Gene to Pubmed
Created: 2011-02-08 13:04:06
Last updated: 2011-02-10 16:01:41
Download WorkflowThis workflow takes in a list of gene names and searches the PubMed database for corresponding articles. Any matches to the genes are then retrieved (abstracts only). These abstracts are then returned to the user.
Preview
Run
Run this Workflow in the Taverna Workbench...
Option 1:
Copy and paste this link into File > 'Open workflow location...'
http://www.myexperiment.org/workflows/1842/download?version=2
[ More Info
]
Taverna is available from http://taverna.sourceforge.net/
If you are having problems downloading it in Taverna, you may need to provide your username and password in the URL so that Taverna can access the Workflow:
Replace http:// in the link above with http://yourusername:yourpassword@
Workflow Components
Authors (1)
| Paul Fisher |
Titles (1)
| Gene to Pubmed |
Descriptions (1)
| This workflow takes in a list of gene names and searches the PubMed database for corresponding articles. Any matches to the genes are then retrieved (abstracts only). These abstracts are then returned to the user. |
Dependencies (0)
None
Inputs (3)
| Name | Description |
|---|---|
| gene_names | |
| Phenotype_search_term | |
| pathway_descriptions |
Processors (73)
| Name | Type | Description |
|---|---|---|
| regex | stringconstant |
Value\n |
| remove_nulls | beanshell |
ScriptString[] split = input.split("\n");
Vector nonEmpty = new Vector();
for (int i = 0; i < split.length; i++){
if (!(split[i].equals("")))
{
nonEmpty.add(split[i].trim());
}
}
String[] non_empty = new String[nonEmpty.size()];
for (int i = 0; i < non_empty.length; i ++)
{
non_empty[i] = nonEmpty.elementAt(i);
}
String output = "";
for (int i = 0; i < non_empty.length; i++)
{
output = output + (String) (non_empty[i] + "\n");
} |
| gene_and_abstract | beanshell |
ScriptString[] split = abstracts.split("\n");
String pathway_name = pathway;
Vector nonEmpty = new Vector();
for (int i = 0; i < split.length; i++)
{
String trimmed = split[i].trim();
nonEmpty.add(trimmed);
}
String output = ">> " + pathway_name + "\n";
for (int i = 0; i < nonEmpty.size(); i++)
{
output = output + (String) (nonEmpty.elementAt(i) + "\n");
} |
| split_search_terms | localworker |
ScriptList split = new ArrayList();
if (!string.equals("")) {
String regexString = ",";
if (regex != void) {
regexString = regex;
}
String[] result = string.split(regexString);
for (int i = 0; i < result.length; i++) {
split.add(result[i]);
}
}
|
| merge_outputs_2 | localworker |
ScriptString seperatorString = "\n";
if (seperator != void) {
seperatorString = seperator;
}
StringBuffer sb = new StringBuffer();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
sb.append(item);
if (i.hasNext()) {
sb.append(seperatorString);
}
}
concatenated = sb.toString();
|
| Search_PubMed | workflow | |
| clean_text | workflow | |
| regular_expression | stringconstant |
Value\n |
| Remove_duplicate_genes | localworker |
ScriptList strippedlist = new ArrayList();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
if (strippedlist.contains(item) == false) {
strippedlist.add(item);
}
}
|
| split_gene_names | localworker |
ScriptList split = new ArrayList();
if (!string.equals("")) {
String regexString = ",";
if (regex != void) {
regexString = regex;
}
String[] result = string.split(regexString);
for (int i = 0; i < result.length; i++) {
split.add(result[i]);
}
}
|
| remove_Nulls_2 | beanshell |
ScriptString[] split = input.split("\n");
Vector nonEmpty = new Vector();
for (int i = 0; i < split.length; i++){
