A machine learning framework for extracting information from biological pathway images in the literature

IF 6.8 1区 生物学 Q1 BIOTECHNOLOGY & APPLIED MICROBIOLOGY
Mun Su Kwon , Junkyu Lee , Hyun Uk Kim
{"title":"A machine learning framework for extracting information from biological pathway images in the literature","authors":"Mun Su Kwon ,&nbsp;Junkyu Lee ,&nbsp;Hyun Uk Kim","doi":"10.1016/j.ymben.2024.09.001","DOIUrl":null,"url":null,"abstract":"<div><p>There have been significant advances in literature mining, allowing for the extraction of target information from the literature. However, biological literature often includes biological pathway images that are difficult to extract in an easily editable format. To address this challenge, this study aims to develop a machine learning framework called the “Extraction of Biological Pathway Information” (EBPI). The framework automates the search for relevant publications, extracts biological pathway information from images within the literature, including genes, enzymes, and metabolites, and generates the output in a tabular format. For this, this framework determines the direction of biochemical reactions, and detects and classifies texts within biological pathway images. Performance of EBPI was evaluated by comparing the extracted pathway information with manually curated pathway maps. EBPI will be useful for extracting biological pathway information from the literature in a high-throughput manner, and can be used for pathway studies, including metabolic engineering.</p></div>","PeriodicalId":18483,"journal":{"name":"Metabolic engineering","volume":"86 ","pages":"Pages 1-11"},"PeriodicalIF":6.8000,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Metabolic engineering","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1096717624001125","RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

There have been significant advances in literature mining, allowing for the extraction of target information from the literature. However, biological literature often includes biological pathway images that are difficult to extract in an easily editable format. To address this challenge, this study aims to develop a machine learning framework called the “Extraction of Biological Pathway Information” (EBPI). The framework automates the search for relevant publications, extracts biological pathway information from images within the literature, including genes, enzymes, and metabolites, and generates the output in a tabular format. For this, this framework determines the direction of biochemical reactions, and detects and classifies texts within biological pathway images. Performance of EBPI was evaluated by comparing the extracted pathway information with manually curated pathway maps. EBPI will be useful for extracting biological pathway information from the literature in a high-throughput manner, and can be used for pathway studies, including metabolic engineering.

从文献中提取生物通路图像信息的机器学习框架。
文献挖掘领域取得了重大进展,可以从文献中提取目标信息。然而,生物文献通常包括生物通路图像,而这些图像很难以易于编辑的格式提取出来。为了应对这一挑战,本研究旨在开发一个名为 "生物通路信息提取"(EBPI)的机器学习框架。该框架可自动搜索相关出版物,从文献中的图像提取生物通路信息,包括基因、酶和代谢物,并以表格格式生成输出。为此,该框架确定了生化反应的方向,并对生物通路图像中的文本进行了检测和分类。通过将提取的通路信息与人工绘制的通路图进行比较,对 EBPI 的性能进行了评估。EBPI 将有助于以高通量方式从文献中提取生物通路信息,并可用于通路研究,包括代谢工程。
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 求助全文
来源期刊
Metabolic engineering
Metabolic engineering 工程技术-生物工程与应用微生物
CiteScore
15.60
自引率
6.00%
发文量
140
审稿时长
44 days
期刊介绍: Metabolic Engineering (MBE) is a journal that focuses on publishing original research papers on the directed modulation of metabolic pathways for metabolite overproduction or the enhancement of cellular properties. It welcomes papers that describe the engineering of native pathways and the synthesis of heterologous pathways to convert microorganisms into microbial cell factories. The journal covers experimental, computational, and modeling approaches for understanding metabolic pathways and manipulating them through genetic, media, or environmental means. Effective exploration of metabolic pathways necessitates the use of molecular biology and biochemistry methods, as well as engineering techniques for modeling and data analysis. MBE serves as a platform for interdisciplinary research in fields such as biochemistry, molecular biology, applied microbiology, cellular physiology, cellular nutrition in health and disease, and biochemical engineering. The journal publishes various types of papers, including original research papers and review papers. It is indexed and abstracted in databases such as Scopus, Embase, EMBiology, Current Contents - Life Sciences and Clinical Medicine, Science Citation Index, PubMed/Medline, CAS and Biotechnology Citation Index.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信