diff --git a/annotation/src/main/java/lcsb/mapviewer/annotation/services/DrugbankHTMLParser.java b/annotation/src/main/java/lcsb/mapviewer/annotation/services/DrugbankHTMLParser.java
index de70f2f49512d700cc2a4348d59833f1168a960d..8f85a7d9573e011559496bfdb434ee0578a33129 100644
--- a/annotation/src/main/java/lcsb/mapviewer/annotation/services/DrugbankHTMLParser.java
+++ b/annotation/src/main/java/lcsb/mapviewer/annotation/services/DrugbankHTMLParser.java
@@ -39,723 +39,733 @@ import lcsb.mapviewer.model.map.MiriamType;
*/
public class DrugbankHTMLParser extends DrugAnnotation implements IExternalService {
- /**
- * Maximum available length of the pubmed identifiers.
- */
- private static final int MAX_PUBMED_IDENTIFIER_LENGTH = 9;
-
- /**
- * Prefix used for storing data about drug with name key value.
- */
- static final String DRUG_NAME_PREFIX = "drug:";
-
- /**
- * Service used for annotation of proteins using {@link MiriamType#UNIPROT
- * uniprot}.
- */
- @Autowired
- private UniprotAnnotator uniprotAnnotator;
-
- /**
- * Pattern that extract information about drug name when accessing page about
- * target.
- */
- private final Pattern drugNamePattern = Pattern.compile("(?<=<td><strong>)([\\s\\S]*?)(?=</strong></td>)");
-
- /**
- * Default class logger.
- */
- private Logger logger = Logger.getLogger(DrugbankHTMLParser.class);
-
- /**
- * Url used for finding drug by drug name.
- */
- static final String URLB = "https://www.drugbank.ca/search?searcher=drugs&utf8=%E2%9C%93&button=&filter=false&query=";
-
- /**
- * Url used for retrieving general information about drug.
- */
- static final String URLDRUG = "https://www.drugbank.ca/drugs/";
-
- /**
- * Homepage of drugbank.
- */
- static final String URL = "https://www.drugbank.ca/";
-
- /**
- * Url used for accesing information about target synonyms.
- */
- static final String URLPEP = "https://www.drugbank.ca/biodb/polypeptides/";
-
- /**
- * Url that allows to search for dugs using target hgnc name.
- */
- static final String URL_TARGETS = "https://www.drugbank.ca/search?utf8=%E2%9C%93&searcher=targets&query=";
-
- /**
- * Url that helps finding drug name for given target identifier.
- */
- static final String URL_TARGET_DETAIL = "https://www.drugbank.ca/biodb/bio_entities/";
-
- /**
- * Pattern used to get information about {@link Drug#bloodBrainBarrier blood
- * brain barrier}.
- */
- private Pattern bloodBrainBarrierPattern = Pattern.compile("(?<=<td>)([\\s\\S]*?)(?=</td>)");
-
- /**
- * Pattern that extract information about target identifier when searching for
- * targets with given set of hgnc names.
- */
- private Pattern targetPattern = Pattern.compile("(?<=\"/biodb/bio_entities/)([\\s\\S]*?)(?=\")");
-
- /**
- * Default constructor.
- */
- public DrugbankHTMLParser() {
- super(DrugbankHTMLParser.class);
- }
-
- @Override
- public String refreshCacheQuery(Object query) throws SourceNotAvailable {
- String result = null;
- try {
- if (query instanceof String) {
- String name = (String) query;
- if (name.startsWith(DRUG_NAME_PREFIX)) {
- name = name.substring(DRUG_NAME_PREFIX.length());
- result = getDrugSerializer().objectToString(findDrug(name));
- } else if (name.startsWith("http")) {
- result = getWebPageContent(name);
- } else {
- throw new InvalidArgumentException("Don't know what to do with string \"" + query + "\"");
- }
- } else {
- throw new InvalidArgumentException("Don't know what to do with class: " + query.getClass());
- }
- } catch (DrugSearchException e) {
- throw new SourceNotAvailable(e);
- } catch (IOException e) {
- throw new SourceNotAvailable(e);
- }
- return result;
- }
-
- /**
- * Finds the drug identifier in the webpage with information about drug.
- *
- * @param webpageContent
- * content of the webpage with information about drug
- * @return drugbank identifier
- */
- private String findIdInText(String webpageContent) {
- int i = 0, j = 0;
- i = webpageContent.indexOf("href=\"/drugs/");
- if (i == -1) {
- return null;
- }
- i = i + "href=\"/drugs/".length();
- j = webpageContent.indexOf('"', i);
- return webpageContent.substring(i, j);
- }
-
- /**
- * Finds the drug name in the webpage with information about drug.
- *
- * @param webpageContent
- * content of the webpage with information about drug
- * @return name of the drug
- */
- private String findNameInText(String webpageContent) {
- int i = 0, j = 0;
- i = webpageContent.indexOf("a href=\"/drugs/");
- i = webpageContent.indexOf(">", i);
- i = i + 1;
- j = webpageContent.indexOf('<', i);
- return webpageContent.substring(i, j);
- }
-
- /**
- * Finds the description of the drug on the conetnet of the webpage with
- * information about drug.
- *
- * @param webpageContent
- * content of the webpage with information about drug
- * @return description of the drug
- */
- String getDescriptionForDrug(String webpageContent) {
- int startIndex = 0, endIndex = 0;
- startIndex = webpageContent.indexOf("<th>Description</th><td>");
- if (startIndex == -1) {
- return null;
- }
- startIndex = startIndex + "<th>Description</th><td>".length();
- endIndex = webpageContent.indexOf("</td", startIndex);
- String description = webpageContent.substring(startIndex, endIndex);
- // find special html characters
- description = StringEscapeUtils.unescapeHtml4(description);
- description = cleanHtml(description);
- if (description.equalsIgnoreCase("Not Available")) {
- description = null;
- }
-
- return description;
- }
-
- /**
- * Returns list of the drug brand names from the webpage content.
- *
- * @param page
- * content of the webpage with information about drug
- * @return list of the drug brand names
- */
- private List<String> getTargetBrands(String page) {
- List<String> result = new ArrayList<String>();
- Pattern brandNamesParagraphPattern = Pattern.compile("(?<=<th>International Brands</th>)([\\s\\S]*?)(?=<th>Brand mixtures</th>)");
- Matcher matcher = brandNamesParagraphPattern.matcher(page);
-
- if (matcher.find()) {
- String paragraph = matcher.group(1);
- Pattern listElementPattern = Pattern.compile("(?<=<tr><td>)([\\s\\S]*?)(?=</td>)");
- Matcher elementMatcher = listElementPattern.matcher(paragraph);
- while (elementMatcher.find()) {
- result.add(elementMatcher.group(1));
- }
- }
- return result;
- }
-
- /**
- * Returns list of drug synonyms from drugbank database.
