private UniprotEntry CopyEntry()
{
UniprotEntry newEntry = new UniprotEntry();
DbReferenceType[] dbRefTypes = new DbReferenceType[dbEntries.Keys.Count];
dbEntries.Keys.CopyTo(dbRefTypes, 0);
foreach (DbReferenceType refType in dbRefTypes)
{
string[] dbRefIDs = Get(refType);
foreach (string id in dbRefIDs)
{
newEntry.AddDbEntry(refType.UniprotName, id);
foreach (KeyValuePair <string, List <string> > property in dbEntries[refType][id].properties)
{
foreach (string propertyValue in property.Value)
{
newEntry.AddDbEntryProperty(refType.UniprotName, id, property.Key, propertyValue);
}
}
}
}
if (features != null)
{
foreach (FeatureType type in GetAllFeatureTypes())
{
newEntry.AddFeatures(type, GetFeatures(type));
}
}
foreach (string kword in Keywords)
{
newEntry.AddKeyword(kword);
}
newEntry.ProteinFullNames = ProteinFullNames;
newEntry.ProteinShortNames = ProteinShortNames;
newEntry.ProteinEcNumbers = ProteinEcNumbers;
newEntry.Accessions = Accessions;
newEntry.GeneNamesAndTypes = GeneNamesAndTypes;
newEntry.OrganismNames = OrganismNames;
newEntry.UniprotNames = UniprotNames;
newEntry.Sequence = Sequence;
foreach (string taxId in taxonomyIds)
{
newEntry.AddTaxonomyId(taxId);
}
foreach (string hostTaxId in hostTaxonomyIds)
{
newEntry.AddHostTaxonomyId(hostTaxId);
}
return(newEntry);
}
public List <UniprotEntry> ResolveIsoforms(Dictionary <string, List <string> > isoformToEnsembl)
{
DbReferenceType dbRefType = DbReferenceType.ensembl;
List <UniprotEntry> isoforms = new List <UniprotEntry>();
foreach (KeyValuePair <string, List <string> > isofToEnsembl in isoformToEnsembl)
{
UniprotEntry modEntry = CopyEntry();
modEntry.dbEntries.Remove(dbRefType);
Dictionary <string, UniprotDbReference> enstToData = new Dictionary <string, UniprotDbReference>();
foreach (string enst in isofToEnsembl.Value)
{
enstToData.Add(enst, dbEntries[dbRefType][enst]);
}
modEntry.dbEntries.Add(dbRefType, enstToData);
isoforms.Add(modEntry);
}
return(isoforms);
}
private void StartElement(IEquatable<string> qName, IDictionary<string, string> attrs)
{
if (inFeature){
if (qName.Equals("location")){
//inFeatureLocation = true;
} else if (qName.Equals("position")){
string position = attrs["position"];
featureBegin = position;
featureEnd = position;
} else if (qName.Equals("begin")){
string position = attrs.ContainsKey("position") ? attrs["position"] : attrs["status"];
featureBegin = position;
} else if (qName.Equals("end")){
string position = attrs.ContainsKey("position") ? attrs["position"] : attrs["status"];
featureEnd = position;
} else if (qName.Equals("original")){
original = new StringBuilder();
} else if (qName.Equals("variation")){
variation = new StringBuilder();
}else{
throw new Exception("Unknown qname: " + qName);
}
}
if (inOrganism) {
if (qName.Equals("name")) {
string type = attrs["type"];
if (type.Equals("scientific")) {
oname = new StringBuilder();
}
} else if (qName.Equals("dbReference")) {
string type = attrs["type"];
if (type.Equals("NCBI Taxonomy")) {
string id = attrs["id"];
entry.AddTaxonomyId(id);
}
}
}
if (inOrganismHost) {
if (qName.Equals("dbReference")) {
string type = attrs["type"];
if (type.Equals("NCBI Taxonomy")) {
string id = attrs["id"];
entry.AddHostTaxonomyId(id);
}
}
}
if (qName.Equals("entry")) {
entry = new UniprotEntry();
accessions = new List<string>();
proteinFullNames = new List<string>();
proteinShortNames = new List<string>();
proteinEcNumbers = new List<string>();
gnames = new List<Tuple<string, string>>();
