{"id":22731065,"url":"https://github.com/genentech/gamerank","last_synced_at":"2025-04-14T00:30:54.151Z","repository":{"id":72633454,"uuid":"462408068","full_name":"Genentech/GameRank","owner":"Genentech","description":null,"archived":false,"fork":false,"pushed_at":"2024-09-09T10:27:20.000Z","size":20383,"stargazers_count":10,"open_issues_count":0,"forks_count":1,"subscribers_count":6,"default_branch":"main","last_synced_at":"2024-09-10T11:53:10.624Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"R","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/Genentech.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}},"created_at":"2022-02-22T17:40:54.000Z","updated_at":"2024-09-09T10:27:23.000Z","dependencies_parsed_at":"2024-04-04T08:28:19.147Z","dependency_job_id":"6ff433f8-abcc-4763-bbac-7cbc59046d8e","html_url":"https://github.com/Genentech/GameRank","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/Genentech%2FGameRank","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Genentech%2FGameRank/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Genentech%2FGameRank/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Genentech%2FGameRank/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Genentech","download_url":"https://codeload.github.com/Genentech/GameRank/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":229117070,"owners_count":18022819,"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":[],"created_at":"2024-12-10T19:19:18.925Z","updated_at":"2024-12-10T19:19:19.560Z","avatar_url":"https://github.com/Genentech.png","language":"R","funding_links":[],"categories":[],"sub_categories":[],"readme":"# GameRank - An R package for Feature Selection\n\nThe GameRank package is an R package that implements functions for \nvariable and feature selection to create predictive models. This includes a \nnumber of feature selection algorithms, mostly combinatorial\nsearch strategies, which are:\n\n * Forward selection,\n * Backward selection,\n * Bidirectional search, and\n * Plus-L, Minus-R search together with \n * Random search, which draws random combinations across the feature space, and\n * *GameRank* a novel feature selection algorithm, that employs a\n   maximum likelihood ranking model to learn the optimal ranking of features. \n   The following figure illustrates the algorithm: \n   ![The GameRank Algorithm](man/figures/GameRank-Algorithm.png)\n   \nIn addition, it provides methods for feature construction, that is\n\n * functions to screen variable properties,\n * evaluate simple variable transformations, \n * Box-Cox transformations for regression and binomial models, as well as\n * methods for the detection of features with multi-modal distributions.\n \nGameRank allows for direct optimization of measures related to _calibration_ and\n_discrimination_ of models. This approach uses a training:validation:test split-set\napproach. However, for small sample selection projects, functions for bias-corrections via\ncross-validation or bootstrapping are included.\n\nParts of this code have been used to craft a model for chemo-tolerability \nprediction. [https://ascopubs.org/doi/full/10.1200/CCI.21.00121]\n\nThe package can be installed directly from GitHub via\n\n```{r}\ndevtools::install_github(\"Genentech/GameRank\")\n```\n\nHere are some few lines of example code to use the package to \n**screen features:**\n```{r}\nlibrary( dplyr )\nlibrary( ggplot2 )\nvck \u003c- check_variables( toy_data, response_var, list_variables )\nvck %\u003e% \n   ggplot(aes(x=entropy, y=mutual_information) ) +\n   geom_point()\n```\nand do a **forward selection:**\n```{r}\nsel \u003c- forward( toy_data, response_var, list_variables \n                 fn_train_binomial,  # Train a logistic regression model\n                 fn_eval_binomial_auroc,  # Evaluate the Area under ROC curve\n                 m=4L,   # Search for combination of 4 features\n                 splits=2L, # Evaluate on 2 parallel split sets\n                 maximize=TRUE # Maximize the Area under ROC curve\n                 )\nsel$variable_selections\n```\n\nHave fun!","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgenentech%2Fgamerank","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgenentech%2Fgamerank","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgenentech%2Fgamerank/lists"}