- *
- * @param page
- * webpage content with drug information
- * @return list of drug synonyms
- */
- private List<String> getDrugSynonyms(String page) {
- List<String> ans = new ArrayList<String>();
-
- int i, j, end;
- Boolean finding = true;
- i = page.indexOf("Synonyms");
- end = page.indexOf("Prescription Products", i);
- while (finding) {
- i = page.indexOf("<tr><td>", i);
- if (i == -1 || i > end) {
- finding = false;
- continue;
- }
- i = i + "<tr><td>".length();
- j = page.indexOf("</td>", i);
- String synonym = StringEscapeUtils.unescapeHtml4(page.substring(i, j));
- ans.add(cleanHtml(synonym));
- }
-
- return ans;
- }
-
- /**
- * Returns references from reference string (obtained from drugbank homepage)
- * .
- *
- * @param descriptionString
- * string containing references obtained from drugbank webpage
- * @return list of references obtained from drugbank {@link String}
- */
- List<MiriamData> getPubmedFromRef(String descriptionString) {
- List<MiriamData> result = new ArrayList<>();
- int currentStartIndex = 0;
- while (true) {
- currentStartIndex = descriptionString.indexOf("/pubmed/", currentStartIndex);
- if (currentStartIndex == -1) {
- break;
- }
- currentStartIndex = currentStartIndex + "/pubmed/".length();
- int endIndex = descriptionString.indexOf('"', currentStartIndex);
- String identifier = descriptionString.substring(currentStartIndex, endIndex);
- String correctedIdentifier = identifier.replaceAll("[^\\d]", "");
- if (!identifier.equals(correctedIdentifier)) {
- if (correctedIdentifier.length() > MAX_PUBMED_IDENTIFIER_LENGTH) {
- correctedIdentifier = correctedIdentifier.substring(0, MAX_PUBMED_IDENTIFIER_LENGTH);
- }
- logger.warn("Problematic pubmed identfier: \"" + identifier + "\". Trying fixing with the result: " + correctedIdentifier);
- }
- if (correctedIdentifier.equals("")) {
- break;
- }
- result.add(new MiriamData(MiriamRelationType.BQ_BIOL_IS_DESCRIBED_BY, MiriamType.PUBMED, correctedIdentifier));
- }
- return result;
- }
-
- /**
- * Returns targets parsed from page content.
- *
- * @param page
- * webpage content from which data are extracted
- * @throws DrugSearchException
- * thrown when there are problems with connection to DrugBank
- * database
- * @return list of drug {@link Target} parsed from input string
- */
- List<Target> getTargetsForDrug(String page) throws DrugSearchException {
- List<Target> result = new ArrayList<>();
- try {
- int pageStart;
- Target target = new Target();
- target.setType(TargetType.SINGLE_PROTEIN);
-
- pageStart = page.indexOf("<div class=\"target well well");
-
- int end = page.indexOf("<div class=\"enzyme well well");
- if (end < 0) {
- end = page.indexOf("<div class=\"carrier well well");
- if (end < 0) {
- end = page.indexOf("<div class=\"transporter well well");
-
- if (end < 0) {
- end = page.indexOf("<tr id=\"comments\">");
- if (end < 0) {
- end = page.length() - 1;
- }
- }
- }
- }
-
- pageStart = page.indexOf("Details</a></div>", pageStart);
- while (pageStart > 0 && pageStart < end) {
- int targetStart = page.indexOf("</div><strong>", pageStart);
- int nextTargetStart = page.indexOf("</div><strong>", targetStart + 1);
- if (nextTargetStart < 0) {
- nextTargetStart = end;
- }
-
- target = parseTarget(page.substring(targetStart, nextTargetStart));
- if (target != null) {
- result.add(target);
- }
- pageStart = nextTargetStart;
-
- }
- } catch (TaxonomySearchException e) {
- throw new DrugSearchException("Problem with finidng information about organism", e);
- } catch (UniprotSearchException e) {
- throw new DrugSearchException("Problem with finidng information about protein", e);
- }
- return result;
- }
-
- /**
- * Parse html info about target into {@link Target} structure.
- *
- * @param htmlPage
- * string with html content
- * @return {@link Target} for given html content
- * @throws UniprotSearchException
- * thrown when there is a problem with accessing uniprot db
- * @throws TaxonomySearchException
- * thrown when there is a problem with accessing taxonomy db
- */
- protected Target parseTarget(String htmlPage) throws UniprotSearchException, TaxonomySearchException {
- int kindIndex = htmlPage.indexOf("<dt>Kind</dt><dd>");
- kindIndex += "<dt>Kind</dt><dd>".length();
- int endKindIndex = htmlPage.indexOf("</dd>");
- String type = "";
- if (kindIndex > 0 && endKindIndex > kindIndex) {
- type = htmlPage.substring(kindIndex, endKindIndex);
- }
- if (type.trim().equalsIgnoreCase("Protein")) {
- int uniprotIdStart = htmlPage.indexOf("/biodb/polypeptides/") + "/biodb/polypeptides/".length();
- Target result = new Target();
- result.setType(TargetType.SINGLE_PROTEIN);
-
- // Getting ID && Name
- int uniprotIdEnd = htmlPage.indexOf('"', uniprotIdStart);
- String uniprotId = htmlPage.substring(uniprotIdStart, uniprotIdEnd);
- MiriamData uniprotTarget = new MiriamData(MiriamType.UNIPROT, uniprotId);
- MiriamData hgncTarget = uniprotAnnotator.uniProtToHgnc(uniprotTarget);
- if (hgncTarget != null) {
- result.addGene(hgncTarget);
- } else {
- result.addGene(uniprotTarget);
- }
-
- int nameStart = uniprotIdEnd + 2;
- int nameEnd = htmlPage.indexOf("</", uniprotIdStart);
- String name = StringEscapeUtils.unescapeHtml4(htmlPage.substring(nameStart, nameEnd));
- result.setName(name);
-
- // Getting Organism
- int organismStart = htmlPage.indexOf("Organism</dt><dd>", nameEnd) + "Organism</dt><dd>".length();
- int organismEnd = htmlPage.indexOf("</dd>", organismStart);
- result.setOrganism(getTaxonomyBackend().getByName(htmlPage.substring(organismStart, organismEnd)));
-
- // Getting References
- int referencesStart = htmlPage.indexOf("<strong>References</strong>", organismEnd);
- if (referencesStart > 0) {
- int referencesEnd = Math.min(htmlPage.indexOf("Details</a></div>", referencesStart), htmlPage.length());
- if (referencesEnd < 0) {
- referencesEnd = htmlPage.length();
- }
- result.addReferences(getPubmedFromRef(htmlPage.substring(referencesStart, referencesEnd)));
- }
- return result;
- } else {
- logger.warn("Unknown target type: " + type + ". Skipping.");
- return null;
- }
- }
-
- /**
- * Finds information about drug in drugbank database.
