001/* 002 * BioJava development code 003 * 004 * This code may be freely distributed and modified under the 005 * terms of the GNU Lesser General Public Licence. This should 006 * be distributed with the code. If you do not have a copy, 007 * see: 008 * 009 * http://www.gnu.org/copyleft/lesser.html 010 * 011 * Copyright for this code is held jointly by the individual 012 * authors. These should be listed in @author doc comments. 013 * 014 * For more information on the BioJava project and its aims, 015 * or to join the biojava-l mailing list, visit the home page 016 * at: 017 * 018 * http://www.biojava.org/ 019 * 020 */ 021package org.biojava.nbio.genome.parsers.gff; 022 023import org.biojava.nbio.core.sequence.DNASequence; 024 025import java.util.Collection; 026 027/** 028 * 029 * @author Scooter Willis <willishf at gmail dot com> 030 */ 031public class GCStats { 032 033 public static double getGCStats(Collection<DNASequence> sequences) { 034 double gcCount = 0; 035 double total = 0; 036 037 for (DNASequence sequence : sequences) { 038 char[] dna = sequence.toString().toCharArray(); 039 for (char d : dna) { 040 if (d == 'G' || d == 'C' || d == 'g' || d == 'c') { 041 gcCount++; 042 } 043 total++; 044 } 045 } 046 047 return (gcCount / total) * 100.0; 048 } 049 050 public static double getGCStatsString(Collection<String> sequences) { 051 double gcCount = 0; 052 double total = 0; 053 054 for (String sequence : sequences) { 055 char[] dna = sequence.toCharArray(); 056 for (char d : dna) { 057 if (d == 'G' || d == 'C' || d == 'g' || d == 'c') { 058 gcCount++; 059 } 060 total++; 061 } 062 } 063 064 return (gcCount / total) * 100.0; 065 } 066}