static nodeptr uprootTree (tree *tr, nodeptr p, boolean readBranchLengths, boolean readConstraint)
{
nodeptr q, r, s, start;
int n, i;
for(i = tr->mxtips + 1; i < 2 * tr->mxtips - 1; i++)
assert(i == tr->nodep[i]->number);
if(isTip(p->number, tr->mxtips) || p->back)
{
printf("ERROR: Unable to uproot tree.\n");
printf(" Inappropriate node marked for removal.\n");
assert(0);
}
assert(p->back == (nodeptr)NULL);
tr->nextnode = tr->nextnode - 1;
assert(tr->nextnode < 2 * tr->mxtips);
n = tr->nextnode;
assert(tr->nodep[tr->nextnode]);
if (n != tr->mxtips + tr->ntips - 1)
{
printf("ERROR: Unable to uproot tree. Inconsistent\n");
printf(" number of tips and nodes for rooted tree.\n");
assert(0);
}
q = p->next->back; /* remove p from tree */
r = p->next->next->back;
assert(p->back == (nodeptr)NULL);
if(readBranchLengths)
{
double b[NUM_BRANCHES];
int i;
for(i = 0; i < tr->numBranches; i++)
b[i] = (r->z[i] + q->z[i]);
hookup (q, r, b, tr->numBranches);
}
else
hookupDefault(q, r, tr->numBranches);
if(readConstraint && tr->grouped)
{
if(tr->constraintVector[p->number] != 0)
{
printf("Root node to remove should have top-level grouping of 0\n");
assert(0);
}
}
assert(!(isTip(r->number, tr->mxtips) && isTip(q->number, tr->mxtips)));
assert(p->number > tr->mxtips);
if(tr->ntips > 2 && p->number != n)
{
q = tr->nodep[n]; /* transfer last node's conections to p */
r = q->next;
s = q->next->next;
if(readConstraint && tr->grouped)
tr->constraintVector[p->number] = tr->constraintVector[q->number];
hookup(p, q->back, q->z, tr->numBranches); /* move connections to p */
hookup(p->next, r->back, r->z, tr->numBranches);
hookup(p->next->next, s->back, s->z, tr->numBranches);
q->back = q->next->back = q->next->next->back = (nodeptr) NULL;
}
else
p->back = p->next->back = p->next->next->back = (nodeptr) NULL;
assert(tr->ntips > 2);
start = findAnyTip(tr->nodep[tr->mxtips + 1], tr->mxtips);
assert(isTip(start->number, tr->mxtips));
tr->rooted = FALSE;
return start;
}
int treeReadLen (FILE *fp, tree *tr, boolean readBranches, boolean readNodeLabels, boolean topologyOnly)
{
nodeptr
p;
int
i,
ch,
lcount = 0;
for (i = 1; i <= tr->mxtips; i++)
{
tr->nodep[i]->back = (node *) NULL;
/*if(topologyOnly)
tr->nodep[i]->support = -1;*/
}
for(i = tr->mxtips + 1; i < 2 * tr->mxtips; i++)
{
tr->nodep[i]->back = (nodeptr)NULL;
tr->nodep[i]->next->back = (nodeptr)NULL;
tr->nodep[i]->next->next->back = (nodeptr)NULL;
tr->nodep[i]->number = i;
tr->nodep[i]->next->number = i;
tr->nodep[i]->next->next->number = i;
/*if(topologyOnly)
{
tr->nodep[i]->support = -2;
tr->nodep[i]->next->support = -2;
tr->nodep[i]->next->next->support = -2;
}*/
}
if(topologyOnly)
tr->start = tr->nodep[tr->mxtips];
else
tr->start = tr->nodep[1];
tr->ntips = 0;
tr->nextnode = tr->mxtips + 1;
for(i = 0; i < tr->numBranches; i++)
tr->partitionSmoothed[i] = FALSE;
tr->rooted = FALSE;
p = tr->nodep[(tr->nextnode)++];
while((ch = treeGetCh(fp)) != '(');
if(!topologyOnly)
assert(readBranches == FALSE && readNodeLabels == FALSE);
if (! addElementLen(fp, tr, p, readBranches, readNodeLabels, &lcount))
assert(0);
if (! treeNeedCh(fp, ',', "in"))
assert(0);
if (! addElementLen(fp, tr, p->next, readBranches, readNodeLabels, &lcount))
