U mdj @sdZddlmZmZmZmZmZmZmZddl Z ddl m Z ddl mZddlmZeeeeefZddddd ee eeeefeeeeeeeeeeeffd d d Zdd ddde eeeeeeeffeeee jdddZddZdS)zDCalculate scores based on relative expression change of maker pairs )MappingOptional CollectionUnionTupleListDictN)AnnData)versionsettingsg?)fraction filter_genesfilter_samples)adata annotationrrrreturncCsXtddlm}ddlm}tj|_tj|_tj|_tj|_tj |_ ||||||dS)a Calculate marker pairs of genes. [Scialdone15]_ [Fechtner18]_. Calculates the pairs of genes serving as marker pairs for each phase, based on a matrix of gene counts and an annotation of known phases. This reproduces the approach of [Scialdone15]_ in the implementation of [Fechtner18]_. More information and bug reports `here `__. Parameters ---------- adata The annotated data matrix. annotation Mapping from category to genes, e.g. `{'phase': [Gene1, ...]}`. Defaults to ``data.vars['category']``. fraction Fraction of cells per category where marker criteria must be satisfied. filter_genes Genes for sampling the reference set. Defaults to all genes. filter_samples Cells for sampling the reference set. Defaults to all samples. Returns ------- A dict mapping from category to lists of marker pairs, e.g.: `{'Category_1': [(Gene_1, Gene_2), ...], ...}`. Examples -------- >>> from scanpy.external.tl import sandbag >>> from pypairs import datasets >>> adata = datasets.leng15() >>> marker_pairs = sandbag(adata, fraction=0.5) r)sandbagr )datarrrr) _check_import pypairs.pairsrpypairsr verbosityn_jobswritedircachedirlogfile)rrrrrr pp_settingsrT/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/scanpy/external/tl/_pypairs.pyrs.  rid2) iterationsmin_iter min_pairs)r marker_pairsr#r$r%rcCsXtddlm}ddlm}tj|_tj|_tj|_tj|_tj |_ ||||||dS)aT Assigns scores and predicted class to observations [Scialdone15]_ [Fechtner18]_. Calculates scores for each observation and each phase and assigns prediction based on marker pairs indentified by :func:`~scanpy.external.tl.sandbag`. This reproduces the approach of [Scialdone15]_ in the implementation of [Fechtner18]_. Parameters ---------- adata The annotated data matrix. marker_pairs Mapping of categories to lists of marker pairs. See :func:`~scanpy.external.tl.sandbag` output. iterations An integer scalar specifying the number of iterations for random sampling to obtain a cycle score. min_iter An integer scalar specifying the minimum number of iterations for score estimation. min_pairs An integer scalar specifying the minimum number of pairs for score estimation. Returns ------- A :class:`~pandas.DataFrame` with samples as index and categories as columns with scores for each category for each sample and a additional column with the name of the max scoring category for each sample. If `marker_pairs` contains only the cell cycle categories G1, S and G2M an additional column `pypairs_cc_prediction` will be added. Where category S is assigned to samples where G1 and G2M score are < 0.5. r)cycloner )rr&r#r$r%) rrr'rr rrrrr)rr&r#r$r%r'rrrr r'Qs,  r'cCsVz ddl}Wntk r(tdYnXtd}t|j|krRtd|dS)Nrz*You need to install the package `pypairs`.z3.0.9zPlease only use `pypairs` >= )r ImportErrorr parse __version__)r min_versionrrr rs  r)N)N)__doc__typingrrrrrrrZpandaspdZanndatar packagingr r strintboolZGenesfloatrZ DataFramer'rrrrr sB$    C ?