{"id":17087,"name":"data_curation","description":"Python code for handling data curation: SMILES of problematic molecules, dataset selection, train and test split.","url":"https://github.com/phi-grib/data_curation","last_synced_at":"2025-09-04T23:28:41.871Z","repository":{"id":39592253,"uuid":"264214323","full_name":"phi-grib/Data_curation","owner":"phi-grib","description":"Python code for handling data curation: SMILES of problematic molecules, dataset selection, train and test split.","archived":false,"fork":false,"pushed_at":"2025-09-04T14:05:38.000Z","size":399,"stargazers_count":7,"open_issues_count":3,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-09-04T14:19:26.652Z","etag":null,"topics":["data-sel","handling-smiles","problematic-structures","python"],"latest_commit_sha":null,"homepage":"","language":"Python","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/phi-grib.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2020-05-15T14:25:57.000Z","updated_at":"2025-09-04T13:02:16.000Z","dependencies_parsed_at":"2025-04-12T10:11:44.697Z","dependency_job_id":"2d4c0a54-e892-4e54-b287-4edd0fa01cb9","html_url":"https://github.com/phi-grib/Data_curation","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/phi-grib/Data_curation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phi-grib%2FData_curation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phi-grib%2FData_curation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phi-grib%2FData_curation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phi-grib%2FData_curation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/phi-grib","download_url":"https://codeload.github.com/phi-grib/Data_curation/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phi-grib%2FData_curation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273686794,"owners_count":25149976,"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":"phi-grib","name":"Phi GRIB","uuid":"30113653","kind":"organization","description":"PharmacoInformatics laboratory at GRIB (UPF)","email":"manuel.pastor@upf.edu","website":"http://phi.upf.edu","location":"Barcelona","twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/30113653?v=4","repositories_count":47,"last_synced_at":"2024-04-16T01:11:26.256Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/phi-grib","funding_links":[],"total_stars":46,"followers":4,"following":0,"created_at":"2022-11-05T17:06:18.098Z","updated_at":"2024-04-16T01:11:34.877Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/phi-grib","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/phi-grib/repositories"},"packages":[],"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"phi-grib/data_curation","html_url":"https://github.com/phi-grib/data_curation","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":"2025-09-04T23:27:54.530Z","updated_at":"2025-09-04T23:27:54.530Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/phi-grib%2Fdata_curation","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/phi-grib%2Fdata_curation/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":10082413,"issues_count":31239894,"pull_requests_count":96112510,"authors_count":10694151,"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":2,"PushEvent":7,"CreateEvent":1},"last_year":{"WatchEvent":2,"PushEvent":7,"CreateEvent":1}},"keywords":["data-sel","handling-smiles","problematic-structures","python"],"dependencies":[{"ecosystem":"pypi","filepath":"setup.py","sha":null,"kind":"manifest","created_at":"2024-04-05T10:43:35.544Z","updated_at":"2024-04-05T10:43:35.544Z","repository_link":"https://github.com/phi-grib/Data_curation/blob/master/setup.py","dependencies":[]},{"ecosystem":"conda","filepath":"environment.yml","sha":null,"kind":"manifest","created_at":"2025-04-12T10:11:40.688Z","updated_at":"2025-04-12T10:11:40.688Z","repository_link":"https://github.com/phi-grib/Data_curation/blob/master/environment.yml","dependencies":[{"id":22652782286,"package_name":"appdirs","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":22652782287,"package_name":"chembl_structure_pipeline","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":22652782288,"package_name":"chembl_webresource_client","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":22652782289,"package_name":"imbalanced-learn","ecosystem":"conda","requirements":"\u003e0.8.0*","direct":true,"kind":"runtime","optional":false},{"id":22652782290,"package_name":"lxml","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":22652782291,"package_name":"openpyxl","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":22652782292,"package_name":"pip","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":22652782293,"package_name":"psycopg2","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":22652782294,"package_name":"pytest","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":22652782295,"package_name":"python","ecosystem":"conda","requirements":"3.6.*","direct":true,"kind":"runtime","optional":false},{"id":22652782296,"package_name":"pyyaml","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":22652782297,"package_name":"rdkit","ecosystem":"conda","requirements":"2020.09.1.0.*","direct":true,"kind":"runtime","optional":false},{"id":22652782298,"package_name":"requests","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":22652782299,"package_name":"scikit-learn","ecosystem":"conda","requirements":"0.24.1.*","direct":true,"kind":"runtime","optional":false},{"id":22652782300,"package_name":"setuptools","ecosystem":"conda","requirements":"\u003e38.4.0*","direct":true,"kind":"runtime","optional":false},{"id":22652782301,"package_name":"xlrd","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-04T15:50:48.167Z","updated_at":"2025-10-07T08:08:56.760Z","avatar_url":"https://github.com/phi-grib.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/17087","html_url":"https://science.ecosyste.ms/projects/17087","bibtex_url":"https://science.ecosyste.ms/projects/17087/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/17087/export.apalike"}