if (!(split[i].equals("")))
{
nonEmpty.add(split[i].trim());
}
}
String[] non_empty = new String[nonEmpty.size()];
for (int i = 0; i < non_empty.length; i ++)
{
non_empty[i] = nonEmpty.elementAt(i);
}
String output = "";
for (int i = 0; i < non_empty.length; i++)
{
output = output + (String) (non_empty[i] + "\n");
} |
| Merge_string_list_to_string | localworker |
ScriptString seperatorString = "\n";
if (seperator != void) {
seperatorString = seperator;
}
StringBuffer sb = new StringBuffer();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
sb.append(item);
if (i.hasNext()) {
sb.append(seperatorString);
}
}
concatenated = sb.toString();
|
| xpath | stringconstant |
Value/*[local-name(.)='eSearchResult']/*[local-name(.)='IdList']/*[local-name(.)='Id'] |
| run_eSearch | wsdl |
Wsdlhttp://eutils.ncbi.nlm.nih.gov/entrez/eutils/soap/eutils.wsdlWsdl Operationrun_eSearch |
| min_date | stringconstant |
Value2000/01/01 |
| extractPMID | localworker |
Scriptimport org.dom4j.Document;
import org.dom4j.Node;
import org.dom4j.io.SAXReader;
SAXReader reader = new SAXReader(false);
reader.setIncludeInternalDTDDeclarations(false);
reader.setIncludeExternalDTDDeclarations(false);
Document document = reader.read(new StringReader(xmltext));
List nodelist = document.selectNodes(xpath);
// Process the elements in the nodelist
ArrayList outputList = new ArrayList();
ArrayList outputXmlList = new ArrayList();
String val = null;
String xmlVal = null;
for (Iterator iter = nodelist.iterator(); iter.hasNext();) {
Node element = (Node) iter.next();
xmlVal = element.asXML();
val = element.getStringValue();
if (val != null && !val.equals("")) {
outputList.add(val);
outputXmlList.add(xmlVal);
}
}
List nodelist=outputList;
List nodelistAsXML=outputXmlList; |
| remove_Nulls_4 | beanshell |
ScriptString[] split = input.split("\n");
Vector nonEmpty = new Vector();
for (int i = 0; i < split.length; i++){
if (!(split[i].equals("")))
{
nonEmpty.add(split[i].trim());
}
}
String[] non_empty = new String[nonEmpty.size()];
for (int i = 0; i < non_empty.length; i ++)
{
non_empty[i] = nonEmpty.elementAt(i);
}
String output = "";
for (int i = 0; i < non_empty.length; i++)
{
output = output + (String) (non_empty[i] + "\n");
} |
| concat_abstract_ids | beanshell |
ScriptString id = id.trim();
String abstract_text = abstract_text.trim();
String[] abstract_array = abstract_text.split("\n");
String abstract_amended = "";
if(abstract_array.length > 1)
{
abstract_amended = abstract_array[0] + " ";
for(int i = 1; i < abstract_array.length; i++)
{
abstract_amended = abstract_amended + abstract_array[i] + " ";
}
}
else
{
abstract_amended = abstract_array[0];
}
String date_text = date_text.trim();
String output = "";
output = id + "\t" + date_text + "\t" + abstract_amended; |
| max_return_phenotype | stringconstant |
Value5000 |
| pubmed_database | stringconstant |
Valuepubmed |
| merge_phenotype_abstracts | beanshell |
ScriptString[] split = abstracts.split("\n");
String phenotype_term = phenotype.trim();
Vector nonEmpty = new Vector();
for (int i = 0; i < split.length; i++)
{
String trimmed = split[i].trim();
// String mytext = split[i].substring(split[i].indexOf(0), split[i].indexOf(" AND "));
nonEmpty.add(trimmed);
}
String output = ">> " + phenotype_term + "\n";
for (int i = 0; i < nonEmpty.size(); i++)
{
output = output + (String) (nonEmpty.elementAt(i) + "\n");
} |
| merge_abstracts | localworker |
ScriptString seperatorString = "\n";
if (seperator != void) {
seperatorString = seperator;
}
StringBuffer sb = new StringBuffer();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
