Author Citation Network

None

/return/citationList/citation/id
String edgelist="";
int index=0;
Hashtable vertices = new Hashtable();

for(int i=0; i
require(igraph); # use the igraph package

# png("citation_graph.png", width=4096, height=2048);
pdf("c:/tmp/citation_graph.pdf"); citation_graph<-"c:/tmp/citation_graph.pdf";

my_citation_graph<-read.graph(input_file, format="edgelist"); # read edgelist ("a b" means a -> b or that paper a cites paper b)
my_citation_graph<-simplify(my_citation_graph, remove.multiple=TRUE, remove.loops=TRUE);

palette(rainbow(20)); # use rainbow colors for the layers
lay=layout.sugiyama(my_citation_graph,layers=NULL); # automatically assign layers
plot(my_citation_graph, 
     layout=lay$layout,
     vertex.size=2, 
     vertex.label=NA, # NA omits labels
     vertex.color=lay$layout[,2],
     vertex.frame.color=lay$layout[,2],
     edge.arrow.size=0.2,
     edge.width=0.2,
     edge.color="gray",
     edge.curved=TRUE
);
dev.off();

/return/referenceList/reference[id]/id
  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;

/ns1:searchPublicationsResponse/return/resultList/result[citedByCount>0]/id
queryString = "auth:\"" + author_name +  "\" sort_date:y";  // generate query string

vertices = new ArrayList();

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, 1);
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, 1);
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

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_citations_and_references	beanshell	Script String edgelist=""; int index=0; Hashtable vertices = new Hashtable(); for(int i=0; i
draw_graph	rshell	Script require(igraph); # use the igraph package # png("citation_graph.png", width=4096, height=2048); pdf("c:/tmp/citation_graph.pdf"); citation_graph<-"c:/tmp/citation_graph.pdf"; my_citation_graph<-read.graph(input_file, format="edgelist"); # read edgelist ("a b" means a -> b or that paper a cites paper b) my_citation_graph<-simplify(my_citation_graph, remove.multiple=TRUE, remove.loops=TRUE); palette(rainbow(20)); # use rainbow colors for the layers lay=layout.sugiyama(my_citation_graph,layers=NULL); # automatically assign layers plot(my_citation_graph, layout=lay$layout, vertex.size=2, vertex.label=NA, # NA omits labels vertex.color=lay$layout[,2], vertex.frame.color=lay$layout[,2], edge.arrow.size=0.2, edge.width=0.2, edge.color="gray", edge.curved=TRUE ); dev.off(); R Server localhost:6311
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
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;
temp_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:\tmp\temp.txt
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 /ns1:searchPublicationsResponse/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_lite	stringconstant	Value lite
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 vertices = new ArrayList(); for(int i=0; i
Flatten_List	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, 1);
Flatten_List_2	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, 1);
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

Name	Description	Inputs	Outputs
combine_citations_and_references		papers citations references	edgelist
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

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_citations_and_references:papers
extract_reference_id_2:nodelist	combine_citations_and_references:references
extract_citation_id_2:nodelist	combine_citations_and_references:citations
Write_Text_File:outputFile	draw_graph:input_file
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
combine_citations_and_references:edgelist	Write_Text_File:filecontents
temp_filename:value	Write_Text_File:outputFile
searchPublications_input:output	searchPublications:parameters
searchPublications:parameters	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_lite: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:inputlist
Flatten_List:outputlist	Flatten_List_2:inputlist
Flatten_List_2: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
draw_graph:citation_graph	graph

Author Citation Network

Preview

Run

Run this Workflow in the Taverna Workbench...

Workflow Components

Wsdl

Wsdl Operation

Value

Value

Xpath Expression

Script

Script

R Server

Wsdl

Wsdl Operation

Xpath Expression

Script

Value

Wsdl

Wsdl Operation

Xpath Expression

Script

Value

Value

Value

Script

Script

Script

Script

Wsdl

Wsdl Operation

Wsdl

Wsdl Operation

Xpath Expression

Xpath Expression

Reviews (0)

Comments (0)

Other workflows that use similar services (15)