bioinformatics-init-analysis

You can automate single-cell data analysis by running a 7-step pipeline that loads data, performs QC and normalization, applies PCA/UMAP, clusters cells, and runs marker analysis to output a processed dataset and clinical HTML report.

Yes, the pipeline supports modular execution, allowing you to run individual steps like clustering or marker analysis independently rather than executing the full end-to-end pipeline at once.

Yes, the pipeline auto-detects data types and fully supports high-dimensional single-cell biology workflows including CyTOF, scRNA-seq, and flow cytometry files.

The pipeline automatically detects your single-cell data type by evaluating the input path, applying the appropriate processing logic for scRNA-seq, CyTOF, or flow cytometry without requiring manual configuration.

The best way is to use an end-to-end pipeline that processes high-dimensional single-cell data and automatically generates a plain-language HTML clinical report alongside the processed dataset.

Yes, the pipeline requires scanpy, anndata, numpy, pandas, scikit-learn, and fcsparser to handle data loading, normalization, dimensionality reduction, and clustering across single-cell formats.