重叠基因

Question

我正在尝试运行我的程序，但是我收到了很多额外的，不必要的信息。如果在输出窗口中向下滚动，则第二组基因是正确的，不会发生重叠，而不是第一组。我也得到总共202个基因，当时我应该得到89个。

还有其他部分让我很困惑;在我的代码输出中有很多CGRatio和长度数据;我如何组织它，以便程序只给我多少CGRatio＆gt; 0.35，以及长度超过60个字符的字符串数量。注意：CGRatio是DNA串中c和g的数量除以字符串的长度。 我还想知道这个文件中有多少个字符。

注意：main方法已被改为printGenes，因为BlueJ环境无法调用main。 注意：我们还没有学会如何使用除基础之外的任何东西; StorageResource类，DirectoryResource类和FileResource类是本课程中教授的，目前为止来自Duke库（即

import java.io.*;
import edu.duke.FileResource;
import edu.duke.StorageResource;
import edu.duke.DirectoryResource;

） 只是基本的操作字符串和for和while循环。

以下是该计划中使用的文件：http://www.dukelearntoprogram.com/course2/data/dna.zip

这是我的代码：

import java.io.*;
import edu.duke.FileResource;
import edu.duke.StorageResource;
import edu.duke.DirectoryResource;

public class FindMultiGenes5 {
    public int findStopIndex(String dna, int index) {
        int stop1 = dna.indexOf("TGA", index);
        if (stop1 == -1 || (stop1 - index) % 3 != 0) {
            stop1 = dna.length();
        }
        int stop2 = dna.indexOf("TAA", index);
        if (stop2 == -1 || (stop2 - index) % 3 != 0) {
            stop2 = dna.length();
        }
        int stop3 = dna.indexOf("TAG", index);
        if (stop3 == -1 || (stop3 - index) % 3 != 0) {
            stop3 = dna.length();
        }
        return Math.min(stop1, Math.min(stop2, stop3));
    }

    public StorageResource storeAll(String dna) {

        String sequence = dna.toUpperCase();
        StorageResource store = new StorageResource();
        int index = 0;


        while (true) {
            index = sequence.indexOf("ATG", index);
            if (index == -1)
                break;

            int stop = findStopIndex(sequence, index + 3);

            if (stop != sequence.length()) {
                String gene = dna.substring(index, stop + 3);
                store.add(gene);

                System.out.println("From: " + index + " to " + stop + " Gene: " + gene );//index = sequence.substring(index, stop + 3).length();
            index = stop + 3; // start at the end of the stop codon
          }else{  index = index + 3;
        }

    }
    return store;//System.out.println(sequence);
    }
   public void testStorageFinder() {
      DirectoryResource dr = new DirectoryResource();
      StorageResource dnaStore = new StorageResource(); 
    for (File f : dr.selectedFiles()) {
        FileResource fr = new FileResource(f);
        String s = fr.asString();
        dnaStore = storeAll(s);
        printGenes(dnaStore);
    }


        System.out.println("size = " + dnaStore.size());

    }  
  public String readStrFromFile(){

        FileResource readFile = new FileResource();

        String DNA = readFile.asString();

        //System.out.println("DNA: " + DNA);

        return DNA;

    }//end readStrFromFile() method;
  public float calCGRatio(String gene){

        gene = gene.toUpperCase();  
        int len = gene.length();
        int CGCount = 0;

        for(int i=0; i<len; i++){

            if(gene.charAt(i) == 'C' || gene.charAt(i) == 'G')
                CGCount++;

        }//end for loop

        System.out.println("CGCount " + CGCount + " Length: " + len + " Ratio: " + (float)CGCount/len);
        return (float)CGCount/len;
    }//end of calCGRatio() method;
    public void printGenes(StorageResource sr){
   for(String gene: sr.data()){
     if (gene.length() > 60) {
       System.out.println(gene.length()+"\t"+gene);
     }
     if(calCGRatio(gene)> 0.35) {
       System.out.println(gene.length()+"\t"+gene);
      }
  }

        //create a FindMultiGenesFile object FMG
        FindMultiGenes5 FMG = new FindMultiGenes5();

        //read a DNA sequence from file
        String dna = FMG.readStrFromFile();



        FMG.storeAll(dna);

        //store all genes into a document
        StorageResource dnaStore = new StorageResource();



        int longerthan60 = 0;
        int CGGreaterthan35 = 0;





        System.out.println("\n There are " + dnaStore.size() + " genes. ");
        System.out.println("There are " + longerthan60 + " genes longer than 60.");
        System.out.println("There are " + CGGreaterthan35 + " genes with CG ratio greater than 0.35.");
    }//end main();
}