Java Bioinformatics - Get all indices of multiple specific words in a string
I have a project in my Bioinformatics course at university and one of the things in my project is gene prediction.
My problem today is how to get all the indices of more than one specific word in a string. For example, in my case, I want to find all occurrences of start codons ("AUG")
and stop codons ("UAA","UAG", "UGA")
and use them to predict genes, just trying to do an Open Reading Frame (ORF)
Here's my source code:
private void jButton3ActionPerformed(java.awt.event.ActionEvent evt) {
// TODO add your handling code here:
// textArea1.setText(null);\
String str = jTextField1.getText(), y = "", gene = "", dnax = "", text = "";
SymbolList dna = null;
int start_codon_index = -1, stop_codon_index = -1;
if ("".equals(str)) {
jTextArea1.setText("No DNA strand entered.. ");
} else {
if (checksum(str) == 100) {
try {
dna = DNATools.createDNA(str);
} catch (IllegalSymbolException ex) {
Logger.getLogger(m.class.getName()).log(Level.SEVERE, null, ex);
}
try {
dna = DNATools.toRNA(dna);
} catch (IllegalAlphabetException ex) {
Logger.getLogger(m.class.getName()).log(Level.SEVERE, null, ex);
}
dnax = dna.seqString().toUpperCase();
if (dnax.length() % 3 != 0) {
if (dnax.length() % 3 == 1) {
dnax += "-";
}
if (dnax.length() % 3 == 2) {
dnax += "-";
}
}
// System.out.println(dnax);
for (int g = 0; g < dnax.length(); g += 3) {
y = dnax.substring(g, g + 3);
if ("AUG".equals(y)) {
start_codon_index = g;
} else if (start_codon_index != -1 && ("UGA".equals(y) || "UAG".equals(y) || "UAA".equals(y))) {
stop_codon_index = g + 3;
}
}
if (stop_codon_index != -1 && start_codon_index != -1) {
String k = "";
int a = 0;
for (a = start_codon_index; a < stop_codon_index; a++) {
gene += dnax.charAt(a);
}
text += "\nGene start position: " + start_codon_index + "\nGene end position: " + a + "\n Gene: " + gene;
jTextArea1.setText(text);
} else {
jTextArea1.setText("No genes found in Seq: " + dnax);
}
} else {
jTextArea1.setText("Text entered is not a DNA strand..");
}
}
}
Here is the checksum () method:
private static int checksum(String x) {
int i = 0, checks = 0, count = 0;
char c;
x = x.toUpperCase();
while (i < x.length()) {
c = x.charAt(i);
if (c == 'A' || c == 'T' || c == 'G' || c == 'C' || c == '-') {
count++;
}
i++;
}
try {
checks = (count / x.length()) * 100;
} catch (Exception e) {
e.printStackTrace();
}
return checks;
}
I've tried other solutions but nothing works for me. Any help / suggestion is greatly appreciated.
+3
source to share
2 answers
I think you are asking how to find the indices of these specific codons? And dnax is the string you are checking?
You can use indexOf(String str, int fromIndex)
. It returns -1 if no substring was found.
Perhaps something like this might help,
List<Integer> startCodonIndices = new ArrayList<Integer>();
int index;
for (int i=0; i+3<dnax.length(); i++) {
index = indexOf("AUG", i);
startCodonIndices.add(index);
}
+1
source to share
this is what i changed and added based on your suggestions in my code:
for (int i = 0; i + 3 < dnax.length(); i++) {
index = indexOf("AUG", i);
startCodonIndices.add(index);
}
List stopCodonIndices = new ArrayList();
int i2, i3, i4;
for (int j = 0; j + 3 < dnax.length(); j++) {
i2 = indexOf("UGA", j);
i3 = indexOf("UAA", j);
i4 = indexOf("UAG", j);
stopCodonIndices.add(i2);
stopCodonIndices.add(i3);
stopCodonIndices.add(i4);
}
for (int n = 0; n < dnax.length(); n++) {
for (int k = 0; k < startCodonIndices.size() - 1; k++) {
for (int h = 0; h < stopCodonIndices.size() - 1; h++) {
gene = dnax.substring(k, h);
jTextArea1.append("\n" + gene);
}
}
}
Seq result = ATGACCTGA:
A
AU
AUG
AUGA
AUGAC
AUGACC
AUGACCU
AUGACCUG
AUGACCUGA
Mistake:
Exception in thread "AWT-EventQueue-0" java.lang.StringIndexOutOfBoundsException: String index out of range: 10
