david.java

package biojava.biojava_project;

import java.io.BufferedReader;
import java.io.File;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.PrintStream;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.LinkedHashMap;
import java.util.List;
import org.biojava.nbio.core.sequence.DNASequence;
import org.biojava.nbio.core.sequence.compound.NucleotideCompound;
import org.biojava.nbio.core.sequence.features.FeatureInterface;
import org.biojava.nbio.core.sequence.io.GenbankReaderHelper;
import org.biojava.nbio.core.sequence.template.AbstractSequence;

public class SimpleRest {

	public static void main(String[] args)  throws Exception {

		// Getting the protein ID
		String [] protein_id = {"NP_414542.1"};

		// Defining the polarity of amino acids

		String polar = "YSTNQCHRDEK";
		String Aliphatics = "AVLIPGR";
		String nonpolar = "AVLGIMWPF";
		String Aromatics ="WYFH";
		String Heterocyclics = "WHP";

		// Determining the amount of each amino acid
		int numberpolar = 0;
		int numberAliphatics = 0;
		int numbernonpolar = 0;
		int numberAromatics = 0;
		int numberHeterocyclics = 0;

		// Getting the gbff file - E. coli
		File dnaFile = new File("/Users/andreszuniga/Downloads/ecoli.gbff");
		LinkedHashMap<String,DNASequence> dnaSequences = GenbankReaderHelper.readGenbankDNASequence(dnaFile, true);

		PrintStream out;

		// Output file with requested information
		out = new PrintStream("/Users/andreszuniga/Downloads/output_eco.txt");

		for (DNASequence sequence : dnaSequences.values()) {

			numberpolar = 0;
			numberAliphatics = 0;
			numbernonpolar = 0;
			numberAromatics = 0;
			numberHeterocyclics = 0;

			int flag = 0;
			String Protein_id = "";

			// Checking the protein inside the genome
			for (int i = 0; i < protein_id.length; i++) {

				System.out.println("Protein ID: " +protein_id[i]);

				System.out.println("Prueba________________");
				System.out.println( sequence.getSequenceAsString() );


				List<FeatureInterface<AbstractSequence<NucleotideCompound>,NucleotideCompound>>
				features = sequence.getFeatures();
				for (int j = 0; j < features.size(); j++) {
					if (features.get(j).getDescription().equals("CDS")) {

						Protein_id = features.get(j).getQualifiers().values().toArray()[3].toString().split("'")[3];
					}
					else {
						continue;
					}

					if (protein_id[i].equals(Protein_id)) {
						flag = 1;

						System.out.println("Information of protein: ");
						System.out.println("____________________________________________");

						// Printing the length of protein sequence
						System.out.println("Length: " + sequence.getLength());
						// Printing the description of protein
						System.out.println("Description: " +features.get(j).getDescription());
						// Getting the qualifiers
						System.out.println("Protein ID: " + features.get(j).getQualifiers().values().toArray()[3].toString().split("'")[3]);
						String a = features.get(j).getQualifiers().values().toArray()[3].toString().split("'")[3];
						String protein = a.split("\\.")[0];
						System.out.println(protein);
						System.out.println("Gen: "+features.get(j).getQualifiers().values().toArray()[4].toString().split("'")[3]);
						String aminosequence = features.get(j).getQualifiers().values().toArray()[6].toString().split("'")[3];


						// Verifying the amino acids inside genome

						for (int q = 0; q<aminosequence.split("").length; q+=1) {
							for (int p = 0; p<polar.split("").length;p+=1) {
								if (aminosequence.split("")[q].equals(polar.split("")[p])) {
									numberpolar += 1;

								}
							}


							for (int a_a = 0; a_a<Aliphatics.split("").length;a_a+=1) {
								if (aminosequence.split("")[q].equals(Aliphatics.split("")[a_a])) {
									numberAliphatics += 1;

