* The contents of this file are subject to the Mozilla Public License Version 1.1
* See LICENSE.TXT at the top of this package for the full license terms.
*/
-
package eu.etaxonomy.cdm.model.molecular;
+import java.net.URI;
import java.util.HashSet;
import java.util.Set;
-import javax.persistence.Basic;
import javax.persistence.Entity;
import javax.persistence.FetchType;
+import javax.persistence.ManyToMany;
import javax.persistence.ManyToOne;
-import javax.persistence.OneToMany;
import javax.persistence.Transient;
+import javax.validation.constraints.Size;
import javax.xml.bind.annotation.XmlAccessType;
import javax.xml.bind.annotation.XmlAccessorType;
import javax.xml.bind.annotation.XmlAttribute;
import javax.xml.bind.annotation.XmlRootElement;
import javax.xml.bind.annotation.XmlSchemaType;
import javax.xml.bind.annotation.XmlType;
-import javax.xml.bind.annotation.adapters.XmlJavaTypeAdapter;
import org.apache.log4j.Logger;
+import org.codehaus.plexus.util.StringUtils;
import org.hibernate.annotations.Cascade;
import org.hibernate.annotations.CascadeType;
-import org.hibernate.annotations.Index;
-import org.hibernate.annotations.Table;
-import org.hibernate.annotations.Type;
import org.hibernate.envers.Audited;
-import org.joda.time.DateTime;
+import org.hibernate.search.annotations.IndexedEmbedded;
import org.springframework.beans.factory.annotation.Configurable;
-import eu.etaxonomy.cdm.jaxb.DateTimeAdapter;
-import eu.etaxonomy.cdm.model.common.IReferencedEntity;
-import eu.etaxonomy.cdm.model.common.IdentifiableEntity;
-import eu.etaxonomy.cdm.model.media.IMediaDocumented;
+import eu.etaxonomy.cdm.model.common.AnnotatableEntity;
+import eu.etaxonomy.cdm.model.common.DefinedTerm;
+import eu.etaxonomy.cdm.model.common.TermType;
import eu.etaxonomy.cdm.model.media.Media;
import eu.etaxonomy.cdm.model.reference.Reference;
-import eu.etaxonomy.cdm.strategy.cache.common.IIdentifiableEntityCacheStrategy;
-import eu.etaxonomy.cdm.strategy.cache.common.IdentifiableEntityDefaultCacheStrategy;
/**
+ * Alignment of multiple single sequences to a consensus sequence,
+ * may also include the extracted barcode sequence.
+ *
+ * This class holds information about both the combining process of
+ * {@link SingleSequence single sequences} to one consensus sequence
+ * (singleSequences, contigFile) as well as sequence related information.
+ * The later includes the sequence string itself, important genetic information
+ * (marker, haplotype) as well as registration information (genetic accession number)
+ * citations and barcoding information.
+ *
* @author m.doering
- * @version 1.0
* @created 08-Nov-2007 13:06:51
+ * @author a.mueller
+ * @updated 11-Jul-2013
*/
@XmlAccessorType(XmlAccessType.FIELD)
@XmlType(name = "Sequence", propOrder = {
- "sequence",
- "length",
- "dateSequenced",
- "barcode",
- "citationMicroReference",
- "publishedIn",
- "locus",
- "citations",
- "genBankAccession",
- "chromatograms"
+ "dnaSample",
+ "consensusSequence",
+ "isBarcode",
+ "barcodeSequencePart",
+ "marker",
+ "geneticAccessionNumber",
+ "boldProcessId",
+ "haplotype",
+ "contigFile",
+ "singleSequences",
+ "citations"
})
-@XmlRootElement(name = "Sequence")
+@XmlRootElement(name = "Sequencing")
@Entity
@Audited
@Configurable
-@Table(appliesTo="Sequence", indexes = { @Index(name = "sequenceTitleCacheIndex", columnNames = { "titleCache" }) })
-public class Sequence extends IdentifiableEntity<IIdentifiableEntityCacheStrategy<Sequence>> implements IReferencedEntity, IMediaDocumented{
+//@Table(appliesTo="Sequence", indexes = { @Index(name = "sequenceTitleCacheIndex", columnNames = { "titleCache" }) })
+public class Sequence extends AnnotatableEntity implements Cloneable{
