private String getSubstrateSymbol(
Matcher patternSubstrateSymbol, SubstrateDatabaseEntry substratedatabase) {
String Substratesymbol = null;
if (patternSubstrateSymbol.find()) {
Substratesymbol = patternSubstrateSymbol.group(2);
substratedatabase.setS_Symbol(Substratesymbol);
// System.out.println(Substratesymbol);
} else {
Substratesymbol = "n.d.";
substratedatabase.setS_Symbol(Substratesymbol);
// System.out.println(Substratesymbol);
}
return Substratesymbol;
}
private String getSubstrateAccession(
Matcher patternSubstrateAccession, SubstrateDatabaseEntry subtratedatabase) {
String accession = null;
if (patternSubstrateAccession.find()) {
accession = patternSubstrateAccession.group(1);
accession = accession.trim();
subtratedatabase.setS_UniprotID(accession);
// System.out.println(accession);
} else {
accession = "n.d.";
subtratedatabase.setS_UniprotID(accession);
// System.out.println(accession);
}
return accession;
}
private String getUniSubstrategenename(
NodeList entries, int i, SubstrateDatabaseEntry substratedatabase) {
// GET SUBSTRATE GENE NAME using getInformation method
LinkedList<String> genenamelist =
getInformation("./gene/name[@type][1]/text()", entries.item(i));
String genename = null;
if (!genenamelist.isEmpty()) {
genename = genenamelist.getFirst();
System.out.println(genename);
substratedatabase.setS_Symbol(genename);
}
return genename;
}
private void getUniSubstratepproteinname(
NodeList entries, int i, SubstrateDatabaseEntry substratedatabase) {
// GET SUBSTRATE PROTEIN NAME using getInformation method
LinkedList<String> protnamelist =
getInformation("./protein/recommendedName/fullName/text()", entries.item(i));
String protname = null;
if (!protnamelist.isEmpty()) {
protname = protnamelist.getFirst();
protname = protname.replaceAll(",", "");
System.out.println(protname);
substratedatabase.setS_Name(protname);
}
}
private String getSubstrateNameSymbolId(
Matcher patternSubstrateName,
SubstrateDatabaseEntry substratedatabase,
CsDatabaseEntry csdatabase,
String entry,
String substrateTaxon)
throws IOException {
String commentS = null;
Matcher patternSubstrateAccession =
getPatternmatcher(
"UniProt\\s+Accession:</th>[^<]+<td><a\\s+href\\s+=\\s+\"[^\"]+\"\\s+target=\"[^\"]+\">"
+ "([^<]+)",
entry);
String accession = getSubstrateAccession(patternSubstrateAccession, substratedatabase);
Matcher patternSubstrateSymbol =
getPatternmatcher(
"Substrate[^<]+</th>[^<]+<td>[^<]+<table>[^<]+<tr>[^<]+<th\\s+class=\"th3\">Definition:</th>[^<]+<td><b>"
+ "[^<]+"
+ "</b></td>[^<]+<tr>[^<]+<th\\s+class=\"th3\">Symbol:</th>"
+ "([^<]+<td><b>)?([^<]+)",
entry);
String symbol = getSubstrateSymbol(patternSubstrateSymbol, substratedatabase);
if (patternSubstrateName.find()) {
String Substratename = "to check";
String Substratesymbol = "to check";
String Substrateaccession = "to check";
substratedatabase.setS_NL_Name(Substratename);
substratedatabase.setS_Name(Substratename);
substratedatabase.setS_Symbol(Substratesymbol);
substratedatabase.setS_UniprotID(Substrateaccession);
Substratename = patternSubstrateName.group(1);
Substratename = Substratename.trim();
Substratename = Substratename.replaceAll(",", "");
Substratename = Substratename.replaceAll(";", "");
substratedatabase.setS_NL_Name(Substratename);
commentS = "Check Substrate Symbol and Accession; add to Substrate Librairy";
BufferedReader bReader = null;
if (substrateTaxon.contains("H**o")) {
