@Override
public boolean hasNextChar() {
if (nvalid) return true;
while (true) {
if (protein == null) {
if (!getProtein()) break;
}
// BioJava indexes from 1
if (position > protein.getLength()) {
protein = null;
continue;
}
AminoAcidCompound aa = protein.getCompoundAt(position++);
String base = aa.getUpperedBase();
int chind = alphabet.indexOf(base);
if (chind < 0) {
System.out.println("Bad aa " + base);
continue;
}
nextch = base.charAt(0);
nvalid = true;
return true;
}
return false;
}
public static void main(String[] args) {
ProteinSequence proteinSequence = new ProteinSequence("ARNDCEQGHILKMFPSTWYVBZJX");
System.out.println(proteinSequence.toString());
StringProxySequenceReader<AminoAcidCompound> sequenceStringProxyLoader =
new StringProxySequenceReader<AminoAcidCompound>(
"XRNDCEQGHILKMFPSTWYVBZJA", AminoAcidCompoundSet.getAminoAcidCompoundSet());
ProteinSequence proteinSequenceFromProxy = new ProteinSequence(sequenceStringProxyLoader);
System.out.println(proteinSequenceFromProxy.toString());
}
public static void main(String[] args) {
try {
UniprotProxySequenceReader<AminoAcidCompound> uniprotSequence =
new UniprotProxySequenceReader<AminoAcidCompound>(
"YA745_GIBZE", AminoAcidCompoundSet.getAminoAcidCompoundSet());
ProteinSequence proteinSequence = new ProteinSequence(uniprotSequence);
logger.info("Accession: {}", proteinSequence.getAccession().getID());
logger.info("Sequence: {}", proteinSequence.getSequenceAsString());
} catch (Exception e) {
logger.error("Exception: ", e);
}
}
/**
* By stworzyć drzewo należy mieć sekwencje protein w formie listy, w której wszystkie sekwencje
* są tej samej długości. Teoria była na wykładzie, tutaj tylko ważne jest, że ta f-cja robi
* odpowiednie przesunięcia i wkłada do odpowiedniej struktury.
*/
private void alignSequences() {
multipleSequenceAlignment = new MultipleSequenceAlignment<ProteinSequence, AminoAcidCompound>();
Profile<ProteinSequence, AminoAcidCompound> profile =
Alignments.getMultipleSequenceAlignment(sequences);
List<AlignedSequence<ProteinSequence, AminoAcidCompound>> l = profile.getAlignedSequences();
ProteinSequence p;
for (int i = 0; i < l.size(); i++) {
Sequence<AminoAcidCompound> s = l.get(i);
p = new ProteinSequence(s.getSequenceAsString(), s.getCompoundSet());
p.setAccession(s.getAccession());
multipleSequenceAlignment.addAlignedSequence(p);
}
}
public static void writeProteinSequence(ProteinSequence sequence, DataOutput out)
throws IOException {
String string = sequence.getSequenceAsString();
out.writeInt(string.length());
for (int i = 0; i < string.length(); i += 3) {
String substring = string.substring(i, Math.min(i + 3, string.length()));
int value = 0;
for (int j = 0; j < 3; j++) {
value += (j < substring.length() ? getSerializedAminoAcid(substring.charAt(j)) : 0);
if (j != 2) {
value <<= 5;
}
}
out.writeShort(value);
}
}
/** @param args */
public static void main(String[] args) {
System.out.println("parseHeader");
String header = "";
ProteinSequence sequence = new ProteinSequence("");
GenericFastaHeaderParser<ProteinSequence, AminoAcidCompound> instance =
new GenericFastaHeaderParser<ProteinSequence, AminoAcidCompound>();
header = "gi|gi-number|gb|accession|locus";
instance.parseHeader(header, sequence);
System.out.println("accession" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.GENBANK);
header = "gi|gi-number|emb|accession|locus";
instance.parseHeader(header, sequence);
System.out.println("accession" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.ENA);
header = "gi|gi-number|dbj|accession|locus";
instance.parseHeader(header, sequence);
System.out.println("accession" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.DDBJ);
header = "pir||entry";
instance.parseHeader(header, sequence);
System.out.println("entry" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.NBRF);
header = "prf||name";
instance.parseHeader(header, sequence);
System.out.println("name" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.PRF);
header = "sp|accession|name";
instance.parseHeader(header, sequence);
System.out.println("accession" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.UNIPROT);
header = "pdb|entry|chain";
instance.parseHeader(header, sequence);
System.out.println("entry:chain" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.PDB1);
header = "entry:chain|PDBID|CHAIN|SEQUENCE";
instance.parseHeader(header, sequence);
System.out.println("entry:chain" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.PDB2);
header = "PDB:1ECY_A mol:protein length:142 ECOTIN";
instance.parseHeader(header, sequence);
System.out.println("1ECY_A" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.PDBe);
header = "pat|country|number";
instance.parseHeader(header, sequence);
System.out.println("number" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.PATENTS);
header = "bbs|number";
instance.parseHeader(header, sequence);
System.out.println("number" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.GENINFO);
header = "gnl|database|identifier";
instance.parseHeader(header, sequence);
System.out.println("identifier" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.GENERAL);
header = "ref|accession|locus";
instance.parseHeader(header, sequence);
System.out.println("accession" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.NCBI);
header = "lcl|identifier";
instance.parseHeader(header, sequence);
System.out.println("identifier" + "=" + sequence.getAccession());
System.out.println(sequence.getAccession().getDataSource() + "=" + DataSource.LOCAL);
}