{"id":9618,"name":"biologicaltokenizers","description":"Effect of tokenization on transformers for biological sequence","url":"https://github.com/technion-cs-nlp/biologicaltokenizers","last_synced_at":"2025-09-04T20:33:18.406Z","repository":{"id":231136415,"uuid":"781014196","full_name":"technion-cs-nlp/BiologicalTokenizers","owner":"technion-cs-nlp","description":"Effect of tokenization on transformers for biological sequence","archived":false,"fork":false,"pushed_at":"2024-04-16T17:26:37.000Z","size":36645,"stargazers_count":16,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-04-11T16:33:52.655Z","etag":null,"topics":["bioinformatics","dna-sequences","nlp","protein-sequences","tokenizer","transformers"],"latest_commit_sha":null,"homepage":"https://academic.oup.com/bioinformatics/article/40/4/btae196/7645044","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/technion-cs-nlp.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-04-02T15:34:33.000Z","updated_at":"2025-03-29T17:24:10.000Z","dependencies_parsed_at":"2025-04-11T16:43:55.685Z","dependency_job_id":null,"html_url":"https://github.com/technion-cs-nlp/BiologicalTokenizers","commit_stats":null,"previous_names":["technion-cs-nlp/biologicaltokenizers"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/technion-cs-nlp/BiologicalTokenizers","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/technion-cs-nlp%2FBiologicalTokenizers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/technion-cs-nlp%2FBiologicalTokenizers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/technion-cs-nlp%2FBiologicalTokenizers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/technion-cs-nlp%2FBiologicalTokenizers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/technion-cs-nlp","download_url":"https://codeload.github.com/technion-cs-nlp/BiologicalTokenizers/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/technion-cs-nlp%2FBiologicalTokenizers/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273668987,"owners_count":25146871,"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","status":"online","status_checked_at":"2025-09-04T02:00:08.968Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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"}},"owner":{"login":"technion-cs-nlp","name":"technion-cs-nlp","uuid":"82336448","kind":"organization","description":null,"email":null,"website":null,"location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/82336448?v=4","repositories_count":9,"last_synced_at":"2023-05-12T17:50:16.717Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/technion-cs-nlp","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2023-02-20T20:37:19.899Z","updated_at":"2023-05-12T17:50:16.734Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/technion-cs-nlp","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/technion-cs-nlp/repositories"},"packages":null,"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"technion-cs-nlp/biologicaltokenizers","html_url":"https://github.com/technion-cs-nlp/biologicaltokenizers","last_synced_at":null,"status":null,"issues_count":null,"pull_requests_count":null,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":null,"issues_closed_count":null,"pull_requests_closed_count":null,"pull_request_authors_count":null,"issue_authors_count":null,"avg_comments_per_issue":null,"avg_comments_per_pull_request":null,"merged_pull_requests_count":null,"bot_issues_count":null,"bot_pull_requests_count":null,"past_year_issues_count":null,"past_year_pull_requests_count":null,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":null,"past_year_pull_requests_closed_count":null,"past_year_pull_request_authors_count":null,"past_year_issue_authors_count":null,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":null,"past_year_bot_pull_requests_count":null,"past_year_merged_pull_requests_count":null,"created_at":"2025-09-04T20:32:41.002Z","updated_at":"2025-09-04T20:32:41.002Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/technion-cs-nlp%2Fbiologicaltokenizers","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/technion-cs-nlp%2Fbiologicaltokenizers/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{},"pull_request_author_associations_count":{},"issue_authors":{},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.939Z","repositories_count":10081047,"issues_count":31277651,"pull_requests_count":96104459,"authors_count":10693669,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{"WatchEvent":7},"last_year":{"WatchEvent":7}},"keywords":["bioinformatics","dna-sequences","nlp","protein-sequences","tokenizer","transformers"],"dependencies":[],"score":null,"created_at":"2025-09-04T15:50:31.937Z","updated_at":"2025-10-07T08:06:37.988Z","avatar_url":"https://github.com/technion-cs-nlp.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":["https://doi.org/10.1093/bioinformatics/btae196"],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/9618","html_url":"https://science.ecosyste.ms/projects/9618","bibtex_url":"https://science.ecosyste.ms/projects/9618/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/9618/export.apalike"}