Gradient Biotech
U

Menu

Research Areas

Computational BiologySingle-cell, bulk RNA-seq, spatial, and biomarkers
CardiologyCardiovascular signals, cohorts, and interpretationImmunologyImmune cell states, signaling networks, and repertoire dynamicsNeurologyBrain connectivity, functional imaging, and electrophysiologyOncologyTumor microenvironment, immune response, mutations, and survivalPathologyWhole-slide imaging, tissue quantification, and spatial pathology

Application

Documentation

Documentation

Back to studies

FAQ

Is this a clinical diagnostic tool?

No. Oncology in Gradient Biotech is a research and translational analysis workspace. Outputs must not be used for clinical diagnosis, treatment selection, or regulatory decision-making. This is not a replacement for expert oncology review.

Do I need R, CellPhoneDB, or maftools installed locally?

No. Upload files through the web UI or register dataset paths; all analysis runs in backend-analysis. Reference implementations in products/oncology/applications/ inform algorithm ports but are not executed at runtime.

How do I run my first pipeline?

Create a study, prepare a MAF or clinical CSV (see Sample data), and dispatch a job via the workflow page or analysis API. See Quick start.

Cell communication failed — missing expression_path

The cell_communication pipeline requires parameters.expression_path and parameters.metadata_path pointing to valid CSV files on the analysis server filesystem.

Mutation landscape failed — missing mutation_path

The mutation_landscape pipeline requires parameters.mutation_path pointing to a MAF-style CSV.

Survival analysis failed — missing clinical_path

The survival pipeline requires parameters.clinical_path with patient_id, time_to_event_days, and event_observed columns.

Interpretation failed — source runs not found

The interpret pipeline requires parameters.source_run_ids referencing completed runs whose artifacts exist under data/oncology/artifacts/.

Where are files stored locally?

Artifacts: data/oncology/artifacts/{run_id}/
Metadata: Supabase PostgreSQL (biochem_onco_* tables) via the metadata API

These paths are gitignored.

How does oncology relate to Computational Biology?

Computational Biology owns single-cell clustering, spatial transcriptomics, differential expression, and biomarker ML. Oncology adds cell-cell communication, immune deconvolution, mutation landscape, survival analysis, and clinical endpoint integration. TME profiling calls compbio infrastructure rather than duplicating it.

How does oncology relate to Pathology?

Pathology owns whole-slide imaging, tissue segmentation, and spatial quantification. Oncology uses pathology outputs for pathology-integrated spatial TME analysis without rebuilding the image processing layer.

How do I add a new pipeline?

Implement in backend-analysis/app/oncology/pipelines/, register in backend-analysis/app/oncology/routers/run.py, and expose via job endpoints. See products/oncology/todo.md and repo root claude.md for conventions.

Is cloud deployment supported?

Production GCP deployment with object storage and Cloud Tasks for async jobs is planned but not the current local focus. See products/oncology/product.md.

How do I list available pipelines?

curl http://localhost:8001/oncology/pipelines
curl http://localhost:8000/oncology/studies
curl http://localhost:8001/health