- *
- * @param name
- * name of the dug that we are looking for
- * @throws DrugSearchException
- * thrown when there are problems with connection to DrugBank
- * database
- * @return drug with the information abtained from drugbank or
- * <code>null</code> if such data couldn't be found
- */
- private Drug findMoreInformation(String name) throws DrugSearchException {
- Drug result = null;
- try {
- name = URLEncoder.encode(name, "UTF-8");
-
- String accessUrl = URLB + name;
-
- String content = getWebPageContent(accessUrl);
-
- String[] lines = content.split("\n");
- for (String inputLine : lines) {
- String tmp = findIdInText(inputLine);
- if (tmp != null) {
- result = new Drug();
- result.addSource(new MiriamData(MiriamRelationType.BQ_BIOL_IS_DESCRIBED_BY, MiriamType.DRUGBANK, tmp));
- result.setName(super.cleanHtml(findNameInText(inputLine)));
- break;
- }
- }
-
- if (result != null) {
-
- accessUrl = URLDRUG + result.getSources().get(0).getResource();
-
- String page = getWebPageContent(accessUrl);
-
- result.setDescription(getDescriptionForDrug(page));
-
- result.setSynonyms(getDrugSynonyms(page));
-
- // Getting drug brand names
- result.setBrandNames(getTargetBrands(page));
-
- result.addTargets(getTargetsForDrug(page));
-
- result.setBloodBrainBarrier(getBloodBrainBarrier(page));
-
- result.setApproved(getApproved(page));
-
- if (!nameMatch(result, name)) {
- result = null;
- }
- }
- } catch (IOException e) {
- throw new DrugSearchException(e);
- }
- return result;
- }
-
- /**
- * Check if drug data mateches with the search name.
- *
- * @param drug
- * drug to be checked
- * @param name
- * name of the drug that we were looking for
- * @return true if if drug data matches with the search name
- */
- private boolean nameMatch(Drug drug, String name) {
- Set<String> foundNames = new HashSet<>();
- foundNames.add(drug.getName());
- foundNames.addAll(drug.getSynonyms());
- foundNames.addAll(drug.getBrandNames());
- String lowerCaseName;
- try {
- lowerCaseName = java.net.URLDecoder.decode(name, "UTF-8").toLowerCase().replaceAll("[^A-Za-z0-9]", "");
- } catch (UnsupportedEncodingException e) {
- lowerCaseName = name.toLowerCase().replaceAll("[^A-Za-z0-9]", "");
- }
- for (String string : foundNames) {
- String query = string.toLowerCase().replaceAll("[^A-Za-z0-9]", "");
- if (query.contains(lowerCaseName)) {
- return true;
- }
- }
- return false;
- }
-
- /**
- * Finds blood brain barrier info about drug in the webpage content.
- *
- * @param page
- * webpage content used for parsing
- *
- * @return status of blood brain barrier
- */
- String getBloodBrainBarrier(String page) {
- int index = page.indexOf("<td>Blood Brain Barrier</td>");
- if (index <= 0) {
- return "N/A";
- }
-
- Matcher matcher = bloodBrainBarrierPattern.matcher(page.substring(index));
-
- matcher.find();
- if (!matcher.find()) {
- logger.warn("Invalid html for Blood Brain Barrier...");
- return "N/A";
- }
- String match = matcher.group(1);
- if (match.contains("+")) {
- return "YES";
- } else if (match.contains("-")) {
- return "NO";
- } else {
- logger.warn("Unknown Blood Brain Barrier status: " + match);
- return "N/A";
- }
- }
-
- /**
- * Finds if drug is approved.
- *
- * @param page
- * webpage content used for parsing
- *
- * @return <code>true</code> if drug is approved
- */
- private Boolean getApproved(String page) {
- int index = page.indexOf("<th>Groups</th>");
- if (index <= 0) {
- return null;
- }
-
- int end = page.indexOf("<th>", index + 1);
-
- if (end < index) {
- end = page.length();
- }
- String match = page.substring(index, end).toLowerCase();
- if (match.contains("approved")) {
- if (match.contains("investigational") || match.contains("withdrawn") || match.contains("experimental")) {
- logger.warn("Contradicting info about approved status: " + match);
- return null;
- }
- return true;
- } else if (match.contains("investigational") || match.contains("withdrawn") || match.contains("experimental")) {
- return false;
- } else {
- logger.warn("Unknown approved status: " + match);
- return null;
- }
- }
-
- @Override
- public Drug findDrug(String drugName) throws DrugSearchException {
- String query = DRUG_NAME_PREFIX + drugName;
- Drug drug = null;
- try {
- drug = getDrugSerializer().xmlToObject(getCacheNode(query));
- } catch (SerializationException e) {
- logger.error("Problem with deserializing element by query: " + query);
- }
- if (drug != null) {
- return drug;
- }
-
- drug = findMoreInformation(drugName);
-
- try {
- setCacheValue(query, getDrugSerializer().objectToString(drug));
- } catch (SerializationException e) {
- logger.error("Problem with serializing element ");
- }
-
- return drug;
- }
-
- @Override
- public ExternalServiceStatus getServiceStatus() {
- ExternalServiceStatus status = new ExternalServiceStatus("DrugBank", URL);
-
- GeneralCacheInterface cacheCopy = getCache();
- this.setCache(null);
-
- try {
- Drug drug = findDrug("Amantadine");
- status.setStatus(ExternalServiceStatusType.OK);
- if (drug == null) {
- status.setStatus(ExternalServiceStatusType.CHANGED);
- }
- } catch (Exception e) {
- logger.error("DrugBank is down", e);
- status.setStatus(ExternalServiceStatusType.DOWN);
- }
- this.setCache(cacheCopy);
- return status;
- }
-
- @Override
- public List<Drug> getDrugListByTarget(MiriamData targetMiriamData, Collection<MiriamData> organisms) throws DrugSearchException {
- List<Drug> result = new ArrayList<>();
- if (targetMiriamData == null) {
- return result;
- }
- if (!(MiriamType.HGNC_SYMBOL.equals(targetMiriamData.getDataType()))) {
- throw new InvalidArgumentException("Only " + MiriamType.HGNC_SYMBOL + " type is accepted");
- }
- String url = URL_TARGETS + targetMiriamData.getResource();
-
- try {
- String page = getWebPageContent(url);
-
- Set<String> drugNames = new HashSet<>();
-
- Matcher matcher = targetPattern.matcher(page);
- while (matcher.find()) {
- String drugbankTargetId = matcher.group(0);
- drugNames.addAll(getDrugNamesForTarget(new MiriamData(MiriamType.DRUGBANK_TARGET_V4, drugbankTargetId), targetMiriamData, organisms));
- }
- for (String string : drugNames) {
- Drug drug = findDrug(string);
- if (drug == null) {
- logger.warn("Cannot find drug that should be there: " + string);
- } else {
- boolean targets = false;
- for (Target target : drug.getTargets()) {
- for (MiriamData gene : target.getGenes()) {
- if (gene.equals(targetMiriamData)) {
- targets = true;
- }
- }
- }
- if (targets) {
- result.add(drug);
- } else {
- logger.debug("Skipping drug that doesn't target required target. Drug name: " + drug.getName() + "; target: " + targetMiriamData);
- }
- }
- }
-
- return result;
- } catch (IOException e) {
- throw new DrugSearchException("Cannot access drug database", e);
- }
- }
-
- /**
- * Returns list of drugs that target element (target) identified be drugbank
- * identifier.
