{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T02:26:59Z","timestamp":1790562419609,"version":"4.1.0"},"reference-count":51,"publisher":"Ubiquity Press, Ltd.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,29]]},"DOI":"10.5334\/dsj-2024-023","type":"journal-article","created":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T06:26:25Z","timestamp":1714371985000},"source":"Crossref","is-referenced-by-count":8,"title":["Detailed Implementation of a Reproducible Machine Learning-Enabled Workflow"],"prefix":"10.5334","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1658-3699","authenticated-orcid":false,"suffix":"III","given":"Kenneth E.","family":"Schackart","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4748-7453","authenticated-orcid":false,"given":"Heidi J.","family":"Imker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4145-8048","authenticated-orcid":false,"given":"Charles E.","family":"Cook","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"3285","reference":[{"key":"key20240429062615_B1","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1145\/3526062.3536353","volume-title":"Proceedings of the 5th International Workshop on Practical Reproducible Evaluation of Computer Systems","year":"2022"},{"issue":"1","key":"key20240429062615_B2","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1002\/leap.1210","article-title":"How can we ensure visibility and diversity in research contributions? How the Contributor Role Taxonomy (CRediT) is helping the shift from authorship to contributorship","volume":"32","year":"2019","journal-title":"Learned Publishing"},{"key":"key20240429062615_B3","unstructured":"Bader, D 2016 pytest-mypy: Mypy static type checker plugin for Pyest. Available at https:\/\/github.com\/realpython\/pytest-mypy [Last accessed 22 November 2022]."},{"issue":"4","key":"key20240429062615_B4","first-page":"1309","article-title":"Deriving chemosensitivity from cell lines: Forensic bioinformatics and reproducible research in high-throughput biology","volume":"3","year":"2009","journal-title":"The Annals of Applied Statistics"},{"issue":"7604","key":"key20240429062615_B5","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1038\/533452a","article-title":"1,500 scientists lift the lid on reproducibility","volume":"533","year":"2016","journal-title":"Nature"},{"issue":"1","key":"key20240429062615_B6","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The Protein Data Bank","volume":"28","year":"2000","journal-title":"Nucleic Acids Research"},{"key":"key20240429062615_B7","article-title":"Lessons learned: A neuroimaging research center\u2019s transition to open and reproducible science","volume":"5","year":"2022","journal-title":"Frontiers in Big Data"},{"issue":"1","key":"key20240429062615_B8","article-title":"Testing our assumptions: Preliminary results from the Data Curation Network","volume":"9","year":"2020","journal-title":"Journal of eScience Librarianship"},{"key":"key20240429062615_B9","unstructured":"Conda 2017 Available at https:\/\/www.anaconda.com [Last accessed 22 November 2022]."},{"key":"key20240429062615_B10","unstructured":"Country Codes \u2013 ISO 3166 n.d. Available at https:\/\/www.iso.org\/iso-3166-country-codes.html."},{"key":"key20240429062615_B11","volume-title":"Le petit prince [The little prince]","year":"1943"},{"issue":"11","key":"key20240429062615_B12","doi-asserted-by":"crossref","first-page":"2628","DOI":"10.1073\/pnas.1708272114","article-title":"Is science really facing a reproducibility crisis, and do we need it to?","volume":"115","year":"2018","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"D1","key":"key20240429062615_B13","doi-asserted-by":"crossref","first-page":"D1507","DOI":"10.1093\/nar\/gkaa994","article-title":"Europe PMC in 2020","volume":"49","year":"2021","journal-title":"Nucleic Acids Research"},{"key":"key20240429062615_B14","doi-asserted-by":"crossref","unstructured":"Fielding, R, Nottingham, M and Reschke, J 2022 RFC 9910 HTTP Semantics. Internet Engineering Task Force. Available at https:\/\/www.doi.org\/10.17487\/RFC9110.","DOI":"10.17487\/RFC9110"},{"issue":"9","key":"key20240429062615_B15","article-title":"A simple kit to use computational notebooks for more openness, reproducibility, and productivity in research","volume":"18","year":"2022","journal-title":"PLOS Computational Biology"},{"key":"key20240429062615_B16","unstructured":"Gee, C 2015 pytest-pylint: pytest plugin for running pylint against your codebase. Available at https:\/\/github.com\/carsongee\/pytest-pylint [Last accessed 22 November 2022]."