private static final long serialVersionUID = 8298983152731241775L;
private static final Logger logger = Logger.getLogger(Sequence.class);
- //the sequence as a string of base pairs. 5'->3'
- @XmlElement(name = "Sequence")
- private String sequence;
+ private static final String GENBANK_BASE_URI = "http://www.ncbi.nlm.nih.gov/nuccore/%s";
+ private static final String EMBL_BASE_URI = "http://www.ebi.ac.uk/ena/data/view/%s";
+ private static final String DDBJ_BASE_URI = "http://getentry.ddbj.nig.ac.jp/getentry/na/%s/?filetype=html";
+ private static final String BOLD_BASE_URI = "http://www.boldsystems.org/index.php/Public_RecordView?processid=%s";
+
+ @XmlElement( name = "DnaSample")
+ @XmlIDREF
+ @XmlSchemaType(name = "IDREF")
+ @ManyToOne(fetch = FetchType.LAZY)
+ @IndexedEmbedded
+ private DnaSample dnaSample;
+
- //should be calculated in case sequence is set
- @XmlElement(name = "Length")
- private Integer length;
+ /** @see #getContigFile() */
+ @XmlElement(name = "ContigFile")
+ @XmlIDREF
+ @XmlSchemaType(name = "IDREF")
+ @ManyToOne(fetch = FetchType.LAZY)
+ private Media contigFile;
+
+ /** @see #getConsensusSequence() */
+ @XmlElement(name = "ConsensusSequence")
+ private SequenceString consensusSequence = SequenceString.NewInstance();
- //should be calculated in case sequence is set
- @XmlElement (name = "DateSequenced", type= String.class)
- @XmlJavaTypeAdapter(DateTimeAdapter.class)
- @Type(type="dateTimeUserType")
- @Basic(fetch = FetchType.LAZY)
- private DateTime dateSequenced;
+// /**{@link #getSequence()}*/
+// @XmlElement(name = "Sequence")
+// @Lob
+// private String sequence;
+//
+// @XmlElement(name = "Length")
+// private Integer length;
+
- //should be calculated in case sequence is set
@XmlAttribute(name = "isBarcode")
- private boolean barcode;
+ private Boolean isBarcode = null;
- //the sequence as a string of base pairs. 5'->3'
- @XmlElement(name = "CitationMicroReference")
- private String citationMicroReference;
+ /** @see #getBarcodeSequence()*/
+ @XmlElement(name = "BarcodeSequencePart")
+ private SequenceString barcodeSequencePart = SequenceString.NewInstance();
+
+ /** @see #getGeneticAccessionNumber()*/
+ @XmlElement(name = "GeneticAccessionNumber")
+ @Size(max=20)
+ private String geneticAccessionNumber;
+
+ /** @see #getBoldProcessId() */
+ @XmlElement(name = "BoldProcessId")
+ @Size(max=20)
+ private String boldProcessId;
- @XmlElement(name = "PublishedIn")
+ @XmlElementWrapper(name = "SingleSequences")
+ @XmlElement(name = "SingleSequence")
+ @XmlIDREF
+ @XmlSchemaType(name = "IDREF")
+ @ManyToMany(fetch = FetchType.LAZY)
+ @Cascade({CascadeType.SAVE_UPDATE})
+ private Set<SingleSequence> singleSequences = new HashSet<SingleSequence>();
+
+ /** @see #getMarker() */
+ @XmlElement(name = "Marker")
@XmlIDREF
@XmlSchemaType(name = "IDREF")
@ManyToOne(fetch = FetchType.LAZY)
- @Cascade(CascadeType.SAVE_UPDATE)
- private Reference<?> publishedIn;
+ //no cascade as it is a defined term
+ private DefinedTerm marker;
+
+
+ /** @see #getHaplotype() */
+ @XmlElement(name = "Haplotype")
+ @Size(max=100)
+ private String haplotype;
+ /** @see #getCitations() */
@XmlElementWrapper(name = "Citations")
- @XmlElement(name = "Citation")
+ @XmlElement(name = "Citation")
@XmlIDREF
@XmlSchemaType(name = "IDREF")
- @OneToMany(fetch = FetchType.LAZY)
+ @ManyToMany(fetch = FetchType.LAZY)
+ @Cascade({CascadeType.SAVE_UPDATE})
private Set<Reference> citations = new HashSet<Reference>();
- @XmlElementWrapper(name = "GenBankAccessions")
- @XmlElement(name = "GenBankAccession")
- @OneToMany(fetch = FetchType.LAZY)
- @Cascade(CascadeType.SAVE_UPDATE)
- private Set<GenBankAccession> genBankAccession = new HashSet<GenBankAccession>();
