Skip to content

Add an EMBL file parser to BioJava #621 #713

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sbliven merged 12 commits into from
Feb 20, 2018
Merged

Add an EMBL file parser to BioJava #621 #713

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
68dffbb
add classes of new feature parser for embl file
Oct 19, 2017
3dc43b4
t
Oct 19, 2017
fc23c95
t
Oct 19, 2017
9976d2c
testing embl parser
Nov 19, 2017
1eb16b2
Merge branch 'master' of https://github.com/biojava/biojava
Nov 19, 2017
d3e8e83
first version of embl parser
Nov 21, 2017
d49b3f9
pull changes request
NoorAldeenMB Dec 3, 2017
79f0ed4
Embl Changes
NoorAldeenMB Dec 3, 2017
d24230a
Embl Changes
NoorAldeenMB Dec 3, 2017
141a8da
Embl changes
NoorAldeenMB Dec 3, 2017
9673da4
using resource loader in testing.
NoorAldeenMB Dec 4, 2017
40ddf40
insert license header
NoorAldeenMB Dec 5, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
113 changes: 113 additions & 0 deletions biojava-core/src/main/java/org/biojava/nbio/core/sequence/io/embl/EmblId.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,113 @@
/*
* BioJava development code
*
* This code may be freely distributed and modified under the
* terms of the GNU Lesser General Public Licence. This should
* be distributed with the code. If you do not have a copy,
* see:
*
* http://www.gnu.org/copyleft/lesser.html
*
* Copyright for this code is held jointly by the individual
* authors. These should be listed in @author doc comments.
*
* For more information on the BioJava project and its aims,
* or to join the biojava-l mailing list, visit the home page
* at:
*
* http://www.biojava.org/
*
*/
package org.biojava.nbio.core.sequence.io.embl;
Copy link
Copy Markdown
Member

@heuermh heuermh Dec 4, 2017

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

All source code in biojava requires the license header

Copy link
Copy Markdown
Contributor Author

@NoorAldeenMB NoorAldeenMB Dec 5, 2017

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done.


import jdk.nashorn.internal.ir.annotations.Immutable;

/**
* This class contains the processed data of embl file
* Primary accession number
* Sequence version number
* Topology: 'circular' or 'linear'
* Molecule type
* Data class
* Taxonomic division
* Sequence length
*
* @author Noor Aldeen Al Mbaidin
* @since 5.0.0
*/
@Immutable
public class EmblId {


private final String primaryAccession;
private final String sequenceVersion;
private final String topology;
private final String moleculeType;
private final String dataClass;
private final String taxonomicDivision;
private final String sequenceLength;

public EmblId(String primaryAccession, String sequenceVersion, String topology,
String moleculeType, String dataClass, String taxonomicDivision,
String sequenceLength) {
this.primaryAccession = primaryAccession;
this.sequenceVersion = sequenceVersion;
this.topology = topology;
this.moleculeType = moleculeType;
this.dataClass = dataClass;
this.taxonomicDivision = taxonomicDivision;
this.sequenceLength = sequenceLength;
}

/**
* @return String
*/
public String getPrimaryAccession() {
return primaryAccession;
}

/**
* return the sequence version
*
* @return String
*/
public String getSequenceVersion() {
return sequenceVersion;
}

public String getTopology() {
return topology;
}

/**
* Molecule type this represents the type of molecule as stored
*
* @return String
*/
public String getMoleculeType() {
return moleculeType;
}

public String getDataClass() {
return dataClass;
}

/**
* @return String
*/
public String getTaxonomicDivision() {
return taxonomicDivision;
}

/**
* Sequence length The last item on the ID line is the length of the
* sequence (the total number of bases in the sequence). This number includes
* base positions reported as present but undetermined (coded as "N").
*
* @return String
*/
public String getSequenceLength() {
return sequenceLength;
}

}
163 changes: 163 additions & 0 deletions biojava-core/src/main/java/org/biojava/nbio/core/sequence/io/embl/EmblReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,163 @@
/*
* BioJava development code
*
* This code may be freely distributed and modified under the
* terms of the GNU Lesser General Public Licence. This should
* be distributed with the code. If you do not have a copy,
* see:
*
* http://www.gnu.org/copyleft/lesser.html
*
* Copyright for this code is held jointly by the individual
* authors. These should be listed in @author doc comments.
*
* For more information on the BioJava project and its aims,
* or to join the biojava-l mailing list, visit the home page
* at:
*
* http://www.biojava.org/
*
*/
package org.biojava.nbio.core.sequence.io.embl;
Copy link
Copy Markdown
Member

@heuermh heuermh Dec 4, 2017

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

All source code in biojava requires the license header

Copy link
Copy Markdown
Contributor Author

@NoorAldeenMB NoorAldeenMB Dec 5, 2017

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done.



import java.io.*;
import java.util.Arrays;
import java.util.LinkedList;


/**
* This class should process the data of embl file
*
* @author Noor Aldeen Al Mbaidin
* @since 5.0.0
*/
public class EmblReader {

