{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:05:30Z","timestamp":1784300730334,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF 2403747"],"award-info":[{"award-number":["CCF 2403747"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["IIS-2313890"],"award-info":[{"award-number":["IIS-2313890"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,5]]},"DOI":"10.1145\/3803437.3805577","type":"proceedings-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:27:39Z","timestamp":1784298459000},"page":"1307-1311","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Bio-Aware Software Engineering for Reproducible Research"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5842-0130","authenticated-orcid":false,"given":"Yiming","family":"Zeng","sequence":"first","affiliation":[{"name":"University of Connecticut, Storrs, Connecticut, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9675-6824","authenticated-orcid":false,"given":"Dingbang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Connecticut, Storrs, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6114-486X","authenticated-orcid":false,"given":"Ryan","family":"Green","sequence":"additional","affiliation":[{"name":"Siemens Digital Industries Software, Cincinnati, Ohio, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0172-7087","authenticated-orcid":false,"given":"Sandeep Kaur","family":"Kuttal","sequence":"additional","affiliation":[{"name":"North Carolina State University, Raleigh, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0555-9412","authenticated-orcid":false,"given":"Jinze","family":"Liu","sequence":"additional","affiliation":[{"name":"Virginia Commonwealth University, Richmond, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9461-4251","authenticated-orcid":false,"given":"Tingting","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Connecticut, Storrs, Connecticut, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1177\/10943420251339317"},{"key":"e_1_3_2_1_2_1","unstructured":"Anaconda. 2025. conda - anaconda. https:\/\/anaconda.org\/channels\/anaconda\/packages\/conda\/overview"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Niels Bantilan. 2020. pandera: Statistical Data Validation of Pandas Dataframes. In SciPy. https:\/\/api.semanticscholar.org\/CorpusID:226191171","DOI":"10.25080\/Majora-342d178e-021"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723872.2723882"},{"key":"e_1_3_2_1_5_1","volume-title":"Louis Letourneau, Joel Fillon, Marc Michaud, Maxime Caron, Johanna Sandoval, Francois Lefebvre, et al.","author":"Bourgey Mathieu","year":"2019","unstructured":"Mathieu Bourgey, Rola Dali, Robert Eveleigh, Kuang Chung Chen, Louis Letourneau, Joel Fillon, Marc Michaud, Maxime Caron, Johanna Sandoval, Francois Lefebvre, et al. 2019. GenPipes: an open-source framework for distributed and scalable genomic analyses. Gigascience 8, 6 (2019), giz037."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa274"},{"key":"e_1_3_2_1_7_1","volume-title":"SciDataFlow: a tool for improving the flow of data through science. Bioinformatics 40, 1","author":"Buffalo Vince","year":"2024","unstructured":"Vince Buffalo. 2024. SciDataFlow: a tool for improving the flow of data through science. Bioinformatics 40, 1 (2024), btad754."},{"key":"e_1_3_2_1_8_1","volume-title":"Terrence Dorsey, David Montague, Serge Matveenko, Marcelo Trylesinski","author":"Colvin Samuel","year":"2024","unstructured":"Samuel Colvin, Eric Jolibois, Hasan Ramezani, Adrian Garcia Badaracco, Terrence Dorsey, David Montague, Serge Matveenko, Marcelo Trylesinski, Sydney Runkle, David Hewitt, et al. 2024. Pydantic. Zenodo (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Emilio Palumbo, and Cedric Notredame.","author":"Tommaso Paolo Di","year":"2017","unstructured":"Paolo Di Tommaso, Maria Chatzou, Evan W Floden, Pablo Prieto Barja, Emilio Palumbo, and Cedric Notredame. 2017. Nextflow enables reproducible computational workflows. Nature biotechnology 35, 4 (2017), 316\u2013319."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Keyan Ding Jing Yu Junjie Huang Yuchen Yang Qiang Zhang and Huajun Chen. 2025. SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration. arXiv:2507.20280","DOI":"10.1038\/s43588-025-00849-y"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Robert C Gentleman Vincent J Carey Douglas M Bates Ben Bolstad Marcel Dettling Sandrine Dudoit Byron Ellis Laurent Gautier Yongchao Ge Jeff Gentry et al. 2004. Bioconductor: open software development for computational biology and bioinformatics. Genome biology 5 10 (2004) R80.","DOI":"10.1186\/gb-2004-5-10-r80"},{"key":"e_1_3_2_1_12_1","volume-title":"SEURAT: visual analytics for the integrated analysis of microarray data. BMC medical genomics 3, 1","author":"Gribov Alexander","year":"2010","unstructured":"Alexander Gribov, Martin Sill, Sonja L\u00fcck, Frank R\u00fccker, Konstanze D\u00f6hner, Lars Bullinger, Axel Benner, and Antony Unwin. 2010. SEURAT: visual analytics for the integrated analysis of microarray data. BMC medical genomics 3, 1 (2010), 21."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/SECSE.2009.5069155"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1009244"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1958824.1958904"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1101\/2025.05.30.656746"},{"key":"e_1_3_2_1_17_1","volume-title":"a bio-workflow design system for massive genome data analysis on high performance cluster infrastructure. BMC bioinformatics 25, 1","author":"Ko Gunhwan","year":"2024","unstructured":"Gunhwan Ko, Pan-Gyu Kim, Byung-Ha Yoon, JaeHee Kim, Wangho Song, IkSu Byeon, JongCheol Yoon, Byungwook Lee, and Young-Kuk Kim. 2024. Closha 2.0: a bio-workflow design system for massive genome data analysis on high performance cluster infrastructure. BMC bioinformatics 25, 1 (2024), 353."