{"id":20837744,"url":"https://github.com/astrazeneca/skywalkr","last_synced_at":"2025-05-08T20:30:21.863Z","repository":{"id":41037184,"uuid":"371064106","full_name":"AstraZeneca/skywalkR","owner":"AstraZeneca","description":"code for Gogleva et al manuscript ","archived":false,"fork":false,"pushed_at":"2022-11-30T11:08:58.000Z","size":1083,"stargazers_count":45,"open_issues_count":0,"forks_count":16,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-31T17:59:07.308Z","etag":null,"topics":["drug-discovery","knowledge-graph","recommender-system","shiny-apps","ui"],"latest_commit_sha":null,"homepage":"","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AstraZeneca.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-05-26T14:30:45.000Z","updated_at":"2024-09-10T18:14:46.000Z","dependencies_parsed_at":"2023-01-21T17:46:14.435Z","dependency_job_id":null,"html_url":"https://github.com/AstraZeneca/skywalkR","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/AstraZeneca%2FskywalkR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AstraZeneca%2FskywalkR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AstraZeneca%2FskywalkR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AstraZeneca%2FskywalkR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AstraZeneca","download_url":"https://codeload.github.com/AstraZeneca/skywalkR/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253144498,"owners_count":21861072,"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":["drug-discovery","knowledge-graph","recommender-system","shiny-apps","ui"],"created_at":"2024-11-18T01:08:28.168Z","updated_at":"2025-05-08T20:30:21.841Z","avatar_url":"https://github.com/AstraZeneca.png","language":"R","funding_links":[],"categories":[],"sub_categories":[],"readme":"![Maturity level-Prototype](https://img.shields.io/badge/Maturity%20Level-Prototype-red) [![DOI](https://zenodo.org/badge/371064106.svg)](https://zenodo.org/badge/latestdoi/371064106)\n\n\n## skywalkR\n\nThis repository contains code and documentation to accompany Gogleva et al manuscript: **Knowledge Graph-based Recommendation Framework Identifies Novel Drivers of Resistance in EGFR mutant Non-small Cell Lung Cancer**. \n\nTo read the paper please follow: [https://www.biorxiv.org/content/10.1101/2021.07.23.453506v1.full.pdf+html](https://www.nature.com/articles/s41467-022-29292-7)\n\nThe repository has the following structure:\n\n```\n.\n├── DESCRIPTION\n├── CONTRIBUTING.md\n├── LICENSE\n├── 🛠️ R --\u003e helper functions for shiny apps\n│   ├── server_utils.R\n│   └── ui_utils.R\n├── README.md\n├── renv.lock\n├── 💾 data --\u003e necessary input data and sample data files\n│   ├── app_data.csv\n│   ├── heatmap_data.tsv\n│   ├── mtcars.csv\n│   ├── nlp_allowed.csv\n│   └── sample_data.csv\n├── 📄 docs --\u003e within the app documentation\n│   ├── intro.md\n│   ├── intro_light.md\n│   ├── pareto_bar_explained.md\n│   ├── pareto_hist_explained.md\n│   └── variables_explained.md\n├── 🖼️ img --\u003e readme plots\n│   ├── skywalkR_interface.png\n│   └── skywalkr_light_interface.png\n├── 🧬 skywalkR_app.R --\u003e main Shiny app\nre-rank CRISPR hits to find promising genes driving drug\nresistance in EGFR mutant lung cancer;\n└── 🧪 skywalkR_light_app.R --\u003e a demo shiny app,\ninput any table to test out how multi-objective optimisation works;\n```\n\n### SkywalkR app\n\nThis Shiny app is tailored to finding genes driving resistance in EGFR mutant Non-small Cell Line Cancer (NSCLC). The app will automatically load required data. To re-rank genes set directions of optimization by moving sliders and press ``rank!`` button.\n\n![skywalkr_app](https://github.com/AstraZeneca/skywalkR/blob/master/img/skywalkR_interface.png)\n\n\n### SkywalkR_light app\n\nThis is a generic app, bare bones app that allows users to apply the same idea of multi-objective optimization to their own data. Any tabular numeric data should work. To include categorical data, please represent it as numeric. By default we will treat the first column as labels. Columns will be automatically mapped to sliders.\n\n![skywalkr_light_app](https://github.com/AstraZeneca/skywalkR/blob/master/img/skywalkR_light_interface.png)\n\n\n### Running apps\n\nTo install all the packages required to run the apps, call ``renv::restore()`` as declared in the lockfile. Typically, it can take a few minutes to install the dependencies, depending on which ones are already installed in your environment.\n\nAfter installing run the respective app, it should start immediately:\n\n``R -e \"shiny::runApp('skywalkR_light_app.R')\"``\n\nor\n\n``R -e \"shiny::runApp('skywalkR_app.R')\"``\n\nTypical start time for the app 10-20 seconds. Time estimates are provided for MacBook Pro, 6-Core Intel Core i7, 2.6 GHz, 6 cores, 32 GB, Big Sur.\n\n### Citation \n```\n@Article{Gogleva2022,\nauthor={Gogleva, Anna\nand Polychronopoulos, Dimitris\nand Pfeifer, Matthias\nand Poroshin, Vladimir\nand Ughetto, Micha{\\\"e}l\nand Martin, Matthew J.\nand Thorpe, Hannah\nand Bornot, Aurelie\nand Smith, Paul D.\nand Sidders, Ben\nand Dry, Jonathan R.\nand Ahdesm{\\\"a}ki, Miika\nand McDermott, Ultan\nand Papa, Eliseo\nand Bulusu, Krishna C.},\ntitle={Knowledge graph-based recommendation framework identifies drivers of resistance in EGFR mutant non-small cell lung cancer},\njournal={Nature Communications},\nyear={2022},\nmonth={Mar},\nday={29},\nvolume={13},\nnumber={1},\npages={1667},\nabstract={Resistance to EGFR inhibitors (EGFRi) presents a major obstacle in treating non-small cell lung cancer (NSCLC). One of the most exciting new ways to find potential resistance markers involves running functional genetic screens, such as CRISPR, followed by manual triage of significantly enriched genes. This triage process to identify `high value' hits resulting from the CRISPR screen involves manual curation that requires specialized knowledge and can take even experts several months to comprehensively complete. To find key drivers of resistance faster we build a recommendation system on top of a heterogeneous biomedical knowledge graph integrating pre-clinical, clinical, and literature evidence. The recommender system ranks genes based on trade-offs between diverse types of evidence linking them to potential mechanisms of EGFRi resistance. This unbiased approach identifies 57 resistance markers from \u003e3,000 genes, reducing hit identification time from months to minutes. In addition to reproducing known resistance markers, our method identifies previously unexplored resistance mechanisms that we prospectively validate.},\nissn={2041-1723},\ndoi={10.1038/s41467-022-29292-7},\nurl={https://doi.org/10.1038/s41467-022-29292-7}\n}\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fastrazeneca%2Fskywalkr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fastrazeneca%2Fskywalkr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fastrazeneca%2Fskywalkr/lists"}