sb.append(item);
if (i.hasNext()) {
sb.append(seperatorString);
}
}
concatenated = sb.toString();
|
| max_date | stringconstant |
Value2011/01/31 |
| parametersXML_eSearch | xmlsplitter | |
| merge_abstract_ids | localworker |
ScriptString seperatorString = "\n";
if (seperator != void) {
seperatorString = seperator;
}
StringBuffer sb = new StringBuffer();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
sb.append(item);
if (i.hasNext()) {
sb.append(seperatorString);
}
}
concatenated = sb.toString();
|
| merge_dates | localworker |
ScriptString seperatorString = "\n";
if (seperator != void) {
seperatorString = seperator;
}
StringBuffer sb = new StringBuffer();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
sb.append(item);
if (i.hasNext()) {
sb.append(seperatorString);
}
}
concatenated = sb.toString();
|
| Fetch_Abstracts | workflow | |
| clean_text_3 | workflow | |
| Encode_byte_to_base64 | localworker |
Scriptimport org.apache.commons.codec.binary.Base64; base64 = new String(Base64.encodeBase64(bytes)); |
| merge_strings_2 | localworker |
ScriptString seperatorString = "\n";
if (seperator != void) {
seperatorString = seperator;
}
StringBuffer sb = new StringBuffer();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
sb.append(item);
if (i.hasNext()) {
sb.append(seperatorString);
}
}
concatenated = sb.toString();
|
| regex_3 | stringconstant |
Value\n |
| xpath_2 | stringconstant |
Value/*[local-name(.)='generateTerminologyResponse']/*[local-name(.)='return'] |
| extract_abstracts | beanshell |
ScriptString[] split = input.split("\n");
Vector nonEmpty = new Vector();
for (int i = 1; i < split.length; i++)
{
String trimmed = split[i].trim();
String[] split_2 = trimmed.split("\t");
if(split_2.length == 3)
{
nonEmpty.add(split_2[2]);
}
}
String output_search = split[0] + "\n";
String output = "";
for (int i = 0; i < nonEmpty.size(); i++)
{
output = output + (String) (nonEmpty.elementAt(i) + "\n");
} |
| merge_search_and_terms | beanshell |
ScriptString term_input = terms.trim(); String search_input = search_term.trim(); String output = ""; output = search_input + "\n" + term_input; |
| extract_Terms_2 | localworker |
Scriptimport org.dom4j.Document;
import org.dom4j.Node;
import org.dom4j.io.SAXReader;
SAXReader reader = new SAXReader(false);
reader.setIncludeInternalDTDDeclarations(false);
reader.setIncludeExternalDTDDeclarations(false);
Document document = reader.read(new StringReader(xmltext));
List nodelist = document.selectNodes(xpath);
// Process the elements in the nodelist
ArrayList outputList = new ArrayList();
ArrayList outputXmlList = new ArrayList();
String val = null;
String xmlVal = null;
for (Iterator iter = nodelist.iterator(); iter.hasNext();) {
Node element = (Node) iter.next();
xmlVal = element.asXML();
val = element.getStringValue();
if (val != null && !val.equals("")) {
outputList.add(val);
outputXmlList.add(xmlVal);
}
}
List nodelist=outputList;
List nodelistAsXML=outputXmlList; |
| merge_strings | localworker |
ScriptString seperatorString = "\n";
if (seperator != void) {
seperatorString = seperator;
}
StringBuffer sb = new StringBuffer();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
sb.append(item);
if (i.hasNext()) {
sb.append(seperatorString);
}
}
concatenated = sb.toString();
|
| remove_Nulls_5 | beanshell |
ScriptString[] split = input.split("\n");
Vector nonEmpty = new Vector();
for (int i = 0; i < split.length; i++){
if (!(split[i].equals("")))
{
nonEmpty.add(split[i].trim());
}
}
String[] non_empty = new String[nonEmpty.size()];
