{"id":20074656,"url":"https://github.com/greenelab/pancancer-evaluation","last_synced_at":"2025-05-05T21:32:04.897Z","repository":{"id":37955530,"uuid":"283575430","full_name":"greenelab/pancancer-evaluation","owner":"greenelab","description":"Evaluating genome-wide prediction of driver mutations using pan-cancer data","archived":false,"fork":false,"pushed_at":"2024-10-21T11:15:57.000Z","size":90839,"stargazers_count":9,"open_issues_count":17,"forks_count":3,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-10-21T16:22:34.425Z","etag":null,"topics":["analysis","cancer","classifier","gene-expression","genome","machine-learning","pancancer"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/greenelab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-07-29T18:38:57.000Z","updated_at":"2023-05-11T05:46:12.000Z","dependencies_parsed_at":"2024-10-21T15:17:11.958Z","dependency_job_id":null,"html_url":"https://github.com/greenelab/pancancer-evaluation","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/greenelab%2Fpancancer-evaluation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/greenelab%2Fpancancer-evaluation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/greenelab%2Fpancancer-evaluation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/greenelab%2Fpancancer-evaluation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/greenelab","download_url":"https://codeload.github.com/greenelab/pancancer-evaluation/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224470631,"owners_count":17316704,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["analysis","cancer","classifier","gene-expression","genome","machine-learning","pancancer"],"created_at":"2024-11-13T14:53:17.357Z","updated_at":"2024-11-13T14:53:17.921Z","avatar_url":"https://github.com/greenelab.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# pancancer-evaluation\n\n**Note:** This repository is currently a work in progress, so some aspects of\nthe code/analysis may not be fully described or documented here.\n\nIn general, the goal of this project is to follow up on and generalize previous\nGreene Lab studies predicting driver mutation status from TCGA gene expression\ndata. See previous repos and associated publications\n[here](https://github.com/greenelab/pancancer) and\n[here](https://github.com/greenelab/biobombe) for more detail on past work and\nbiological significance/interpretation of mutation prediction from gene\nexpression.\n\nBroad research questions and analysis plan:\n\n* Replicate results from BioBombe repo for stratified train/test sets\n* Set up cross-validation holding out individual cancer types, and compare\n  results to negative control with shuffled labels\n* Comparison of pan-cancer and single-cancer training sets: when does adding\n  pan-cancer data help? Does it ever hurt?\n* Learning curve experiments: Is the effect of added data dependent on the\n  number of samples for the cancer type in question, or the label balance for\n  the driver gene in question?\n* External validation, generalization to other ICGC or pediatric cancer\n  datasets: how/when can we use pan-cancer data to help?\n* More to come\n\nIssues are mostly up-to-date for future ideas/research directions (filter by\nthe \"research question\" tag), as well as known bugs/limitations of the code\nand evaluation infrastructure (other tags).\n\n## Setup\n\nWe recommend using the conda environment specified in the `environment.yml` file\nto run these analyses. To build and activate this environment, run:\n\n```shell\n# conda version 4.5.0\nconda env create --file environment.yml\n\nconda activate pancancer-evaluation\n```\n\nTo make the relative file paths in\n[pancancer_evaluation/config.py](pancancer_evaluation/config.py) work correctly,\nyou'll also need to install the `pancancer_evaluation` package in development\nmode:\n\n```shell\npip install -e .\n```\n\n(note that currently running `pip install .` will break the file paths, this\nwill be fixed eventually but at the moment we recommend using the `-e`/\ndevelopment flag)\n\n## Running tests\n\nRunning the tests requires the `pytest` module (included in the specified\nConda environment). Once this module is installed, you can run the tests\nby executing the command\n\n```shell\npytest tests/\n```\n\nfrom the repo root.\n\n## Regenerating test data\n\nIf you make changes to the model fitting code, hyperparameters, cross-validation\ncode, etc., you may need to regenerate the model output used for\n[the model regression tests](tests/test_model.py). To do this, you can run\nthe following command from the repo root:\n\n```shell\npython pancancer_evaluation/scripts/generate_test_data.py --verbose\n```\n\nThis will print messages showing which files are being rewritten.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgreenelab%2Fpancancer-evaluation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgreenelab%2Fpancancer-evaluation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgreenelab%2Fpancancer-evaluation/lists"}