- *
- * @param drugbankTarget
- * {@link MiriamType#DRUGBANK_TARGET_V4 identifier} of the target
- * @param hgncTarget
- * identifier of the target using {@link MiriamType#HGNC_SYMBOL},
- * used for verification if the target really points to proper
- * protein/gene
- * @param organisms
- * list of organisms to which results should be limited (when no
- * organisms defined filtering will be turned off)
- * @return list of drugs that target this target
- * @throws DrugSearchException
- * thrown when there are problems with connection to DrugBank
- * database
- */
- private Set<String> getDrugNamesForTarget(MiriamData drugbankTarget, MiriamData hgncTarget, Collection<MiriamData> organisms) throws DrugSearchException {
- if (!MiriamType.DRUGBANK_TARGET_V4.equals(drugbankTarget.getDataType())) {
- throw new InvalidArgumentException("drugbankTarget must be of type: " + MiriamType.DRUGBANK_TARGET_V4);
- }
-
- try {
- Set<String> drugNames = new HashSet<>();
- String url = URL_TARGET_DETAIL + drugbankTarget.getResource();
-
- String page = getWebPageContent(url);
-
- int idPosition = page.indexOf("<th>DrugBank ID</th>");
- if (idPosition < 0) {
- throw new DrugSearchException("Problematic web page for target: " + drugbankTarget + "(" + hgncTarget + ")");
- }
-
- int protienLinkPosition = page.indexOf("/polypeptides/");
- // sometimes there might not be an element
- if (protienLinkPosition >= 0) {
- protienLinkPosition = protienLinkPosition + "/polypeptides/".length(); // 20;
- int j = page.indexOf('"', protienLinkPosition);
- String uniprotId = page.substring(protienLinkPosition, j);
- MiriamData uniprotMiriam = new MiriamData(MiriamType.UNIPROT, uniprotId);
- MiriamData hgncMiriam = uniprotAnnotator.uniProtToHgnc(uniprotMiriam);
- if (hgncMiriam == null || !hgncMiriam.equals(hgncTarget)) {
- logger.debug("Invalid target found. Expected " + hgncTarget + ", but found: " + hgncMiriam + " (" + uniprotMiriam + ")");
- return drugNames;
- }
-
- } else {
- logger.warn("Invalid target found. No protein data available.");
- return drugNames;
- }
-
- int organismPosition = page.indexOf("Organism<");
- if (organismPosition >= 0) {
- int organismStart = page.indexOf("<td>", organismPosition) + "<td>".length();
- int organismEnd = page.indexOf("<", organismStart + 1);
- String organismName = page.substring(organismStart, organismEnd);
- if (!organismMatch(organismName, organisms)) {
- logger.debug("Organism doesn't match. Found" + organismName + ". Expected: " + organisms);
- return drugNames;
- }
- }
-
- Matcher matcher = drugNamePattern.matcher(page.substring(idPosition));
-
- while (matcher.find()) {
- drugNames.add(matcher.group(1));
- }
-
- return drugNames;
- } catch (IOException e) {
- throw new DrugSearchException("Problem with accessing drugbank db", e);
- } catch (UniprotSearchException e) {
- throw new DrugSearchException("Problem with uniprot annotations", e);
- }
- }
-
- /**
- * @return the uniprotAnnotator
- * @see #uniprotAnnotator
- */
- public UniprotAnnotator getUniprotAnnotator() {
- return uniprotAnnotator;
- }
-
- /**
- * @param uniprotAnnotator
- * the uniprotAnnotator to set
- * @see #uniprotAnnotator
- */
- public void setUniprotAnnotator(UniprotAnnotator uniprotAnnotator) {
- this.uniprotAnnotator = uniprotAnnotator;
- }
-
- @Override
- protected WebPageDownloader getWebPageDownloader() {
- return super.getWebPageDownloader();
- }
-
- @Override
- protected void setWebPageDownloader(WebPageDownloader webPageDownloader) {
- super.setWebPageDownloader(webPageDownloader);
- }
-
-}
+ /**
+ * Maximum available length of the pubmed identifiers.
+ */
+ private static final int MAX_PUBMED_IDENTIFIER_LENGTH = 9;
+
+ /**
+ * Prefix used for storing data about drug with name key value.
+ */
+ static final String DRUG_NAME_PREFIX = "drug:";
+
+ /**
+ * Service used for annotation of proteins using {@link MiriamType#UNIPROT
+ * uniprot}.
+ */
+ @Autowired
+ private UniprotAnnotator uniprotAnnotator;
+
+ /**
+ * Pattern that extract information about drug name when accessing page about
+ * target.
+ */
+ private final Pattern drugNamePattern = Pattern.compile("(?<=<td><strong>)([\\s\\S]*?)(?=</strong></td>)");
+
+ /**
+ * Default class logger.
+ */
+ private Logger logger = Logger.getLogger(DrugbankHTMLParser.class);
+
+ /**
+ * Url used for finding drug by drug name.
