Cell type prediction based on marker genes from reference dataset

From the previous release

This page was recovered from the PIASO v1.1.0 documentation and has not been re-run against the current release. The code is preserved as published; some calls may have changed. The pages under All tutorials are the ones executed against this release.

The original v1.1.0 site is archived at https://genecell.github.io/PIASO/.

Cell type prediction based on marker genes from reference dataset

import numpy as np
import pandas as pd
import scanpy as sc
sc.set_figure_params(dpi=80,dpi_save=300, color_map='viridis',facecolor='white')
from matplotlib import rcParams
# To modify the default figure size, use rcParams.
rcParams['figure.figsize'] = 4, 4
rcParams['font.sans-serif'] = "Arial"
rcParams['font.family'] = "Arial"
sc.settings.verbosity = 3
sc.logging.print_header()

path = '.../Analysis/Jupyter/Python/Longitudinal/Integration'
import sys
sys.path.append(path)
from env_settings import *
sc.set_figure_params(dpi=80,dpi_save=300, color_map='viridis',facecolor='white')
rcParams['figure.figsize'] = 4, 4
save_dir='.../Result/single-cell/Methods/COSG/Database'
### Create the save_dir if not existed
!mkdir -p {save_dir}

adata=sc.read('.../Result/single-cell/Enhancer/AdultCortexMultiome/AdultCortexMultiomeRNA_integrated_anno.h5ad')

sc.pl.umap(adata,
           color=['CellTypes'],
           palette=self_palette2,
           # legend_loc='on data',
           legend_fontoutline=2,
           legend_fontweight=5,
           cmap='Spectral_r',
           ncols=3,
           size=10,
           frameon=False)

cosgMarkerDB=pd.read_csv('.../Result/single-cell/Enhancer/WholeMouseBrainRNAAllen/WholeMouseBrainRNAAllen_isocortex_subclass_leidenlocalRes0.5_markerGenes.csv',
                         index_col=0)

cosgMarkerDB.shape

cosgMarkerDB.head()

cosgMarkerScoreDB=pd.read_csv('.../Result/single-cell/Enhancer/WholeMouseBrainRNAAllen/WholeMouseBrainRNAAllen_isocortex_subclass_leidenlocalRes0.5_markerGenesScores.csv', index_col=0)

cosgMarkerScoreDB.head()

import piaso

%%time
piaso.tl.infog(adata, layer='raw')

adata

piaso.tl.predictCellTypeByMarker(
    adata,
    marker_gene_set=cosgMarkerDB[:50], ### Use the top 50 marker genes,
    score_method = 'piaso',
    score_layer = 'infog',
    use_score  = True,
    max_workers = 32,
    smooth_prediction = True,
    use_rep = 'X_pca_harmony', ### Use the specified low-dimensional cell embeddings for kNN graph-based cell type prediction smoothing
    k_nearest_neighbors = 9,
    return_confidence  = False,
    use_existing_adjacency_graph = False,
    use_faiss = False,
    key_added  = 'Subclass_predicted',
    extract_cell_type  = True, delimiter_cell_type  = '-', ## Set True to extract the subclass, as now it's clusters of subclass level

    inplace  = True,
    random_seed = 1927,
    verbosity = 1,
    n_jobs  = -1,
)

sc.pl.umap(adata,
           color=['Subclass_predicted'],
           palette=piaso.pl.color.d_color10,
           # legend_loc='on data',
           legend_fontoutline=2,
           legend_fontweight=5,
           cmap='Spectral_r',
           ncols=3,
           size=10,
           frameon=False)

sc.pl.umap(adata,
           color=['CellTypes'],
           palette=piaso.pl.color.d_color10,
           legend_loc='on data',
           legend_fontoutline=2,
           legend_fontsize=6,
           legend_fontweight=5,
           # cmap='Spectral_r',
           cmap=sp_cmap,
           ncols=1,
           size=10,
           frameon=False)

sc.pl.umap(adata,
           color=['Subclass_predicted_score'],
           palette=piaso.pl.color.d_color10,
           # legend_loc='on data',
           legend_fontoutline=2,
           legend_fontweight=5,
           # cmap='Spectral_r',
           cmap=piaso.pl.color.c_color6,

           ncols=1,
           size=10,
           frameon=False)

piaso.tl.predictCellTypeByMarker(
    adata,
    marker_gene_set=cosgMarkerDB[:50], ### Use the top 50 marker genes,
    score_method = 'piaso',
    score_layer = 'infog',
    use_score  = False,
    max_workers = 32,
    smooth_prediction = True,
    use_rep = 'X_pca_harmony', ### Use the specified low-dimensional cell embeddings for kNN graph-based cell type prediction smoothing
    k_nearest_neighbors = 9,
    return_confidence  = False,
    use_existing_adjacency_graph = False,
    use_faiss = False,
    key_added  = 'Subclass_predicted_pvals',
    extract_cell_type  = True, delimiter_cell_type  = '-', ## Set True to extract the subclass, as now it's clusters of subclass level

    inplace  = True,
    random_seed = 1927,
    verbosity = 1,
    n_jobs  = -1,
)

sc.pl.umap(adata,
           color=['Subclass_predicted', 'Subclass_predicted_pvals'],
           palette=piaso.pl.color.d_color10,
           # legend_loc='on data',
           legend_fontoutline=2,
           legend_fontweight=5,
           cmap='Spectral_r',
           ncols=1,
           size=10,
           frameon=False)

sc.pl.umap(adata,
           color=['CellTypes'],
           palette=piaso.pl.color.d_color10,
           legend_loc='on data',
           legend_fontoutline=2,
           legend_fontsize=6,
           legend_fontweight=5,
           # cmap='Spectral_r',
           cmap=sp_cmap,
           ncols=1,
           size=10,
           frameon=False)

sc.pl.umap(adata,
           color=['Subclass_predicted_pvals_nlog10pvals'],
           palette=piaso.pl.color.d_color10,
           # legend_loc='on data',
           legend_fontoutline=2,
           legend_fontweight=5,
           # cmap='Spectral_r',
           cmap=piaso.pl.color.c_color6,
           vcenter= -np.log10(0.05), vmin=0,

           ncols=1,
           size=10,
           frameon=False)

sc.pl.umap(adata,
           color=['Sample', 'Leiden'],
           palette=self_palette2,
           # legend_loc='on data',
           legend_fontoutline=2,
           legend_fontweight=5,
           # cmap='Spectral_r',
           cmap=sp_cmap,
           ncols=1,
           size=10,
           frameon=False)

piaso.pl.plotConfusionMatrix(adata, 'CellTypes', 'Subclass_predicted',)