U md  @sdZddlmZddlmZddlmZddlm Z m Z ddl m Z dd lm Zdd lmZdeeeeeeeeedddZdeeeeeedddZdeeeeeeedddZdS)z)Preprocessing recipes from the literature)Optional)AnnData) preprocessing)filter_genes_dispersionfilter_genes_cv_deprecated)normalize_total)logging) AnyRandomT{Gz?2 randomizedF)adatalogmean_threshold cv_thresholdn_pcs random_statecopyreturnc Csddlm}m} ddlm} | |jr.td|r:|}|rHt |||jddd|_t |j||} | | tj | |j|||d } | |j d <|r|Sd S) a# Normalization and filtering as of [Weinreb17]_. Expects non-logarithmized data. If using logarithmized data, pass `log=False`. Parameters ---------- adata Annotated data matrix. log Logarithmize data? copy Return a copy if true. r)'normalize_per_cell_weinreb16_deprecatedzscore_deprecatedr)issparsez3`recipe_weinreb16 does not support sparse matrices.g?T)Z max_fractionZmult_with_mean)Zn_comps svd_solverrX_pcaN)Z _deprecatedrrZ scipy.sparserX ValueErrorrpplog1pr_inplace_subset_varZpcaZobsm) rrrrrrrrrrr gene_subsetrr"V/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/scanpy/preprocessing/_recipes.pyrecipe_weinreb17s.     r$)rrplotrrcCs|r |}tj|ddtj|ddt|ddt|jddd| d }|rjd d lm}|j|| d | |j |rt |tj |d d|r|SdS)z Normalization and filtering as of Seurat [Satija15]_. This uses a particular preprocessing. Expects non-logarithmized data. If using logarithmized data, pass `log=False`. )Z min_genes)Z min_cellsg@)Z target_sumg?g?)Zmin_meanZmax_meanZmin_disprr_preprocessingr )Z max_valueN) rrZ filter_cells filter_genesr rrplottingr)r r!rscale)rrr%r filter_resultpppr"r"r# recipe_seuratCs(     r1)r n_top_genesrr%rrcCstd}|r|}tj|ddt|ddt|jd|dd}|r`d d lm }|j|d d | |j t||rt |t |tjd |d|r|SdS)u Normalization and filtering as of [Zheng17]_. Reproduces the preprocessing of [Zheng17]_ – the Cell Ranger R Kit of 10x Genomics. Expects non-logarithmized data. If using logarithmized data, pass `log=False`. The recipe runs the following steps .. code:: python sc.pp.filter_genes(adata, min_counts=1) # only consider genes with more than 1 count sc.pp.normalize_per_cell( # normalize with total UMI count per cell adata, key_n_counts='n_counts_all' ) filter_result = sc.pp.filter_genes_dispersion( # select highly-variable genes adata.X, flavor='cell_ranger', n_top_genes=n_top_genes, log=False ) adata = adata[:, filter_result.gene_subset] # subset the genes sc.pp.normalize_per_cell(adata) # renormalize after filtering if log: sc.pp.log1p(adata) # log transform: adata.X = log(adata.X + 1) sc.pp.scale(adata) # scale to unit variance and shift to zero mean Parameters ---------- adata Annotated data matrix. n_top_genes Number of genes to keep. log Take logarithm. plot Show a plot of the gene dispersion vs. mean relation. copy Return a copy of `adata` instead of updating it. Returns ------- Returns or updates `adata` depending on `copy`. zrunning recipe zheng17r)Z min_countsZ n_counts_all)Z key_addedZ cell_rangerF)Zflavorr3rrr(Tr*z finished)timeN)logginforrr,r rrr-r)r r!rr.)rr3rr%rstartr/r0r"r"r#recipe_zheng17cs*2      r8N)Tr rr rrF)TFF)r2TFF)__doc__typingrZanndatarrrZ!_deprecated.highly_variable_genesrrZ_normalizationr r r5_utilsr boolfloatintr$r1r8r"r"r"r#s\       3 "