+// //should be calculated in case sequence is set
+// @XmlElement (name = "DateSequenced", type= String.class)
+// @XmlJavaTypeAdapter(DateTimeAdapter.class)
+// @Type(type="dateTimeUserType")
+// @Basic(fetch = FetchType.LAZY)
+// private DateTime dateSequenced;
- @XmlElement(name = "Locus")
- @XmlIDREF
- @XmlSchemaType(name = "IDREF")
- @ManyToOne(fetch = FetchType.LAZY)
- @Cascade(CascadeType.SAVE_UPDATE)
- private Locus locus;
-
- @XmlElementWrapper(name = "Chromatograms")
- @XmlElement(name = "Chromatogram")
- @XmlIDREF
- @XmlSchemaType(name = "IDREF")
- @OneToMany(fetch = FetchType.LAZY)
- private Set<Media> chromatograms = new HashSet<Media>();
//*********************** FACTORY ****************************************************/
- public static Sequence NewInstance(String sequence){
+ public static Sequence NewInstance(String consensusSequence){
Sequence result = new Sequence();
- result.setSequence(sequence);
+ result.setSequenceString(consensusSequence);
return result;
}
//*********************** CONSTRUCTOR ****************************************************/
- protected Sequence() {
- super(); // FIXME I think this is explicit - do we really need to call this?
- this.cacheStrategy = new IdentifiableEntityDefaultCacheStrategy<Sequence>();
- }
+ protected Sequence() {}
//*********************** GETTER / SETTER ****************************************************/
- public Locus getLocus(){
- return this.locus;
- }
- public void setLocus(Locus locus){
- this.locus = locus;
+ /**
+ * The {@link DnaSample dna sample} this sequencing belongs too.
+ */
+ public DnaSample getDnaSample() {
+ return dnaSample;
}
- public Reference getPublishedIn(){
- return this.publishedIn;
- }
-
- public void setPublishedIn(Reference publishedIn){
- this.publishedIn = publishedIn;
+ //TODO bidirectionality??
+ /**
+ * @see #getDnaSample()
+ */
+ private void setDnaSample(DnaSample dnaSample) {
+ this.dnaSample = dnaSample;
}
- public Set<Reference> getCitations() {
- return citations;
+ /**
+ * The consensus sequence achieved by this sequencing.
+ */
+ public SequenceString getConsensusSequence() {
+ return consensusSequence;
}
- protected void setCitations(Set<Reference> citations) {
- this.citations = citations;
+
+
+ /**
+ * @see #getConsensusSequence()
+ */
+ public void setConsensusSequence(SequenceString sequenceString) {
+ if (sequenceString == null){
+ sequenceString = SequenceString.NewInstance();
+ }
+ this.consensusSequence = sequenceString;
}
- public void addCitation(Reference citation) {
- this.citations.add(citation);
+
+ /**
+ * The isBarcode flag should be set to true if this (consensus) sequence is or includes
+ * a barcode sequence. If the barcode sequence is only a part of the consensus sequence
+ * this part is to be stored as {@link #getBarcodeSequencePart() barcode sequence part}.
+ * A isBarcode value of <code>null</code> indicates that we do have no knowledge
+ * wether the sequence is a barcoding sequence or not.
+ *
+ * @see #getBarcodeSequencePart()
+ * @see #getSequenceString()
+ * @returns the isBarcode flag value (tri-state)
+ *
+ */
+ public Boolean getIsBarcode() {
+ return isBarcode;
}
- public void removeCitation(Reference citation) {
- this.citations.remove(citation);
+
+ /**
+ * @see #getIsBarcode()
+ * @see #getBarcodeSequencePart()
+ */
+ public void setIsBarcode(Boolean isBarcode) {
+ this.isBarcode = isBarcode;
}
- public Set<GenBankAccession> getGenBankAccession() {
- return genBankAccession;
+ /**
+ * If the barcode sequence string does not include 100% of the (consensus) sequence
+ * the part used as barcode is provided here. However, the barcode part
+ * should be kept if consensus sequence string and barcode sequence string are equal.