for (int i = 0; i < non_empty.length; i ++)
{
non_empty[i] = nonEmpty.elementAt(i);
}
String output = "";
for (int i = 0; i < non_empty.length; i++)
{
output = output + (String) (non_empty[i] + "\n");
} |
| Remove_duplicate_strings_2 | localworker |
ScriptList strippedlist = new ArrayList();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
if (strippedlist.contains(item) == false) {
strippedlist.add(item);
}
}
|
| parametersXML | xmlsplitter | |
| split_by_regex | localworker |
ScriptList split = new ArrayList();
if (!string.equals("")) {
String regexString = ",";
if (regex != void) {
regexString = regex;
}
String[] result = string.split(regexString);
for (int i = 0; i < result.length; i++) {
split.add(result[i]);
}
}
|
| generateTerminology | wsdl |
Wsdlhttp://gopubmed4.biotec.tu-dresden.de/GoPubMedTermGenerationService/services/GoPubMedTermGeneration?wsdlWsdl OperationgenerateTerminology |
| clean_text_4 | soaplab |
Endpointhttp://phoebus.cs.man.ac.uk:1977/axis/services/text_mining.clean_text |
| pubmed_database_2 | stringconstant |
Valuepubmed |
| xpath_3 | stringconstant |
Value/*[local-name(.)='eSearchResult']/*[local-name(.)='Count'] |
| count | stringconstant |
Valuecount |
| xpath_count | stringconstant |
Value/*[local-name(.)='eInfoResult']/*[local-name(.)='DbInfo']/*[local-name(.)='Count'] |
| eSearch_database | stringconstant |
Valuepubmed |
| regular_expression_2 | stringconstant |
Value\n |
| extract_terms_3 | beanshell |
ScriptString[] split = input.split("\n");
Vector nonEmpty = new Vector();
for (int i = 1; i < split.length; i++)
{
String trimmed = split[i].trim();
// if((trimmed.contains("=")) || (trimmed.contains("-")))
// {
// next;
// }
// else
// {
// String[] trimmed_array = trimmed.split("\t");
// String term = trimmed_array[0];
nonEmpty.add(trimmed);
// }
}
String output = "";
for (int i = 0; i < nonEmpty.size(); i++)
{
output = output + (String) (nonEmpty.elementAt(i) + "\n");
} |
| merge_term_count | beanshell |
ScriptString term_input = term.trim(); String count_input = count.trim(); String output = ""; output = term_input + "\t" + count_input; |
| split_extracted_terms | localworker |
ScriptList split = new ArrayList();
if (!string.equals("")) {
String regexString = ",";
if (regex != void) {
regexString = regex;
}
String[] result = string.split(regexString);
for (int i = 0; i < result.length; i++) {
split.add(result[i]);
}
}
|
| merge_pubmed_count | localworker |
ScriptString seperatorString = "\n";
if (seperator != void) {
seperatorString = seperator;
}
StringBuffer sb = new StringBuffer();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
sb.append(item);
if (i.hasNext()) {
sb.append(seperatorString);
}
}
concatenated = sb.toString();
|
| merge_extracted | localworker |
ScriptString seperatorString = "\n";
if (seperator != void) {
seperatorString = seperator;
}
StringBuffer sb = new StringBuffer();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
sb.append(item);
if (i.hasNext()) {
sb.append(seperatorString);
}
}
concatenated = sb.toString();
|
| merge_list | localworker |
ScriptString seperatorString = "\n";
if (seperator != void) {
seperatorString = seperator;
}
StringBuffer sb = new StringBuffer();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
sb.append(item);
if (i.hasNext()) {
sb.append(seperatorString);
}
}
concatenated = sb.toString();
|
| extractCount_2 | localworker |
Scriptimport org.dom4j.Document;
import org.dom4j.Node;
import org.dom4j.io.SAXReader;
SAXReader reader = new SAXReader(false);
reader.setIncludeInternalDTDDeclarations(false);
