{"id":32639470,"url":"https://github.com/raghavagps/skcm_prognostic_biomarker","last_synced_at":"2026-04-18T00:32:06.479Z","repository":{"id":300723648,"uuid":"1006933990","full_name":"raghavagps/skcm_prognostic_biomarker","owner":"raghavagps","description":"Pronostic biomarkers for SKCM","archived":false,"fork":false,"pushed_at":"2025-06-27T11:36:27.000Z","size":988,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-31T02:20:47.146Z","etag":null,"topics":["biomarkers","expression-profiles","machine-learning","prognostic-models"],"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/raghavagps.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":"2025-06-23T08:04:52.000Z","updated_at":"2025-06-27T11:36:30.000Z","dependencies_parsed_at":"2025-06-26T10:42:07.463Z","dependency_job_id":null,"html_url":"https://github.com/raghavagps/skcm_prognostic_biomarker","commit_stats":null,"previous_names":["shivanim007/skcm_prognostic_biomarker","raghavagps/skcm_prognostic_biomarker"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/raghavagps/skcm_prognostic_biomarker","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raghavagps%2Fskcm_prognostic_biomarker","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raghavagps%2Fskcm_prognostic_biomarker/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raghavagps%2Fskcm_prognostic_biomarker/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raghavagps%2Fskcm_prognostic_biomarker/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/raghavagps","download_url":"https://codeload.github.com/raghavagps/skcm_prognostic_biomarker/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raghavagps%2Fskcm_prognostic_biomarker/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31951291,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-17T17:29:20.459Z","status":"ssl_error","status_checked_at":"2026-04-17T17:28:47.801Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["biomarkers","expression-profiles","machine-learning","prognostic-models"],"created_at":"2025-10-31T02:12:05.565Z","updated_at":"2026-04-18T00:32:06.366Z","avatar_url":"https://github.com/raghavagps.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"---\nAuthor: Shivani Malik\nDate: 2025-06-20\nTitle: SKCM README\n---\n\n## R Markdown\n\n# 🧬 Identification of Multiple Prognostic Biomarkers sets for Risk stratification in SKCM\n\nThis project identifies and validates prognostic biomarker sets in\n**skin cutaneous melanoma (SKCM)** using statistical and machine\nlearning approaches.\n\n------------------------------------------------------------------------\n\n## 🔍 Overview\n\n-   **Data Retrieval**: Gene expression data (473 samples, 60,660 genes)\n    was downloaded from TCGA using `TCGAbiolinks` in R.\n-   **Normalization**: Data was normalized to TPM.\n-   **Statistical Analysis**: Performed correlation analysis, survival\n    analysis (Cox, Kaplan-Meier), and LASSO.\n-   **Survival Class Creation**: OS time was used to create 4 survival\n    classes (0--1, 1--3, 3--5, \\\u003e5 years → Class 0,1,2,3).\n-   **Feature Selection**: Applied SVC-L1, RFE, SelectKBest, and SFS to\n    identify top genes.\n-   **Class Balancing**: Used SMOTE to balance the dataset.\n-   **Biomarker Sets**: Created 7 biomarker sets (each with 20 genes).\n-   **Model Performance**: AUC ranged from **0.84 to 0.91**, and Kappa\n    from **0.48 to 0.64** across sets.\n-   **Model Training**: Applied many models but best Trained classifiers\n    (CatBoost) and evaluated using AUC-ROC.\n-   **Validation**: Validated on **GSE65904 (214 samples)** using\n    overlapping genes.\n    -   **First Set**: 15 matching genes → AUC 0.85 (train), 0.83\n        (test)\n    -   **Third Set**: 12 matching genes → AUC 0.85 (train), 0.86 (test)\n\n------------------------------------------------------------------------\nThis repository contains all relevant files and scripts used to identify and validate prognostic biomarkers in SKCM using statistical and machine learning approaches.\n\n---\n\n## 📁 Repository Structure\n\n### 1. `Biomarkers/`\nContains lists of genes identified through feature selection and validated on a new dataset.\n\n- `Primary_biomarker/`\n  - `List_1st_set.txt` – First set of 20 genes selected from TCGA using SVC-L1.\n  - `List_2nd_set.txt` – Second set of 20 genes selected using alternative feature selection methods.\n  - `List_3rd_set.txt` – Third set of 20 genes selected from TCGA.\n  - `List_4th_set.txt` – Fourth set of 20 selected biomarker genes.\n  - `List_5th_set.txt` – Fifth set of 20 selected biomarker genes.\n  - `List_6th_set.txt` – Sixth set of 20 selected biomarker genes.\n  - `List_7th_set.txt` – Seventh set of 20 selected biomarker genes.\n\n- `Validated_biomarker/`\n  - `List_match_1st.txt` – List of 15 matched genes from the first biomarker set validated on GEO dataset (GSE65904).\n  - `List_match_3rd.txt` – List of 12 matched genes from the third biomarker set validated on GEO dataset (GSE65904).\n\n\n### 2. `Dataset/`\nIncludes scripts and data access instructions for both primary (TCGA) and validation (GEO) datasets.\n\n#### a. `Primary_data_TCGA/`\n- `Script/`\n  - `TCGA_SKCM.R` – R script for downloading SKCM expression data using `TCGAbiolinks`.\n- `Link/`\n  - `Data_link.txt` – Contains links to TCGA data portal and UCSC Xena browser for direct download.\n\n#### b. `Validation_data_GEO/`\n- `Script/`\n  - `GEO_SKCM.R` – R script for downloading GSE65904 dataset.\n- `Link/`\n  - `Data_link.txt` – Contains GEO accession links.\n\n---\n\n### 3. `Scripts/`\nIncludes preprocessing, feature selection, and machine learning implementation scripts.\n\n - `Preprocessing_TCGA.py` – Preprocessing steps: Remove 50% zeroes and low variance gene. \n\n - `Feature_selection_ML_TCGA.py` – Feature selection using SVC-L1 on the basis of ranking, ML training and evaluate performance\n\n - `15_1stset_ML_GEO.py` – ML analysis on 15 matched genes from the primary biomarker set.\n\n\n  - `12_3rdset_ML_GEO.py` – ML analysis on 12 matched genes from the third biomarker set.\n\n## use the same code for other set of biomarkers##\n\nAll the GEO and TCGA relevant data files and models could be downloaded from the google drive link: https://drive.google.com/drive/folders/1HIVw_rfpHolB3tAvJTtOZVV0USOANil-.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fraghavagps%2Fskcm_prognostic_biomarker","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fraghavagps%2Fskcm_prognostic_biomarker","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fraghavagps%2Fskcm_prognostic_biomarker/lists"}