U md # @sddlmZddlmZddlmZddlmZm Z m Z m Z m Z m Z ddlZddlmZddlmZddlmZd Zd Zd Zeeeed dd ddee e eefe e eefeeejdddZeeeed d ddee eeeejdddZeeeed ddd ddeeee eeeejdddZeeeed dd dddeeeeeejdd d!Zeeed"d#eid$e e ee ee effee eefejd%d&d'Z e !ed#d(d)dddeid*eee eee"e e"e e"e ee eefejd+ d,d-Z#dS).N)singledispatch)MappingProxyType)AnyUnionOptionalIterableDictMapping)AnnData)rank_genes_groups_df) _doc_paramsznorg Organism to query. Must be an organism in ensembl biomart. "hsapiens", "mmusculus", "drerio", etc.zhost A valid BioMart host URL. Alternative values include archive urls (like "grch37.ensembl.org") or regional mirrors (like "useast.ensembl.org").zuse_cache Whether pybiomart should use a cache for requests. Will create a `.pybiomart.sqlite` file in current directory if used.)doc_orgZdoc_hostZ doc_use_cachezwww.ensembl.orgF)filtershost use_cache)orgattrsrrrreturnc Cst|tr|g}n*t|tjr(t|}ntdt|dzddlm}Wnt k rht dYnX|||d}|j dj d |}|j ||d d }|S) z A simple interface to biomart. Params ------ {doc_org} attrs What you want returned. filters What you want to pick out. {doc_host} {doc_use_cache} z'attrs must be of type list or str, was .r)Serverz>> import scanpy as sc >>> annot = sc.queries.biomart_annotations( "hsapiens", ["ensembl_gene_id", "start_position", "end_position", "chromosome_name"], ).set_index("ensembl_gene_id") >>> adata.var[annot.columns] = annot rrrrr%r&r#r#r$biomart_annotationsJs"r(Zexternal_gene_namer#) gene_attr chr_excluderr)r gene_namer)r*rrrcCs0t|dddg||i||d}||d|S)ap Retrieve gene coordinates for specific organism through BioMart. Parameters ---------- {doc_org} gene_name The gene symbol (e.g. "hgnc_symbol" for human) for which to retrieve coordinates. gene_attr The biomart attribute the gene symbol should show up for. chr_exclude A list of chromosomes to exclude from query. {doc_host} {doc_use_cache} Returns ------- Dataframe containing gene coordinates for the specified gene symbol. Examples -------- >>> import scanpy as sc >>> sc.queries.gene_coordinates("hsapiens", "MT-TF") chromosome_nameZstart_positionZ end_position)rrrrr)r%isin)rr+r)r*rrr"r#r#r$gene_coordinatesos#r.ZMT)attrnamerr chromosome)rr/rrr0rcCst||gd|gi||dS)aP Mitochondrial gene symbols for specific organism through BioMart. Parameters ---------- {doc_org} attrname Biomart attribute field to return. Possible values include "external_gene_name", "ensembl_gene_id", "hgnc_symbol", "mgi_symbol", and "zfin_id_symbol". {doc_host} {doc_use_cache} chromosome Mitochrondrial chromosome name used in BioMart for organism. Returns ------- Dataframe containing identifiers for mitochondrial genes. Examples -------- >>> import scanpy as sc >>> mito_gene_names = sc.queries.mitochondrial_genes("hsapiens") >>> mito_ensembl_ids = sc.queries.mitochondrial_genes("hsapiens", attrname="ensembl_gene_id") >>> mito_gene_names_fly = sc.queries.mitochondrial_genes("dmelanogaster", chromosome="mitochondrion_genome") r,)rrrrr')rr/rrr0r#r#r$mitochondrial_geness#r1)rZhsapiensrgprofiler_kwargs) containerrr3rcCszddlm}Wntk r,tdYnX|ddd}t|}dD]"}||dk rFtd |d qF|j|fd |i|S) aa Get enrichment for DE results. This is a thin convenience wrapper around the very useful gprofiler_. This method dispatches on the first argument, leading to the following two signatures:: enrich(container, ...) enrich(adata: AnnData, group, key: str, ...) Where:: enrich(adata, group, key, ...) = enrich(adata.uns[key]["names"][group], ...) .. _gprofiler: https://pypi.org/project/gprofiler-official/#description Parameters ---------- container Contains list of genes you'd like to search. If container is a `dict` all enrichment queries are made at once. adata AnnData object whose group will be looked for. group The group whose genes should be used for enrichment. key Key in `uns` to find group under. {doc_org} gprofiler_kwargs Keyword arguments to pass to `GProfiler.profile`, see gprofiler_. Some useful options are `no_evidences=False` which reports gene intersections, `sources=['GO:BP']` which limits gene sets to only GO biological processes and `all_results=True` which returns all results including the non-significant ones. **kwargs All other keyword arguments are passed to `sc.get.rank_genes_groups_df`. E.g. pval_cutoff, log2fc_min. Returns ------- Dataframe of enrichment results. Examples -------- Using `sc.queries.enrich` on a list of genes: >>> import scanpy as sc >>> sc.queries.enrich(['KLF4', 'PAX5', 'SOX2', 'NANOG'], org="hsapiens") >>> sc.queries.enrich({{'set1':['KLF4', 'PAX5'], 'set2':['SOX2', 'NANOG']}}, org="hsapiens") Using `sc.queries.enrich` on an :class:`anndata.AnnData` object: >>> pbmcs = sc.datasets.pbmc68k_reduced() >>> sc.tl.rank_genes_groups(pbmcs, "bulk_labels") >>> sc.queries.enrich(pbmcs, "CD34+") r) GProfilerzEThis method requires the `gprofiler-official` module to be installed.ZscanpyT) user_agentZreturn_dataframe)organismNz Argument `zL` should be passed directly through `enrich`, not through `gprofiler_kwargs`r7) gprofilerr5rdictget ValueErrorZprofile)r4rr3r5r8kr#r#r$enrichs@   r=Zrank_genes_groupsg?)rkey pval_cutoff log2fc_min log2fc_max gene_symbolsr3) adatagrouprr>r?r@rArBr3rc CsNt|||||||d} |dk r0t| |} nt| d} t| ||dS)N)rDr>r?r@rArBnamesr2)r rZdropnar=) rCrDrr>r?r@rArBr3deZ gene_listr#r#r$_enrich_anndatas  rG)$collections.abcabcr functoolsrtypesrtypingrrrrrr ZpandaspdZanndatar r:r _utilsr Z_doc_orgZ _doc_hostZ_doc_use_cacherboolZ DataFramer%r(r.r1r=registerfloatrGr#r#r#r$s        ) $ , + O