Author Citation Network

None

/return/citationList/citation/id
String pajek="";
String nonself_vertex="\"cadetblue1\""; // Using R color names here, not Pajek color names!
String self_vertex="\"red4\"";
String nonself_edge="\"burlywood1\""; 
String self_edge="\"red\"";
int index=1;
int weight=1;
Hashtable vertices = new Hashtable();

pajek="*Vertices " + papers.size() + "\n";
for(int i=0; i
/return/referenceList/reference[id]/id
/return/resultList/result[citedByCount>0]/id
queryString = "auth:\"" + author_name +  "\" sort_date:y";  // generate query string

String[] myArray=new String[author_papers.size()+citing_papers.size()+referred_to_papers.size()];

j=0;
for(int i=0; i
flatten(inputs, outputs, depth) {
	for (i = inputs.iterator(); i.hasNext();) {
	    element = i.next();
		if (element instanceof Collection && depth > 0) {
			flatten(element, outputs, depth - 1);
		} else {
			outputs.add(element);
		}
	}
}

outputlist = new ArrayList();

flatten(inputlist, outputlist, 2);
List strippedlist = new ArrayList();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
	String item = (String) i.next();
	if (strippedlist.contains(item) == false) {
		strippedlist.add(item);
	}
}

/return/referenceList/reference[id]/id
/return/citationList/citation/id
require(igraph); # use the igraph package

png("citation_graph.png", width=4096, height=2048);

my_citation_graph<-read.graph(input_file, format="pajek"); # read PAJEK format
my_citation_graph<-simplify(my_citation_graph, remove.multiple=TRUE, remove.loops=TRUE);
lay=layout.sugiyama(my_citation_graph,layers=NULL); # automatically assign layers
plot(my_citation_graph, 
     layout=lay$layout,
     vertex.size=2, 
     vertex.label=NA, # NA omits labels/frames etc. 
     vertex.frame.color=NA,
     edge.arrow.size=0.2,
     edge.width=0.2,
     edge.curved=TRUE
);
dev.off();

pdf(PDF_filename);
plot(my_citation_graph, 
     layout=lay$layout,
     vertex.size=2, 
     vertex.label=NA, # NA omits labels/frames etc. 
     vertex.frame.color=NA,
     edge.arrow.size=0.2,
     edge.width=0.2,
     edge.curved=TRUE
);
dev.off();

Pajek_file<-"c:/temp/my_citation_graph.pajek";
write_graph(my_citation_graph, Pajek_file, format="pajek");

  BufferedWriter out;
  if (encoding == void) {
  	out = new BufferedWriter(new FileWriter(outputFile));
  }
  else {
  	out = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(outputFile), encoding)); 
  }
out.write(filecontents);
out.flush();
out.close();
outputFile = filecontents;

/return/resultList/result/authorList/author[1]/lastName
/return/resultList/result/journalInfo/yearOfPublication