/**
* The parsing is done in this method.<br>
* This method tries to process all the Embl records
* in the File , closes the underlying resource,
* and return the results in object of EmblRecord.<br>
*
* @return EmblRecord containing all the parsed Embl records
* @throws IOException
*/
public static EmblRecord process(File file) throws IOException {

EmblRecord emblRecord = new EmblRecord();
StringBuilder sequence = new StringBuilder("");
LinkedList<EmblReference> emblReferences = new LinkedList<>();
EmblReference emblReference = new EmblReference();
LinkedList<String> accessionNumber = new LinkedList<>();
LinkedList<String> keyword = new LinkedList<>();

if (file == null)
throw new NullPointerException("file can't be null");

if (file.isDirectory())
throw new IllegalArgumentException("the file can't be a directory");

try (FileReader fileReader = new FileReader(file)) {
String line = "";
String lineIdentifier;
String lineInfo;
try (BufferedReader bufferedReader = new BufferedReader(fileReader)) {
while ((line = bufferedReader.readLine()) != null) {
if (line.length() > 1) {
lineInfo = line.substring(2, line.length()).trim();
lineIdentifier = line.substring(0, 2);
if (lineIdentifier.equals("ID"))
emblRecord.setEmblId(populateID(lineInfo));
else if (lineIdentifier.equals("AC"))
populateAccessionNumber(line, accessionNumber);
else if (lineIdentifier.equals("DT") && line.contains("Created"))
emblRecord.setCreatedDate(lineInfo);
else if (lineIdentifier.equals("DT") && line.contains("updated"))
emblRecord.setLastUpdatedDate(lineInfo);
else if (lineIdentifier.equals("DE"))
emblRecord.setSequenceDescription(lineInfo);
else if (lineIdentifier.equals("KW"))
keyword.add(lineInfo);
else if (lineIdentifier.equals("OS"))
emblRecord.setOrganismSpecies(lineInfo);
else if (lineIdentifier.equals("OC"))
emblRecord.setOrganismClassification(lineInfo);
else if (lineIdentifier.equals("OG"))
emblRecord.setOrGanelle(lineInfo);
else if (lineIdentifier.equals("RN") || lineIdentifier.equals("RP")
|| lineIdentifier.equals("RX") || lineIdentifier.equals("RG")
|| lineIdentifier.equals("RA") || lineIdentifier.equals("RT")
|| lineIdentifier.equals("RL"))
populateEmblReferences(lineIdentifier, lineInfo, emblReference, emblReferences);
else if (lineIdentifier.equals("DR"))
emblRecord.setDatabaseCrossReference(lineInfo);
else if (lineIdentifier.equals("AH"))
emblRecord.setAssemblyHeader(lineInfo);
else if (lineIdentifier.equals("AS"))
emblRecord.setAssemblyInformation(lineInfo);
else if (lineIdentifier.equals("CO"))
emblRecord.setConstructedSequence(lineInfo);
else if (lineIdentifier.equals("FH"))
emblRecord.setFeatureHeader(lineInfo);
else if (lineIdentifier.equals("FT"))
emblRecord.setFeatureTable(lineInfo);
else if (lineIdentifier.equals("SQ"))
emblRecord.setSequenceHeader(lineInfo);
else if (lineIdentifier.equals(" ") && !lineIdentifier.equals("//"))
populateSequence(line, sequence);
else if (lineIdentifier.equals("//")) {
emblRecord.setKeyword(keyword);
emblRecord.setEmblReference(emblReferences);
emblRecord.setAccessionNumber(accessionNumber);
emblRecord.setSequence(sequence.toString());
}

}
}
}
}

return emblRecord;
}

private static void populateSequence(String line, StringBuilder sequence) {
String sequenceLine = line.replace(" ", "").
replaceAll("[0-9]", "");
sequence.append(sequenceLine);
}

private static void populateEmblReferences(String lineIdentifier, String lineInfo, EmblReference emblReference
, LinkedList<EmblReference> emblReferences) {
if (lineIdentifier.equals("RN"))
emblReference.setReferenceNumber(lineInfo);
else if (lineIdentifier.equals("RP"))
emblReference.setReferencePosition(lineInfo);
else if (lineIdentifier.equals("RX"))
emblReference.setReferenceCrossReference(lineInfo);
else if (lineIdentifier.equals("RG"))
emblReference.setReferenceGroup(lineInfo);
else if (lineIdentifier.equals("RA"))
emblReference.setReferenceAuthor(lineInfo);
else if (lineIdentifier.equals("RT"))
emblReference.setReferenceTitle(lineInfo);
else if (lineIdentifier.equals("RL")) {
emblReference.setReferenceLocation(lineInfo);
emblReferences.add(emblReference.copyEmblReference(emblReference));
}
}

private static void populateAccessionNumber(String line, LinkedList<String> accessionNumber) {
accessionNumber.add(line);
}

private static EmblId populateID(String line) {
String[] strings = line.split(";");
Arrays.stream(strings).map(String::trim).toArray(unused -> strings);
EmblId emblId = new EmblId(strings[0], strings[1], strings[2]
, strings[3], strings[4], strings[5], strings[6]);
return emblId;
}


}
Loading