assert(0);
if (! tr->rooted)
{
if ((ch = treeGetCh(fp)) == ',')
{
if (! addElementLen(fp, tr, p->next->next, readBranches, readNodeLabels, &lcount))
assert(0);
}
else
{ /* A rooted format */
tr->rooted = TRUE;
if (ch != EOF) (void) ungetc(ch, fp);
}
}
else
{
p->next->next->back = (nodeptr) NULL;
}
if (! treeNeedCh(fp, ')', "in"))
assert(0);
if(topologyOnly)
assert(!(tr->rooted && readNodeLabels));
(void) treeFlushLabel(fp);
if (! treeFlushLen(fp))
assert(0);
if (! treeNeedCh(fp, ';', "at end of"))
assert(0);
if (tr->rooted)
{
assert(!readNodeLabels);
p->next->next->back = (nodeptr) NULL;
tr->start = uprootTree(tr, p->next->next, FALSE, FALSE);
if (! tr->start)
{
printf("FATAL ERROR UPROOTING TREE\n");
assert(0);
}
}
else
tr->start = findAnyTip(p, tr->mxtips);
assert(tr->ntips == tr->mxtips);
return lcount;
}
nodeptr findAnyTip(nodeptr p, int numsp)
{
return isTip(p->number, numsp) ? p : findAnyTip(p->next->back, numsp);
}
boolean treeReadLenMULT (FILE *fp, tree *tr, analdef *adef)
{
nodeptr p, r, s;
int i, ch, n, rn;
int partitionCounter = 0;
double randomResolution;
srand((unsigned int) time(NULL));
for(i = 0; i < 2 * tr->mxtips; i++)
tr->constraintVector[i] = -1;
for (i = 1; i <= tr->mxtips; i++)
tr->nodep[i]->back = (node *) NULL;
for(i = tr->mxtips + 1; i < 2 * tr->mxtips; i++)
{
tr->nodep[i]->back = (nodeptr)NULL;
tr->nodep[i]->next->back = (nodeptr)NULL;
tr->nodep[i]->next->next->back = (nodeptr)NULL;
tr->nodep[i]->number = i;
tr->nodep[i]->next->number = i;
tr->nodep[i]->next->next->number = i;
}
tr->start = tr->nodep[tr->mxtips];
tr->ntips = 0;
tr->nextnode = tr->mxtips + 1;
for(i = 0; i < tr->numBranches; i++)
tr->partitionSmoothed[i] = FALSE;
tr->rooted = FALSE;
p = tr->nodep[(tr->nextnode)++];
while((ch = treeGetCh(fp)) != '(');
if (! addElementLenMULT(fp, tr, p, partitionCounter)) return FALSE;
if (! treeNeedCh(fp, ',', "in")) return FALSE;
if (! addElementLenMULT(fp, tr, p->next, partitionCounter)) return FALSE;
if (! tr->rooted)
{
if ((ch = treeGetCh(fp)) == ',')
{
if (! addElementLenMULT(fp, tr, p->next->next, partitionCounter)) return FALSE;
while((ch = treeGetCh(fp)) == ',')
{
n = (tr->nextnode)++;
assert(n <= 2*(tr->mxtips) - 2);
r = tr->nodep[n];
tr->constraintVector[r->number] = partitionCounter;
rn = randomInt(10000);
if(rn == 0)
randomResolution = 0;
else
randomResolution = ((double)rn)/10000.0;
if(randomResolution < 0.5)
{
s = p->next->next->back;
r->back = p->next->next;
p->next->next->back = r;
r->next->back = s;
s->back = r->next;
addElementLenMULT(fp, tr, r->next->next, partitionCounter);
}
else
{
s = p->next->back;
r->back = p->next;
p->next->back = r;
r->next->back = s;
s->back = r->next;
addElementLenMULT(fp, tr, r->next->next, partitionCounter);
}
}
if(ch != ')')
{
printf("Missing /) in treeReadLenMULT\n");
exit(-1);
}
else
ungetc(ch, fp);
}
else
{
tr->rooted = TRUE;
if (ch != EOF) (void) ungetc(ch, fp);
}
}
else
{
p->next->next->back = (nodeptr) NULL;
}
if (! treeNeedCh(fp, ')', "in")) return FALSE;
(void) treeFlushLabel(fp);
if (! treeFlushLen(fp, tr)) return FALSE;
if (! treeNeedCh(fp, ';', "at end of")) return FALSE;
if (tr->rooted)
{
p->next->next->back = (nodeptr) NULL;
tr->start = uprootTree(tr, p->next->next, FALSE, TRUE);
