{"id":28900280,"url":"https://github.com/bbuchfink/deepclust-data","last_synced_at":"2026-01-20T16:34:07.899Z","repository":{"id":299798976,"uuid":"731170775","full_name":"bbuchfink/deepclust-data","owner":"bbuchfink","description":null,"archived":false,"fork":false,"pushed_at":"2025-06-18T11:04:57.000Z","size":18705,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-06-18T11:27:24.753Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Shell","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/bbuchfink.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,"zenodo":null}},"created_at":"2023-12-13T14:04:42.000Z","updated_at":"2025-06-18T11:05:00.000Z","dependencies_parsed_at":"2025-06-18T11:38:24.212Z","dependency_job_id":null,"html_url":"https://github.com/bbuchfink/deepclust-data","commit_stats":null,"previous_names":["bbuchfink/deepclust-data"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bbuchfink/deepclust-data","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bbuchfink%2Fdeepclust-data","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bbuchfink%2Fdeepclust-data/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bbuchfink%2Fdeepclust-data/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bbuchfink%2Fdeepclust-data/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bbuchfink","download_url":"https://codeload.github.com/bbuchfink/deepclust-data/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bbuchfink%2Fdeepclust-data/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261101636,"owners_count":23109860,"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":"2025-06-21T09:39:38.933Z","updated_at":"2026-01-20T16:34:07.885Z","avatar_url":"https://github.com/bbuchfink.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"Scripts to reproduce the results of Buchfink et al., \"Sensitive clustering of protein sequences at tree-of-life scale using DIAMOND DeepClust\".\n\n# Data files\n\nData files that are required (see Data availability):\n\n- `arch80_all.tsv`: File mapping NCBI accessions to Pfam domain architectures.\n- `nr_accessions.tsv.zst`: List of all accessions in NR database that was used for the main benchmark.\n- `clan2acc.tsv`: File mapping Pfam accessions to clans.\n- `clust.dedup2.tsv.zst`: TSV file mapping cluster member sequences to representatives for the big ~19bn clustering run.\n- `centroids.dedup.faa`: FASTA file of representatives for the big ~19bn clustering run.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbbuchfink%2Fdeepclust-data","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbbuchfink%2Fdeepclust-data","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbbuchfink%2Fdeepclust-data/lists"}