基于rentrez提取PubMed XML文献的作者及关联信息技术问询

已参考相关代码实现PubMed文献收稿、录用、发表日期及间隔提取，现需获取以下学术指标：

• 作者数量
• 第一作者所属机构
• 最后作者所属机构
• 单篇文献引用数
• 第一作者学术度
  同时希望了解PubMed XML可提取的完整字段范围。当前已实现首尾作者姓名提取，但无法拆分出首尾作者对应的机构，可复现代码如下：

#load in packages
library(reprex)
library(devtools)
#> Loading required package: usethis
install_github("ropensci/rentrez")
#> Skipping install of 'rentrez' from a github remote, the SHA1 (a225f213) has not changed since last install.
#>   Use `force = TRUE` to force installation
library(rentrez)
require(XML)
#> Loading required package: XML
require(ggplot2)
#> Loading required package: ggplot2
require(ggridges)
#> Loading required package: ggridges
require(gridExtra)
#> Loading required package: gridExtra
# search pubmed using a search term (use_history allows retrieval of all records)
pp <- entrez_search(db="pubmed", term="cell[ta] AND 2010 : 2021[pdat] AND (journal article[pt] NOT review[pt] NOT comment[pt]
                    NOT autobiography[pt] NOT biography[pt] NOT case reports[pt] NOT clinical trial[pt]
                    NOT historical article[pt] NOT comparative study[pt] NOT evaluation study[pt]
                    NOT evaluation study[pt] NOT introductory journal article[pt])", use_history = TRUE)
pp_rec <- entrez_fetch(db="pubmed", web_history=pp$web_history, rettype="xml", parsed=TRUE)
# save records as XML file
saveXML(pp_rec, file = "Data/records.xml")
#> Error in saveXML(pp_rec, file = "Data/records.xml"): cannot create file Data/records.xml. Check the directory exists and permissions are appropriate
filename <- "~/Data/records.xml"
## extract a data frame from XML file
## This is modified from christopherBelter's pubmedXML R code
extract_xml <- function(theFile) {
  library(XML)
  newData <- xmlParse(theFile)
  records <- getNodeSet(newData, "//PubmedArticle")
  pmid <- xpathSApply(newData,"//MedlineCitation/PMID", xmlValue)
  doi <- lapply(records, xpathSApply, ".//ELocationID[@EIdType = \"doi\"]", xmlValue)
  doi[sapply(doi, is.list)] <- NA
  doi <- unlist(doi)
  authLast <- lapply(records, xpathSApply, ".//Author/LastName", xmlValue)
  authLast[sapply(authLast, is.list)] <- NA
  authInit <- lapply(records, xpathSApply, ".//Author/Initials", xmlValue)
  authInit[sapply(authInit, is.list)] <- NA
  authors <- mapply(paste, authLast, authInit, collapse = "|")
  authAffil <- lapply(records, xpathSApply, ".//Author/AffiliationInfo", xmlValue)
  authAffil[sapply(authAffil, is.list)] <- NA
  authAffil <- sapply(authAffil, paste, collapse = "|")
  theDF <- data.frame(pmid, doi, authors,authAffil, stringsAsFactors = FALSE)
  
  return(theDF)
}
#extract into a dataframe
theData <- extract_xml(filename)
#show the author affiliations as bunched
print(theData$authAffil[1])
#> [1] "Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA. Electronic address: kjsiddle@broadinstitute.org.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA 02138, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA 02138, USA; Department of Immunology and Infectious Diseases, Harvard T.H. Chan School of Public Health, Harvard University, Boston, MA 02115, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Division of Infectious Diseases, Massachusetts General Hospital, Boston, MA 02114, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Faculty of Arts and Sciences, Harvard University, Cambridge, MA 02138, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA 02138, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Department of Systems Biology, Harvard Medical School, Boston, MA 02115, USA.|Department of Epidemiology, Harvard T.H. Chan School of Public Health, Harvard University, Boston, MA 02115, USA; Center for Communicable Disease Dynamics, Department of Epidemiology, Harvard T. H. Chan School of Public Health, Harvard University, Boston, MA 02115, USA.|Department of Epidemiology, Harvard T.H. Chan School of Public Health, Harvard University, Boston, MA 02115, USA; Center for Communicable Disease Dynamics, Department of Epidemiology, Harvard T. H. Chan School of Public Health, Harvard University, Boston, MA 02115, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA; Applied Epidemiology Fellowship, Council of State and Territorial Epidemiologists, Atlanta, GA 30345, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Barnstable County Department of Health and the Environment, Barnstable, MA 02630, USA.|Barnstable County Department of Health and the Environment, Barnstable, MA 02630, USA.|Barnstable County Department of Health and the Environment, Barnstable, MA 02630, USA.|Barnstable County Department of Human Services, Barnstable, MA 02630, USA.|Community Tracing Collaborative, Commonwealth of Massachusetts, Boston, MA 02199, USA.|Community Tracing Collaborative, Commonwealth of Massachusetts, Boston, MA 02199, USA.|Community Tracing Collaborative, Commonwealth of Massachusetts, Boston, MA 02199, USA.|Department of Epidemiology, Harvard T.H. Chan School of Public Health, Harvard University, Boston, MA 02115, USA; Center for Communicable Disease Dynamics, Department of Epidemiology, Harvard T. H. Chan School of Public Health, Harvard University, Boston, MA 02115, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Massachusetts Department of Public Health, Boston, MA 02199, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Department of Immunology and Infectious Diseases, Harvard T.H. Chan School of Public Health, Harvard University, Boston, MA 02115, USA; Massachusetts Consortium for Pathogen Readiness, Boston, MA 02115, USA. Electronic address: bronwyn@broadinstitute.org.|Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, MA 02138, USA; Department of Immunology and Infectious Diseases, Harvard T.H. Chan School of Public Health, Harvard University, Boston, MA 02115, USA; Howard Hughes Medical Institute, Chevy Chase, MD 20815, USA; Massachusetts Consortium for Pathogen Readiness, Boston, MA 02115, USA."

