o Nrf@sddlmZddlZddlZddlZddlmZm Z e e Z dZ ddZddd Zd d Z dd d ZiddfddZddZdS))FastaN) natsortedget_quadtree_depthics`t|ddtfddD}t}Wdn1s$wYt||S)NFZone_based_attributesc3s"|] }|tj|fVqdSN)lenrecords).0seqfa\/var/www/html/software/conda/envs/catlas/lib/python3.10/site-packages/clodius/tiles/fasta.py s z!get_chromsizes..)rdictkeysrpdSeries)fapath chromsizesZ chromosomesrr rget_chromsizes s rcCs||durt|}g}|D] \}}||t|gg7}qn |}dd|D}t|t}dgt|gtd|t||d}|S)a' Get the tileset info for a FASTA file Parameters ---------- fapath: string The path to the FASTA file from which to retrieve data chromsizes: [[chrom, size],...] A list of chromosome sizes associated with this tileset. Typically passed in to specify in what order data from the FASTA should be returned. Returns ------- tileset_info: {'min_pos': [], 'max_pos': [], 'tile_size': 1024, 'max_zoom': 7 } NcSg|]}t|dqSrintr crrr 0z tileset_info..r)Zmin_posZmax_pos max_width tile_sizemax_zoomr)ritemsrr TILE_SIZEsum)rrZchromsizes_listchromsizer# tileset_inforrrr)s"  r)c cstjdt|f}tj|||gddd\}}|||}|||}|}t||D] } | ||| fVd}q,|||fVdS)a Convert absolute genomic sizes to genomic Parameters: ----------- chromsizes: [1000,...] An array of the lengths of the chromosomes start_pos: int The starting genomic position end_pos: int The ending genomic position rright)ZsiderN)npZr_ZcumsumZ searchsortedrange) r start_posend_posZabs_chrom_offsetsZcid_loZcid_hiZ rel_pos_loZ rel_pos_histartcidrrr abs2genomic=s   r1csr|durt|}|tt|||}t|ddfdd|D}Wdn1s/wYd|S)NFrcs(g|]\}}}|||jqSr)r )r r0r/endZ chrom_namesr rrr`sz"get_fasta_tile..)rrlistr1rjoin)r zoom_levelr-r.rZcids_starts_endsZarraysrr3rget_fasta_tileWs  r8cCsNg}|D]}|ddd}|dd}|d} ttt| dd} tdd|D} |rGd d|D} d d|D} tj| | d }nd}d | vrQ| d }||vrZ||}nd}| d}| d}|durlt|}t|t }t d ||}|r||kr|dd|ifgS||}||}t |||||}||d|ifg7}q|S)ai Generate tiles from a FASTA file. Parameters ---------- fapath: str The filepath of the FASTA file tile_ids: [str,...] A list of tile_ids (e.g. xyx.0.0) identifying the tiles to be retrieved chromsizes_map: {uid: []} A set of chromsizes listings corresponding to the parameters of the tile_ids. To be used if a chromsizes id is passed in with the tile id with the `|cos:id` tag in the tile id chromsizes: [[chrom, size],...] A 2d array containing chromosome names and sizes. Overrides the chromsizes in chromsizes_map 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. Returns ------- tile_list: [(tile_id, tile_data),...] A list of tile_id, tile_data tuples |rNr.cSsg|]}|dqS):)split)r orrrrsztiles..cSsg|]}|dqS)rrrrrrrscSrrrrrrrrr)indexcosr errorz1Tile too large, no data returned. Max tile size: sequence) r=r5maprrrrrrr%r8)rZtile_idsZchromsizes_maprZmax_tile_widthZgenerated_tilesZtile_idZtile_option_partsZtile_no_optionsZ tile_id_partsZ tile_positionZ tile_optionsZ chromnamesZ chromlengthsZchromsizes_to_useZ chromsizes_idr7Ztile_pos max_depthr"r-r.ZtilerrrtilesfsD     rEc Csdzt|}g}|D] \}}|||gq |WSty1}z t|td|d}~ww)a* Get a list of chromosome sizes from this [presumably] fasta file. Parameters: ----------- filename: string The filename of the fasta file Returns ------- chromsizes: [(name:string, size:int), ...] An ordered list of chromosome names and sizes z-Error loading chromsizes from bigwig file: {}N)rr$append ExceptionloggerrAformat)filenameZ chrom_seriesdatar'r(exrrrrs rr)Zpyfaidxrnumpyr+Zpandasrloggingutilsrr getLogger__name__rHr%rr)r1r8rErrrrrs   *  J