reader.setIncludeExternalDTDDeclarations(false);
Document document = reader.read(new StringReader(xmltext));
List nodelist = document.selectNodes(xpath);
// Process the elements in the nodelist
ArrayList outputList = new ArrayList();
ArrayList outputXmlList = new ArrayList();
String val = null;
String xmlVal = null;
for (Iterator iter = nodelist.iterator(); iter.hasNext();) {
Node element = (Node) iter.next();
xmlVal = element.asXML();
val = element.getStringValue();
if (val != null && !val.equals("")) {
outputList.add(val);
outputXmlList.add(xmlVal);
}
}
List nodelist=outputList;
List nodelistAsXML=outputXmlList; |
| extractCount | localworker |
Scriptimport org.dom4j.Document;
import org.dom4j.Node;
import org.dom4j.io.SAXReader;
SAXReader reader = new SAXReader(false);
reader.setIncludeInternalDTDDeclarations(false);
reader.setIncludeExternalDTDDeclarations(false);
Document document = reader.read(new StringReader(xmltext));
List nodelist = document.selectNodes(xpath);
// Process the elements in the nodelist
ArrayList outputList = new ArrayList();
ArrayList outputXmlList = new ArrayList();
String val = null;
String xmlVal = null;
for (Iterator iter = nodelist.iterator(); iter.hasNext();) {
Node element = (Node) iter.next();
xmlVal = element.asXML();
val = element.getStringValue();
if (val != null && !val.equals("")) {
outputList.add(val);
outputXmlList.add(xmlVal);
}
}
List nodelist=outputList;
List nodelistAsXML=outputXmlList; |
| parametersXML_1 | xmlsplitter | |
| run_eInfo | wsdl |
Wsdlhttp://eutils.ncbi.nlm.nih.gov/soap/v2.0/eutils.wsdlWsdl Operationrun_eInfo |
| run_eSearch_2 | wsdl |
Wsdlhttp://eutils.ncbi.nlm.nih.gov/soap/v2.0/eutils.wsdlWsdl Operationrun_eSearch |
| run_eSearch_request | xmlsplitter | |
| GENE_RankPhenotypeTerms | workflow | |
| max_return_gene_pathway | stringconstant |
Value500 |
| maxNumberOfTerms_value | stringconstant |
Value20000 |
| split_search_terms_2 | localworker |
ScriptList split = new ArrayList();
if (!string.equals("")) {
String regexString = ",";
if (regex != void) {
regexString = regex;
}
String[] result = string.split(regexString);
for (int i = 0; i < result.length; i++) {
split.add(result[i]);
}
}
|
| pathway_and_abstract | beanshell |
ScriptString[] split = abstracts.split("\n");
String pathway_name = pathway;
Vector nonEmpty = new Vector();
for (int i = 0; i < split.length; i++)
{
String trimmed = split[i].trim();
nonEmpty.add(trimmed);
}
String output = ">> " + pathway_name + "\n";
for (int i = 0; i < nonEmpty.size(); i++)
{
output = output + (String) (nonEmpty.elementAt(i) + "\n");
} |
| remove_nulls_3 | beanshell |
ScriptString[] split = input.split("\n");
Vector nonEmpty = new Vector();
for (int i = 0; i < split.length; i++){
if (!(split[i].equals("")))
{
nonEmpty.add(split[i].trim());
}
}
String[] non_empty = new String[nonEmpty.size()];
for (int i = 0; i < non_empty.length; i ++)
{
non_empty[i] = nonEmpty.elementAt(i);
}
String output = "";
for (int i = 0; i < non_empty.length; i++)
{
output = output + (String) (non_empty[i] + "\n");
} |
| merge_outputs_2_2 | localworker |
ScriptString seperatorString = "\n";
if (seperator != void) {
seperatorString = seperator;
}
StringBuffer sb = new StringBuffer();
for (Iterator i = stringlist.iterator(); i.hasNext();) {
String item = (String) i.next();
sb.append(item);
if (i.hasNext()) {
sb.append(seperatorString);
}
}
concatenated = sb.toString();
|
| regex_2 | stringconstant |
Value\n |
| extract_terms | beanshell |
ScriptString[] split = input.split("\n");
Vector nonEmpty = new Vector();
for (int i = 0; i < split.length; i++)
