{"id":24529017,"url":"https://github.com/saezlab/decouplerbench","last_synced_at":"2025-04-14T17:10:52.374Z","repository":{"id":47721135,"uuid":"389619737","full_name":"saezlab/decoupleRBench","owner":"saezlab","description":"Package to benchmark methods from decoupleR","archived":false,"fork":false,"pushed_at":"2023-05-02T14:41:33.000Z","size":84,"stargazers_count":8,"open_issues_count":2,"forks_count":7,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-03-28T05:51:01.776Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/saezlab.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":"2021-07-26T12:09:36.000Z","updated_at":"2024-01-31T23:10:00.000Z","dependencies_parsed_at":"2025-01-22T07:34:31.188Z","dependency_job_id":"000f4389-54ed-431e-a7c7-6e1ac06a384d","html_url":"https://github.com/saezlab/decoupleRBench","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/saezlab%2FdecoupleRBench","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saezlab%2FdecoupleRBench/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saezlab%2FdecoupleRBench/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saezlab%2FdecoupleRBench/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/saezlab","download_url":"https://codeload.github.com/saezlab/decoupleRBench/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248923764,"owners_count":21183954,"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":"2025-01-22T07:34:26.959Z","updated_at":"2025-04-14T17:10:52.348Z","avatar_url":"https://github.com/saezlab.png","language":"R","funding_links":[],"categories":[],"sub_categories":[],"readme":"# decoupleRBench\n`decoupleRBench` allows to evaluate the performance of biological activity \ninference methods using perturbation experiments. It builds on `decoupleR`, and \nmore specifically the `decouple` wrapper function. As such, it requires the \ndecoupleR package to be installed and it is recommended that the user is familiar \nwith the [basics of decoupleR](https://saezlab.github.io/decoupleR/articles/decoupleR.html#basics-1).\nThe benchmark pipeline requires an input tibble with user-specified settings,\nbenchmark data in the form of a count table and a corresponding metadata table.\n\nFor more information, please check:\n\n- `decoupleRBench` vignette: https://github.com/saezlab/decoupleRBench/blob/main/vignettes/how-to-bench.Rmd\n- `decoupleR` repository: https://github.com/saezlab/decoupleR\n- Manuscript repository: https://github.com/saezlab/decoupleR_manuscript\n\n## Install\nTo install `deocupleRBench` please run:\n```\ndevtools::install_github('saezlab/decoupleRBench')\n```\n\n## Evaluation\nFor a given `decoupleR` method, activities are inferred for each regulator and \nexperiment. To evaluate their performance, all experiments are concatenated \ntogether to generate a response vector (whether a regulator is perturbed or not)\nand a predictor vector (the regulator activities). Then, using different \nthresholds we can calculate AUROC and AUPRC for each method. Given that the true \npositive classes are limited by the regulators covered in the perturbation \nexperiments, we use a downsampling strategy, where for each permutation an \nequal number of  negative classes are randomly sampled.\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsaezlab%2Fdecouplerbench","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsaezlab%2Fdecouplerbench","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsaezlab%2Fdecouplerbench/lists"}