{"id":22555824,"url":"https://github.com/samuelnicaise/cached_spliceai","last_synced_at":"2026-04-18T17:06:00.015Z","repository":{"id":266871524,"uuid":"899132704","full_name":"SamuelNicaise/cached_spliceai","owner":"SamuelNicaise","description":"SpliceAI with an in-memory key-value database to cache already seen variants","archived":false,"fork":false,"pushed_at":"2024-12-06T16:19:51.000Z","size":17,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-28T11:13:12.061Z","etag":null,"topics":["cache","database","keydb","nosql","redis","spliceai"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SamuelNicaise.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":"2024-12-05T17:20:10.000Z","updated_at":"2025-02-18T15:29:25.000Z","dependencies_parsed_at":"2024-12-06T17:39:02.857Z","dependency_job_id":null,"html_url":"https://github.com/SamuelNicaise/cached_spliceai","commit_stats":null,"previous_names":["samuelnicaise/cached_spliceai"],"tags_count":0,"template":false,"template_full_name":"SamuelNicaise/python-template","purl":"pkg:github/SamuelNicaise/cached_spliceai","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SamuelNicaise%2Fcached_spliceai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SamuelNicaise%2Fcached_spliceai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SamuelNicaise%2Fcached_spliceai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SamuelNicaise%2Fcached_spliceai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SamuelNicaise","download_url":"https://codeload.github.com/SamuelNicaise/cached_spliceai/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SamuelNicaise%2Fcached_spliceai/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31976806,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-18T16:27:12.723Z","status":"ssl_error","status_checked_at":"2026-04-18T16:27:11.140Z","response_time":103,"last_error":"SSL_read: 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":["cache","database","keydb","nosql","redis","spliceai"],"created_at":"2024-12-07T19:09:06.460Z","updated_at":"2026-04-18T17:05:59.986Z","avatar_url":"https://github.com/SamuelNicaise.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# cached_spliceai\n\nThis module runs [SpliceAI](https://github.com/Illumina/SpliceAI) and stores every computed variant in a separately launched key-value cache database.\n\nThis greatly accelerates SpliceAI over time as more and more variants' scores are already known.\n\n## Installation\n\n```bash\nconda create -n cached_spliceai python=3.10\nconda activate cached_spliceai\n\ngit clone --shared https://github.com/SamuelNicaise/cached_spliceai.git\ncd cached_spliceai\npip install -e .\n\n# Then install the CPU or GPU version of tensorflow\npip install -e .[cpu]\n# or\npip install -e .[gpu]\n```\n\nThe DB API is [redis-py](https://github.com/redis/redis-py), meaning any key-value database compatible with redis API can be used.\n\nFor HUS devs: to start the cache database, run the docker-compose in HUB/bin/keydb\n\n## Usage\n\n```bash\npython -m cached_spliceai --help\n```\n\nOr see the example in the Makefile.\n\n## Benchmark\n\nOn a 32 CPUs node, using SpliceAI in CPU mode.\n\nRunning cached_spliceai on a 46k variants VCF (none of them seen before):\n\n\u003e real    1107m20.129s  \n\u003e **user    5215m14.631s**  \n\u003e sys     475m18.729s\n\nRunning cached_spliceai on a 46k variants VCF (all of them seen before):\n\n\u003e real    0m30.897s  \n\u003e **user    0m21.210s**  \n\u003e sys     0m2.915s\n\nBest record for the Kessel run: 11 parsecs\n\nAverage percent of already seen variants in routine exome analysis: ??\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsamuelnicaise%2Fcached_spliceai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsamuelnicaise%2Fcached_spliceai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsamuelnicaise%2Fcached_spliceai/lists"}