{
String mytext = split[i].substring(split[i].indexOf(" "), split[i].lastIndexOf(" - "));
nonEmpty.add(mytext);
}
String output = "";
for (int i = 0; i < nonEmpty.size(); i++)
{
output = output + (String) (nonEmpty.elementAt(i) + "\n");
} |
| add_MeSH_to_string | beanshell |
ScriptString[] split = input.split("\n");
Vector nonEmpty = new Vector();
for (int i = 0; i < split.length; i++)
{
String trimmed = split[i].trim();
nonEmpty.add(trimmed);
}
String output = "";
for (int i = 0; i < nonEmpty.size(); i++)
{
output = output + (String) (nonEmpty.elementAt(i) + " AND \"Metabolic Networks and Pathways\"[MeSH Terms]" + "\n");
} |
| Search_PubMed_2 | workflow | |
| clean_text_2 | workflow | |
| PATHWAY_RankPhenotypeTerms | workflow |
Beanshells (22)
| Name | Description | Inputs | Outputs |
|---|---|---|---|
| remove_nulls | input | output | |
| gene_and_abstract |
pathway abstracts |
output | |
| remove_Nulls_2 | input | output | |
| remove_Nulls_4 | input | output | |
| concat_abstract_ids |
id abstract_text date_text |
output | |
| merge_phenotype_abstracts |
phenotype abstracts |
output | |
| extract_abstracts | input |
output output_search |
|
| merge_search_and_terms |
terms search_term |
output | |
| remove_Nulls_5 | input | output | |
| extract_terms_3 | input | output | |
| merge_term_count |
term count |
output | |
| pathway_and_abstract |
pathway abstracts |
output | |
| remove_nulls_3 | input | output | |
| extract_terms | input | output | |
| add_MeSH_to_string | input | output | |
| format_rankings | ranked_terms | title_term_rankings | |
| remove_Nulls | input | output | |
| stringToBytes | string | bytes | |
| stringToBytes | string | bytes | |
| concat_abstract_ids |
id abstract_text date_text |
output | |
| concat_abstract_ids |
id abstract_text date_text |
output | |
| stringToBytes | string | bytes |
Outputs (10)
| Name | Description |
|---|---|
| gene_abstracts | |
| phenotype_abstracts | |
| phenotype_terms | |
| phenotype_term_counts | |
| pubmed_abstract_number | |
| gene_cosine | |
| gene_term_enrichment_scores | |
| pathway_abstracts | |
| pathway_cosine_vector_scores | |
| pathway_concept_rankings |
Datalinks (104)
| Source | Sink |
|---|---|
| gene_and_abstract:output | remove_nulls:input |
| Search_PubMed:concat_data | gene_and_abstract:abstracts |
| split_search_terms:split | gene_and_abstract:pathway |
| regex:value | split_search_terms:regex |
| remove_Nulls_2:output | split_search_terms:string |
| clean_text:cleaned_text | merge_outputs_2:stringlist |
| split_search_terms:split | Search_PubMed:search_term |
| min_date:value | Search_PubMed:min_date |
| max_date:value | Search_PubMed:max_date |
| max_return_gene_pathway:value | Search_PubMed:max_return |
| remove_nulls:output | clean_text:input |
| split_gene_names:split | Remove_duplicate_genes:stringlist |
| gene_names | split_gene_names:string |
| regular_expression:value | split_gene_names:regex |
| Merge_string_list_to_string:concatenated | remove_Nulls_2:input |
| Remove_duplicate_genes:strippedlist | Merge_string_list_to_string:stringlist |
| parametersXML_eSearch:output | run_eSearch:parameters |
| xpath:value | extractPMID:xpath |
| run_eSearch:parameters | extractPMID:xml-text |
| merge_phenotype_abstracts:output | remove_Nulls_4:input |
| extractPMID:nodelist | concat_abstract_ids:id |
| merge_abstracts:concatenated | concat_abstract_ids:abstract_text |
| merge_dates:concatenated | concat_abstract_ids:date_text |
| merge_abstract_ids:concatenated | merge_phenotype_abstracts:abstracts |
