The 3Ranker: An AI-based Algorithm for Finding Non-animal Alternative Methods.

IF 2.4 4区 医学 Q3 MEDICINE, RESEARCH & EXPERIMENTAL Atla-Alternatives To Laboratory Animals Pub Date : 2023-11-01 Epub Date: 2023-10-21 DOI:10.1177/02611929231210777
Niels van Beuningen, Sinne Alkema, Nils Hijlkema, Brun Ulfhake, Rafael Frias, Merel Ritskes-Hoitinga, Wynand Alkema
{"title":"The 3Ranker: An AI-based Algorithm for Finding Non-animal Alternative Methods.","authors":"Niels van Beuningen,&nbsp;Sinne Alkema,&nbsp;Nils Hijlkema,&nbsp;Brun Ulfhake,&nbsp;Rafael Frias,&nbsp;Merel Ritskes-Hoitinga,&nbsp;Wynand Alkema","doi":"10.1177/02611929231210777","DOIUrl":null,"url":null,"abstract":"<p><p>The search for existing non-animal alternative methods for use in experiments is currently challenging because of the lack of both comprehensive structured databases and balanced keyword-based search strategies to mine unstructured textual databases. In this paper we describe 3Ranker, which is a fast, keyword-independent algorithm for finding non-animal alternative methods for use in biomedical research. The 3Ranker algorithm was created by using a machine learning approach, consisting of a Random Forest model built on a dataset of 35 million abstracts and constructed with weak supervision, followed by iterative model improvement with expert curated data. We found a satisfactory trade-off between sensitivity and specificity, with Area Under the Curve (AUC) values ranging from 0.85-0.95. Trials showed that the AI-based classifier was able to identify articles that describe potential alternatives to animal use, among the thousands of articles returned by generic PubMed queries on dermatitis and Parkinson's disease. Application of the classification models on time series data showed the earlier implementation and acceptance of Three Rs principles in the area of cosmetics and skin research, as compared to the area of neurodegenerative disease research. The 3Ranker algorithm is freely available at www.open3r.org; the future goal is to expand this framework to cover multiple research domains and to enable its broad use by researchers, policymakers, funders and ethical review boards, in order to promote the replacement of animal use in research wherever possible.</p>","PeriodicalId":55577,"journal":{"name":"Atla-Alternatives To Laboratory Animals","volume":" ","pages":"376-386"},"PeriodicalIF":2.4000,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Atla-Alternatives To Laboratory Animals","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/02611929231210777","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/10/21 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}
引用次数: 1

Abstract

The search for existing non-animal alternative methods for use in experiments is currently challenging because of the lack of both comprehensive structured databases and balanced keyword-based search strategies to mine unstructured textual databases. In this paper we describe 3Ranker, which is a fast, keyword-independent algorithm for finding non-animal alternative methods for use in biomedical research. The 3Ranker algorithm was created by using a machine learning approach, consisting of a Random Forest model built on a dataset of 35 million abstracts and constructed with weak supervision, followed by iterative model improvement with expert curated data. We found a satisfactory trade-off between sensitivity and specificity, with Area Under the Curve (AUC) values ranging from 0.85-0.95. Trials showed that the AI-based classifier was able to identify articles that describe potential alternatives to animal use, among the thousands of articles returned by generic PubMed queries on dermatitis and Parkinson's disease. Application of the classification models on time series data showed the earlier implementation and acceptance of Three Rs principles in the area of cosmetics and skin research, as compared to the area of neurodegenerative disease research. The 3Ranker algorithm is freely available at www.open3r.org; the future goal is to expand this framework to cover multiple research domains and to enable its broad use by researchers, policymakers, funders and ethical review boards, in order to promote the replacement of animal use in research wherever possible.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
The 3Ranker:一种基于人工智能的算法,用于寻找非动物的替代方法。
目前,由于缺乏全面的结构化数据库和平衡的基于关键字的搜索策略来挖掘非结构化文本数据库,搜索用于实验的现有非动物替代方法具有挑战性。在本文中,我们描述了3Ranker,这是一种快速、独立于关键字的算法,用于寻找生物医学研究中使用的非动物替代方法。3Ranker算法是通过使用机器学习方法创建的,包括建立在3500万摘要数据集上的随机森林模型,并在弱监督下构建,然后用专家策划的数据迭代改进模型。我们发现灵敏度和特异性之间存在令人满意的折衷,曲线下面积(AUC)值在0.85-0.95之间。试验表明,在PubMed关于皮炎和帕金森病的通用查询返回的数千篇文章中,基于人工智能的分类器能够识别描述动物使用的潜在替代品的文章。分类模型在时间序列数据上的应用表明,与神经退行性疾病研究领域相比,Three Rs原则在化妆品和皮肤研究领域的实施和接受更早。3Ranker算法可在www.open3r.org上免费获得;未来的目标是将这一框架扩展到多个研究领域,并使其能够被研究人员、政策制定者、资助者和伦理审查委员会广泛使用,以促进在可能的情况下取代动物在研究中的使用。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
3.80
自引率
3.70%
发文量
60
审稿时长
>18 weeks
期刊介绍: Alternatives to Laboratory Animals (ATLA) is a peer-reviewed journal, intended to cover all aspects of the development, validation, implementation and use of alternatives to laboratory animals in biomedical research and toxicity testing. In addition to the replacement of animals, it also covers work that aims to reduce the number of animals used and refine the in vivo experiments that are still carried out.
期刊最新文献
Barriers to the Use of Recombinant Bacterial Endotoxins Test Methods in Parenteral Drug, Vaccine and Device Safety Testing. The 3Ranker: An AI-based Algorithm for Finding Non-animal Alternative Methods. Modelling the Sorafenib-resistant Liver Cancer Microenvironment by Using 3-D Spheroids. Editorial. Resources Round-up.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1