Add cancer genomics datasets and tasks (ClinVar, COSMIC, TCGA-PRAD) #625
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This PR adds support for cancer genomics data to PyHealth: Datasets: - ClinVarDataset: Variant clinical significance annotations - COSMICDataset: Cancer somatic mutations catalogue - TCGAPRADDataset: TCGA Prostate Adenocarcinoma multi-omics data Tasks: - VariantClassificationClinVar: Predict pathogenic/benign variants - MutationPathogenicityPrediction: FATHMM-based mutation prediction - CancerSurvivalPrediction: Patient survival outcome prediction - CancerMutationBurden: High vs low TMB classification Features: - YAML configs for all three datasets - Helper methods for data cleaning (_safe_float, _extract_genes, etc.) - Class constants for category mappings (ACMG/AMP guidelines) - Comprehensive docstrings with examples - 43 unit tests (all passing)
jhnwu3
requested changes
Nov 23, 2025
Collaborator
jhnwu3
left a comment
jhnwu3
left a comment
There was a problem hiding this comment.
Wow! Thanks for doing this! Can you add a couple doc pages for each of your datasets here? Here's an exemplar with the task and dataset contributions:
https://github.com/sunlabuiuc/PyHealth/pull/392/files
Very nice PR! I'm excited to merge this since I know it's from your guys' paper.
Author
|
Hi @jhnwu3 I'm working on it, and push it soon |
- Add RST docs for ClinVarDataset, COSMICDataset, TCGAPRADDataset - Add RST docs for variant classification and cancer survival tasks - Update datasets.rst and tasks.rst index files
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds support for cancer genomics datasets to PyHealth, enabling
variant classification and survival prediction research.
Datasets
Tasks
Implementation
Test Plan
Background
This contribution stems from our cancer genomics benchmarking work:
Prostate-VarBench: A Somatic Variant Calling Benchmark for Prostate Cancer
arXiv: https://arxiv.org/abs/2511.09576
Repository: https://github.com/AbrahamArellano/uiuc-cancer-research
These datasets enable reproducible cancer genomics research within PyHealth.