Api scsa

class pySCSA(object):

    def __init__(self,adata:anndata.AnnData,
                foldchange:float=1.5,pvalue:float=0.05,
                output:str='temp/rna_anno.txt',
                model_path:str='',
                outfmt:str='txt',Gensymbol:bool=True,
                species:str='Human',weight:int=100,tissue:str='All',target:str='cellmarker',
                celltype:str='normal',norefdb:bool=False,cellrange:str=None,
                noprint:bool=True,list_tissue:bool=False) -> None:

        r"""Initialize the pySCSA class.

        Arguments:
            adata: AnnData object of scRNA-seq after preprocessing
            foldchange: Fold change threshold for marker filtering. (1.5)
            pvalue: P-value threshold for marker filtering. (0.05)
            output: Output file for marker annotation. ('temp/rna_anno.txt')
            model_path: Path to the Database for annotation. If not provided, the model will be downloaded from the internet. ('')
            outfmt: Output format for marker annotation. ('txt')
            Gensymbol: Using gene symbol ID instead of ensembl ID in input file for calculation. (True)
            species: Species for annotation. Only used for cellmarker database. ('Human')
            weight: Weight threshold for marker filtering from cellranger v1.0 results. (100)
            tissue: Tissue for annotation. you can use `get_model_tissue` to see the available tissues. ('All')
            target: Target to annotation class in Database. ('cellmarker')
            celltype: Cell type for annotation. ('normal')
            norefdb: Only using user-defined marker database for annotation. (False)
            cellrange: Cell sub_type for annotation. (if you input T cell, it will only provide T helper cell, T cytotoxic cell, T regulatory cell, etc.) (None)
            noprint: Do not print any detail results. (True)
            list_tissue: List all available tissues in the database. (False)

        Returns:
            None
        """

        #create temp directory
        try:
            if not os.path.isdir('temp'):
                print("...Creating directory {}".format('temp'))
                os.makedirs('temp', exist_ok=True)
        except OSError as e:
            print("...Unable to create directory {}. Reason {}".format('temp',e))

        self.adata=adata
        self.foldchange=foldchange
        self.pvalue=pvalue
        self.output=output
        self.outfmt=outfmt
        self.Gensymbol=Gensymbol
        self.species=species
        self.weight=weight
        self.tissue=tissue
        self.celltype=celltype
        self.norefdb=norefdb
        self.noprint=noprint
        self.list_tissue=list_tissue
        self.target=target
        self.cellrange=cellrange
        if model_path =='':
            self.model_path=data_downloader(url='https://figshare.com/ndownloader/files/41369037',
                                            path='temp/pySCSA_2023_v2_plus.db',title='whole')
        else:
            self.model_path=model_path

    def get_model_tissue(self,species:str="Human")->None:
        r"""List all available tissues in the database.

        Arguments:
            species: Species for annotation. Only used for cellmarker database. ('Human')

        Returns:
            None
        """

        anno = Annotator(foldchange=self.foldchange,
                    weight=self.weight,
                    pvalue=self.pvalue,
                    tissue=self.tissue,
                    species=self.species,
                    target=self.target,
                    norefdb=self.norefdb,
                    MarkerDB=None,
                    db=self.model_path,
                    noprint=self.noprint,
                    input="temp/rna.csv",
                    output=self.output,
                    source="scanpy",
                    cluster='all',
                    fc=self.foldchange,
                    outfmt=self.outfmt,
                    celltype=self.celltype,
                    Gensymbol=self.Gensymbol,
                    list_tissue=self.list_tissue,
                    cellrange=self.cellrange)
        anno.load_pickle_module(self.model_path)
        anno.get_list_tissue(species)


    def cell_anno(self,clustertype:str='leiden',
                  cluster:str='all',rank_rep=False)->pd.DataFrame:
        r"""Annotate cell type for each cluster.