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bts480"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0177459"},{"key":"e_1_3_2_1_20_1","unstructured":"Cognition Labs. 2024. Introducing Devin the First AI Software Engineer. https:\/\/www.cognition-labs.com\/introducing-devin"},{"key":"e_1_3_2_1_21_1","volume-title":"The democratization of bioinformatics: a software engineering perspective. GigaScience 9, 6","author":"Lawlor Brendan","year":"2020","unstructured":"Brendan Lawlor and Roy D Sleator. 2020. The democratization of bioinformatics: a software engineering perspective. GigaScience 9, 6 (2020), giaa063."},{"key":"e_1_3_2_1_22_1","volume-title":"Federico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, et al.","author":"Lozhkov Anton","year":"2024","unstructured":"Anton Lozhkov, Raymond Li, Loubna Ben Allal, Federico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, et al. 2024. Starcoder 2 and the stack v2: The next generation. arXiv preprint arXiv:2402.19173 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"BioGPT: generative pre-trained transformer for biomedical text generation and mining. Briefings in bioinformatics 23, 6","author":"Luo Renqian","year":"2022","unstructured":"Renqian Luo, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon, and Tie-Yan Liu. 2022. BioGPT: generative pre-trained transformer for biomedical text generation and mining. Briefings in bioinformatics 23, 6 (2022), bbac409."},{"key":"e_1_3_2_1_24_1","volume-title":"Benjamin Statz, et al.","author":"Mangul Serghei","year":"2019","unstructured":"Serghei Mangul, Thiago Mosqueiro, Richard J Abdill, Dat Duong, Keith Mitchell, Varuni Sarwal, Brian Hill, Jaqueline Brito, Russell Jared Littman, Benjamin Statz, et al. 2019. Challenges and recommendations to improve the installability and archival stability of omics computational tools. PLoS biology 17, 6 (2019), e3000333."},{"key":"e_1_3_2_1_25_1","unstructured":"Serghei Mangul Thiago Mosqueiro Dat Duong Keith Mitchell Varuni Sarwal Brian Hill Jaqueline Brito Russell Littman Benjamin Statz Angela Lam et al. 2018. A comprehensive analysis of the usability and archival stability of omics computational tools and resources. BioRxiv (2018) 10\u20131101."},{"key":"e_1_3_2_1_26_1","volume-title":"AlphaPulldown2\u2014a general pipeline for high-throughput structural modeling. Bioinformatics 41, 3","author":"Molodenskiy Dmitry","year":"2025","unstructured":"Dmitry Molodenskiy, Valentin J Maurer, Dingquan Yu, Grzegorz Chojnowski, Stefan Bienert, Gerardo Tauriello, Konstantin Gilep, Torsten Schwede, and Jan Kosinski. 2025. AlphaPulldown2\u2014a general pipeline for high-throughput structural modeling. Bioinformatics 41, 3 (2025), btaf115."},{"key":"e_1_3_2_1_27_1","volume-title":"Frank Austin Nothaft, Eric Tongching Tu, Justin Paschall, Nir Yosef, and Anthony Douglas Joseph.","author":"Morrow Alyssa Kramer","year":"2019","unstructured":"Alyssa Kramer Morrow, George Zhixuan He, Frank Austin Nothaft, Eric Tongching Tu, Justin Paschall, Nir Yosef, and Anthony Douglas Joseph. 2019. Mango: exploratory data analysis for large-scale sequencing datasets. Cell systems 9, 6 (2019), 609\u2013613."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2019.00077"},{"key":"e_1_3_2_1_29_1","volume-title":"Typer: FastAPI of CLIs. https:\/\/typer.tiangolo.com.","author":"Ram\u00edrez Sebasti\u00e1n","year":"2020","unstructured":"Sebasti\u00e1n Ram\u00edrez. 2020. Typer: FastAPI of CLIs. https:\/\/typer.tiangolo.com."},{"key":"e_1_3_2_1_30_1","volume-title":"Computational reproducibility of Jupyter notebooks from biomedical publications. GigaScience 13","author":"Samuel Sheeba","year":"2024","unstructured":"Sheeba Samuel and Daniel Mietchen. 2024. Computational reproducibility of Jupyter notebooks from biomedical publications. GigaScience 13 (2024), giad113."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1708290115"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781003097471"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"John Yang Carlos E. Jimenez Alexander Wettig Kilian Lieret Shunyu Yao Karthik Narasimhan and Ofir Press. 2024. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering. arXiv:2405.15793","DOI":"10.52202\/079017-1601"},{"key":"e_1_3_2_1_34_1","volume-title":"Gene name errors are widespread in the scientific literature. Genome biology 17, 1","author":"Ziemann Mark","year":"2016","unstructured":"Mark Ziemann, Yotam Eren, and Assam El-Osta. 2016. Gene name errors are widespread in the scientific literature. Genome biology 17, 1 (2016), 177."}],"event":{"name":"FSE Companion '26: 34th ACM International Conference on the Foundations of Software Engineering","location":"Concordia University Montreal QC Canada","acronym":"FSE Companion '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 34th ACM International Conference on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3803437.3805577","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3803437.3805577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:30:50Z","timestamp":1784298650000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3803437.3805577"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":34,"alternative-id":["10.1145\/3803437.3805577","10.1145\/3803437"],"URL":"https:\/\/doi.org\/10.1145\/3803437.3805577","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}