+ */
+ static final String URLB = "https://www.drugbank.ca/search?searcher=drugs&utf8=%E2%9C%93&button=&filter=false&query=";
+
+ /**
+ * Url used for retrieving general information about drug.
+ */
+ static final String URLDRUG = "https://www.drugbank.ca/drugs/";
+
+ /**
+ * Homepage of drugbank.
+ */
+ static final String URL = "https://www.drugbank.ca/";
+
+ /**
+ * Url used for accessing information about target synonyms.
+ */
+ static final String URLPEP = "https://www.drugbank.ca/biodb/polypeptides/";
+
+ /**
+ * Url that allows to search for drugs using target hgnc name.
+ */
+ static final String URL_TARGETS = "https://www.drugbank.ca/search?utf8=%E2%9C%93&searcher=targets&query=";
+
+ /**
+ * Url that helps finding drug name for given target identifier.
+ */
+ static final String URL_TARGET_DETAIL = "https://www.drugbank.ca/biodb/bio_entities/";
+
+ /**
+ * Pattern used to get information about {@link Drug#bloodBrainBarrier blood
+ * brain barrier}.
+ */
+ private Pattern bloodBrainBarrierPattern = Pattern.compile("(?<=<td>)([\\s\\S]*?)(?=</td>)");
+
+ /**
+ * Pattern that extract information about target identifier when searching for
+ * targets with given set of HGNC names.
+ */
+ private Pattern targetPattern = Pattern.compile("(?<=\"/biodb/bio_entities/)([\\s\\S]*?)(?=\")");
+
+ /**
+ * Default constructor.
+ */
+ public DrugbankHTMLParser() {
+ super(DrugbankHTMLParser.class);
+ }
+
+ @Override
+ public String refreshCacheQuery(Object query) throws SourceNotAvailable {
+ String result = null;
+ try {
+ if (query instanceof String) {
+ String name = (String) query;
+ if (name.startsWith(DRUG_NAME_PREFIX)) {
+ name = name.substring(DRUG_NAME_PREFIX.length());
+ result = getDrugSerializer().objectToString(findDrug(name));
+ } else if (name.startsWith("http")) {
+ result = getWebPageContent(name);
+ } else {
+ throw new InvalidArgumentException("Don't know what to do with string \"" + query + "\"");
+ }
+ } else {
+ throw new InvalidArgumentException("Don't know what to do with class: " + query.getClass());
+ }
+ } catch (DrugSearchException e) {
+ throw new SourceNotAvailable(e);
+ } catch (IOException e) {
+ throw new SourceNotAvailable(e);
+ }
+ return result;
+ }
+ /**
+ * Finds the drug identifier in the web page with information about drug.
+ *
+ * @param webpageContent
+ * content of the web page with information about drug
+ * @return drugbank identifier
+ */
+ private String findIdInText(String webpageContent) {
+ int i = 0, j = 0;
+ i = webpageContent.indexOf("href=\"/drugs/");
+ if (i == -1) {
+ return null;
+ }
+ i = i + "href=\"/drugs/".length();
+ j = webpageContent.indexOf('"', i);
+ return webpageContent.substring(i, j);
+ }
+
+ /**
+ * Finds the drug name in the webpage with information about drug.
+ *
+ * @param webpageContent
+ * content of the webpage with information about drug
+ * @return name of the drug
+ */
+ private String findNameInText(String webpageContent) {
+ int i = 0, j = 0;
+ i = webpageContent.indexOf("a href=\"/drugs/");
+ i = webpageContent.indexOf(">", i);
+ i = i + 1;
+ j = webpageContent.indexOf('<', i);
+ return webpageContent.substring(i, j);
+ }
+
+ /**
+ * Finds the description of the drug on the content of the web page with
+ * information about drug.
+ *
+ * @param webpageContent
+ * content of the web page with information about drug
+ * @return description of the drug
+ */
+ String getDescriptionForDrug(String webpageContent) {
+ int startIndex = 0, endIndex = 0;
+ startIndex = webpageContent.indexOf("Description</dt><dd class=\"col-md-10 col-sm-8\">");
+ if (startIndex == -1) {
+ return null;
+ }
+ startIndex = startIndex + "Description</dt><dd class=\"col-md-10 col-sm-8\">".length();
+ endIndex = webpageContent.indexOf("</dd", startIndex);
+ String description = webpageContent.substring(startIndex, endIndex);
+ // find special html characters
+ description = StringEscapeUtils.unescapeHtml4(description);
+ description = cleanHtml(description);
+ if (description.equalsIgnoreCase("Not Available")) {
+ description = null;
+ }
+
+ return description;
+ }
+
+ /**
+ * Returns list of the drug brand names from the web page content.
+ *
+ * @param page
+ * content of the web page with information about drug
+ * @return list of the drug brand names
+ */
+ private List<String> getTargetBrands(String page) {
+ List<String> result = new ArrayList<>();
+ int i, j, end;
+ Boolean finding = true;
+ i = page.indexOf("International/Other Brands");
+ end = page.indexOf("<dt", i);
+ while (finding) {
+ i = page.indexOf("separated-list-item\">", i);
+ if (i == -1 || i > end) {
+ finding = false;
+ continue;
+ }
+ i = i + "separated-list-item\">".length();
+ j = page.indexOf("<", i);
+ String synonym = StringEscapeUtils.unescapeHtml4(page.substring(i, j));
+ synonym = cleanHtml(synonym).trim();
+ if (synonym.indexOf("(") > 0) {
+ synonym = synonym.substring(0, synonym.indexOf("(")).trim();
+ }
+ result.add(synonym);
+ }
+ return result;
+ }
+
+ /**
+ * Returns list of drug synonyms from drugbank database.
+ *
+ * @param page
+ * web page content with drug information
+ * @return list of drug synonyms
+ */
+ private List<String> getDrugSynonyms(String page) {
+ List<String> ans = new ArrayList<>();
+
+ int i, j, end;
+ Boolean finding = true;
+ i = page.indexOf("Synonyms");
+ end = page.indexOf("Prescription Products", i);
+ while (finding) {
+ i = page.indexOf("<li>", i);
+ if (i == -1 || i > end) {
+ finding = false;
+ continue;
+ }
+ i = i + "<li>".length();
+ j = page.indexOf("<", i);
+ String synonym = StringEscapeUtils.unescapeHtml4(page.substring(i, j));
+ ans.add(cleanHtml(synonym));
+ }
+
+ return ans;
+ }
+
+ /**
+ * Returns references from reference string (obtained from drugbank homepage) .
