{"id":49135555,"url":"https://github.com/cobilab/geco3","last_synced_at":"2026-04-21T21:11:12.199Z","repository":{"id":78623192,"uuid":"253201558","full_name":"cobilab/geco3","owner":"cobilab","description":"An efficient DNA sequence compressor using Neural Networks","archived":false,"fork":false,"pushed_at":"2023-01-25T14:54:44.000Z","size":375,"stargazers_count":12,"open_issues_count":0,"forks_count":8,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-01-21T05:40:22.693Z","etag":null,"topics":["compression-algorithm","dna-sequences","neural-networks"],"latest_commit_sha":null,"homepage":"","language":"C","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cobilab.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}},"created_at":"2020-04-05T09:47:50.000Z","updated_at":"2022-12-15T20:33:46.000Z","dependencies_parsed_at":"2023-07-16T11:17:50.724Z","dependency_job_id":null,"html_url":"https://github.com/cobilab/geco3","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/cobilab/geco3","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cobilab%2Fgeco3","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cobilab%2Fgeco3/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cobilab%2Fgeco3/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cobilab%2Fgeco3/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cobilab","download_url":"https://codeload.github.com/cobilab/geco3/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cobilab%2Fgeco3/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32110299,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-21T11:25:29.218Z","status":"ssl_error","status_checked_at":"2026-04-21T11:25:28.499Z","response_time":128,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 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":["compression-algorithm","dna-sequences","neural-networks"],"created_at":"2026-04-21T21:11:11.515Z","updated_at":"2026-04-21T21:11:12.188Z","avatar_url":"https://github.com/cobilab.png","language":"C","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"left\"\u003e\n     \u003cimg src=\"https://github.com/cobilab/geco3/blob/master/geco3.png?raw=true\" alt=\"GeCo3\" height=\"140\"/\u003e\n\u003c/p\u003e\n\u003ca href=\"https://anaconda.org/bioconda/geco3\"\u003e \u003cimg src=\"https://anaconda.org/bioconda/geco3/badges/downloads.svg\" /\u003e \u003c/a\u003e\n\u003ca href=\"https://anaconda.org/bioconda/geco3\"\u003e \u003cimg src=\"https://anaconda.org/bioconda/geco3/badges/platforms.svg\" /\u003e \u003c/a\u003e\n\n\u003cbr\u003e\nGeCo3 is a DNA compressor that uses a neural network to do the mixing of experts.\n\nInstallation\n---\nInstallation is available with conda.\n```\nconda install -y -c bioconda geco3\n```\n\nBuild\n----\nGeCo3 depends on `make` and `gcc`.\n\n```\ncd src\nmake\n```\n**NOTE:** The default compilation options use micro-architecture dependent instructions, because GeCo3 greatly benefits from vector instructions. This means that due to the different floating point accuracies (e.g. fused multiply–add) the compressed file might not decompress with a binary compressed in a different computer or with a different compiler version or options. To ensure the file decompresses, use binaries (GeCo3 and GeDe3) that were compiled in the same environment.\n\nExample usage\n----\nReference free:\n```\n# Compression of file BuEb, using level 1, learning rate 0.06 and 8 hidden nodes\n./GeCo3 -l 1 -lr 0.06 -hs 8 BuEb\n\n# Decompression\n./GeDe3 BuEd.co\n```\n\nReferential:\n```\n# Compression of file GG_C4 using as reference file PT_C4.\n./GeCo3 -rm 20:500:1:35:0.95/3:100:0.95 -rm 13:200:1:1:0.95/0:0:0 -rm 10:10:0:0:0.95/0:0:0 -lr 0.03 -hs 64 -r PT_C4 GG_C4\n\n# Decompression\n./GeDe3 -r PT_C4 GG_C4.co\n```\n\nA complete description of the parameters can be read by invoking:\n```\n./GeCo3 -h\n./GeDe3 -h\n```\n\nExport mixer to other compressors\n----\nCheck the instructions and code in: https://github.com/cobilab/nn-expert-mixer\n\nCitation\n----\nIf you use GeCo3, please cite:\n* Milton Silva, Diogo Pratas, Armando J Pinho, **\"Efficient DNA sequence compression with neural networks\"**, GigaScience, Volume 9, Issue 11, November 2020, giaa119, https://doi.org/10.1093/gigascience/giaa119\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcobilab%2Fgeco3","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcobilab%2Fgeco3","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcobilab%2Fgeco3/lists"}