UniProt Protein Protein Network

None

queryString = "(TITLE:\"" + phrase + "\" OR ABSTRACT:\"" + phrase + "\") AND UNIPROT_PUBS:" + UniProt_ID;  // generate query string

/resultList/result/id
/dbCrossReferenceList/dbCrossReference/dbCrossReferenceInfo/info1
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);
x<-sort(table(UniProt_IDs), decreasing = TRUE);
proteins<-names(x);
frequencies<-x;
topNproteins<-names(x[1:10]);

queryString = "(TITLE:\"" + phrase + "\" OR ABSTRACT:\"" + phrase + "\") AND UNIPROT_PUBS:" + UniProt_ID;  // generate query string

/resultList/result/id
/dbCrossReferenceList/dbCrossReference/dbCrossReferenceInfo/info1
String pajek="";
Hashtable vertices = new Hashtable();
Hashtable weights = new Hashtable();
int weight=1;
double temp;

pajek="*Vertices " + unique_UniProt_IDs.size() + "\n";
for(int i=0; i
List strippedlist = new ArrayList();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
	String item = (String) i.next();
	if (strippedlist.contains(item) == false) {
		strippedlist.add(item);
	}
}

require(igraph); # use the igraph package

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

my_uniprot_graph<-read.graph(input_file, format="pajek"); # read Pajek format
my_uniprot_graph<-simplify(my_uniprot_graph, remove.multiple=TRUE, remove.loops=TRUE);

lay<-layout.fruchterman.reingold(my_uniprot_graph);
plot(my_uniprot_graph, 
     layout=lay,
     vertex.size=3*degree(my_uniprot_graph)/max(degree(my_uniprot_graph))+4, 
     vertex.label=V(my_uniprot_graph)$id, # NA would omits labels 
     vertex.label.cex=2.5,
     vertex.label.family="sans",
     vertex.label.color="black",
     vertex.color=c("red",rep("blue",gorder(my_uniprot_graph)-1)),
     vertex.frame.color=NA,
     edge.arrow.size=0,
     edge.color="gray",
     edge.width=2*E(my_uniprot_graph)$weight/max(E(my_uniprot_graph)$weight),
     edge.curved=F
);                           
dev.off();

pdf(PDF_filename);
plot(my_uniprot_graph, 
     layout=lay,
     vertex.size=3*degree(my_uniprot_graph)/max(degree(my_uniprot_graph))+4, 
     vertex.label=V(my_uniprot_graph)$id, 
     vertex.label.cex=0.5,
     vertex.label.family="sans",
     vertex.label.color="black",
     vertex.color=c("red",rep("blue",gorder(my_uniprot_graph)-1)),
     vertex.frame.color=NA,
     edge.arrow.size=0,
     edge.color="gray",
     edge.width=2*E(my_uniprot_graph)$weight/max(E(my_uniprot_graph)$weight),
     edge.curved=F
);     
dev.off();

Pajek_file<-"c:/temp/my_uniprot_graph.pajek";
write.graph(my_uniprot_graph, Pajek_file, format="pajek");

gml_file<-"c:/temp/my_uniprot_graph.gml";
write.graph(my_uniprot_graph, gml_file, format="gml");


  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;

/dbCountList/db/count
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);
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);

Name	Description
UniProt_ID_in_paper	UniProt identifier of starting protein
phrase_in_title_or_abstract	Arbitrary word or phrase required in title or abstract.
proteins_to_retrieve	The number of co-occuring proteins to retrieve per paper. Should be kept small to avoid incorporating too many long list from proteomics studies.

