Python client and API for accessing PIASOmarkerDB

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/.

Python client and API for accessing PIASOmarkerDB

import piaso

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)

marker_df = piaso.tl.queryPIASOmarkerDB(gene="Fezf2")

marker_df.head(10)

marker_df = piaso.tl.queryPIASOmarkerDB(gene=["Fezf2", "Satb2", "Tbr1"])

marker_df.head(10)

marker_df = piaso.tl.queryPIASOmarkerDB(
        study="AllenWholeMouseBrain_isocortex",
        species="mouse",
        # limit=10
)

marker_df

marker_df = piaso.tl.queryPIASOmarkerDB(
    species="Human",
    min_score=8.0,
    limit=100
)

marker_df.head(20)

marker_df, marker_dict = piaso.tl.queryPIASOmarkerDB(
    study='AllenWholeMouseBrain_isocortex',
        # species="Human",
        # min_score=3.0,
        # limit=500,
    as_dict=True
)

print(f"DataFrame shape: {marker_df.shape}")
print(f"Cell types in dict: {len(marker_dict)}")

# Show sample
for ct, genes in list(marker_dict.items())[:3]:
    print(f"\n  {ct}:")
    print(f"    Markers: {genes[:5]}...")

studies = piaso.tl.queryPIASOmarkerDB(list_studies=True)
print(f"Total studies: {len(studies)}")
print("First 10 studies:")
for study in studies[:10]:
    print(f"  - {study}")

def example_analyze_single_list():
    """Demonstrate single gene list analysis."""
    print("\n" + "="*60)
    print("Example 4: Analyze Single Gene List")
    print("="*60)

    # T-cell marker genes
    t_cell_genes = ["CD3E", "CD3D", "CD8A", "GZMK", "PRF1", "IFNG"]

    print(f"\n--- Analyzing genes: {t_cell_genes} ---")
    df = piaso.tl.analyzeMarkers(t_cell_genes, species="Human")

    print(f"Found {len(df)} cell type matches")
    if len(df) > 0:
        print("\nTop 5 matches:")
        print(df[['cell_type', 'matched_gene_count', 'avg_specificity']].head())

query_genes = ["Syt6", "Tle4", "Hs3st4", "Col6a1", "Zfpm2", "Sema5a", "Bcl11b", "Fezf2", "Foxp2", "Col12a1"]
print(f"\n--- Analyzing genes: {query_genes} ---")
marker_df = piaso.tl.analyzeMarkers(query_genes)
marker_df.head()

gene_sets = {
    'Cluster_0': ['Cx3cr1', 'P2ry12', 'Teme119', 'Csf1r', 'Itgam', 'Aif1', 'Trem2'],
    'Cluster_1': ["Syt6", "Tle4", "Hs3st4", "Col6a1", "Zfpm2", "Sema5a", "Bcl11b", "Fezf2", "Foxp2", "Col12a1"],
}

print("\n--- Input Gene Sets ---")
for name, genes in gene_sets.items():
    print(f"  {name}: {genes}")

print("\n--- Analyzing... ---")
# results, top_hits = piaso.tl.analyzeMarkers(gene_sets, species="Mouse")
results, top_hits = piaso.tl.analyzeMarkers(gene_sets)

print("\nCell Type Predictions:")
for cluster, cell_type in top_hits.items():
    print(f"  {cluster}: {cell_type}")

# Show detailed results
print(f"\n--- Detailed results for Cluster_0 ---")
if 'Cluster_0' in results and len(results['Cluster_0']) > 0:
    print(results['Cluster_0'][['cell_type', 'matched_gene_count',  'avg_specificity',  'study_publication']].head())

print(f"\n--- Detailed results for Cluster_1 ---")
if 'Cluster_0' in results and len(results['Cluster_1']) > 0:
    print(results['Cluster_1'][['cell_type', 'matched_gene_count',  'avg_specificity',  'study_publication']].head())

import cosg

%%time
groupby='CellTypes'
cosg.cosg(adata,
    key_added='cosg',
    use_raw=False, layer='log1p', ## e.g., if you want to use the log1p layer in adata
    mu=100,
    expressed_pct=0.1,
    remove_lowly_expressed=True,
    n_genes_user=adata.n_vars, ### Use all the genes, to enable the calculation of transformed COSG scores
    # n_genes_user=100,
    groupby=groupby,
    return_by_group=True,
    verbosity=1
)

cosg_marker_df=pd.DataFrame(adata.uns['cosg']['names']).head(50)

cosg_marker_df.head()

%%time
results, top_hits = piaso.tl.analyzeMarkers(
        cosg_marker_df,
        n_top_genes=50,
        species="mouse",
)

print("\nCell Type Predictions:")
for cluster, cell_type in top_hits.items():
    print(f"  {cluster}: {cell_type}")

results['L2-3 IT'].head(5)

adata.obs['Tophits_piasomarkerdb']=adata.obs['CellTypes'].map(top_hits)

sc.pl.umap(adata,
           color=['Tophits_piasomarkerdb'],
           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_color4,
           # legend_loc='on data',
           legend_fontoutline=2,
           legend_fontweight=5,
           cmap='Spectral_r',
           ncols=3,
           size=10,
           frameon=False)

piaso.pl.plotConfusionMatrix(adata, 'Tophits_piasomarkerdb', 'CellTypes', figsize=(10, 8))

%%time
results, top_hits = piaso.tl.analyzeMarkers(
        cosg_marker_df,
        n_top_genes=50,
        min_genes=5,
        studies=['AllenWholeMouseBrain_isocortex'],
        species="mouse"
)

top_hits

adata.obs['Tophits_piasomarkerdb_AllenWholeMouseBrain_isocortex']=adata.obs['CellTypes'].map(top_hits)

sc.pl.umap(adata,
           color=[
               'Tophits_piasomarkerdb_AllenWholeMouseBrain_isocortex',
               'Tophits_piasomarkerdb'
                 ],
           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_color4,
           # legend_loc='on data',
           legend_fontoutline=2,
           legend_fontweight=5,
           cmap='Spectral_r',
           ncols=3,
           size=10,
           frameon=False)

piaso.pl.plotConfusionMatrix(adata, 'Tophits_piasomarkerdb_AllenWholeMouseBrain_isocortex', 'CellTypes', figsize=(10, 8))

client = piaso.tl.PIASOmarkerDB()
print(f"\nClient: {client}")

# Get all markers with pagination
print("\n--- Get all markers for a gene (with pagination) ---")
df = client.getAllMarkers(gene="Chrna2", verbose=True)
print(f"Total Chrna2 entries: {len(df)}")
df.head(10)

# Get recommended study
print("\n--- Recommended Studies ---")
for species, tissue in [("human", "blood"), ("human", "brain"), ("human", "spleen")]:
    study = client.getRecommendedStudy(species, tissue)
    print(f"  {species}/{tissue}: {study}")