        Arguments:
            clustertype: Clustering name used in scanpy. ('leiden')
            cluster: Only deal with one cluster of marker genes. ('all')
            rank_rep: Whether to repeat ranking. (False)

        Returns:
            result: Annotation result as DataFrame
        """

        dat=data_preprocess(self.adata,clustertype=clustertype,path='temp/rna.csv',rank_rep=rank_rep)
        dat.to_csv('temp/rna.csv')

        print('...Auto annotate cell')

        p = Process()
        p.run_cmd_p(foldchange=self.foldchange,
                    weight=self.weight,
                    pvalue=self.pvalue,
                    tissue=self.tissue,
                    species=self.species,
                    target=self.target,
                    norefdb=self.norefdb,
                    MarkerDB=None,
                    db=self.model_path,
                    noprint=self.noprint,
                    input="temp/rna.csv",
                    output=self.output,
                    source="scanpy",
                    cluster=cluster,
                    fc=self.foldchange,
                    outfmt=self.outfmt,
                    celltype=self.celltype,
                    Gensymbol=self.Gensymbol,
                    list_tissue=self.list_tissue,
                    cellrange=self.cellrange)


        result=pd.read_csv('temp/rna_anno.txt',sep='\t')
        self.result=result
        add_reference(self.adata,'pySCSA','cell annotation with SCSA')
        return result

    def cell_anno_print(self)->None:
        r"""Print the annotation result.

        Returns:
            None
        """
        for i in set(self.result['Cluster']):
            test=self.result.loc[self.result['Cluster']==i].iloc[:2]
            if test.iloc[0]['Z-score']>test.iloc[1]['Z-score']*2:
                print('Nice:Cluster:{}\tCell_type:{}\tZ-score:{}'.format(i,test.iloc[0]['Cell Type'],
                                                            np.around(test.iloc[0]['Z-score'],3)))
            else:
                print('Cluster:{}\tCell_type:{}\tZ-score:{}'.format(i,('|').join(test['Cell Type'].values.tolist()),
                                                            ('|').join(np.around(test['Z-score'].values,3).astype(str).tolist())))

    def cell_auto_anno(self,adata:anndata.AnnData,
                       clustertype:str='leiden',key='scsa_celltype')->None:
        r"""Add cell type annotation to anndata.obs['scsa_celltype'].

        Arguments:
            adata: anndata object
            clustertype: Clustering name used in scanpy. ('leiden')
            key: Key to store cell type annotation. ('scsa_celltype')

        Returns:
            None
        """
        test_li=[]
        for i in adata.obs[clustertype].value_counts().index:
            if int(i) in self.result['Cluster'].values:
                test_li.append(self.result.loc[self.result['Cluster']==int(i)].iloc[0]['Cell Type'])
            else:
                test_li.append('Unknown')
        scsa_anno=dict(zip([str(i) for i in adata.obs[clustertype].value_counts().index],
            test_li))
        adata.obs[key] = adata.obs[clustertype].map(scsa_anno).astype('category')
        print('...cell type added to {} on obs of anndata'.format(key))

    def get_celltype_marker(self,adata:anndata.AnnData,
                            clustertype:str='leiden',
                            log2fc_min:int=2,scores_type='scores',
                            pval_cutoff:float=0.05,rank:bool=True,
                            unique:bool=True,global_unique:bool=False)->dict:
        r"""Get marker genes for each clusters.

        Arguments:
            adata: anndata object
            clustertype: Clustering name used in scanpy. (leiden)
            log2fc_min: Minimum log2 fold change of marker genes. (2)
            pval_cutoff: Maximum p value of marker genes. (0.05)
            rank: Whether to rank genes by wilcoxon test. (True)
            scores_type: The type of scores. can be selected from `scores` and `logfoldchanges`
            unique: Whether to remove duplicates within each cell type. (True)
            global_unique: Whether to remove duplicates across all cell types. (False)

        Returns:
            cellmarker: A dictionary of marker genes for each clusters.
        """
        print('...get cell type marker')
        cell_marker_dict=get_celltype_marker(adata=adata,
                            clustertype=clustertype,
                            log2fc_min=log2fc_min,scores_type=scores_type,
                            pval_cutoff=pval_cutoff,rank=rank,
                            unique=unique,global_unique=global_unique)

        return cell_marker_dict