if (! tr->start) return FALSE;
}
else
{
tr->start = findAnyTip(p, tr->rdta->numsp);
}
if(tr->ntips < tr->mxtips)
makeParsimonyTreeIncomplete(tr, adef);
if(!adef->rapidBoot)
onlyInitrav(tr, tr->start);
return TRUE;
}
int treeReadLen (FILE *fp, tree *tr, boolean readBranches, boolean readNodeLabels, boolean topologyOnly, analdef *adef, boolean completeTree, boolean storeBranchLabels)
{
nodeptr
p;
int
i,
ch,
lcount = 0;
tr->branchLabelCounter = 0;
for (i = 1; i <= tr->mxtips; i++)
{
tr->nodep[i]->back = (node *) NULL;
if(topologyOnly)
tr->nodep[i]->support = -1;
}
for(i = tr->mxtips + 1; i < 2 * tr->mxtips; i++)
{
tr->nodep[i]->back = (nodeptr)NULL;
tr->nodep[i]->next->back = (nodeptr)NULL;
tr->nodep[i]->next->next->back = (nodeptr)NULL;
tr->nodep[i]->number = i;
tr->nodep[i]->next->number = i;
tr->nodep[i]->next->next->number = i;
if(topologyOnly)
{
tr->nodep[i]->support = -2;
tr->nodep[i]->next->support = -2;
tr->nodep[i]->next->next->support = -2;
}
}
if(topologyOnly)
tr->start = tr->nodep[tr->mxtips];
else
tr->start = tr->nodep[1];
tr->ntips = 0;
tr->nextnode = tr->mxtips + 1;
for(i = 0; i < tr->numBranches; i++)
tr->partitionSmoothed[i] = FALSE;
tr->rooted = FALSE;
tr->wasRooted = FALSE;
p = tr->nodep[(tr->nextnode)++];
while((ch = treeGetCh(fp)) != '(');
if(!topologyOnly)
{
if(adef->mode != CLASSIFY_ML)
{
if(adef->mode != OPTIMIZE_BR_LEN_SCALER)
assert(readBranches == FALSE && readNodeLabels == FALSE);
else
assert(readBranches == TRUE && readNodeLabels == FALSE);
}
else
{
if(adef->useBinaryModelFile)
assert(readBranches == TRUE && readNodeLabels == FALSE);
else
assert(readBranches == FALSE && readNodeLabels == FALSE);
}
}
if (! addElementLen(fp, tr, p, readBranches, readNodeLabels, &lcount, adef, storeBranchLabels))
assert(0);
if (! treeNeedCh(fp, ',', "in"))
assert(0);
if (! addElementLen(fp, tr, p->next, readBranches, readNodeLabels, &lcount, adef, storeBranchLabels))
assert(0);
if (! tr->rooted)
{
if ((ch = treeGetCh(fp)) == ',')
{
if (! addElementLen(fp, tr, p->next->next, readBranches, readNodeLabels, &lcount, adef, storeBranchLabels))
assert(0);
}
else
{
/* A rooted format */
tr->rooted = TRUE;
tr->wasRooted = TRUE;
if (ch != EOF) (void) ungetc(ch, fp);
}
}
else
{
p->next->next->back = (nodeptr) NULL;
tr->wasRooted = TRUE;
}
if(!tr->rooted && adef->mode == ANCESTRAL_STATES)
{
printf("Error: The ancestral state computation mode requires a rooted tree as input, exiting ....\n");
exit(0);
}
if (! treeNeedCh(fp, ')', "in"))
assert(0);
if(topologyOnly)
assert(!(tr->rooted && readNodeLabels));
(void) treeFlushLabel(fp);
if (! treeFlushLen(fp, tr))
assert(0);
if (! treeNeedCh(fp, ';', "at end of"))
assert(0);
if (tr->rooted)
{
assert(!readNodeLabels);
p->next->next->back = (nodeptr) NULL;
tr->start = uprootTree(tr, p->next->next, readBranches, FALSE);
/*tr->leftRootNode = p->back;
tr->rightRootNode = p->next->back;
*/
if (! tr->start)
{
printf("FATAL ERROR UPROOTING TREE\n");
assert(0);
}
}
else
tr->start = findAnyTip(p, tr->rdta->numsp);
if(!topologyOnly || adef->mode == CLASSIFY_MP)
{
assert(tr->ntips <= tr->mxtips);
if(tr->ntips < tr->mxtips)
{
if(completeTree)
{
printBothOpen("Hello this is your friendly RAxML tree parsing routine\n");