Name	Type	Description
getCitations	wsdl	The getCitations call fetches data for all articles citing cited work by author_name. Note that this is a different call with different input and output than searchPublications. Input is a list of pmid. Wsdl http://www.ebi.ac.uk/europepmc/webservices/soap?wsdl Wsdl Operation getCitations
getCitations_input	xmlsplitter
PubMed_and_MEDLINE	stringconstant	Value MED
pageSize	stringconstant	Value 100
getCitations_output	xmlsplitter
extract_citation_id	xpath	Xpath Expression /return/citationList/citation/id
combine_and_make_Pajek_file	beanshell	Script String pajek=""; String nonself_vertex="\"cadetblue1\""; // Using R color names here, not Pajek color names! String self_vertex="\"red4\""; String nonself_edge="\"burlywood1\""; String self_edge="\"red\""; int index=1; int weight=1; Hashtable vertices = new Hashtable(); pajek="*Vertices " + papers.size() + "\n"; for(int i=0; i
getReferences	wsdl	Wsdl http://www.ebi.ac.uk/europepmc/webservices/soap?wsdl Wsdl Operation getReferences
getReferences_input	xmlsplitter
getReferences_output	xmlsplitter
extract_reference_id	xpath	Xpath Expression /return/referenceList/reference[id]/id
searchPublications	wsdl	The searchPublications calls the Europe PMC Web service to retrieve the bibliographic information for all published work indexed in PubMed by author_name. Wsdl http://www.ebi.ac.uk/europepmc/webservices/soap?wsdl Wsdl Operation searchPublications
extract_id_for_cited_work	xpath	Xpath Expression /return/resultList/result[citedByCount>0]/id
build_query	beanshell	The build_query BeanShell constructs the Europe PMC search query for a single author, sorting the results by year. Script queryString = "auth:\"" + author_name + "\" sort_date:y"; // generate query string
searchPublications_input	xmlsplitter
articles_to_retrieve	stringconstant	Value 1000
resultType_core	stringconstant	Value core
offSet_zero	stringconstant	Value 0
collect_all_vertices	beanshell	This BeanShell collects all the papers (vertices) that will be included in the graph. Note that these Web services calls do not provide all the edges in this graph - only the vertices. Citations between papers citing the author are not included, for example. Script String[] myArray=new String[author_papers.size()+citing_papers.size()+referred_to_papers.size()]; j=0; for(int i=0; i
Flatten_List_twice	localworker	Script flatten(inputs, outputs, depth) { for (i = inputs.iterator(); i.hasNext();) { element = i.next(); if (element instanceof Collection && depth > 0) { flatten(element, outputs, depth - 1); } else { outputs.add(element); } } } outputlist = new ArrayList(); flatten(inputlist, outputlist, 2);
Remove_String_Duplicates	localworker	Script List strippedlist = new ArrayList(); for (Iterator i = stringlist.iterator(); i.hasNext();) { String item = (String) i.next(); if (strippedlist.contains(item) == false) { strippedlist.add(item); } }
getCitations_2	wsdl	Second getCitations call to get the citations between included papers not authored by author_name. Wsdl http://www.ebi.ac.uk/europepmc/webservices/soap?wsdl Wsdl Operation getCitations
getCitations_2_input	xmlsplitter
getReferences_2	wsdl	Second getReferences call to get the references between included papers not authored by author_name. This should be redundant with the getCitations_2 if PubMed was complete and contained all references and citations between PubMed articles in the database. At present (October 2015), it does not. Wsdl http://www.ebi.ac.uk/europepmc/webservices/soap?wsdl Wsdl Operation getReferences
getReferences_2_input	xmlsplitter
getCitations_2_output	xmlsplitter
getReferences_2_output	xmlsplitter
extract_reference_id_2	xpath	Xpath Expression /return/referenceList/reference[id]/id
extract_citation_id_2	xpath	Xpath Expression /return/citationList/citation/id
draw_graph	rshell	Script require(igraph); # use the igraph package png("citation_graph.png", width=4096, height=2048); my_citation_graph<-read.graph(input_file, format="pajek"); # read PAJEK format my_citation_graph<-simplify(my_citation_graph, remove.multiple=TRUE, remove.loops=TRUE); lay=layout.sugiyama(my_citation_graph,layers=NULL); # automatically assign layers plot(my_citation_graph, layout=lay$layout, vertex.size=2, vertex.label=NA, # NA omits labels/frames etc. vertex.frame.color=NA, edge.arrow.size=0.2, edge.width=0.2, edge.curved=TRUE ); dev.off(); pdf(PDF_filename); plot(my_citation_graph, layout=lay$layout, vertex.size=2, vertex.label=NA, # NA omits labels/frames etc. vertex.frame.color=NA, edge.arrow.size=0.2, edge.width=0.2, edge.curved=TRUE ); dev.off(); Pajek_file<-"c:/temp/my_citation_graph.pajek"; write_graph(my_citation_graph, Pajek_file, format="pajek"); R Server localhost:6311
Write_Text_File	localworker	Script BufferedWriter out; if (encoding == void) { out = new BufferedWriter(new FileWriter(outputFile)); } else { out = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(outputFile), encoding)); } out.write(filecontents); out.flush(); out.close(); outputFile = filecontents;
Pajek_filename	stringconstant	The temporary filename is the name (and path) to the file used to transfer the data to the Rshell component draw_graph. Value C:\temp\temp.txt
PDF_filename	stringconstant	Value c:/temp/my_citation_graph.pdf
searchPublications_output	xmlsplitter
extract_first_author_last_name	xpath	Xpath Expression /return/resultList/result/authorList/author[1]/lastName
extract_publication_year	xpath	Xpath Expression /return/resultList/result/journalInfo/yearOfPublication

