private final Sample maybeAddImplicitSample(
SampleDB sampleDB, final String id, final String familyID, final Gender gender) {
if (id != null && sampleDB.getSample(id) == null) {
Sample s =
new Sample(
id, sampleDB, familyID, null, null, gender, Affection.UNKNOWN, Sample.UNSET_QT);
sampleDB.addSample(s);
return s;
} else return null;
}
public final List<Sample> parse(
Reader reader, EnumSet<MissingPedField> missingFields, SampleDB sampleDB) {
final List<String> lines = new XReadLines(reader).readLines();
// What are the record offsets?
final int familyPos = missingFields.contains(MissingPedField.NO_FAMILY_ID) ? -1 : 0;
final int samplePos = familyPos + 1;
final int paternalPos = missingFields.contains(MissingPedField.NO_PARENTS) ? -1 : samplePos + 1;
final int maternalPos =
missingFields.contains(MissingPedField.NO_PARENTS) ? -1 : paternalPos + 1;
final int sexPos =
missingFields.contains(MissingPedField.NO_SEX) ? -1 : Math.max(maternalPos, samplePos) + 1;
final int phenotypePos =
missingFields.contains(MissingPedField.NO_PHENOTYPE)
? -1
: Math.max(sexPos, Math.max(maternalPos, samplePos)) + 1;
final int nExpectedFields =
MathUtils.arrayMaxInt(
Arrays.asList(samplePos, paternalPos, maternalPos, sexPos, phenotypePos))
+ 1;
// go through once and determine properties
int lineNo = 1;
boolean isQT = false;
final List<String[]> splits = new ArrayList<String[]>(lines.size());
for (final String line : lines) {
if (line.startsWith(commentMarker)) continue;
if (line.trim().equals("")) continue;
final String[] parts = line.split("\\s+");
if (parts.length != nExpectedFields)
throw new UserException.MalformedFile(
reader.toString(), "Bad PED line " + lineNo + ": wrong number of fields");
if (phenotypePos != -1) {
isQT = isQT || !CATAGORICAL_TRAIT_VALUES.contains(parts[phenotypePos]);
}
splits.add(parts);
lineNo++;
}
logger.info("Phenotype is other? " + isQT);
// now go through and parse each record
lineNo = 1;
final List<Sample> samples = new ArrayList<Sample>(splits.size());
for (final String[] parts : splits) {
String familyID = null, individualID, paternalID = null, maternalID = null;
Gender sex = Gender.UNKNOWN;
String quantitativePhenotype = Sample.UNSET_QT;
Affection affection = Affection.UNKNOWN;
if (familyPos != -1) familyID = maybeMissing(parts[familyPos]);
individualID = parts[samplePos];
if (paternalPos != -1) paternalID = maybeMissing(parts[paternalPos]);
if (maternalPos != -1) maternalID = maybeMissing(parts[maternalPos]);
if (sexPos != -1) {
if (parts[sexPos].equals(SEX_MALE)) sex = Gender.MALE;
else if (parts[sexPos].equals(SEX_FEMALE)) sex = Gender.FEMALE;
else sex = Gender.UNKNOWN;
}
if (phenotypePos != -1) {
if (isQT) {
if (parts[phenotypePos].equals(MISSING_VALUE1)) affection = Affection.UNKNOWN;
else {
affection = Affection.OTHER;
quantitativePhenotype = parts[phenotypePos];
}
} else {
if (parts[phenotypePos].equals(MISSING_VALUE1)) affection = Affection.UNKNOWN;
else if (parts[phenotypePos].equals(MISSING_VALUE2)) affection = Affection.UNKNOWN;
else if (parts[phenotypePos].equals(PHENOTYPE_UNAFFECTED))
affection = Affection.UNAFFECTED;
else if (parts[phenotypePos].equals(PHENOTYPE_AFFECTED)) affection = Affection.AFFECTED;
else
throw new ReviewedGATKException(
"Unexpected phenotype type " + parts[phenotypePos] + " at line " + lineNo);
}
}
final Sample s =
new Sample(
individualID,
sampleDB,
familyID,
paternalID,
maternalID,
sex,
affection,
quantitativePhenotype);
samples.add(s);
sampleDB.addSample(s);
lineNo++;
}
for (final Sample sample : new ArrayList<Sample>(samples)) {
Sample dad =
maybeAddImplicitSample(
sampleDB, sample.getPaternalID(), sample.getFamilyID(), Gender.MALE);
if (dad != null) samples.add(dad);
Sample mom =
maybeAddImplicitSample(
sampleDB, sample.getMaternalID(), sample.getFamilyID(), Gender.FEMALE);
if (mom != null) samples.add(mom);
}
return samples;
}
