DUf# ddlmZ ddlmZn#e$r ddlmZYnwxYwddlmZm Z m Z m Z m Z  ddlm Z n#e$r ddlm Z YnwxYwddlZddlZddlZddlmZddgZed d z ZeGd d Zd ejfdZ ddede e e e e dfde e e e e dfd efdZdS)) dataclass)files)DictListOptionalTupleUnion)LiteralN)make_viewframeassemblies_available assembly_infoz bioframe.iodataceZdZUdZeed<eed<eed<eed<ejed<dZejed<dZ eed <dZ e eefed <d Z e d ejfd Ze d eefdZe d ejfdZd efdZdS)GenomeAssemblyzR A dataclass containing information about sequences in a genome assembly. organismproviderprovider_build release_yearseqinfoN cytobandsurl alias_dictci|_|jdjd}|jd}t ||D]\}}|D] }||j|< dS)Naliases,name)rrstrsplitzip)self alias_listsnamesrraliass Q/var/www/html/software/conda/lib/python3.11/site-packages/bioframe/io/assembly.py __post_init__zGenomeAssembly.__post_init__)s|l9-177<<  V$ e44 . .MGT  . .)-&& . . .returncB|jddS)Nrlength)r set_indexr s r$ chromsizeszGenomeAssembly.chromsizes1s|%%f--h77r&c@|jdS)Nr)rtolistr+s r$ chromnameszGenomeAssembly.chromnames5s|F#**,,,r&cNt|jS)N)r r,to_dictr+s r$ viewframezGenomeAssembly.viewframe9sdo5577888r&c Hd|jd|jd|jd|jd S)NzGenomeAssembly(organism='z ', provider='z', provider_build='z', release_year='z', ...))rrrrr+s r$__repr__zGenomeAssembly.__repr__=sM 8  8 8DM 8 8#2 8 8!. 8 8 8 r&)__name__ __module__ __qualname____doc__r__annotations__pd DataFramerrrrr%propertySeriesr,rr/r2r4r&r$rrs8MMMMMM \"Ir|"""COOO!%JS#X%%%...8BI888X8-DI---X-92<999X9 #      r&rr'cttdz 5}tj|}dddn #1swxYwYtj|S)a@ Get a list of available genome assembly metadata in local storage. Returns ------- pandas.DataFrame A dataframe with metadata fields for available assemblies, including 'provider', 'provider_build', 'default_roles', 'default_units', and names of seqinfo and cytoband files. z_assemblies.ymlN)openASSEMBLY_METADATA_ROOTyaml safe_loadr:r; from_records)f assembliess r$r r Es $'88 9 9'Q^A&& ''''''''''''''' < $ $Z 0 00s 9==rrolesallunitsc t}d}d|vr-|dd\}}|}|d|d}n d|d|d}||}t |dkrt d |t |dkrt d ||jdtj gdg }|d }|d } |d } tj t| z } tjt | t} || | d|z} nht#|t$t&fr| | d|z} n-t#|t(r|dkrt d||| | d| z} nht#|t$t&fr| | d|z} n-t#|t(r|dkrt d|| j| } d} |d}|tj t|z } t-|d|d|d|d| | |dS)a Get information about a genome assembly. Parameters ---------- name : str Name of the assembly. If the name contains a dot, it is interpreted as a provider name and a build, e.g. "hg38". Otherwise, the provider is inferred if the build name is unique. roles : list or tuple or "all", optional Sequence roles to include in the assembly info. If not specified, only sequences with the default sequence roles for the assembly are shown. e.g. "assembled", "unlocalized", "unplaced" units : list or tuple or "all", optional Assembly units to include in the assembly info. If not specified, only sequences from the default units for the assembly are shown. e.g. "primary", "non-nuclear", "decoy" Returns ------- GenomeAssembly A dataclass containing information about the assembly. Raises ------ ValueError If the assembly name is not found or is not unique. Examples -------- >>> hg38 = assembly_info("hg38") >>> hg38.chromsizes name chr1 248956422 chr2 242193529 chr3 198295559 ... ... >>> assembly_info("hg38", roles=("assembled", "non-nuclear")) >>> assembly_info("ucsc.hg38", units=("unplaced",)) N.zprovider_build == ''z provider == 'z' and provider_build == 'rzAssembly not found: zAssembly identifer not unique: default_roles default_unitsr)dtyperolerHz$roles must be a tuple or 'all', not unitz$units must be a tuple or 'all', not rrrrrr)rrrrrrr)r rlowerquerylen ValueErrorilocreplacenpnanr1r: read_tablerAonesboolisin isinstancetuplelistrlocr)rrGrIrFrqresultassemblyrNrO seqinfo_pathrmaskrcytobands_paths r$r r Us`&''JH d{{C++$>>## )$ ) ) ) FH F Ft F F F   a F 6{{a666777 VqC6CCDDD{1~%%rvh77??AAH_-M_-MI&Lm2\ABBG 73w<"IJJ *%*% 01n- UO   r&)NN) dataclassesrimportlib.resourcesr resource_path ImportErrorimportlib_resourcestypingrrrrr r typing_extensionsnumpyrYpandasr:rBbioframer __all__rArr;r rr r>r&r$rts!!!!!!;:::::::;;;::::::::;65555555555555****))))))))* ###### !? 3&}55> ' ' ' ' ' ' '  ' T 1bl 1 1 1 1$;?:>cc c E$wu~56 7c E$wu~56 7c ccccccs 6 AA