+ *
+ * @param descriptionString
+ * string containing references obtained from drugbank webpage
+ * @return list of references obtained from drugbank {@link String}
+ */
+ List<MiriamData> getPubmedFromRef(String descriptionString) {
+ List<MiriamData> result = new ArrayList<>();
+ int currentStartIndex = 0;
+ while (true) {
+ currentStartIndex = descriptionString.indexOf("/pubmed/", currentStartIndex);
+ if (currentStartIndex == -1) {
+ break;
+ }
+ currentStartIndex = currentStartIndex + "/pubmed/".length();
+ int endIndex = descriptionString.indexOf('"', currentStartIndex);
+ String identifier = descriptionString.substring(currentStartIndex, endIndex);
+ String correctedIdentifier = identifier.replaceAll("[^\\d]", "");
+ if (!identifier.equals(correctedIdentifier)) {
+ if (correctedIdentifier.length() > MAX_PUBMED_IDENTIFIER_LENGTH) {
+ correctedIdentifier = correctedIdentifier.substring(0, MAX_PUBMED_IDENTIFIER_LENGTH);
+ }
+ logger.warn("Problematic pubmed identfier: \"" + identifier + "\". Trying fixing with the result: "
+ + correctedIdentifier);
+ }
+ if (correctedIdentifier.equals("")) {
+ break;
+ }
+ result.add(new MiriamData(MiriamRelationType.BQ_BIOL_IS_DESCRIBED_BY, MiriamType.PUBMED, correctedIdentifier));
+ }
+ return result;
+ }
+
+ /**
+ * Returns targets parsed from page content.
+ *
+ * @param page
+ * webpage content from which data are extracted
+ * @throws DrugSearchException
+ * thrown when there are problems with connection to DrugBank database
+ * @return list of drug {@link Target} parsed from input string
+ */
+ List<Target> getTargetsForDrug(String page) throws DrugSearchException {
+ List<Target> result = new ArrayList<>();
+ try {
+ int pageStart;
+ Target target = new Target();
+ target.setType(TargetType.SINGLE_PROTEIN);
+
+ pageStart = page.indexOf("bond-list-container targets");
+
+ int end = page.indexOf("bond-list-container enzymes");
+ if (end < 0) {
+ end = page.indexOf("bond-list-container carriers");
+ if (end < 0) {
+ end = page.indexOf("bond-list-container transporters");
+
+ if (end < 0) {
+ end = page.indexOf("<tr id=\"comments\">");
+ if (end < 0) {
+ end = page.length() - 1;
+ }
+ }
+ }
+ }
+
+ while (pageStart > 0 && pageStart < end) {
+ int targetStart = page.indexOf("Details</a>", pageStart);
+ int nextTargetStart = page.indexOf("Details</a>", targetStart + 1);
+ if (nextTargetStart < 0) {
+ nextTargetStart = end;
+ }
+
+ target = parseTarget(page.substring(targetStart, nextTargetStart));
+ if (target != null) {
+ result.add(target);
+ }
+ pageStart = nextTargetStart;
+
+ }
+ } catch (TaxonomySearchException e) {
+ throw new DrugSearchException("Problem with finidng information about organism", e);
+ } catch (UniprotSearchException e) {
+ throw new DrugSearchException("Problem with finidng information about protein", e);
+ }
+ return result;
+ }
+
+ /**
+ * Parse html info about target into {@link Target} structure.
+ *
+ * @param htmlPage
+ * string with html content
+ * @return {@link Target} for given html content
+ * @throws UniprotSearchException
+ * thrown when there is a problem with accessing uniprot db
+ * @throws TaxonomySearchException
+ * thrown when there is a problem with accessing taxonomy db
+ */
+ protected Target parseTarget(String htmlPage) throws UniprotSearchException, TaxonomySearchException {
+ int kindIndex = htmlPage.indexOf("Kind</dt><dd class=\"col-md-7 col-sm-6\">");
+ kindIndex += "Kind</dt><dd class=\"col-md-7 col-sm-6\">".length();
+ int endKindIndex = htmlPage.indexOf("</dd>");
+ String type = "";
+ if (kindIndex > 0 && endKindIndex > kindIndex) {
+ type = htmlPage.substring(kindIndex, endKindIndex);
+ }
+ if (type.trim().equalsIgnoreCase("Protein")) {
+ int uniprotIdStart = htmlPage.indexOf("/biodb/polypeptides/") + "/biodb/polypeptides/".length();
+ Target result = new Target();
+ result.setType(TargetType.SINGLE_PROTEIN);
+
+ // Getting ID && Name
+ int uniprotIdEnd = htmlPage.indexOf('"', uniprotIdStart);
+ String uniprotId = htmlPage.substring(uniprotIdStart, uniprotIdEnd);
+ MiriamData uniprotTarget = new MiriamData(MiriamType.UNIPROT, uniprotId);
+ MiriamData hgncTarget = uniprotAnnotator.uniProtToHgnc(uniprotTarget);
+ if (hgncTarget != null) {
+ result.addGene(hgncTarget);
+ } else {
+ result.addGene(uniprotTarget);
+ }
+
+ int nameStart = uniprotIdEnd + 2;
+ int nameEnd = htmlPage.indexOf("</", uniprotIdStart);
+ String name = StringEscapeUtils.unescapeHtml4(htmlPage.substring(nameStart, nameEnd));
+ result.setName(name);
+
+ // Getting Organism
+ int organismStart = htmlPage.indexOf("Organism</dt><dd class=\"col-md-7 col-sm-6\">", nameEnd)
+ + "Organism</dt><dd class=\"col-md-7 col-sm-6\">".length();
+ int organismEnd = htmlPage.indexOf("</dd>", organismStart);
+ String organismString = htmlPage.substring(organismStart, organismEnd);
+ result.setOrganism(getTaxonomyBackend().getByName(organismString));
+
+ // Getting References
+ int referencesStart = htmlPage.indexOf("<h5>References</h5>", organismEnd);
+ if (referencesStart > 0) {
+ int referencesEnd = Math.min(htmlPage.indexOf("Details</a>", referencesStart), htmlPage.length());
+ if (referencesEnd < 0) {
+ referencesEnd = htmlPage.length();
+ }
+ result.addReferences(getPubmedFromRef(htmlPage.substring(referencesStart, referencesEnd)));
+ }
+ return result;
+ } else {
+ logger.warn("Unknown target type: " + type + ". Skipping.");
+ return null;
+ }
+ }
+
+ /**
+ * Finds information about drug in drugbank database.
