FINAL VERSION

Endpoint

Value

Script

/*
This Java code has an input 2 lists. One list with UniProt's IDs and one with sequences from transeq.
It connects to the website, gets the data and creates a GenBank file.
*/

import java.io.*;

		//Stores Header of GenBank file into genbankfile string
		String genbankfile = "LOCUS\nDEFINITION\n\nACCESSION\nVERSION\nKEYWORDS\nSOURSE\n  ORGANISM\n\n\nREFERENCE\n  AUTHORS\n  TITLE\n\n   JOURNAL\n\n   PUBMED\n\n\nREFERENCE\n  AUTHORS\n  TITLE\n\nJOURNAL\n\n   PUBMED\n\n\nREFERENCE\n  AUTHORS\n  TITLE\n\n FEATURES\n";
		//Loop that goes through the list of IDs
		//This is used to annotate every gene from Blast results
		for (int i = 0; i < uniProtIDs.size(); i++) {
			//seqin is the the second list that is used as an input
			//It takes the "i"th sequence from the list
			//It splits at every space and stores it into str2 array
			String[] seqarray = aaSequences.get(i).split("[ ]+");
			//It gets the second element of the array which is the start position of the gene
			String inStartPos = seqarray[1];
			//It gets the third element of the array which is the end position of the gene
			String inEndPos = seqarray[2];
			//It gets the forth element of the array which is the frame number holding the gene
			String inFrameNumber = seqarray[3];
			//It gets the fifth element of the array which is the actual Amino Acid sequence after it gets translated from transeq
			String inSequence = seqarray[4];
			
			//Variables
			boolean seqfound = false;
			String geneID = null;
			String uniprotSequence = "";
			String lineLength = "";
			String geneName = "";
			String organismName = "";
			String uniprotFunction = "";
			String geneOntologies = "";
			String line = null;
			boolean goChecker = true;
			int functionChecker = 0;
			List gos = new ArrayList();
			//Gets the "i"th element from uniProtIDs list that contains uniprot identifiers and declares it as a URL
			URL inputURL = new URL("http://www.uniprot.org/uniprot/"
					+ uniProtIDs.get(i) + ".txt");
			//Open a connection between our machine and the previous URL
			URLConnection con = inputURL.openConnection();
			//Stream the content of the website
			InputStream in = con.getInputStream();
			StringBuffer result = new StringBuffer();
			BufferedReader reader;
			//Get website's encoding
			String encoding = con.getContentEncoding();
			//Check if there is encoding in the website
			//If there in not buffer the website
			//but if there is buffer using the encoding that was found above
			if (encoding == null) {
				reader = new BufferedReader(new InputStreamReader(in));
			} else {
				reader = new BufferedReader(new InputStreamReader(in, encoding));
			}
			//Loop through the website's data
			while ((line = reader.readLine()) != null) {
				//Split each line at every space and semicolon
				String[] uniProtDataLine = line.split("[ ;]+");
				//Find ID
				//Check first position of the array uniProtDataLine if it equals to ID
				//If true assign the second element of the array to id
				if (uniProtDataLine[0].equals("ID")) {
					geneID = uniProtDataLine[1];

				}
				//Find Gene's name
				//Check first position of the array uniProtDataLine if it equals to GN
				//If true assign the second element of the array to geneName
				if (uniProtDataLine[0].equals("GN")) {
					geneName = uniProtDataLine[1];
					//Remove = character
					String[] arraygene = geneName.split("=");
					geneName = arraygene[1];

				}
				//Find Organism's name
				//Check first position of the array uniProtDataLine if it equals to OS
				//If true assign the second element of the array to organismName
				if (uniProtDataLine[0].equals("OS")) {
					for (int i = 1; i < uniProtDataLine.length; i++) {
						organismName = organismName + uniProtDataLine[i] + " ";
					}
				}
				//Find gene's function
				//Check first position of the array uniProtDataLine if it equals to CC			
				if (uniProtDataLine[0].equals("CC") && (functionChecker <= 1)) {
					//Because UniProt's file format has "CC   -!- FUNCTION:" before the declaration
					//we have to use some check methods to get the function
					if (uniProtDataLine[1].equals("-!-")) {
						functionChecker++;
						if (functionChecker == 0) {
							for (int i = 3; i < uniProtDataLine.length; i++) {
								if (uniProtDataLine[i].contains("--")) {
									uniProtDataLine[i] = "";
									functionChecker++;
								}
								uniprotFunction += uniProtDataLine[i] + " ";
							}
						}
					}
					if (!uniProtDataLine[1].equals("-!-") && (functionChecker == 1)) {