| Phenotype_search_term | merge_phenotype_abstracts:phenotype |
| Fetch_Abstracts:abstracts | merge_abstracts:stringlist |
| max_return_phenotype:value | parametersXML_eSearch:RetMax |
| pubmed_database:value | parametersXML_eSearch:db |
| max_date:value | parametersXML_eSearch:maxdate |
| min_date:value | parametersXML_eSearch:mindate |
| Phenotype_search_term | parametersXML_eSearch:term |
| concat_abstract_ids:output | merge_abstract_ids:stringlist |
| Fetch_Abstracts:pubmed_dates | merge_dates:stringlist |
| extractPMID:nodelist | Fetch_Abstracts:pubmed_ids |
| remove_Nulls_4:output | clean_text_3:input |
| clean_text_3:cleaned_text | Encode_byte_to_base64:bytes |
| merge_strings:concatenated | merge_strings_2:stringlist |
| clean_text_4:output | extract_abstracts:input |
| merge_strings_2:concatenated | merge_search_and_terms:terms |
| extract_abstracts:output_search | merge_search_and_terms:search_term |
| generateTerminology:parameters | extract_Terms_2:xml-text |
| xpath_2:value | extract_Terms_2:xpath |
| Remove_duplicate_strings_2:strippedlist | merge_strings:stringlist |
| merge_search_and_terms:output | remove_Nulls_5:input |
| extract_Terms_2:nodelist | Remove_duplicate_strings_2:stringlist |
| split_by_regex:split | parametersXML:texts |
| maxNumberOfTerms_value:value | parametersXML:maxNumberOfTerms |
| regex_3:value | split_by_regex:regex |
| extract_abstracts:output | split_by_regex:string |
| parametersXML:output | generateTerminology:parameters |
| Encode_byte_to_base64:base64 | clean_text_4:file_direct_data |
| remove_Nulls_5:output | extract_terms_3:input |
| split_extracted_terms:split | merge_term_count:term |
| merge_extracted:concatenated | merge_term_count:count |
| extract_terms_3:output | split_extracted_terms:string |
| regular_expression_2:value | split_extracted_terms:regex |
| extractCount:nodelist | merge_pubmed_count:stringlist |
| extractCount_2:nodelist | merge_extracted:stringlist |
| merge_term_count:output | merge_list:stringlist |
| xpath_3:value | extractCount_2:xpath |
| run_eSearch_2:result | extractCount_2:xml-text |
| xpath_count:value | extractCount:xpath |
| run_eInfo:result | extractCount:xml-text |
| pubmed_database_2:value | parametersXML_1:db |
| parametersXML_1:output | run_eInfo:request |
| run_eSearch_request:output | run_eSearch_2:request |
| eSearch_database:value | run_eSearch_request:db |
| count:value | run_eSearch_request:rettype |
| split_extracted_terms:split | run_eSearch_request:term |
| min_date:value | run_eSearch_request:mindate |
| max_date:value | run_eSearch_request:maxdate |
| merge_pubmed_count:concatenated | GENE_RankPhenotypeTerms:pubmed_abstract_number |
| merge_list:concatenated | GENE_RankPhenotypeTerms:phenotype_term_counts |
| merge_outputs_2:concatenated | GENE_RankPhenotypeTerms:query_abstracts |
| clean_text_3:cleaned_text | GENE_RankPhenotypeTerms:phenotype_abstracts |
| remove_Nulls_5:output | GENE_RankPhenotypeTerms:phenotype_terms |
| add_MeSH_to_string:output | split_search_terms_2:string |
| regex_2:value | split_search_terms_2:regex |
| Search_PubMed_2:concat_data | pathway_and_abstract:abstracts |
| split_search_terms_2:split | pathway_and_abstract:pathway |
| pathway_and_abstract:output | remove_nulls_3:input |
| clean_text_2:cleaned_text | merge_outputs_2_2:stringlist |
| pathway_descriptions | extract_terms:input |
| extract_terms:output | add_MeSH_to_string:input |
| split_search_terms_2:split | Search_PubMed_2:Pathway_search_term |
| min_date:value | Search_PubMed_2:min_date |
| max_date:value | Search_PubMed_2:max_date |