+ *
+ * @param name
+ * name of the dug that we are looking for
+ * @throws DrugSearchException
+ * thrown when there are problems with connection to DrugBank database
+ * @return drug with the information obtained from drugbank or <code>null</code>
+ * if such data couldn't be found
+ */
+ private Drug findMoreInformation(String name) throws DrugSearchException {
+ Drug result = null;
+ try {
+ name = URLEncoder.encode(name, "UTF-8");
+
+ // minus is to prevent redirection from search that have single result
+ String accessUrl = URLB + name + "+-";
+
+ String content = getWebPageContent(accessUrl);
+
+ String[] lines = content.split("\n");
+ for (String inputLine : lines) {
+ String tmp = findIdInText(inputLine);
+ if (tmp != null) {
+ result = new Drug();
+ result.addSource(new MiriamData(MiriamRelationType.BQ_BIOL_IS_DESCRIBED_BY, MiriamType.DRUGBANK, tmp));
+ result.setName(super.cleanHtml(findNameInText(inputLine)));
+ break;
+ }
+ }
+
+ if (result != null) {
+
+ accessUrl = URLDRUG + result.getSources().get(0).getResource();
+
+ String page = getWebPageContent(accessUrl);
+
+ result.setDescription(getDescriptionForDrug(page));
+
+ result.setSynonyms(getDrugSynonyms(page));
+
+ // Getting drug brand names
+ result.setBrandNames(getTargetBrands(page));
+
+ result.addTargets(getTargetsForDrug(page));
+
+ result.setBloodBrainBarrier(getBloodBrainBarrier(page));
+
+ result.setApproved(getApproved(page));
+
+ if (!nameMatch(result, name)) {
+ result = null;
+ }
+ }
+ } catch (IOException e) {
+ throw new DrugSearchException(e);
+ }
+ return result;
+ }
+
+ /**
+ * Check if drug data mateches with the search name.
+ *
+ * @param drug
+ * drug to be checked
+ * @param name
+ * name of the drug that we were looking for
+ * @return true if if drug data matches with the search name
+ */
+ private boolean nameMatch(Drug drug, String name) {
+ Set<String> foundNames = new HashSet<>();
+ foundNames.add(drug.getName());
+ foundNames.addAll(drug.getSynonyms());
+ foundNames.addAll(drug.getBrandNames());
+ String lowerCaseName;
+ try {
+ lowerCaseName = java.net.URLDecoder.decode(name, "UTF-8").toLowerCase().replaceAll("[^A-Za-z0-9]", "");
+ } catch (UnsupportedEncodingException e) {
+ lowerCaseName = name.toLowerCase().replaceAll("[^A-Za-z0-9]", "");
+ }
+ for (String string : foundNames) {
+ String query = string.toLowerCase().replaceAll("[^A-Za-z0-9]", "");
+ if (query.contains(lowerCaseName)) {
+ return true;
+ }
+ }
+ return false;
+ }
+
+ /**
+ * Finds blood brain barrier info about drug in the webpage content.
+ *
+ * @param page
+ * webpage content used for parsing
+ *
+ * @return status of blood brain barrier
+ */
+ String getBloodBrainBarrier(String page) {
+ int index = page.indexOf("<td>Blood Brain Barrier</td>");
+ if (index <= 0) {
+ return "N/A";
+ }
+
+ Matcher matcher = bloodBrainBarrierPattern.matcher(page.substring(index));
+
+ matcher.find();
+ if (!matcher.find()) {
+ logger.warn("Invalid html for Blood Brain Barrier...");
+ return "N/A";
+ }
+ String match = matcher.group(1);
+ if (match.contains("+")) {
+ return "YES";
+ } else if (match.contains("-")) {
+ return "NO";
+ } else {
+ logger.warn("Unknown Blood Brain Barrier status: " + match);
+ return "N/A";
+ }
+ }
+
+ /**
+ * Finds if drug is approved.
+ *
+ * @param page
+ * webpage content used for parsing
+ *
+ * @return <code>true</code> if drug is approved
+ */
+ private Boolean getApproved(String page) {
+ int index = page.indexOf("<dt class=\"col-md-2 col-sm-4\">Groups</dt>");
+ if (index <= 0) {
+ return null;
+ }
+
+ int end = page.indexOf("</dd>", index + 1);
+
+ if (end < index) {
+ end = page.length();
+ }
+ String match = page.substring(index, end).toLowerCase();
+ if (match.contains("approved")) {
+ if (match.contains("investigational") || match.contains("withdrawn") || match.contains("experimental")) {
+ logger.warn("Contradicting info about approved status: " + match);
+ return null;
+ }
+ return true;
+ } else if (match.contains("investigational") || match.contains("withdrawn") || match.contains("experimental")) {
+ return false;
+ } else {
+ logger.warn("Unknown approved status: " + match);
+ return null;
+ }
+ }
+
+ @Override
+ public Drug findDrug(String drugName) throws DrugSearchException {
+ String query = DRUG_NAME_PREFIX + drugName;
+ Drug drug = null;
+ try {
+ drug = getDrugSerializer().xmlToObject(getCacheNode(query));
+ } catch (SerializationException e) {
+ logger.error("Problem with deserializing element by query: " + query);
+ }
+ if (drug != null) {
+ return drug;
+ }
+
+ drug = findMoreInformation(drugName);
+
+ try {
+ setCacheValue(query, getDrugSerializer().objectToString(drug));
+ } catch (SerializationException e) {
+ logger.error("Problem with serializing element ");
+ }
+
+ return drug;
+ }
+
+ @Override
+ public ExternalServiceStatus getServiceStatus() {
+ ExternalServiceStatus status = new ExternalServiceStatus("DrugBank", URL);
+
+ GeneralCacheInterface cacheCopy = getCache();
+ this.setCache(null);
+
+ try {
+ Drug drug = findDrug("Amantadine");
+ status.setStatus(ExternalServiceStatusType.OK);
+ if (drug == null) {
+ status.setStatus(ExternalServiceStatusType.CHANGED);
+ }
+ } catch (Exception e) {
+ logger.error("DrugBank is down", e);
+ status.setStatus(ExternalServiceStatusType.DOWN);
+ }
+ this.setCache(cacheCopy);
+ return status;
+ }
+
+ @Override
+ public List<Drug> getDrugListByTarget(MiriamData targetMiriamData, Collection<MiriamData> organisms)
+ throws DrugSearchException {
+ List<Drug> result = new ArrayList<>();
+ if (targetMiriamData == null) {
+ return result;
+ }
+ if (!(MiriamType.HGNC_SYMBOL.equals(targetMiriamData.getDataType()))) {
+ throw new InvalidArgumentException("Only " + MiriamType.HGNC_SYMBOL + " type is accepted");
+ }
+ String url = URL_TARGETS + targetMiriamData.getResource();
+
+ try {
+ String page = getWebPageContent(url);
+
+ Set<String> drugNames = new HashSet<>();
+
+ Matcher matcher = targetPattern.matcher(page);
+ while (matcher.find()) {
+ String drugbankTargetId = matcher.group(0);
+ drugNames.addAll(getDrugNamesForTarget(new MiriamData(MiriamType.DRUGBANK_TARGET_V4, drugbankTargetId),
+ targetMiriamData, organisms));
+ }
+ for (String string : drugNames) {
+ Drug drug = findDrug(string);
+ if (drug == null) {
+ logger.warn("Cannot find drug that should be there: " + string);
+ } else {
+ boolean targets = false;
+ for (Target target : drug.getTargets()) {
+ for (MiriamData gene : target.getGenes()) {
+ if (gene.equals(targetMiriamData)) {
+ targets = true;
+ }
+ }
+ }
+ if (targets) {
+ result.add(drug);
+ } else {
+ logger.debug("Skipping drug that doesn't target required target. Drug name: " + drug.getName()
+ + "; target: " + targetMiriamData);
+ }
+ }
+ }
+
+ return result;
+ } catch (IOException e) {
+ throw new DrugSearchException("Cannot access drug database", e);
+ }
+ }
+
+ /**
+ * Returns list of drugs that target element (target) identified be drugbank
+ * identifier.