at java.lang.String.substring(String.java:1951)
at bio.m.jButton3ActionPerformed(m.java:365)
at bio.m.access$200(m.java:36)
at bio.m$3.actionPerformed(m.java:142)
at javax.swing.AbstractButton.fireActionPerformed(AbstractButton.java:2022)
at javax.swing.AbstractButton$Handler.actionPerformed(AbstractButton.java:2346)
at javax.swing.DefaultButtonModel.fireActionPerformed(DefaultButtonModel.java:402)
at javax.swing.DefaultButtonModel.setPressed(DefaultButtonModel.java:259)
at javax.swing.plaf.basic.BasicButtonListener.mouseReleased(BasicButtonListener.java:252)
at com.jtattoo.plaf.BaseButtonListener.mouseReleased(BaseButtonListener.java:60)
at java.awt.Component.processMouseEvent(Component.java:6525)
at javax.swing.JComponent.processMouseEvent(JComponent.java:3324)
at java.awt.Component.processEvent(Component.java:6290)
at java.awt.Container.processEvent(Container.java:2234)
at java.awt.Component.dispatchEventImpl(Component.java:4881)
at java.awt.Container.dispatchEventImpl(Container.java:2292)
at java.awt.Component.dispatchEvent(Component.java:4703)
at java.awt.LightweightDispatcher.retargetMouseEvent(Container.java:4898)
at java.awt.LightweightDispatcher.processMouseEvent(Container.java:4533)
at java.awt.LightweightDispatcher.dispatchEvent(Container.java:4462)
at java.awt.Container.dispatchEventImpl(Container.java:2278)
at java.awt.Window.dispatchEventImpl(Window.java:2750)
at java.awt.Component.dispatchEvent(Component.java:4703)
at java.awt.EventQueue.dispatchEventImpl(EventQueue.java:751)
at java.awt.EventQueue.access$500(EventQueue.java:97)
at java.awt.EventQueue$3.run(EventQueue.java:702)
at java.awt.EventQueue$3.run(EventQueue.java:696)
at java.security.AccessController.doPrivileged(Native Method)
at java.security.ProtectionDomain$1.doIntersectionPrivilege(ProtectionDomain.java:75)
at java.security.ProtectionDomain$1.doIntersectionPrivilege(ProtectionDomain.java:86)
at java.awt.EventQueue$4.run(EventQueue.java:724)
at java.awt.EventQueue$4.run(EventQueue.java:722)
at java.security.AccessController.doPrivileged(Native Method)
at java.security.ProtectionDomain$1.doIntersectionPrivilege(ProtectionDomain.java:75)
at java.awt.EventQueue.dispatchEvent(EventQueue.java:721)
at java.awt.EventDispatchThread.pumpOneEventForFilters(EventDispatchThread.java:201)
at java.awt.EventDispatchThread.pumpEventsForFilter(EventDispatchThread.java:116)
at java.awt.EventDispatchThread.pumpEventsForHierarchy(EventDispatchThread.java:105)
at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:101)
at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:93)
at java.awt.EventDispatchThread.run(EventDispatchThread.java:82)
It comes back as you can see the gene, but there is something wrong with the edited code
Edit: The code finally does what it needs: getting the start and stop codes from my RNA sequence Here's my final edit:
List startCodonIndices = new ArrayList();
int index = 0;
for (int i = 0; i + 3 < dnax.length(); i++) {
index = dnax.indexOf("AUG", i);
if (index != -1) {
startCodonIndices.add(index);
}
List stopCodonIndices = new ArrayList();
int i2, i3, i4;
for (int j = 0; j + 3 < dnax.length(); j++) {
i2 = dnax.indexOf("UGA", j);
System.out.println("i2: "+i2);
if (i2 != -1) {
stopCodonIndices.add(i2);
}
i3 = dnax.indexOf("UAA", j);
System.out.println("i3: "+i3);
if (i3 != -1) {
stopCodonIndices.add(i3);
}
i4 = dnax.indexOf("UAG", j);
System.out.println("i4: "+i4);
if (i4 != -1) {
stopCodonIndices.add(i4);
}
}
for (int v = 0; v < startCodonIndices.size(); v++) {
for (int h = 0; h < stopCodonIndices.size(); h++) {
gene = dnax.substring((int)startCodonIndices.get(v), (int)stopCodonIndices.get(h)+3);
jTextArea1.setText(gene+"\n");
}}
Thank you for your help!
0
source to share