+ *
+ * @see #getIsBarcode()
+ */
+ public SequenceString getBarcodeSequencePart() {
+ return barcodeSequencePart;
}
- public void addGenBankAccession(GenBankAccession genBankAccession) {
- this.genBankAccession.add(genBankAccession);
+ /**
+ * @see #getBarcodeSequence()
+ */
+ public void setBarcodeSequence(SequenceString barcodeSequencePart) {
+ if (barcodeSequencePart == null){
+ barcodeSequencePart = SequenceString.NewInstance();
+ }
+ this.barcodeSequencePart = barcodeSequencePart;
}
- public void removeGenBankAccession(GenBankAccession genBankAccession) {
- this.genBankAccession.remove(genBankAccession);
+ /**
+ * Sets the {@link TermType#DnaMarker marker} examined and described by this sequencing.
+ * @return
+ */
+ public DefinedTerm getMarker(){
+ return this.marker;
}
-
- public Set<Media> getChromatograms() {
- return chromatograms;
+
+ /**
+ * @see #getMarker()
+ * @param marker
+ */
+ public void setMarker(DefinedTerm marker){
+ this.marker = marker;
}
- public void addChromatogram(Media chromatogram) {
- this.chromatograms.add(chromatogram);
+ /**
+ * The accession number used in GenBank, EMBL and DDBJ.
+ * @return
+ */
+ public String getGeneticAccessionNumber() {
+ return geneticAccessionNumber;
}
-
- public void removeChromatogram(Media chromatogram) {
- this.chromatograms.remove(chromatogram);
+
+ /**
+ * Sets the genetic accession number.
+ * @see #getGeneticAccessionNumber()
+ */
+ public void setGeneticAccessionNumber(String geneticAccessionNumber) {
+ this.geneticAccessionNumber = geneticAccessionNumber;
}
- @Transient
- public Set<Media> getMedia() {
- return getChromatograms();
+
+ /**
+ * The identifier used by the Barcode of Life Data Systems (BOLD, http://www.boldsystems.org/).
+ */
+ public String getBoldProcessId() {
+ return boldProcessId;
}
- public String getSequence(){
- return this.sequence;
+ public void setBoldProcessId(String boldProcessId) {
+ this.boldProcessId = boldProcessId;
}
/**
- *
- * @param sequence sequence
+ * Returns the name of the haplotype.
+ * A haplotype (haploide genotype) is a variant of nucleotide sequences on the same chromosome.
+ * A certain haplotype may be specific for an individual, a population or a species.
+ * @return
*/
- public void setSequence(String sequence){
- this.sequence = sequence;
+ public String getHaplotype() {
+ return haplotype;
}
- public Integer getLength(){
- return this.length;
+ /**
+ * @see #getHaplotype()
+ */
+ public void setHaplotype(String haplotype) {
+ this.haplotype = haplotype;
}
/**
- *
- * @param length length
+ * The contigFile containing all data and data processing for this sequencing.
*/
- public void setLength(Integer length){
- this.length = length;
+ public Media getContigFile() {
+ return contigFile;
}
- public DateTime getDateSequenced(){
- return this.dateSequenced;
+ /**
+ * @see #getContigFile()
+ */
+ public void setContigFile(Media contigFile) {
+ this.contigFile = contigFile;
+ }
+
+
+ /**
+ * Citations are the set of references in which this sequence was published.
+ * Unlike taxonomic names the first publication of a sequence
+ * is not so important (maybe because it is required by publishers
+ * that they are all registered at Genbank) therefore we do not have something like an
+ * "original reference" attribute.<BR>
+ * Links to these references are to be stored within the reference itself.
+ * @return the set of references in which this sequence was published.
+ */
+ public Set<Reference> getCitations() {
+ return citations;
+ }
+ /**
+ * @see #getCitations()
+ */
+ protected void setCitations(Set<Reference> citations) {
+ this.citations = citations;
+ }
+ /**
+ * @see #getCitations()
+ */
+ public void addCitation(Reference citation) {
+ this.citations.add(citation);
+ }
+ /**
+ * @see #getCitations()
+ */
+ public void removeCitation(Reference citation) {
+ this.citations.remove(citation);
}
/**
- *
- * @param dateSequenced dateSequenced
+ * The single sequences that where used to create this consensus sequence.