+ *
+ * @param drugbankTarget
+ * {@link MiriamType#DRUGBANK_TARGET_V4 identifier} of the target
+ * @param hgncTarget
+ * identifier of the target using {@link MiriamType#HGNC_SYMBOL}, used
+ * for verification if the target really points to proper protein/gene
+ * @param organisms
+ * list of organisms to which results should be limited (when no
+ * organisms defined filtering will be turned off)
+ * @return list of drugs that target this target
+ * @throws DrugSearchException
+ * thrown when there are problems with connection to DrugBank database
+ */
+ private Set<String> getDrugNamesForTarget(MiriamData drugbankTarget, MiriamData hgncTarget,
+ Collection<MiriamData> organisms) throws DrugSearchException {
+ if (!MiriamType.DRUGBANK_TARGET_V4.equals(drugbankTarget.getDataType())) {
+ throw new InvalidArgumentException("drugbankTarget must be of type: " + MiriamType.DRUGBANK_TARGET_V4);
+ }
+
+ try {
+ Set<String> drugNames = new HashSet<>();
+ String url = URL_TARGET_DETAIL + drugbankTarget.getResource();
+
+ String page = getWebPageContent(url);
+
+ int idPosition = page.indexOf("<th>DrugBank ID</th>");
+ if (idPosition < 0) {
+ throw new DrugSearchException("Problematic web page for target: " + drugbankTarget + "(" + hgncTarget + ")");
+ }
+
+ int protienLinkPosition = page.indexOf("/polypeptides/");
+ // sometimes there might not be an element
+ if (protienLinkPosition >= 0) {
+ protienLinkPosition = protienLinkPosition + "/polypeptides/".length(); // 20;
+ int j = page.indexOf('"', protienLinkPosition);
+ String uniprotId = page.substring(protienLinkPosition, j);
+ MiriamData uniprotMiriam = new MiriamData(MiriamType.UNIPROT, uniprotId);
+ MiriamData hgncMiriam = uniprotAnnotator.uniProtToHgnc(uniprotMiriam);
+ if (hgncMiriam == null || !hgncMiriam.equals(hgncTarget)) {
+ logger.debug("Invalid target found. Expected " + hgncTarget + ", but found: " + hgncMiriam + " ("
+ + uniprotMiriam + ")");
+ return drugNames;
+ }
+
+ } else {
+ logger.warn("Invalid target found. No protein data available.");
+ return drugNames;
+ }
+
+ int organismPosition = page.indexOf("Organism</dt><dd class=\"col-md-10 col-sm-8\">");
+ if (organismPosition >= 0) {
+ int organismStart = organismPosition+ "Organism</dt><dd class=\"col-md-10 col-sm-8\">".length();
+ int organismEnd = page.indexOf("<", organismStart + 1);
+ String organismName = page.substring(organismStart, organismEnd);
+ if (!organismMatch(organismName, organisms)) {
+ logger.debug("Organism doesn't match. Found" + organismName + ". Expected: " + organisms);
+ return drugNames;
+ }
+ }
+
+ Matcher matcher = drugNamePattern.matcher(page.substring(idPosition));
+
+ while (matcher.find()) {
+ drugNames.add(matcher.group(1));
+ }
+
+ return drugNames;
+ } catch (IOException e) {
+ throw new DrugSearchException("Problem with accessing drugbank db", e);
+ } catch (UniprotSearchException e) {
+ throw new DrugSearchException("Problem with uniprot annotations", e);
+ }
+ }
+
+ /**
+ * @return the uniprotAnnotator
+ * @see #uniprotAnnotator
+ */
+ public UniprotAnnotator getUniprotAnnotator() {
+ return uniprotAnnotator;
+ }
+
+ /**
+ * @param uniprotAnnotator
+ * the uniprotAnnotator to set
+ * @see #uniprotAnnotator
+ */
+ public void setUniprotAnnotator(UniprotAnnotator uniprotAnnotator) {
+ this.uniprotAnnotator = uniprotAnnotator;
+ }
+
+ @Override
+ protected WebPageDownloader getWebPageDownloader() {
+ return super.getWebPageDownloader();
+ }
+
+ @Override
+ protected void setWebPageDownloader(WebPageDownloader webPageDownloader) {
+ super.setWebPageDownloader(webPageDownloader);
+ }
+
+}
\ No newline at end of file
diff --git a/persist/src/db/11.0.5/fix_db_20171109.sql b/persist/src/db/11.0.5/fix_db_20171109.sql
new file mode 100644
index 0000000000000000000000000000000000000000..3e427bea81e51a58776c8af9fd8d72bae191da94
--- /dev/null
+++ b/persist/src/db/11.0.5/fix_db_20171109.sql
@@ -0,0 +1,2 @@
+---clear drugbank cache
+delete from cachequery where type = (select iddb from cache_type where classname='lcsb.mapviewer.annotation.services.DrugbankHTMLParser');