1. 提取首尾作者对应机构 #

核心思路是针对每个Author节点单独提取机构，而非直接抓取所有机构的集合。修改extract_xml函数，新增首尾机构提取逻辑：

extract_xml <- function(theFile) {
  library(XML)
  newData <- xmlParse(theFile)
  records <- getNodeSet(newData, "//PubmedArticle")
  
  # 初始化存储向量
  pmid <- c()
  doi <- c()
  authors <- c()
  author_count <- c()
  first_affil <- c()
  last_affil <- c()
  authAffil <- c()
  
  for (rec in records) {
    # 提取PMID
    pmid_val <- xpathSApply(rec, ".//MedlineCitation/PMID", xmlValue)
    pmid <- c(pmid, ifelse(length(pmid_val)==0, NA, pmid_val))
    
    # 提取DOI
    doi_val <- xpathSApply(rec, ".//ELocationID[@EIdType = \"doi\"]", xmlValue)
    doi <- c(doi, ifelse(length(doi_val)==0, NA, doi_val))
    
    # 提取作者信息
    author_nodes <- getNodeSet(rec, ".//Author")
    auth_last <- sapply(author_nodes, xpathSApply, ".//LastName", xmlValue)
    auth_init <- sapply(author_nodes, xpathSApply, ".//Initials", xmlValue)
    auth_full <- mapply(paste, auth_last, auth_init, SIMPLIFY = FALSE)
    authors <- c(authors, paste(unlist(auth_full), collapse = "|"))
    
    # 作者数量
    author_count <- c(author_count, length(author_nodes))
    
    # 提取所有机构
    all_affils <- sapply(author_nodes, xpathSApply, ".//AffiliationInfo/Affiliation", xmlValue)
    all_affils <- lapply(all_affils, function(x) ifelse(length(x)==0, NA, paste(x, collapse = "; ")))
    authAffil <- c(authAffil, paste(unlist(all_affils), collapse = "|"))
    
    # 第一作者机构
    first_affil_val <- ifelse(length(author_nodes)>=1, all_affils[[1]], NA)
    first_affil <- c(first_affil, first_affil_val)
    
    # 最后作者机构
    last_affil_val <- ifelse(length(author_nodes)>=1, all_affils[[length(author_nodes)]], NA)
    last_affil <- c(last_affil, last_affil_val)
  }
  
  theDF <- data.frame(pmid, doi, authors, author_count, first_affil, last_affil, authAffil, stringsAsFactors = FALSE)
  return(theDF)
}

修改后调用函数，即可得到包含author_count（作者数量）、first_affil（第一作者机构）、last_affil（最后作者机构）的数据集。

2. 其他目标指标获取方向 #

单篇文献引用数 #

PubMed XML本身不包含引用数据，需通过外部API获取：

• 使用rcrossref包，通过DOI查询CrossRef数据库的引用计数
• 调用Web of Science/Scopus的API，通过PMID/DOI查询引用数据（需申请API密钥）

第一作者学术度 #

无统一提取字段，需结合外部数据源：

• 通过作者姓名+机构匹配ORCID，再调用ORCID API获取作者发表记录
• 使用Scopus/Web of Science API，查询作者的h指数、总引用数等指标

3. PubMed XML可提取的完整字段范围 #

PubMed的Medline XML包含以下核心字段：

• 文献标识：PMID、DOI、PMCID
• 基本信息：标题、英文摘要、中文摘要（若有）
• 作者信息：所有作者姓名、机构、ORCID、邮箱
• 出版信息：期刊名、ISSN、卷期页、收稿日期、录用日期、在线发表日期、印刷发表日期
• 主题标注：MeSH术语、关键词、化学物质标识
• 研究信息：研究类型、资助机构、伦理声明、临床试验注册号
• 关联文献：参考文献列表、相关PMID

内容的提问来源于stack exchange，提问作者mickmars51