						for (int i = 1; i < uniProtDataLine.length; i++) {
							if (uniProtDataLine[i].contains("--")) {
								uniProtDataLine[i] = "";
								functionChecker++;
							}
							uniprotFunction += uniProtDataLine[i] + " ";
						}
					}
				}
				//Reset goChecker and geneOntologies variables because they might have data from previous runs
				goChecker = true;
				geneOntologies = "";
				//Find Gene's ontologies
				//Check first position of the array uniProtDataLine if it equals to DR and the second to GO
				if (uniProtDataLine[0].equals("DR") && uniProtDataLine[1].contains("GO")) {
					for (int i = 2; i < uniProtDataLine.length; i++) {
						//Remove unwanted data
						if (uniProtDataLine[i].contains("IEA")) {
							goChecker = false;
						}
						if (goChecker == true) {
							geneOntologies += uniProtDataLine[i] + " ";
						}
					}
				}
				if (!geneOntologies.equals("")) {
					gos.add(geneOntologies);
				}
				//Find end of file
				//Check first position of the array uniProtDataLine if it equals to //
				if (uniProtDataLine[0].equals("//")) {
					seqfound = false;
				}
				/*
				 * This code was actually implemented to get the protein's sequence from
				 * uniprot record. Wasn't used at the end because we got the sequence from transeq
				if (seqfound == true) {
					for (int i = 0; i < uniProtDataLine.length; i++) {
						uniprotSequence += uniProtDataLine[i];
						if (uniprotSequence.toString().length() % 58 == 0) {
						}
					}
					uniprotSequence += "\n\t\t\t\t\t";

				}
				if (uniProtDataLine[0].equals("SQ")) {
					seqfound = true;
				}
			}*/
			//Stores information from the previous steps into genbankfile String
			genbankfile += "\tgene\t\t";
			genbankfile += inStartPos + "..." + inEndPos + "\n";
			genbankfile += "\t\t\t/gene=\"" + geneName + "\"\n";
			genbankfile += "\tCDS\t\t";
			genbankfile += inStartPos + "..." + inEndPos + "\n";
			genbankfile += "\t\t\t/gene=\"" + geneName + "\"\n";
			genbankfile += "\t\t\t/function=\"" + uniprotFunction + "\"\n";
			genbankfile += "\t\t\t/protein_id=\"" + geneID + "\n";
			for (int k = 0; k < gos.size(); k++) {
				genbankfile += "\t\t\t/db_xref=\"" + gos.get(k) + "\"\n";
			}
			genbankfile += "\t\t\t/codon_start=" + inFrameNumber + "\"\n";
			String[] arrayline3 = inSequence.split("[= .]+");
			genbankfile += "\t\t\t/translation=\"" + arrayline3[2] + "\"\n";
			reader.close();
		}
		genbankfile += "\n\nORIGIN";
		//Saves the genbank file to the given directory. This can be easy changed to you own path
		FileWriter fstream = new FileWriter(
				"/home/george/Desktop/EScience/GENBANKFILE/genbank.txt");
		BufferedWriter out = new BufferedWriter(fstream);
		out.write(genbankfile);
		out.close();
		contents = genbankfile;
}

Script

/*
 * This Java code gets the output of glimmerspliter and stores each fasta sequence into a list
 */
import java.io.File;
import java.io.FileNotFoundException;
import java.util.ArrayList;
import java.util.List;
import java.util.Scanner;

		List fastaSeqList = new ArrayList();
		Scanner sc = null;
		//Gets the multifasta file
		//The file is stored in /home/george/Desktop/Scripts/ but you can define your own path
		try {
			sc = new Scanner(
					new File(
							"/home/george/Desktop/Scripts/ordered_gi|49482253|ref|NC_002952.2|_g3.tfa"));
		} catch (FileNotFoundException e) {
			e.printStackTrace();
		}
		String file = "";
		boolean guard = false;
		int i = 0;
		//Loops through the whole file
		while (sc.hasNextLine()) {
			String output = sc.nextLine();
			//Check for > character that indicates a new fastA sequence
			if (output.charAt(0) != '>') {
				file += output + "\n";
				guard = true;
			} else {
				//Add the sequence to fastaSeqList
				if (guard) {
					i++;
					fastaSeqList.add(file);
					file = "";
				}
				file += output + "\n";
			}
		}
		fastaSeqList.add(file);
		out = fastaSeqList;