Name	Type	Description
build_query	beanshell	This build_query BeanShell constructs the Europe PMC search query for a single protein in UniProt. Script queryString = "(TITLE:\"" + phrase + "\" OR ABSTRACT:\"" + phrase + "\") AND UNIPROT_PUBS:" + UniProt_ID; // generate query string
articles_to_retrieve	stringconstant	Value 1000
extract_id	xpath	Xpath Expression /resultList/result/id
UniProt	stringconstant	Value UNIPROT
PubMed_and_MEDLINE	stringconstant	Value MED
extract_UniProt_id	xpath	Xpath Expression /dbCrossReferenceList/dbCrossReference/dbCrossReferenceInfo/info1
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);
count_frequencies	rshell	Script x<-sort(table(UniProt_IDs), decreasing = TRUE); proteins<-names(x); frequencies<-x; topNproteins<-names(x[1:10]); R Server localhost:6311
build_query_2	beanshell	The build_query_2 BeanShell constructs the second stage Europe PMC search queries for all the proteins co-occuring with the input protein. Script queryString = "(TITLE:\"" + phrase + "\" OR ABSTRACT:\"" + phrase + "\") AND UNIPROT_PUBS:" + UniProt_ID; // generate query string
extract_id_2	xpath	Xpath Expression /resultList/result/id
extract_UniProt_id_2	xpath	Xpath Expression /dbCrossReferenceList/dbCrossReference/dbCrossReferenceInfo/info1
combine_and_make_Pajek_file	beanshell	Script String pajek=""; Hashtable vertices = new Hashtable(); Hashtable weights = new Hashtable(); int weight=1; double temp; pajek="*Vertices " + unique_UniProt_IDs.size() + "\n"; for(int i=0; i
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); } }
draw_graph	rshell	This component visualizes the protein-protein network as a graph and exports the results in Pajek and GML format. Script require(igraph); # use the igraph package png("protein_network.png", width=4096, height=2048); my_uniprot_graph<-read.graph(input_file, format="pajek"); # read Pajek format my_uniprot_graph<-simplify(my_uniprot_graph, remove.multiple=TRUE, remove.loops=TRUE); lay<-layout.fruchterman.reingold(my_uniprot_graph); plot(my_uniprot_graph, layout=lay, vertex.size=3degree(my_uniprot_graph)/max(degree(my_uniprot_graph))+4, vertex.label=V(my_uniprot_graph)$id, # NA would omits labels vertex.label.cex=2.5, vertex.label.family="sans", vertex.label.color="black", vertex.color=c("red",rep("blue",gorder(my_uniprot_graph)-1)), vertex.frame.color=NA, edge.arrow.size=0, edge.color="gray", edge.width=2E(my_uniprot_graph)$weight/max(E(my_uniprot_graph)$weight), edge.curved=F ); dev.off(); pdf(PDF_filename); plot(my_uniprot_graph, layout=lay, vertex.size=3degree(my_uniprot_graph)/max(degree(my_uniprot_graph))+4, vertex.label=V(my_uniprot_graph)$id, vertex.label.cex=0.5, vertex.label.family="sans", vertex.label.color="black", vertex.color=c("red",rep("blue",gorder(my_uniprot_graph)-1)), vertex.frame.color=NA, edge.arrow.size=0, edge.color="gray", edge.width=2E(my_uniprot_graph)$weight/max(E(my_uniprot_graph)$weight), edge.curved=F ); dev.off(); Pajek_file<-"c:/temp/my_uniprot_graph.pajek"; write.graph(my_uniprot_graph, Pajek_file, format="pajek"); gml_file<-"c:/temp/my_uniprot_graph.gml"; write.graph(my_uniprot_graph, gml_file, format="gml"); 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_uniprot_graph.pdf
extract_dbCount	xpath	Xpath Expression /dbCountList/db/count
searchPublications	component	Component searchPublications
getDatabaseLinks	component	Component getDatabaseLinks
searchPublications_2	component	Component searchPublications
getDatabaseLinks_2	component	Component getDatabaseLinks
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);
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);
Flatten_List_3	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);

Name	Description	Inputs	Outputs
build_query	This build_query BeanShell constructs the Europe PMC search query for a single protein in UniProt.	UniProt_ID phrase	queryString
build_query_2	The build_query_2 BeanShell constructs the second stage Europe PMC search queries for all the proteins co-occuring with the input protein.	UniProt_ID phrase	queryString
combine_and_make_Pajek_file		UniProt_IDs topNproteins unique_UniProt_IDs countList	pajek

Name	Description
gml_file
Pajek_file
protein_network

Source	Sink
UniProt_ID_in_paper	build_query:UniProt_ID
phrase_in_title_or_abstract	build_query:phrase
searchPublications:resultList	extract_id:xml_text
getDatabaseLinks:dbCrossReferenceList	extract_UniProt_id:xml_text
extract_UniProt_id:nodelist	Flatten_List:inputlist
Flatten_List:outputlist	count_frequencies:UniProt_IDs
phrase_in_title_or_abstract	build_query_2:phrase
count_frequencies:topNproteins	build_query_2:UniProt_ID
searchPublications_2:resultList	extract_id_2:xml_text
getDatabaseLinks_2:dbCrossReferenceList	extract_UniProt_id_2:xml_text
count_frequencies:topNproteins	combine_and_make_Pajek_file:topNproteins
Remove_String_Duplicates:strippedlist	combine_and_make_Pajek_file:unique_UniProt_IDs
Flatten_List_twice:outputlist	combine_and_make_Pajek_file:countList
Flatten_List_2:outputlist	combine_and_make_Pajek_file:UniProt_IDs
Flatten_List_3:outputlist	Remove_String_Duplicates:stringlist
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
getDatabaseLinks_2:dbCountList	extract_dbCount:xml_text
build_query:queryString	searchPublications:queryString
articles_to_retrieve:value	searchPublications:pageSize
UniProt:value	getDatabaseLinks:database
extract_id:nodelist	getDatabaseLinks:id
proteins_to_retrieve	getDatabaseLinks:pageSize
PubMed_and_MEDLINE:value	getDatabaseLinks:source
build_query_2:queryString	searchPublications_2:queryString
articles_to_retrieve:value	searchPublications_2:pageSize
extract_id_2:nodelist	getDatabaseLinks_2:id
UniProt:value	getDatabaseLinks_2:database
proteins_to_retrieve	getDatabaseLinks_2:pageSize
PubMed_and_MEDLINE:value	getDatabaseLinks_2:source
extract_dbCount:nodelist	Flatten_List_twice:inputlist
extract_UniProt_id_2:nodelist	Flatten_List_2:inputlist
Flatten_List_2:outputlist	Flatten_List_3:inputlist
draw_graph:gml_file	gml_file
draw_graph:Pajek_file	Pajek_file
draw_graph:protein_network	protein_network

UniProt Protein Protein Network

Preview

Run

Run this Workflow in the Taverna Workbench...

Workflow Components

Script

Value

Xpath Expression

Value

Value

Xpath Expression

Script

Script

R Server

Script

Xpath Expression

Xpath Expression

Script

Script

Script

R Server

Script

Value

Value

Xpath Expression

Component

Component

Component

Component

Script

Script

Script

Reviews (0)

Comments (0)

Other workflows that use similar services (0)