},{"key":"key20240429062615_B17","unstructured":"GNU Make 1988. Available at https:\/\/www.gnu.org\/software\/make\/ [Last accessed 22 November 2022]."},{"key":"key20240429062615_B18","unstructured":"Google Inc. yapf: A formatter for Python files, 2004. Available at https:\/\/github.com\/google\/yapf [Last accessed 22 November 2022]."},{"issue":"6","key":"key20240429062615_B19","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1016\/j.cels.2018.03.014","article-title":"Practical computational reproducibility in the life sciences","volume":"6","year":"2018","journal-title":"Cell Systems"},{"key":"key20240429062615_B20","unstructured":"Hall, M and Letcher, B 2020 Snakefmt: The uncompromising Snakemake code formatter. Available at https:\/\/github.com\/snakemake\/snakefmt [Last accessed 22 November 2022]."},{"issue":"5","key":"key20240429062615_B21","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1080\/13697137.2018.1476968","article-title":"Lack of research reproducibility, the rise of open science and the need for continuing education in research methods","volume":"21","year":"2018","journal-title":"Climacteric"},{"issue":"3","key":"key20240429062615_B22","article-title":"The effect of non-linear signal in classification problems using gene expression","volume":"19","year":"2023","journal-title":"PLoS Computational Biology"},{"issue":"10","key":"key20240429062615_B23","doi-asserted-by":"crossref","first-page":"1132","DOI":"10.1038\/s41592-021-01256-7","article-title":"Reproducibility standards for machine learning in the life sciences","volume":"18","year":"2021","journal-title":"Nature Methods"},{"key":"key20240429062615_B24","doi-asserted-by":"crossref","unstructured":"Hook, D W and Porter, S J 2021 Scaling scientometrics: Dimensions on Google BigQuery as an infrastructure for large-scale analysis. Frontiers in Research Metrics and Analytics, 6. Available at https:\/\/www.frontiersin.org\/articles\/10.3389\/frma.2021.656233 [Last accessed 3 February 2023].","DOI":"10.3389\/frma.2021.656233"},{"key":"key20240429062615_B25","article-title":"Open Science implementation plan for the biodata resource inventory","year":"2022","journal-title":"Zenodo"},{"key":"key20240429062615_B26","article-title":"Manual review process for the biodata resource inventory","year":"2023","journal-title":"Zenodo"},{"issue":"11","key":"key20240429062615_B27","first-page":"1","article-title":"A machine learning-enabled open biodata resource inventory from the scientific literature","volume":"18","year":"2023","journal-title":"PLOS ONE"},{"key":"key20240429062615_B28","article-title":"ChampKit: A framework for rapid evaluation of deep neural networks for patch-based histopathology classification","volume":"239","year":"2023","journal-title":"Computer Methods and Programs in Biomedicine"},{"issue":"7","key":"key20240429062615_B29","article-title":"Experimenting with reproducibility: A case study of robustness in bioinformatics","volume":"7","year":"2018","journal-title":"GigaScience"},{"issue":"19","key":"key20240429062615_B30","doi-asserted-by":"crossref","first-page":"2520","DOI":"10.1093\/bioinformatics\/bts480","article-title":"Snakemake\u2014a scalable bioinformatics workflow engine","volume":"28","year":"2012","journal-title":"Bioinformatics"},{"key":"key20240429062615_B31","unstructured":"Krekel, H 2004 pytest: The pytest framework makes it easy to write small tests, yet scales to support complex functional testing. Available at https:\/\/github.com\/pytest-dev\/pytest [Last accessed 22 November 2022]."},{"issue":"1","key":"key20240429062615_B32","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1146\/annurev-statistics-060116-054104","article-title":"Is Most Published Research Really False?","volume":"4","year":"2017","journal-title":"Annual Review of Statistics and Its Application"},{"key":"key20240429062615_B33","unstructured":"Lehtosalo, J 2012 mypy: Optional static typing for Python. Available at https:\/\/github.com\/python\/mypy [Last accessed 22 November 2022]."},{"key":"key20240429062615_B34","unstructured":"Lockhert, T 2015 pytest-flake8: Pytest plugin to run flake8. Available at https:\/\/github.com\/tholo\/pytest-flake8 [Last accessed 22 November 2022]."