								}
							}

							for (int np = 0; np<nonpolar.split("").length;np+=1) {
								if (aminosequence.split("")[q].equals(nonpolar.split("")[np])) {
									numbernonpolar += 1;
								}
							}


							for (int ar = 0; ar<Aromatics.split("").length;ar+=1) {
								if (aminosequence.split("")[q].equals(Aromatics.split("")[ar])) {
									numberAromatics += 1;
								}
							}

							for (int w = 0; w<Heterocyclics.split("").length;w+=1) {
								if (aminosequence.split("")[q].equals(Heterocyclics.split("")[w])) {
									numberHeterocyclics += 1;
								}
							}
						}


						System.out.println("Information about amino acids: ");
						System.out.println("____________________________________________");

						System.out.println("Amount of Non Polars: "+ numbernonpolar);
						System.out.println("Amount of  Polars: "+ numberpolar);
						System.out.println("Amount of Aliphatics: "+ numberAliphatics);
						System.out.println("Amount of Aromatics: "+ numberAromatics);
						System.out.println("Amount of Heterocyclics: "+ numberHeterocyclics);

						numberpolar = 0;
						numberAliphatics = 0;
						numbernonpolar = 0;
						numberAromatics = 0;
						numberHeterocyclics = 0;

						int pol = numbernonpolar;
						System.out.println("Val pol: " +pol);
						int alif = numberAromatics;
						System.out.println("Val alif: "+ alif);
						System.out.println("Relation No Polar / Aromatics: "+pol);
						System.out.println("Relation Aromatics: "+numberAromatics);
						System.out.println("Relation Heterocyclics: "+numberHeterocyclics);
						System.out.println("Relation Aromatics / Heterocyclics: "+alif);


						// Request information in KEGG Database
						String request = "http://rest.kegg.jp/conv/eco/ncbi-proteinid:"+protein;
						System.out.println(request);
						String str ="";
						try {
							str = httpGet(request);
						} catch (IOException e) {
							e.printStackTrace();
						}

						String KEGG_ferment = str.split("	")[1];

						// Requesting in KEGG using the protein ID
						String request2 = "http://rest.kegg.jp/link/pathway/"+KEGG_ferment;

						System.out.println(request2);

						// Getting the amino acids properties from KEGG data base
						try {
							out.print(features.get(j).getQualifiers().keySet().toArray()[2]);
							out.println(" "+features.get(j).getQualifiers().values().toArray()[2].toString().split("'")[3]);
							out.println(features.get(j).getQualifiers().values().toArray()[4].toString().split("'")[3]);
							out.println();
							out.println("Number of Non Polar Amino Acids: "+numbernonpolar);
							out.println("Relation No Polar / Aromatics: "+pol);
							out.println("Number of Aromatics: "+numberAromatics);
							out.println("Number of Heterocyclics: " +numberHeterocyclics);
							out.println("Relation Aromatics / Heterocyclics: "+alif);
							out.println();
							out.println("YYYYYYY");
							String str2 = httpGet(request2);
							for (int k = 1; k<str2.split(KEGG_ferment+"     ").length; k+=1) {
								System.out.println(str2.split(KEGG_ferment+"    ")[k]);
								String request3 = "http://rest.kegg.jp/list/" + str2.split(KEGG_ferment+"       ")[k];
								String str3 = httpGet(request3);
								System.out.println(str3);
								out.println(str3);
							}
							out.println("______________________________________________________________________________________");
							out.println();
						} catch (IOException e) {
							e.printStackTrace();
						}
						System.out.println();
					}
				}
				if (flag == 0) {
					System.out.println("XXXXXXXX");
					System.out.println();
				}                              
			}
		}
		out.close();
	}

	public static String httpGet(String urlStr) throws IOException {
		URL url = new URL(urlStr);
		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
		if (conn.getResponseCode() != 200) {
			throw new IOException(conn.getResponseMessage());
		} // Buffer the result into a string
		BufferedReader rd = new BufferedReader(new InputStreamReader(
				conn.getInputStream()));
		StringBuilder sb = new StringBuilder();
		String line;
		while ((line = rd.readLine()) != null) {
			sb.append(line);
		}
		rd.close();
		conn.disconnect();
		return sb.toString();
	}
}