Biojava Fetchgenbank

Question

[J.Ashley]

Hi everyone

Can someone help with this error please. I am trying to translate 6 open reading frames from the fetchgenbank.java program and Translation:SixFrames java program. used in biojava. I am trying to combine the two error but keep receiving the exception error.

Here is what I have so far

 import java.io.BufferedReader;
import java.io.File;
import java.io.FileOutputStream;
import java.io.FileReader;
import java.io.IOException;
import java.io.PrintStream;
import java.util.NoSuchElementException;

import org.biojava.bio.BioException;
import org.biojavax.bio.db.ncbi.GenbankRichSequenceDB;
import org.biojavax.bio.seq.RichSequence;

import org.biojava.bio.Annotation;
import org.biojava.bio.seq.DNATools;
import org.biojava.bio.seq.RNATools;
import org.biojava.bio.seq.Sequence;
import org.biojava.bio.seq.SequenceIterator;
import org.biojava.bio.seq.SequenceTools;
import org.biojava.bio.seq.io.SymbolTokenization;
import org.biojava.bio.symbol.AlphabetManager;
import org.biojava.bio.symbol.IllegalAlphabetException;
import org.biojava.bio.symbol.SymbolList;

import java.util.Scanner;

public class test4{

     public static void main(String[] args) {
             RichSequence rs = null;
             GenbankRichSequenceDB grsdb = new GenbankRichSequenceDB();
             Scanner input = new ScannerSystem.in);

             try{
             // get data via GenBank accession number or gi number
                 System.out.println("Enter a GenBank accession number or gi number: ");
                 String id = input.nextLine();
             }
finally{
                 String id;
                rs = grsdb.getRichSequence(id);
                 System.out.println(rs.getName()+" | "+rs.getDescription());
                 System.out.println(rs.seqString());
             }

             String type;
            SymbolTokenization toke = AlphabetManager.alphabetForName(type)
                     .getTokenization("token");
BufferedReader br = new BufferedReader(new FileReader(type));

SequenceIterator seqi = RichSequence.IOTools.readFasta(br,toke, 
null);

SequenceIterator seqi1 = RichSequence.IOTools.readFasta(br,
toke, null);
                while (seqi1.hasNext()) {
                Sequence seq = seqi1.nextSequence();

                // for each frame
                for (int i = 0; i < 3; i++) {
                    SymbolList prot;
                    Sequence trans;


SymbolList syms = seq.subList(i + 1, seq.length()
- (seq.length() - i) % 3);
if (syms.getAlphabet() == DNATools.getDNA()) {
syms = DNATools.toRNA(syms);
}
prot = RNATools.translate(syms);
trans = SequenceTools.createSequence(prot, "", seq
            .getName()
        + "TranslationFrame: +" + i,
    Annotation.EMPTY_ANNOTATION);

    syms = RNATools.reverseComplement(syms);
    prot = RNATools.translate(syms);
    trans = SequenceTools.createSequence(prot, "", seq
    .getName()
    + " TranslationFrame: -" + i,
    Annotation.EMPTY_ANNOTATION);

            }
            br.close();
        } 
     }
} catch (IOException e) {
    e.printStackTrace();
} catch (IllegalAlphabetException e) {
    e.printStackTrace();
} catch (NoSuchElementException e) {
    e.printStackTrace();
} catch (BioException e) {
    e.printStackTrace();
}
}
}

[Pierre Lindenbaum]

and what is the stacktrace ??

[J.Ashley]

this is the error I am receiving

Exception in thread "main" java.lang.Error: Unresolved compilation problem: 

    at test4.main(test4.java:28)

I am not quite sure since from looking at the other biojava programs the "catch (exceptions) seems to be right

[Pierre Lindenbaum]

are you running your program from eclipse ?

[J.Ashley]

yes I am using eclipse

[Pierre Lindenbaum]

a *.jar is missing in your configuration.

[J.Ashley]

i added the *.jar but still recieved the same results

[Istvan Albert]

make sure to show the entire traceback and also specify exactly which jar files are in discussion

Answer 1

[Hamish]

As your exception message states, the provided code will not compile.

The following code is a corrected version which does the fetch from GenBank and performs the translation, outputting the sequences in fasta format:

import java.io.IOException;
import java.util.NoSuchElementException;
import java.util.Scanner;
import org.biojava.bio.Annotation;
import org.biojava.bio.BioException;
import org.biojava.bio.seq.DNATools;
import org.biojava.bio.seq.RNATools;
import org.biojava.bio.seq.Sequence;
import org.biojava.bio.seq.SequenceTools;
import org.biojava.bio.symbol.IllegalAlphabetException;
import org.biojava.bio.symbol.SymbolList;
import org.biojavax.bio.db.ncbi.GenbankRichSequenceDB;
import org.biojavax.bio.seq.RichSequence;

/** Fetch a GenBank entry and output the translated sequence.
 * 
 * Based on:
 * http://biojava.org/wiki/BioJava:CookBook:ExternalSources:NCBIFetch
 * http://biojava.org/wiki/BioJava:Cookbook:Translation:SixFrames
 *
 */
public class test4 {
    public static void main(String[] args) {
        RichSequence rs = null;
        GenbankRichSequenceDB grsdb = new GenbankRichSequenceDB();
        Scanner input = new ScannerSystem.in);
        try {
            // get data via GenBank accession number or gi number
            System.out.println("Enter a GenBank accession number or gi number: ");
            String id = input.nextLine();
            // Fetch the entry from GenBank/RefSeq.
            rs = grsdb.getRichSequence(id);
            // Output in fasta format.
            RichSequence.IOTools.writeFasta(System.out, rs, null);
            // Assuming this is a nucleotide sequence...
            // For each frame
            for (int i = 0; i < 3; i++) {
                SymbolList syms = rs.subList(i + 1, rs.length() - (rs.length() - i) % 3);
                if (syms.getAlphabet() == DNATools.getDNA()) {
                    syms = DNATools.toRNA(syms);
                }
                // Forward frame.
                SymbolList prot = RNATools.translate(syms);
                Sequence trans = SequenceTools.createSequence(prot, "", 
                        rs.getName() + " TranslationFrame: +" + i,
                        Annotation.EMPTY_ANNOTATION);
                RichSequence.IOTools.writeFasta(System.out, trans, null);
                // Reverse frame.
                syms = RNATools.reverseComplement(syms);
                prot = RNATools.translate(syms);
                trans = SequenceTools.createSequence(prot, "", 
                        rs.getName() + " TranslationFrame: -" + i,
                        Annotation.EMPTY_ANNOTATION);
                RichSequence.IOTools.writeFasta(System.out, trans, null);
            }
        } catch (IllegalAlphabetException e) {
            e.printStackTrace();
        } catch (NoSuchElementException e) {
            e.printStackTrace();
        } catch (BioException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

Please note that the use of GenBank entry names is not a good idea, since these can change and are specific to GenBank and do not appear in the other INSDC databases. I would suggest using the INSDC primary accessions (i.e. getAccession() instead of getName()) instead to avoid future confusion.