+ */
+ public Set<SingleSequence> getSingleSequences() {
+ return singleSequences;
+ }
+ /**
+ * @see #getSingleSequences()
+ */
+ public void addSingleSquence(SingleSequence singleSequence) {
+ this.singleSequences.add(singleSequence);
+ }
+ /**
+ * @see #getSingleSequences()
+ */
+ public void removeSingleSquence(SingleSequence singleSequence) {
+ this.singleSequences.remove(singleSequence);
+ }
+ /**
+ * @see #getSingleSequences()
+ */
+ //TODO private as long it is unclear how bidirectionality is handled
+ private void setSingleSequences(Set<SingleSequence> singleSequences) {
+ this.singleSequences = singleSequences;
+ }
+
+
+ //*************************** Transient GETTER /SETTER *****************************/
+
+ /**
+ * Delegate method to get the text representation of the consensus sequence
+ * @see #setSequenceString(String)
*/
- public void setDateSequenced(DateTime dateSequenced){
- this.dateSequenced = dateSequenced;
+ @Transient
+ public String getSequenceString() {
+ return consensusSequence.getString();
}
- public boolean isBarcode(){
- return this.barcode;
+ /**
+ * Delegate method to set the text representation of the {@link #getConsensusSequence()
+ * consensus sequence}.
+ */
+ @Transient
+ public void setSequenceString(String sequence) {
+ consensusSequence.setString(sequence);
}
+
+ /**
+ * Convenience method which computes the set of all related pherograms
+ * @return the set of pherograms.
+ */
+ @Transient
+ public Set<Media> getPherograms(){
+ Set<Media> result = new HashSet<Media>();
+ for (SingleSequence singleSeq : singleSequences){
+ if (singleSeq.getPherogram() != null){
+ result.add(singleSeq.getPherogram());
+ }
+ }
+ return result;
+ }
+
+ //***** Registrations ************/
/**
- *
- * @param isBarcode isBarcode
+ * Returns the computed genBank uri.
+ * @return
*/
- public void setBarcode(boolean barcode){
- this.barcode = barcode;
+ @Transient
+ public URI getGenBankUri() {
+ return createExternalUri(GENBANK_BASE_URI);
}
- public String getCitationMicroReference(){
- return this.citationMicroReference;
+ /**
+ * Returns the computed EMBL uri.
+ * @return
+ */
+ @Transient
+ public URI getEmblUri() {
+ return createExternalUri(EMBL_BASE_URI);
}
/**
- *
- * @param citationMicroReference citationMicroReference
+ * Returns the computed DDBJ uri.
+ * @return
+ */
+ @Transient
+ public URI getDdbjUri() {
+ return createExternalUri(DDBJ_BASE_URI);
+ }
+
+ /**
+ * Returns the URI for the BOLD entry.
+ * @see #getBoldProcessId()
*/
- public void setCitationMicroReference(String citationMicroReference){
- this.citationMicroReference = citationMicroReference;
+ @Transient
+ public URI getBoldUri() {
+ return createExternalUri(BOLD_BASE_URI);
}
- public Reference getCitation(){
- return publishedIn;
+
+ private URI createExternalUri(String baseUri){
+ if (StringUtils.isNotBlank(geneticAccessionNumber)){
+ return URI.create(String.format(baseUri, geneticAccessionNumber.trim()));
+ }else{
+ return null;
+ }
}
+
//*********************** CLONE ********************************************************/
/**
* Clones <i>this</i> sequence. This is a shortcut that enables to create
- * a new instance that differs only slightly from <i>this</i> sequence by
+ * a new instance that differs only slightly from <i>this</i> sequencing by
* modifying only some of the attributes.<BR><BR>
*
*
try{
Sequence result = (Sequence)super.clone();
- result.citations = new HashSet<Reference>();
- for (Reference ref: this.citations){
- result.citations.add((Reference) ref.clone());
+ //sequences
+ result.consensusSequence = (SequenceString)this.consensusSequence.clone();
+ result.barcodeSequencePart = (SequenceString)this.barcodeSequencePart.clone();
+
+ //single sequences
+ result.singleSequences = new HashSet<SingleSequence>();
+ for (SingleSequence seq: this.singleSequences){
+ result.singleSequences.add((SingleSequence) seq);
}
- result.genBankAccession = new HashSet<GenBankAccession>();
- for (GenBankAccession genBankAcc: this.genBankAccession){
- result.genBankAccession.add((GenBankAccession)genBankAcc.clone());
+ //citations //TODO do we really want to copy these ??
+ result.citations = new HashSet<Reference>();
+ for (Reference ref: this.citations){
+ result.citations.add((Reference) ref);
}
- result.chromatograms = new HashSet<Media>();
- for (Media chromatogram: this.chromatograms){
- result.chromatograms.add((Media)chromatogram.clone());
- }
return result;
}catch (CloneNotSupportedException e) {
return null;
}
}
+
+
}
\ No newline at end of file
BGBM BDI Projects / cdmlib.git / blobdiff