65k pathway figures published between 1995 and 2019

In this study, we aimed to identify pathway figures published in the past 25 years, to characterize the human gene content in figures by optical character recognition, and to describe their utility as a resource for pathway knowledge. First, we trained a machine learning service on manually-classified figures and applied it to 235,081 image query results from PubMed Central. Then, we performed OCR to extract recognized human gene symbols from the images. Altogether, we identified 64,643 pathway figures published between 1995 and 2019, depicting 1,112,551 instances of human genes (13,464 unique NCBI Genes) in various interactions and contexts.<br>This supplementary file contains the tidy results from identification of 65k pathway figures published between 1995 and 2019. Columns include:<br>1. <b>figid</b> - Unique figure identifier: concatentation of PMCID and figure filename (see 11 and 12)<br>2. <b>number</b> - Figure number in parent paper3. <b>reftext</b> - Citation for parent paper4. <b>year</b> - Publication year of parent paper5. <b>pathway_score</b> - Pathway likelihood score from machine learning6. <b>pmc_ranked_result_index</b> - Ranking from original PubMed Central query result7. <b>figtitle</b> - Figure title in parent paper8. <b>papertitle</b> - Title of parent paper9. <b>caption</b> - Figure caption in parent paper10. <b>figlink</b> - URL to figure<br>11. <b>pmcid</b> - PubMed Central Identifier12. <b>filename</b> - Figure filename<br>13. <b>source_f</b> - Local file path (ignore)14. <b>type.man</b> - Manual classification of pathway (p), composite (c) or other (o)15. <b>automl_index</b> - Stored index from sorting by pathway_score (see 5)<br>

本研究旨在识别近25年间发表的通路示意图，通过光学字符识别（Optical Character Recognition，OCR）解析示意图中的人类基因内容，并阐明其作为通路知识资源的应用价值。首先，我们基于人工标注的示意图训练了机器学习模型，并将其应用于来自PubMed中心（PubMed Central）的235081条图像检索结果。随后，我们通过光学字符识别（Optical Character Recognition，OCR）从图像中提取识别出的人类基因符号。最终，我们共识别出1995年至2019年间发表的64643张通路示意图，这些示意图展现了1112551个人类基因实例（涵盖13464个独特的NCBI基因（NCBI Genes）），涉及多种相互作用与应用场景。
本补充文件包含1995年至2019年间64643张通路示意图识别后的标准化结果，各列信息如下：
1. **figid**：唯一示意图标识符，由PMCID与示意图文件名拼接而成（详见第11、12项）
2. **number**：所属论文中的示意图编号
3. **reftext**：所属论文的参考文献著录信息
4. **year**：所属论文的发表年份
5. **pathway_score**：机器学习模型输出的通路相关性得分
6. **pmc_ranked_result_index**：原始PubMed中心（PubMed Central）检索结果的排序索引
7. **figtitle**：所属论文中的示意图标题
8. **papertitle**：所属论文的标题
9. **caption**：所属论文中的示意图说明文字
10. **figlink**：示意图的访问URL
11. **pmcid**：PubMed中心（PubMed Central）稿件标识符
12. **filename**：示意图文件名
13. **source_f**：本地文件路径（无需关注）
14. **type.man**：人工标注分类，包括通路（p）、复合图（c）或其他（o）
15. **automl_index**：基于**pathway_score**排序后的存储索引（详见第5项）