/** Show a string with overall effect */
public String effect(
boolean shortFormat, boolean showAaChange, boolean showBioType, boolean useSeqOntology) {
String e = "";
String codonEffect = codonEffect(showAaChange, showBioType, useSeqOntology); // Codon effect
// Create effect string
if (!codonEffect.isEmpty()) e = codonEffect;
else if (isRegulation())
return getEffectTypeString(useSeqOntology) + "[" + ((Regulation) marker).getName() + "]";
else if (isNextProt())
return getEffectTypeString(useSeqOntology)
+ "["
+ VcfEffect.vcfEffSafe(((NextProt) marker).getId())
+ "]"; // Make sure this 'id' is not dangerous in a VCF 'EFF' field
else if (isMotif())
return getEffectTypeString(useSeqOntology)
+ "["
+ ((Motif) marker).getPwmId()
+ ":"
+ ((Motif) marker).getPwmName()
+ "]";
else if (isCustom()) {
// Custom interval
String label = ((Custom) marker).getLabel();
double score = ((Custom) marker).getScore();
if (!Double.isNaN(score)) label = label + ":" + score;
if (!label.isEmpty()) label = "[" + label + "]";
return getEffectTypeString(useSeqOntology) + label;
} else if (isIntergenic() || isIntron() || isSpliceSite())
e = getEffectTypeString(useSeqOntology);
else if (!message.isEmpty()) e = getEffectTypeString(useSeqOntology) + ": " + message;
else if (marker == null)
e =
getEffectTypeString(
useSeqOntology); // There are cases when no marker is associated (e.g. "Out of
// chromosome", "No such chromosome", etc.)
else e = getEffectTypeString(useSeqOntology) + ": " + marker.getId();
if (shortFormat) e = e.split(":")[0];
return e;
}
/** Show annotations counters in a table */
void analyzeSequenceConservation() {
if (verbose)
Timer.showStdErr(
"Sequence conservation analysis." //
+ "\n\tAA sequence length : "
+ 1 //
+ "\n\tMin AA count : "
+ HIGHLY_CONSERVED_AA_COUNT //
+ "\n\tMin AA conservation : "
+ HIGHLY_CONSERVED_AA_PERCENT //
);
ArrayList<String> keys = new ArrayList<String>();
keys.addAll(countAaSequenceByType.keySet());
Collections.sort(keys);
// Show title
StringBuilder title = new StringBuilder();
for (char aa : GprSeq.AMINO_ACIDS) title.append(aa + "\t");
title.append("\t" + title);
if (verbose)
System.out.println(
"Amino acid regions:\n\tTotal\tMax count\tAvg len\tConservation\tCatergory\tControlled Vocabulary\t"
+ title
+ "\tOther AA sequences:");
// Show AA counts for each 'key'
for (String key : keys) {
long seqLen = 0, totalSeqs = 0, maxCount = 0;
CountByType cbt = countAaSequenceByType.get(key);
long total = cbt.sum();
boolean highlyConservedAaSequence = false;
StringBuilder sb = new StringBuilder();
// For each single amino acid "sequence"
for (char aa : GprSeq.AMINO_ACIDS) {
long count = cbt.get("" + aa);
if (count > 0) {
seqLen += 1 * count;
totalSeqs += count;
maxCount = Math.max(maxCount, count);
sb.append(count);
double perc = ((double) count) / total;
// We estimate that if most AA are the same, then changing this AA can cause a high impact
// in protein coding
if ((perc > HIGHLY_CONSERVED_AA_PERCENT) && (total >= HIGHLY_CONSERVED_AA_COUNT))
highlyConservedAaSequence = true;
}
sb.append("\t");
}
// Sequences of more than one AA
for (String aas : cbt.keySet()) {
long count = cbt.get(aas);
double perc = ((double) count) / total;
if (aas.length() > 1) {
seqLen += aas.length() * count;
totalSeqs += count;
maxCount = Math.max(maxCount, count);
sb.append(String.format("\t" + aas + ":" + count));
if ((perc > HIGHLY_CONSERVED_AA_PERCENT) && (total >= HIGHLY_CONSERVED_AA_COUNT))
highlyConservedAaSequence = true;
}
}
long avgLen = seqLen / totalSeqs;
// Show line
if (verbose)
System.out.println( //
"\t"
+ total //
+ "\t"
+ maxCount //
+ "\t"
+ avgLen //
+ "\t"
+ (highlyConservedAaSequence ? "High" : "") //
+ "\t"
+ key //
+ "\t"
+ sb //
);
// Mark highly conserved
if (highlyConservedAaSequence) {
int count = 0;
for (Marker m : markers) {
NextProt nextProt = (NextProt) m;
if (m.getId().equals(key)) {
nextProt.setHighlyConservedAaSequence(true);
count++;
}
}
if (verbose)
Timer.showStdErr(
"NextProt "
+ count
+ " markers type '"
+ key
+ "' marked as highly conserved AA sequence");
}
}
}
public String toString(boolean useSeqOntology, boolean useHgvs) {
// Get data to show
String geneId = "", geneName = "", bioType = "", transcriptId = "", exonId = "", customId = "";
int exonRank = -1;
if (marker != null) {
// Gene Id, name and biotype
Gene gene = getGene();
Transcript tr = getTranscript();
// CDS size info
if (gene != null) {
geneId = gene.getId();
geneName = gene.getGeneName();
bioType = getBiotype();
}
// Update trId
if (tr != null) transcriptId = tr.getId();
// Exon rank information
Exon exon = getExon();
if (exon != null) {
exonId = exon.getId();
exonRank = exon.getRank();
}
// Regulation
if (isRegulation()) bioType = ((Regulation) marker).getCellType();
}
// Add seqChage's ID
if (!variant.getId().isEmpty()) customId += variant.getId();
// Add custom markers
if ((marker != null) && (marker instanceof Custom))
customId += (customId.isEmpty() ? "" : ";") + marker.getId();
// CDS length
int cdsSize = getCdsLength();
String errWarn = error + (error.isEmpty() ? "" : "|") + warning;
String aaChange = "";
if (useHgvs) aaChange = getHgvs();
else aaChange = ((aaRef.length() + aaAlt.length()) > 0 ? aaRef + "/" + aaAlt : "");
return errWarn //
+ "\t"
+ geneId //
+ "\t"
+ geneName //
+ "\t"
+ bioType //
+ "\t"
+ transcriptId //
+ "\t"
+ exonId //
+ "\t"
+ (exonRank >= 0 ? exonRank : "") //
+ "\t"
+ effect(false, false, false, useSeqOntology) //
+ "\t"
+ aaChange //
+ "\t"
+ ((codonsRef.length() + codonsAlt.length()) > 0 ? codonsRef + "/" + codonsAlt : "") //
+ "\t"
+ (codonNum >= 0 ? (codonNum + 1) : "") //
+ "\t"
+ (codonDegeneracy >= 0 ? codonDegeneracy + "" : "") //
+ "\t"
+ (cdsSize >= 0 ? cdsSize : "") //
+ "\t"
+ (codonsAroundOld.length() > 0 ? codonsAroundOld + " / " + codonsAroundNew : "") //
+ "\t"
+ (aasAroundOld.length() > 0 ? aasAroundOld + " / " + aasAroundNew : "") //
+ "\t"
+ customId //
;
}