onames = new List<string>();
unames = new List<string>();
level = 0;
numIsoforms = 0;
isoformToEnst = new Dictionary<string, List<string>>();
} else if (qName.Equals("dbReference")){
inDbRef = true;
dbReferenceType = attrs["type"];
dbReferenceId = attrs["id"];
entry.AddDbEntry(dbReferenceType, dbReferenceId);
} else if (qName.Equals("molecule") && dbReferenceType.Equals("Ensembl")){
molecule = new StringBuilder();
} else if (qName.Equals("property")){
if (inDbRef){
entry.AddDbEntryProperty(dbReferenceType, dbReferenceId, attrs["type"], attrs["value"]);
}
} else if (qName.Equals("feature")){
inFeature = true;
featureType = attrs.ContainsKey("type") ? attrs["type"] : "";
featureDescription = attrs.ContainsKey("description") ? attrs["description"] : "";
featureStatus = attrs.ContainsKey("status") ? attrs["status"] : "";
featureId = attrs.ContainsKey("id") ? attrs["id"] : "";
entry.AddFeature(featureType, featureDescription, featureStatus, featureId);
} else if (qName.Equals("sequence")) {
sequence = new StringBuilder();
} else if (qName.Equals("keyword")) {
keyword = new StringBuilder();
} else if (qName.Equals("accession")) {
accession = new StringBuilder();
} else if (qName.Equals("protein")){
inProtein = true;
} else if (qName.Equals("recommendedName") && inProtein){
inProteinRecommendedName = true;
} else if (qName.Equals("organism")) {
inOrganism = true;
} else if (qName.Equals("organismHost")) {
inOrganismHost = true;
} else if (qName.Equals("gene")) {
inGene = true;
} else if (qName.Equals("fullName") && inProteinRecommendedName){
proteinFullName = new StringBuilder();
} else if (qName.Equals("shortName") && inProteinRecommendedName){
proteinShortName = new StringBuilder();
} else if (qName.Equals("ecNumber") && inProteinRecommendedName){
proteinEcNumber = new StringBuilder();
} else if (qName.Equals("name") && inGene){
gname = new StringBuilder();
gnameType = attrs["type"];
} else if (qName.Equals("name") && level == 1){
uname = new StringBuilder();
} else if (qName.Equals("isoform")){
if (inDbRef)
++numIsoforms;
}
}
private UniprotEntry CopyEntry()
{
UniprotEntry newEntry = new UniprotEntry();
DbReferenceType[] dbRefTypes = new DbReferenceType[dbEntries.Keys.Count];
dbEntries.Keys.CopyTo(dbRefTypes, 0);
foreach (DbReferenceType refType in dbRefTypes){
string[] dbRefIDs = Get(refType);
foreach (string id in dbRefIDs){
newEntry.AddDbEntry(refType.UniprotName, id);
foreach (KeyValuePair<string, List<string>> property in dbEntries[refType][id].properties){
foreach (var propertyValue in property.Value){
newEntry.AddDbEntryProperty(refType.UniprotName, id, property.Key, propertyValue);
}
}
}
}
if (features != null){
foreach (FeatureType type in GetAllFeatureTypes()){
newEntry.AddFeatures(type, GetFeatures(type));
}
}
foreach (string kword in Keywords){
newEntry.AddKeyword(kword);
}
newEntry.ProteinFullNames = ProteinFullNames;
newEntry.ProteinShortNames = ProteinShortNames;
newEntry.ProteinEcNumbers = ProteinEcNumbers;
newEntry.Accessions = Accessions;
newEntry.GeneNamesAndTypes = GeneNamesAndTypes;
newEntry.OrganismNames = OrganismNames;
newEntry.UniprotNames = UniprotNames;
newEntry.Sequence = Sequence;
foreach (string taxId in taxonomyIds){
newEntry.AddTaxonomyId(taxId);
}
foreach (string hostTaxId in hostTaxonomyIds){
newEntry.AddHostTaxonomyId(hostTaxId);
}
return newEntry;
}
private void StartElement(IEquatable <string> qName, IDictionary <string, string> attrs)
{
if (inFeature)
{
if (qName.Equals("location"))