},{"issue":"2","key":"key20240429062615_B35","first-page":"2","article-title":"Docker: Lightweight linux containers for consistent development and deployment","volume":"239","year":"2014","journal-title":"Linux j"},{"key":"key20240429062615_B36","unstructured":"M\u00fcller, K, Walthert, L and Patil, I 2021 styler: Non-invasive pretty printing of R code. Available at https:\/\/github.com\/r-lib\/styler [Last accessed 22 November 2022]."},{"issue":"6060","key":"key20240429062615_B37","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1126\/science.1213847","article-title":"Reproducible Research in Computational Science","volume":"334","year":"2011","journal-title":"Science"},{"issue":"1","key":"key20240429062615_B38","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1146\/annurev-publhealth-012420-105110","article-title":"Reproducible Research: A Retrospective","volume":"42","year":"2021","journal-title":"Annual Review of Public Health"},{"issue":"7822","key":"key20240429062615_B39","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1038\/d41586-020-02462-7","article-title":"Challenge to scientists: does your ten-year-old code still run?","volume":"584","year":"2020","journal-title":"Nature"},{"key":"key20240429062615_B40","unstructured":"pypi n.d. Python Package Index \u2013 PyPI. Available at https:\/\/pypi.org\/ [Last accessed 22 November 2022]."},{"key":"key20240429062615_B41","unstructured":"Sveidqvist, K 2014 Mermaid: Generation of diagrams like flowcharts or sequence diagrams from text in a similar manner as markdown. Available at https:\/\/github.com\/mermaid-js\/mermaid\/ [Last accessed 22 November 2022]."},{"issue":"D1","key":"key20240429062615_B42","doi-asserted-by":"crossref","first-page":"D1042","DOI":"10.1093\/nar\/gku1061","article-title":"Europe PMC: a full-text literature database for the life sciences and platform for innovation","volume":"43","author":"The Europe PMC Consortium","year":"2015","journal-title":"Nucleic Acids Research"},{"key":"key20240429062615_B43","unstructured":"Th\u00e9nault, S 2001 Pylint: It\u2019s not just a linter that annoys you! Available at https:\/\/github.com\/PyCQA\/pylint [Last accessed 22 November 2022]."},{"key":"key20240429062615_B44","unstructured":"Ushey, K 2022 renv: Project Environments. Available at https:\/\/rstudio.github.io\/renv\/ [Last accessed 6 January 2023]."},{"issue":"10","key":"key20240429062615_B45","doi-asserted-by":"crossref","first-page":"4417","DOI":"10.1021\/acs.jcim.0c01000","article-title":"Code sharing in the Open Science era","volume":"60","year":"2020","journal-title":"Journal of Chemical Information and Modeling"},{"key":"key20240429062615_B46","article-title":"nf-root: A best-practice pipeline for deep learning-based analysis of apoplastic pH in microscopy images of developmental zones in plant root tissue","year":"2023","journal-title":"bioRxiv"},{"issue":"1","key":"key20240429062615_B47","doi-asserted-by":"crossref","first-page":"160018","DOI":"10.1038\/sdata.2016.18","article-title":"The FAIR Guiding Principles for scientific data management and stewardship","volume":"3","year":"2016","journal-title":"Scientific Data"},{"issue":"6","key":"key20240429062615_B48","article-title":"Good enough practices in scientific computing","volume":"13","year":"2017","journal-title":"PLoS Computational Biology"},{"key":"key20240429062615_B49","first-page":"38","article-title":"Transformers: state-of-the-art Natural Language Processing","year":"2020"},{"key":"key20240429062615_B50","unstructured":"Ziade, T and Cordasco, I 2011 Flake8: Your tool for style guide enforcement. Available at https:\/\/github.com\/PyCQA\/flake8 [Last accessed 22 November 2022]."},{"issue":"6","key":"key20240429062615_B51","article-title":"The five pillars of computational reproducibility: bioinformatics and beyond","volume":"24","year":"2023","journal-title":"Briefings in Bioinformatics"}],"container-title":["Data Science Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/storage.googleapis.com\/jnl-up-j-dsj-files\/journals\/1\/articles\/1668\/662f7593d5999.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T08:00:48Z","timestamp":1761552048000},"score":1,"resource":{"primary":{"URL":"http:\/\/datascience.codata.org\/articles\/10.5334\/dsj-2024-023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":51,"alternative-id":["10.5334\/dsj-2024-023"],"URL":"https:\/\/doi.org\/10.5334\/dsj-2024-023","relation":{},"ISSN":["1683-1470"],"issn-type":[{"value":"1683-1470","type":"print"}],"subject":[],"published":{"date-parts":[[2024]]},"article-number":"23"}}