Name	Description	Inputs	Outputs
combine_and_make_Pajek_file		papers citations references author_papers first_author_last_name publication_year	pajek
build_query	The build_query BeanShell constructs the Europe PMC search query for a single author, sorting the results by year.	author_name	queryString
collect_all_vertices	This BeanShell collects all the papers (vertices) that will be included in the graph. Note that these Web services calls do not provide all the edges in this graph - only the vertices. Citations between papers citing the author are not included, for example.	author_papers citing_papers referred_to_papers	vertices

Name	Description
citation_graph
Pajek_file

Source	Sink
getCitations_input:output	getCitations:parameters
PubMed_and_MEDLINE:value	getCitations_input:source
pageSize:value	getCitations_input:pageSize
extract_id_for_cited_work:nodelist	getCitations_input:id
getCitations:parameters	getCitations_output:input
getCitations_output:return	extract_citation_id:xml_text
Remove_String_Duplicates:strippedlist	combine_and_make_Pajek_file:papers
extract_reference_id_2:nodelist	combine_and_make_Pajek_file:references
extract_citation_id_2:nodelist	combine_and_make_Pajek_file:citations
extract_id_for_cited_work:nodelist	combine_and_make_Pajek_file:author_papers
extract_first_author_last_name:nodelist	combine_and_make_Pajek_file:first_author_last_name
extract_publication_year:nodelist	combine_and_make_Pajek_file:publication_year
getReferences_input:output	getReferences:parameters
PubMed_and_MEDLINE:value	getReferences_input:source
pageSize:value	getReferences_input:pageSize
extract_id_for_cited_work:nodelist	getReferences_input:id
getReferences:parameters	getReferences_output:input
getReferences_output:return	extract_reference_id:xml_text
searchPublications_input:output	searchPublications:parameters
searchPublications_output:return	extract_id_for_cited_work:xml_text
author_name	build_query:author_name
build_query:queryString	searchPublications_input:queryString
offSet_zero:value	searchPublications_input:offSet
articles_to_retrieve:value	searchPublications_input:pageSize
resultType_core:value	searchPublications_input:resultType
extract_id_for_cited_work:nodelist	collect_all_vertices:author_papers
extract_reference_id:nodelist	collect_all_vertices:referred_to_papers
extract_citation_id:nodelist	collect_all_vertices:citing_papers
collect_all_vertices:vertices	Flatten_List_twice:inputlist
Flatten_List_twice:outputlist	Remove_String_Duplicates:stringlist
getCitations_2_input:output	getCitations_2:parameters
Remove_String_Duplicates:strippedlist	getCitations_2_input:id
pageSize:value	getCitations_2_input:pageSize
PubMed_and_MEDLINE:value	getCitations_2_input:source
getReferences_2_input:output	getReferences_2:parameters
Remove_String_Duplicates:strippedlist	getReferences_2_input:id
pageSize:value	getReferences_2_input:pageSize
PubMed_and_MEDLINE:value	getReferences_2_input:source
getCitations_2:parameters	getCitations_2_output:input
getReferences_2:parameters	getReferences_2_output:input
getReferences_2_output:return	extract_reference_id_2:xml_text
getCitations_2_output:return	extract_citation_id_2:xml_text
Write_Text_File:outputFile	draw_graph:input_file
PDF_filename:value	draw_graph:PDF_filename
combine_and_make_Pajek_file:pajek	Write_Text_File:filecontents
Pajek_filename:value	Write_Text_File:outputFile
searchPublications:parameters	searchPublications_output:input
searchPublications_output:return	extract_first_author_last_name:xml_text
searchPublications_output:return	extract_publication_year:xml_text
draw_graph:citation_graph	citation_graph
draw_graph:Pajek_file	Pajek_file

Author Citation Network

Preview

Run

Run this Workflow in the Taverna Workbench...

Workflow Components

Wsdl

Wsdl Operation

Value

Value

Xpath Expression

Script

Wsdl

Wsdl Operation

Xpath Expression

Wsdl

Wsdl Operation

Xpath Expression

Script

Value

Value

Value

Script

Script

Script

Wsdl

Wsdl Operation

Wsdl

Wsdl Operation

Xpath Expression

Xpath Expression

Script

R Server

Script

Value

Value

Xpath Expression

Xpath Expression

Reviews (0)

Comments (0)

Other workflows that use similar services (15)