bReader =
createBufferedreader(
"/Users/julieklein/Dropbox/ProteasiX/LIBRAIRIES/SubstrateHSALibrairy.txt");
} else if (substrateTaxon.contains("Mus")) {
bReader =
createBufferedreader(
"/Users/julieklein/Dropbox/ProteasiX/LIBRAIRIES/SubstrateMMULibrairy.txt");
} else if (substrateTaxon.contains("Rattus")) {
bReader =
createBufferedreader(
"/Users/julieklein/Dropbox/ProteasiX/LIBRAIRIES/SubstrateRNOLibrairy.txt");
}
String line;
while ((line = bReader.readLine()) != null) {
String splitarray[] = line.split("\t");
String naturallanguage = splitarray[1];
naturallanguage = naturallanguage.replaceAll("\"", "");
naturallanguage = naturallanguage.replaceAll(",", "");
naturallanguage = naturallanguage.replaceAll(";", "");
if (naturallanguage.equalsIgnoreCase(Substratename)) {
Substratesymbol = splitarray[0];
Substratesymbol = Substratesymbol.replaceAll("sept-0", "SEPT");
Substrateaccession = splitarray[2];
if (Substrateaccession.contains("n.d.")) {
substratedatabase.setS_Name("n.d.");
substratedatabase.setS_UniprotID(Substrateaccession);
substratedatabase.setS_Symbol(Substratesymbol);
} else {
String UniprotURL = "http://www.uniprot.org/uniprot/" + Substrateaccession + ".xml";
NodeList entries = getEntries("/uniprot/entry", parseUniprot(UniprotURL));
for (int i = 0; i < entries.getLength(); i++) {
getUniSubstratepproteinname(entries, i, substratedatabase);
String genename = getUniSubstrategenename(entries, i, substratedatabase);
}
// System.out.println(Substrateaccession);
substratedatabase.setS_UniprotID(Substrateaccession);
commentS = "-";
System.out.println(commentS);
}
}
csdatabase.setSubstrate(substratedatabase);
}
} else if (!symbol.contains("n.d.")) {
String Substratename = "to check";
String Substratesymbol = "to check";
String Substrateaccession = "to check";
substratedatabase.setS_NL_Name(Substratename);
substratedatabase.setS_Name(Substratename);
substratedatabase.setS_Symbol(Substratesymbol);
substratedatabase.setS_UniprotID(Substrateaccession);
BufferedReader bReader = null;
if (substrateTaxon.contains("H**o")) {
bReader =
createBufferedreader(
"/Users/julieklein/Dropbox/ProteasiX/LIBRAIRIES/SubstrateHSALibrairy.txt");
} else if (substrateTaxon.contains("Mus")) {
bReader =
createBufferedreader(
"/Users/julieklein/Dropbox/ProteasiX/LIBRAIRIES/SubstrateMMULibrairy.txt");
} else if (substrateTaxon.contains("Rattus")) {
bReader =
createBufferedreader(
"/Users/julieklein/Dropbox/ProteasiX/LIBRAIRIES/SubstrateRNOLibrairy.txt");
}
String line;
while ((line = bReader.readLine()) != null) {
String splitarray[] = line.split("\t");
String librairisymbol = splitarray[0];
librairisymbol = librairisymbol.replaceAll("\"", "");
librairisymbol = librairisymbol.replaceAll("sept-0", "SEPT");
if (librairisymbol.equals(symbol)) {
Substrateaccession = splitarray[2];
if (Substrateaccession.contains("n.d.")) {
substratedatabase.setS_Name("n.d.");
substratedatabase.setS_UniprotID(Substrateaccession);
substratedatabase.setS_Symbol(symbol);
} else {
String UniprotURL = "http://www.uniprot.org/uniprot/" + Substrateaccession + ".xml";
NodeList entries = getEntries("/uniprot/entry", parseUniprot(UniprotURL));
for (int i = 0; i < entries.getLength(); i++) {
getUniSubstratepproteinname(entries, i, substratedatabase);
String genename = getUniSubstrategenename(entries, i, substratedatabase);
}
// System.out.println(Substrateaccession);
substratedatabase.setS_UniprotID(Substrateaccession);