| max_return_gene_pathway:value | Search_PubMed_2:max_return |
| remove_nulls_3:output | clean_text_2:input |
| merge_outputs_2_2:concatenated | PATHWAY_RankPhenotypeTerms:query_abstracts |
| merge_pubmed_count:concatenated | PATHWAY_RankPhenotypeTerms:pubmed_abstract_number |
| merge_list:concatenated | PATHWAY_RankPhenotypeTerms:phenotype_term_counts |
| remove_Nulls_5:output | PATHWAY_RankPhenotypeTerms:phenotype_terms |
| clean_text_3:cleaned_text | PATHWAY_RankPhenotypeTerms:phenotype_abstracts |
| merge_outputs_2:concatenated | gene_abstracts |
| clean_text_3:cleaned_text | phenotype_abstracts |
| remove_Nulls_5:output | phenotype_terms |
| merge_list:concatenated | phenotype_term_counts |
| merge_pubmed_count:concatenated | pubmed_abstract_number |
| GENE_RankPhenotypeTerms:cosine_vector_scores | gene_cosine |
| GENE_RankPhenotypeTerms:concept_rankings | gene_term_enrichment_scores |
| merge_outputs_2_2:concatenated | pathway_abstracts |
| PATHWAY_RankPhenotypeTerms:cosine_vector_scores | pathway_cosine_vector_scores |
| PATHWAY_RankPhenotypeTerms:concept_rankings | pathway_concept_rankings |
Coordinations (0)
None
Workflow Type
Version 2
(of 4)
(People/Groups)
(Workflows/Files)
- abstracts
- |
- cosine vector space
- |
- data-driven
- |
- disease
- |
- enrichment
- |
- entity recognition
- |
- evidence
- |
- kegg
- |
- Kegg Pathways
- |
- literature
- |
- loci
- |
- locus
- |
- medline
- |
- microarray
- |
- mining
- |
- pathway
- |
- pathway-driven
- |
- pathways
- |
- phenotype
- |
- pubmed
- |
- qtl
- |
- ranking
- |
- re-use
- |
- term
- |
- term extraction
- |
- terms
- |
- text
- |
- text mining
- |
- text mining; term extraction; entity recognition
- |
- trichuris muris
- abstracts
- |
- cosine vector space
- |
- data-driven
- |
- disease
- |
- enrichment
- |
- entity recognition
- |
- evidence
- |
- kegg
- |
- Kegg Pathways
- |
- literature
- |
- loci
- |
- locus
- |
- medline
- |
- microarray
- |
- mining
- |
- pathway
- |
- pathway-driven
- |
- pathways
- |
- phenotype
- |
- pubmed
- |
- qtl
- |
- ranking
- |
- re-use
- |
- term
- |
- term extraction
- |
- terms
- |
- text
- |
- text mining
- |
- text mining; term extraction; entity recognition
- |
- trichuris muris
Log in to add Tags
Shared with Groups (0)
None
Statistics
Version History
In chronological order:
-
Created by Paul Fisher on Tuesday 08 February 2011 13:04:06 (UTC)
-
Created by Paul Fisher on Tuesday 08 February 2011 13:06:21 (UTC)
Last edited by Paul Fisher on Tuesday 08 February 2011 13:07:08 (UTC)
Revision comment:Created output ports for pathway cosine and concept rankings
-
Created by Paul Fisher on Tuesday 08 February 2011 13:10:57 (UTC)
Last edited by Paul Fisher on Tuesday 08 February 2011 13:12:01 (UTC)
Revision comment:Description of workflow updated - in Taverna
-
Created by Paul Fisher on Thursday 10 February 2011 16:00:56 (UTC)
Last edited by Paul Fisher on Thursday 10 February 2011 16:01:41 (UTC)
Revision comment:changed the term extraction service to point to new URL
Reviews
(0)
Other workflows that use similar services
(35)
Only the first 2 workflows that use similar services are shown. View all workflows that use these services.
Pathway and Gene to Pubmed
(2)
Created: 2011-02-10 | Last updated: 2011-02-18
Credits:
Paul Fisher
Attributions:
Cosine vector space
Extract Scientific Terms
Rank Phenotype Terms
Cosine vector space
Rank Phenotype Terms
Pathway to Pubmed
Extract Scientific Terms
Gene to Pubmed
PubMed Search
(1)
Created: 2011-02-03 | Last updated: 2011-02-03
Credits:
Paul Fisher
No comments yet
Log in to make a comment