Biostar9532375 Remove redundant nucleotide sequences in a FASTA file containing ambiguous N

README.md

Compile:

javac Biostar9532375.java

execute

$ java Biostar9532375 <  in.fa
>seq1
ACNTACNT
>seq5
TCGTACTT

Biostar9532375.java

import java.io.*;
import java.util.*;
public class Biostar9532375 {
private static class Sequence {
	String name;
	StringBuilder seq=new StringBuilder();
	boolean same(char c1,char c2) {
		if(c1==c2) return true;
		if(c1=='N' || c2=='N') return true;
		return false;
		}
	boolean same(Sequence o) {
		int L=seq.length();
		if(L!=o.seq.length()) return false;
		for(int i=0;i< L;i++) {
			if(!same(seq.charAt(i),o.seq.charAt(i))) return false;
			}
		return true;
		}
	}
public static void main(final String[] args) {
	try {
		final List<Sequence> sequences =new ArrayList<>();
		Sequence last=null;
		try(BufferedReader br = new BufferedReader(new InputStreamReader(System.in))) {
			for(;;) {
				String line=br.readLine();
				if(line==null || line.startsWith(">")) {
					if(last!=null) {
						final Sequence last2=last;
						if(sequences.stream().noneMatch(S->S.same(last2))) {
							sequences.add(last);
							}
						}
					if(line==null) break;
					last=new Sequence();
					last.name=line;
					continue;
					}
				else
					{
					if(last!=null) last.seq.append(line.trim().toUpperCase());
					}
				}
			}
		for(Sequence s:sequences) {
			System.out.println(s.name);
			System.out.println(s.seq);
			}
		}
	catch(Throwable err) {
		err.printStackTrace();
		}

	}
}