commentS = "-";
System.out.println(commentS);
}
}
csdatabase.setSubstrate(substratedatabase);
}
} else {
String Substratename = "n.d.";
String Substratesymbol = "n.d.";
String Substrateaccession = "n.d";
substratedatabase.setS_NL_Name(Substratename);
substratedatabase.setS_Name(Substratename);
substratedatabase.setS_Symbol(Substratesymbol);
substratedatabase.setS_UniprotID(Substrateaccession);
System.out.println(Substratename);
System.out.println(Substratesymbol);
System.out.println(Substrateaccession);
commentS = "-";
System.out.println(commentS);
csdatabase.setSubstrate(substratedatabase);
}
return commentS;
}
public Main_PDB_Pmap() throws MalformedURLException, IOException {
PrintStream csvWriter = null;
LinkedList<CsDatabaseEntry> PmapnotcuratedProteasixDB = new LinkedList<CsDatabaseEntry>();
java.util.Calendar calendar = java.util.Calendar.getInstance();
String version = "JUNE2012";
File f =
new File(
"//Users/julieklein/Dropbox/ProteasiX/ProteasiX/ProteasixVersionJune2012/PMAPJUIN2012_5");
File[] files = f.listFiles();
for (File file : files) {
String filepath = "file://" + file.getPath() + "/";
String htmlcontentmultipleentries = getHtmlcontent(new URL(filepath)).toString();
Matcher splithtml =
getPatternmatcher(
"(<input\\s+id=\"ballot.*?>Detail</a></td>)", htmlcontentmultipleentries);
String htmlsplitted = putSplittedhtmlintostringbuilder(splithtml);
Matcher retrievepmapentryid =
getPatternmatcher("<td><a\\s+href=\"" + "([^\"]+)" + "\"[^>]*>", htmlsplitted);
while (retrievepmapentryid.find()) {
String url = retrievepmapentryid.group(1);
if (url.equalsIgnoreCase("/relation/show/16398")
|| url.equalsIgnoreCase("/relation/show/17178")
|| url.equalsIgnoreCase("/relation/show/17177")
|| url.equalsIgnoreCase("/relation/show/17074")
|| url.equalsIgnoreCase("/relation/show/17458")
|| url.equalsIgnoreCase("/relation/show/17467")
|| url.equalsIgnoreCase("/relation/show/16083")
|| url.equalsIgnoreCase("/relation/show/16082")
|| url.equalsIgnoreCase("/relation/show/16081")
|| url.equalsIgnoreCase("/relation/show/16080")
|| url.equalsIgnoreCase("/relation/show/16398")
|| url.equalsIgnoreCase("/relation/show/16271")) {
} else {
url = "http://cutdb.burnham.org" + url;
String entry = getHtmlcontent(new URL(url)).toString();
Matcher patternProteaseTaxon =
getPatternmatcher(
"<div\\s+id=\"protdata\">[^<]+<table>[^<]+<tr>[^<]+<th\\s+class=\"th3\">Definition:</th>"
+ "([^<]+<td><b>[^<]+</b></td>)?"
+ "[^<]+</tr>[^<]+<tr>[^<]+<th\\s+class=\"th3\">Organism:</th>[^<]+<td><a\\s+href\\s+=\\s+\"[^\"]+\"\\s+target=\"[^\"]+\">"
+ "([^<]+)",
entry);
String proteaseTaxon = getProteaseTaxon(patternProteaseTaxon);
System.out.println(proteaseTaxon);
Matcher patternSubstrateTaxon =
getPatternmatcher(
"<div\\s+id=\"sbstdata\">[^<]+<table>[^<]+<tr>[^<]+<th\\s+class=\"th3\">Organism:</th>[^<]+<td><a\\s+href\\s+=\\s+\"[^\"]+\"\\s+target=\"[^\"]+\">"
+ "([^<]+)",
entry);
String substrateTaxon = getSubstrateTaxon(patternSubstrateTaxon);
System.out.println(substrateTaxon);
System.out.println("\n" + "******************************" + url);
Matcher patternSubstrateName =
getPatternmatcher(
"Substrate[^<]+</th>[^<]+<td>[^<]+<table>[^<]+<tr>[^<]+<th\\s+class=\"th3\">Definition:</th>[^<]+<td><b>"
+ "([^<]+)",
entry);
SubstrateDatabaseEntry substratedatabase = new SubstrateDatabaseEntry();
CsDatabaseEntry csdatabase = new CsDatabaseEntry();