{
//inFeatureLocation = true;
}
else if (qName.Equals("position"))
{
string position = attrs["position"];
featureBegin = position;
featureEnd = position;
}
else if (qName.Equals("begin"))
{
string position = attrs.ContainsKey("position") ? attrs["position"] : attrs["status"];
featureBegin = position;
}
else if (qName.Equals("end"))
{
string position = attrs.ContainsKey("position") ? attrs["position"] : attrs["status"];
featureEnd = position;
}
else if (qName.Equals("original"))
{
original = new StringBuilder();
}
else if (qName.Equals("variation"))
{
variation = new StringBuilder();
}
else
{
throw new Exception("Unknown qname: " + qName);
}
}
if (inOrganism)
{
if (qName.Equals("name"))
{
string type = attrs["type"];
if (type.Equals("scientific"))
{
oname = new StringBuilder();
}
}
else if (qName.Equals("dbReference"))
{
string type = attrs["type"];
if (type.Equals("NCBI Taxonomy"))
{
string id = attrs["id"];
entry.AddTaxonomyId(id);
}
}
}
if (inOrganismHost)
{
if (qName.Equals("dbReference"))
{
string type = attrs["type"];
if (type.Equals("NCBI Taxonomy"))
{
string id = attrs["id"];
entry.AddHostTaxonomyId(id);
}
}
}
if (qName.Equals("entry"))
{
entry = new UniprotEntry();
accessions = new List <string>();
proteinFullNames = new List <string>();
proteinShortNames = new List <string>();
proteinEcNumbers = new List <string>();
gnames = new List <Tuple <string, string> >();
onames = new List <string>();
unames = new List <string>();
level = 0;
numIsoforms = 0;
isoformToEnst = new Dictionary <string, List <string> >();
}
else if (qName.Equals("dbReference"))
{
inDbRef = true;
dbReferenceType = attrs["type"];
dbReferenceId = attrs["id"];
entry.AddDbEntry(dbReferenceType, dbReferenceId);
}
else if (qName.Equals("molecule") && dbReferenceType.Equals("Ensembl"))
{
molecule = new StringBuilder();
}
else if (qName.Equals("property"))
{
if (inDbRef)
{
entry.AddDbEntryProperty(dbReferenceType, dbReferenceId, attrs["type"], attrs["value"]);
}
}
else if (qName.Equals("feature"))
{
inFeature = true;
featureType = attrs.ContainsKey("type") ? attrs["type"] : "";
featureDescription = attrs.ContainsKey("description") ? attrs["description"] : "";
featureStatus = attrs.ContainsKey("status") ? attrs["status"] : "";
featureId = attrs.ContainsKey("id") ? attrs["id"] : "";
entry.AddFeature(featureType, featureDescription, featureStatus, featureId);
}
else if (qName.Equals("sequence"))
{
sequence = new StringBuilder();
}
else if (qName.Equals("keyword"))
{
keyword = new StringBuilder();
}
else if (qName.Equals("accession"))
{
accession = new StringBuilder();
}
else if (qName.Equals("protein"))
{
inProtein = true;
}
else if (qName.Equals("recommendedName") && inProtein)
{
inProteinRecommendedName = true;
}
else if (qName.Equals("organism"))
{
inOrganism = true;
}
else if (qName.Equals("organismHost"))
{
inOrganismHost = true;
}
else if (qName.Equals("gene"))
{
inGene = true;
}
else if (qName.Equals("fullName") && inProteinRecommendedName)
{
proteinFullName = new StringBuilder();
}
else if (qName.Equals("shortName") && inProteinRecommendedName)
{
proteinShortName = new StringBuilder();
}
else if (qName.Equals("ecNumber") && inProteinRecommendedName)
{
proteinEcNumber = new StringBuilder();
}
else if (qName.Equals("name") && inGene)
{
gname = new StringBuilder();
gnameType = attrs["type"];
}
else if (qName.Equals("name") && level == 1)
{
uname = new StringBuilder();
}
else if (qName.Equals("isoform"))
{
if (inDbRef)
{
++numIsoforms;
}
}
}
