A Java small class to find a protein within a strand of DNA represented as a string of C, G, T, A letters. The library edu.duke is a dependency for the class to work, it should be added into the Java IDE to compile with no errors. Download link http://www.dukelearntoprogram.com/downloads/archives/courserajava.jar

FindGene.java

/**
 * Finds a protein within a strand of DNA represented as a string of c,g,t,a letters.
 * A protein is a part of the DNA strand marked by start and stop codons (DNA triples)
 * that is a multiple of 3 letters long.
 *
 * @author Duke Software Team 
 */
import edu.duke.*;
import java.io.*;

public class FindGene {
    public String findProtein(String dna) {
        dna = dna.toLowerCase();
        
        int start = dna.indexOf("atg");
        
        if (start == -1) {
            return "";
        }
        
        int stopTag = dna.indexOf("tag", start+3);
        int stopTga = dna.indexOf("tga", start+3);
        int stopTaa = dna.indexOf("taa", start+3);
        
        if ( ( stopTag - start ) % 3 == 0 ) {
            return dna.substring( start, stopTag+3 );
        } else if ( ( stopTga - start ) % 3 == 0 ) {
            return dna.substring( start, stopTga+3 );
        } else if ( ( stopTaa - start ) % 3 == 0 ) {
            return dna.substring( start, stopTaa+3 );
        } else {
            return "";
        }
    }
    
    public void testing() {
        String a = "ATGAAATGA";
        String ap = "atggggtttaaataataatag";
        //String a = "atgcctag";
        //String ap = "";
        //String a = "ATGCCCTAG";
        //String ap = "ATGCCCTAG";
        String result = findProtein(a);
        if (ap.equals(result)) {
            System.out.println("success for " + ap + " length " + ap.length());
            System.out.println("Stop Codon: " + stopCodon(result).toUpperCase() + " length " + result.length());
        }
        else {
            System.out.println("mistake for input: " + a);
            System.out.println("got: " + result);
            System.out.println("not: " + ap);
            System.out.println("Stop Codon: " + stopCodon(result).toUpperCase() + " length " + result.length());
        }
    }
    
    public String stopCodon(String gene) {
        String answer = findProtein(gene);
        int size = answer.length();
        
        if ( size > 6 ) {
            return answer.substring(size - 3, size);
        }
        else {
            return "";
        }
    }

    public void realTesting() {
        DirectoryResource dr = new DirectoryResource();
        for (File f : dr.selectedFiles()) {
            FileResource fr = new FileResource(f);
            String s = fr.asString();
            System.out.println("read " + s.length() + " characters");
            String result = findProtein(s);
            System.out.println("found " + result);
        }
    }
}