ProteaseDatabaseEntry proteasedatabase = new ProteaseDatabaseEntry();
substratedatabase.setS_Taxon(substrateTaxon);
String commentS =
getSubstrateNameSymbolId(
patternSubstrateName, substratedatabase, csdatabase, entry, substrateTaxon);
System.out.println("out");
proteasedatabase.setP_Taxon(proteaseTaxon);
// csdatabase.setSubstrate(substratedatabase);
Matcher patternProteaseName =
getPatternmatcher(
"<div\\s+id=\"protdata\">[^<]+<table>[^<]+<tr>[^<]+<th\\s+class=\"th3\">Definition:</th>[^<]+<td><b>"
+ "([^<]+)",
entry);
String commentP =
getProteaseNameSymbolId(
patternProteaseName, csdatabase, proteasedatabase, proteaseTaxon, commentS);
csdatabase.setComment(commentP);
System.out.println(commentP);
csdatabase.setExternal_Link(url);
Matcher patternCleavagesitePosition =
getPatternmatcher(
"<div\\s+id=\"cleav2\">[^<]+<table>[^<]+<th\\s+class=\"th3\">Position:</th>[^<]+<td>"
+ "([^<]+)?",
entry);
getCleavagesitePosition(patternCleavagesitePosition, csdatabase);
Matcher patternCleavagesiteSequence =
getPatternmatcher(
"<div\\s+id=\"cleav\">[^<]+<table>[^<]+<th\\s+class=\"th3\">Sequence:</td>[^<]+<td>"
+ "([^<]+)?",
entry);
String csSequence = getCleavagesiteSequence(patternCleavagesiteSequence, csdatabase);
String csSequencenodash = csSequence.replaceAll("-", "");
csSequencenodash = csSequencenodash.trim();
Matcher patternPmid =
getPatternmatcher(
"<div\\s+id=\"pubmed\">[^<]+<table>[^<]+<td>[^<]+<a\\s+href=\"[^\"]+\"\\s+target=\"[^\"]+\"\\s+>"
+ "([^<]+)",
entry);
getPmid(patternPmid, csdatabase);
Matcher patternErrorUnmatched =
getPatternmatcher("<td><font\\s+color=\"#FF0000\">" + "(\\*Unmatched)", entry);
getErrorUnmatched(patternErrorUnmatched, csdatabase);
SimpleDateFormat format = new SimpleDateFormat("dd-MM-yyyy");
Calendar originalDate = Calendar.getInstance();
String dateString = format.format(originalDate.getTime());
System.out.println(dateString);
csdatabase.setCreation_Date(dateString);
if (!substratedatabase.getS_UniprotID().contains("n.d")
&& !substratedatabase.getS_UniprotID().equalsIgnoreCase("to check")
&& !csdatabase.getP1_Sequence().equalsIgnoreCase("?")
&& !csdatabase.getP1prime_Sequence().equalsIgnoreCase("?")
&& !(csdatabase.getP1_Position() == 0)
&& !(csdatabase.getP1prime_Position() == 0)
&& !csdatabase.getCuration_Status().contains("discarded")) {
String motif = csdatabase.getP1_Sequence() + "-" + csdatabase.getP1prime_Sequence();
int motifposition = csSequence.indexOf(motif) + 1;
NodeList entries =
getEntries(
"/uniprot/entry/sequence/text()",
parseUniprot(
"http://www.uniprot.org/uniprot/"
+ substratedatabase.getS_UniprotID()
+ ".xml"));
for (int i = 0; i < entries.getLength(); i++) {
String sequence = getUniSubstratesequence(entries, i, substratedatabase);
int startcs = 0;
if (csSequence.startsWith("---")) {
startcs = csdatabase.getP1_Position() - 1;
} else if (csSequence.startsWith("--")) {
startcs = csdatabase.getP1_Position() - 2;
} else if (csSequence.startsWith("-")) {
startcs = csdatabase.getP1_Position() - 3;
} else {
startcs = csdatabase.getP1_Position() - 4;
}
int length = csSequencenodash.length();
if ((startcs + length) < sequence.length()
|| (startcs + length) == sequence.length()) {
String csonsequence = sequence.substring(startcs, startcs + length);
System.out.println("CS ON SEQUENCE " + csonsequence);
if (!csonsequence.equals(csSequencenodash)) {
if (sequence.contains(csSequencenodash)) {
int cleavagesiteposition = sequence.indexOf(csSequencenodash);
