tile_values r%alignment_tilesr3s>O #GZ 8F7 c*1-33C8 SmAa&89: K(1M!4D0E+EE jN:#TUcTd!e M!,- :I*,G##%- J * 56 6O97< r'cDtj|}t||SN)r AlignmentFiler)filenamerhres r%rrvs!!(+G !': 66r'c`|s|d}tj||}t||||d|S)Nz.bai)ri)rirhrrj)rrr)rrrirhrrjres r%tilesr|sD $:T*!!(>JG %  r')NNN)NNNNr)rrnumpyrErclodius.tiles.bigwigrbigwigrIclodius.tiles.tabixrrclodius.tiles.utilsrr&rrYr^rrrr'r%rsn  ##A+%RNRqh 24t  @F7  r'