{"id":39625903,"url":"https://github.com/jordan2lee/classify-lab-models-and-tumors","last_synced_at":"2026-01-18T08:35:23.347Z","repository":{"id":288681202,"uuid":"966420848","full_name":"jordan2lee/classify-lab-models-and-tumors","owner":"jordan2lee","description":"Cancer subtype tool for tumors and their lab grown models","archived":false,"fork":false,"pushed_at":"2025-04-18T23:35:34.000Z","size":51,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-19T09:51:40.454Z","etag":null,"topics":["cancer","machine-learning","model","molecular","neural-networks","subtype","tumor"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jordan2lee.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"zenodo":null}},"created_at":"2025-04-14T22:35:00.000Z","updated_at":"2025-04-18T23:35:35.000Z","dependencies_parsed_at":"2025-04-20T13:00:54.954Z","dependency_job_id":null,"html_url":"https://github.com/jordan2lee/classify-lab-models-and-tumors","commit_stats":null,"previous_names":["jordan2lee/classify-lab-models-and-tumors"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jordan2lee/classify-lab-models-and-tumors","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jordan2lee%2Fclassify-lab-models-and-tumors","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jordan2lee%2Fclassify-lab-models-and-tumors/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jordan2lee%2Fclassify-lab-models-and-tumors/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jordan2lee%2Fclassify-lab-models-and-tumors/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jordan2lee","download_url":"https://codeload.github.com/jordan2lee/classify-lab-models-and-tumors/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jordan2lee%2Fclassify-lab-models-and-tumors/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28534148,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-18T00:39:45.795Z","status":"online","status_checked_at":"2026-01-18T02:00:07.578Z","response_time":98,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["cancer","machine-learning","model","molecular","neural-networks","subtype","tumor"],"created_at":"2026-01-18T08:35:23.292Z","updated_at":"2026-01-18T08:35:23.342Z","avatar_url":"https://github.com/jordan2lee.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003ch1 align=\"center\"\u003eSubtype Classification of Tumors and Derived Lab Grown Models\u003c/h1\u003e\n\u003ch4 align=\"center\"\u003eMolecular subtyping using the TMP Toolkit\u003c/h4\u003e\n\n\n## Table of contents\n- [Quickstart Guide](#quickstart-guide)\n- [Download Data from Manifest File Using the GDC Client](#download-data-from-manifest-file-using-the-gdc-client)\n- [Run Processing Pipeline](#run-processing-pipeline)\n- [Sample Subtype Classification using Gene Expression Data](#sample-subtype-classification-using-gene-expression-data)\n- [Sample Subtype Classification using DNA Methylation Data](#sample-subtype-classification-using-dna-methylation-data)\n\n## Quickstart Guide\n\n### Setup\n\nInstall requirements - detailed instructions are found on the [Requirements page](doc/requirements.md):\n\n1. Install Python 3+\n2. Install GDC Data Transfer Tool Client\n\nEnsure that steps are completed on the [Requirements page](doc/requirements.md) - *(includes creating working environment, signining in, and manually downloading required data)*\n\n## Download Data from Manifest File Using the GDC Client\nDownload Gene Expression Data\n```bash\nbash scripts/gdc_download.sh PAAD\n```\n\nThis will create subfolders in `dat`a-raw/\u003cCANCER\u003e_GEXP_\u003cTYPE\u003e` and place GDC molecular matrices here.