int newp1 = motifposition + cleavagesiteposition;
int newp1prime = newp1 + 1;
csdatabase.setP1_Position(newp1);
csdatabase.setP1prime_Position(newp1prime);
System.out.println(newp1);
System.out.println(newp1prime);
csdatabase.setCuration_Status(
"Cleavage site curated based on Uniprot protein sequence");
System.out.println("Cleavage site curated based on Uniprot protein sequence");
} else {
csdatabase.setCuration_Status(
"Unmatched cleavage site; Cleavage site discarded");
System.out.println("Unmatched cleavage site; Cleavage site discarded");
}
}
} else {
if (sequence.contains(csSequencenodash)) {
int cleavagesiteposition = sequence.indexOf(csSequencenodash);
int newp1 = motifposition + cleavagesiteposition;
int newp1prime = newp1 + 1;
if (newp1 == csdatabase.getP1_Position()
&& newp1prime == csdatabase.getP1prime_Position()) {
continue;
} else {
csdatabase.setP1_Position(newp1);
csdatabase.setP1prime_Position(newp1prime);
System.out.println(newp1);
System.out.println(newp1prime);
csdatabase.setCuration_Status(
"Cleavage site curated based on Uniprot protein sequence");
System.out.println("Cleavage site curated based on Uniprot protein sequence");
}
}
}
}
PmapnotcuratedProteasixDB.add(csdatabase);
} else if (!substratedatabase.getS_UniprotID().contains("n.d")
&& !substratedatabase.getS_UniprotID().equalsIgnoreCase("to check")
&& !csdatabase.getP1_Sequence().equalsIgnoreCase("?")
&& !csdatabase.getP1prime_Sequence().equalsIgnoreCase("?")
&& csdatabase.getP1_Position() == 0
&& csdatabase.getP1prime_Position() == 0
&& !csdatabase.getCuration_Status().contains("discarded")) {
String motif = csdatabase.getP1_Sequence() + "-" + csdatabase.getP1prime_Sequence();
int motifposition = csSequence.indexOf(motif) + 1;
NodeList entries =
getEntries(
"/uniprot/entry/sequence/text()",
parseUniprot(
"http://www.uniprot.org/uniprot/"
+ substratedatabase.getS_UniprotID()
+ ".xml"));
for (int i = 0; i < entries.getLength(); i++) {
String sequence = getUniSubstratesequence(entries, i, substratedatabase);
if (sequence.contains(csSequencenodash)) {
int cleavagesiteposition = sequence.indexOf(csSequencenodash);
int newp1 = motifposition + cleavagesiteposition;
int newp1prime = newp1 + 1;
if (newp1 == csdatabase.getP1_Position()
&& newp1prime == csdatabase.getP1prime_Position()) {
continue;
} else {
csdatabase.setP1_Position(newp1);
csdatabase.setP1prime_Position(newp1prime);
System.out.println(newp1);
System.out.println(newp1prime);
csdatabase.setCuration_Status(
"Cleavage site curated based on Uniprot protein sequence");
System.out.println("Cleavage site curated based on Uniprot protein sequence");
}
} else {
csdatabase.setCuration_Status("Unmatched cleavage site; Cleavage site discarded");
System.out.println("Unmatched cleavage site; Cleavage site discarded");
}
}
PmapnotcuratedProteasixDB.add(csdatabase);
} else {
PmapnotcuratedProteasixDB.add(csdatabase);
}
}
}
}
try {
System.out.println("-----------------");
csvWriter = new PrintStream("Pmap5notcuratedProteasixDB" + "_" + version + ".csv");
// populateHeaders(csvWriter);
for (CsDatabaseEntry csDatabaseEntry : PmapnotcuratedProteasixDB) {
System.out.println(csDatabaseEntry.getExternal_Link());
populateData(csvWriter, csDatabaseEntry);
System.out.println("OK");
}
} catch (FileNotFoundException ex) {
Logger.getLogger(Main_PDB_Pmap.class.getName()).log(Level.SEVERE, null, ex);
} finally {
csvWriter.close();
}
}