Skip to main content

​
Overview

The BasicPipeline class provides a streamlined workflow for single-cell RNA-seq analysis of cardiac tissue. It performs standard preprocessing, clustering, and visualization using Scanpy. Inheritance: BasePipeline Source: heartmap.pipelines.BasicPipeline (src/heartmap/pipelines/init.py:48)

​
Constructor

BasicPipeline(config: Config)
​
config
Config
required
Configuration object containing analysis parameters including resolution for clustering.

​
Attributes

Inherited from BasePipeline:
  • config (Config): Configuration object
  • data_processor (DataProcessor): Data processing handler
  • visualizer (Visualizer): Visualization handler
  • exporter (ResultsExporter): Results export handler
  • results (Dict[str, Any]): Dictionary storing pipeline results

​
Methods

​
run()

Run the basic analysis pipeline including data loading, clustering, and visualization. 
def run(data_path: str, output_dir: Optional[str] = None) -> Dict[str, Any]
​
data_path
str
required
Path to raw single-cell data file (10X format or similar).
​
output_dir
Optional[str]
Directory to save results and visualizations. If None, results are returned but not saved.
​
return
Dict[str, Any]
Dictionary containing pipeline results:
​
adata
AnnData
Annotated data object with clustering results
​
results
Dict[str, Any]
Analysis results
​
cluster_labels
np.ndarray
Array of cluster assignments for each cell (from Leiden clustering)
Raises:
  • ImportError: If required dependencies (scanpy, pandas, numpy, matplotlib) are not available
Pipeline Steps:
  1. Data Loading and Processing - Loads raw data using DataProcessor.process_from_raw()
  2. Neighborhood Graph - Computes PCA (40 components) and k-nearest neighbors (k=15) if not present
  3. Cell Clustering - Performs Leiden clustering using the resolution from config
  4. Visualization - Generates UMAP plots and QC metrics (if output_dir provided)
  5. Results Export - Saves annotated data as annotated_data.h5ad and results

​
save_results()

Inherited from BasePipeline. Save pipeline results to disk. 
def save_results(output_dir: str) -> None
​
output_dir
str
required
Directory path where results will be saved

​
Usage Example

from heartmap.config import Config
from heartmap.pipelines import BasicPipeline

# Create configuration
config = Config(
    data_path="data/cardiac_tissue.h5ad",
    analysis={
        "resolution": 0.8
    }
)

# Initialize pipeline
pipeline = BasicPipeline(config)

# Run analysis
results = pipeline.run(
    data_path="data/raw/cardiac_10x",
    output_dir="results/basic_analysis"
)

# Access results
adata = results['adata']
cluster_labels = results['results']['cluster_labels']

print(f"Identified {len(set(cluster_labels))} cell clusters")

​
Output Files

When output_dir is specified, the pipeline generates:
  • annotated_data.h5ad - Processed AnnData object with cluster annotations
  • figures/umap_clusters.png - UMAP visualization colored by cluster
  • figures/qc_*.png - Quality control metric plots
  • Results exported via ResultsExporter

Quickstart Guide

Get started with HeartMAP analysis

Config

Configuration object reference

DataProcessor

Data processing functionality

Build docs developers (and LLMs) love

Get started for freeTalk to us