\n\n\u003e Options for cancer cohort includes `ALL`, `BLCA`, `BRCA`, `COADREAD`, `ESO`, `HNSC`, `KID`, `LGGGBM`, `LIHCCHOL`, `LUNG`, `OV`, `PAAD`, `SARC`, `SKCM`, `UCEC`\n\nFor more details on each cancer cohort option see [Cohort Options Page](doc/cohort_options.md)\n\n\n## Run Processing Pipeline\nExample shown for running PAAD cohort\n```bash\nbash scripts/process.sh PAAD data/prep\n```\n\n\u003e Creates file `data/prep/\u003cCANCER\u003e_GEXP/\u003cCANCER\u003e_GEXP_prep2_\u003cTYPE\u003e.tsv` that is prepped for distance calculations\n\n\u003e Options for cancer cohort includes `ALL`, `BLCA`, `BRCA`, `COADREAD`, `ESO`, `HNSC`, `KID`, `LGGGBM`, `LIHCCHOL`, `LUNG`, `OV`, `PAAD`, `SARC`, `SKCM`, `UCEC`\n\nFor more details on each cancer cohort option see [Cohort Options Page](doc/cohort_options.md)\n\n## Sample Subtype Classification Using Gene Expression Data\nThe goal of this analysis is to get cancer subtype predictions for HCMI samples (organoids, cell cultures , xenografts, etc). To accomplish this we will use the top performing pre-trained machine learning models (dockerized TMP models that were trained using TCGA data that has been pre-proccessed). Specifically we are interested in using gene expression from the HCMI samples and eventually compare primary tumors to their corresponding models (organoids, cell cultures , xenografts, etc).\n\nThe TMP models (pre-trained models) are specific to TCGA cancer cohorts (TCGA abbreviations), therefore we will split HCMI data into TCGA cancer cohorts(based on sample metadata).\n\nRun gene expression classifier pipeline:\n```bash\n# where specify cancer, tumor-file, model-file, transformed-dir\nbash scripts/run_classify_GEXP.sh \\\n    PAAD \\\n    data/prep/PAAD_GEXP/PAAD_GEXP_prep2_Tumor.tsv \\\n    data/prep/PAAD_GEXP/PAAD_GEXP_prep2_Model.tsv \\\n    data/classifier_gexp/ml_ready_qrank\n```\n\nResults can found in `data/classifier_gexp/ml_predictions_qrank/combo/HCMI_TMPsubtype_qRank_\u003cCANCER\u003e.tsv `\n\n*Note: LUNG (includes LUAD and LUSC), ESO (includes GEA and ESCC) during transformation and classification, then is merged in post-classification summary*\n\n\n## Sample Subtype Classification Using DNA Methylation Data\nThe goal of this analysis is to get cancer subtype predictions for HCMI samples (organoids, cell cultures , xenografts, etc). To accomplish this we will use the top performing pre-trained machine learning models (dockerized TMP models that were trained using TCGA data that has been pre-proccessed). Specifically we are interested in using gene expression from the HCMI samples and eventually compare primary tumors to their corresponding models (organoids, cell cultures , xenografts, etc).\n\nThe TMP models (pre-trained models) are specific to TCGA cancer cohorts (TCGA abbreviations), therefore we will split HCMI data into TCGA cancer cohorts(based on sample metadata).\n\nRun DNA methylation classifier pipeline:\n```bash\n# where specify cancer, tumor-file, model-file, transformed-dir\nbash scripts/run_classify_METHYL.sh \\\n    SKCM \\\n    data/classifier_methyl/processed/20231211_HCMI_TMP_subtype_prediction_feature_matrix_SKCM.tsv\n```\n\nResults can found in `data/classifier_methyl/ml_predictions/combo/HCMI_METH_TMPsubtypes.\u003cCANCER\u003e.tsv`\n\n*Note: LUNG (includes LUAD and LUSC), ESO (includes GEA and ESCC) during transformation and classification, then is merged in post-classification summary*\n\n\u003e *Second Example for Combination Cohort*\n\u003e ```bash\n\u003e bash scripts/run_classify_METHYL.sh \\\n\u003e     LUNG \\\n\u003e     data/classifier_methyl/processed/20231211_HCMI_TMP_subtype_prediction_feature_matrix_LUNG.tsv\n\u003e ```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjordan2lee%2Fclassify-lab-models-and-tumors","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjordan2lee%2Fclassify-lab-models-and-tumors","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjordan2lee%2Fclassify-lab-models-and-tumors/lists"}