printBothOpen("The RAxML option you are uisng requires to read in only complete trees\n");
printBothOpen("with %d taxa, there is at least one tree with %d taxa though ... exiting\n", tr->mxtips, tr->ntips);
exit(-1);
}
else
{
if(adef->computeDistance)
{
printBothOpen("Error: pairwise distance computation only allows for complete, i.e., containing all taxa\n");
printBothOpen("bifurcating starting trees\n");
exit(-1);
}
if(adef->mode == CLASSIFY_ML || adef->mode == CLASSIFY_MP)
{
printBothOpen("RAxML placement algorithm: You provided a reference tree with %d taxa; alignmnet has %d taxa\n", tr->ntips, tr->mxtips);
printBothOpen("%d query taxa will be placed using %s\n", tr->mxtips - tr->ntips, (adef->mode == CLASSIFY_ML)?"maximum likelihood":"parsimony");
if(adef->mode == CLASSIFY_ML)
classifyML(tr, adef);
else
{
assert(adef->mode == CLASSIFY_MP);
classifyMP(tr, adef);
}
}
else
{
printBothOpen("You provided an incomplete starting tree %d alignmnet has %d taxa\n", tr->ntips, tr->mxtips);
makeParsimonyTreeIncomplete(tr, adef);
}
}
}
else
{
if(adef->mode == PARSIMONY_ADDITION)
{
printBothOpen("Error you want to add sequences to a trees via MP stepwise addition, but \n");
printBothOpen("you have provided an input tree that already contains all taxa\n");
exit(-1);
}
if(adef->mode == CLASSIFY_ML || adef->mode == CLASSIFY_MP)
{
printBothOpen("Error you want to place query sequences into a tree using %s, but\n", tr->mxtips - tr->ntips, (adef->mode == CLASSIFY_ML)?"maximum likelihood":"parsimony");
printBothOpen("you have provided an input tree that already contains all taxa\n");
exit(-1);
}
}
onlyInitrav(tr, tr->start);
}
return lcount;
}
int treeReadLen (FILE *fp, tree *tr, boolean readBranches, boolean readNodeLabels, boolean topologyOnly, analdef *adef, boolean completeTree)
{
nodeptr
p;
int
i,
ch,
lcount = 0;
for (i = 1; i <= tr->mxtips; i++)
{
tr->nodep[i]->back = (node *) NULL;
if(topologyOnly)
tr->nodep[i]->support = -1;
}
for(i = tr->mxtips + 1; i < 2 * tr->mxtips; i++)
{
tr->nodep[i]->back = (nodeptr)NULL;
tr->nodep[i]->next->back = (nodeptr)NULL;
tr->nodep[i]->next->next->back = (nodeptr)NULL;
tr->nodep[i]->number = i;
tr->nodep[i]->next->number = i;
tr->nodep[i]->next->next->number = i;
if(topologyOnly)
{
tr->nodep[i]->support = -2;
tr->nodep[i]->next->support = -2;
tr->nodep[i]->next->next->support = -2;
}
}
if(topologyOnly)
tr->start = tr->nodep[tr->mxtips];
else
tr->start = tr->nodep[1];
tr->ntips = 0;
tr->nextnode = tr->mxtips + 1;
for(i = 0; i < tr->numBranches; i++)
tr->partitionSmoothed[i] = FALSE;
tr->rooted = FALSE;
p = tr->nodep[(tr->nextnode)++];
while((ch = treeGetCh(fp)) != '(');
if(!topologyOnly)
assert(readBranches == FALSE && readNodeLabels == FALSE);
if (! addElementLen(fp, tr, p, readBranches, readNodeLabels, &lcount))
assert(0);
if (! treeNeedCh(fp, ',', "in"))
assert(0);
if (! addElementLen(fp, tr, p->next, readBranches, readNodeLabels, &lcount))
assert(0);
if (! tr->rooted)
{
if ((ch = treeGetCh(fp)) == ',')
{
if (! addElementLen(fp, tr, p->next->next, readBranches, readNodeLabels, &lcount))
assert(0);
}
else
{ /* A rooted format */
tr->rooted = TRUE;
if (ch != EOF) (void) ungetc(ch, fp);
}
}
else
{
p->next->next->back = (nodeptr) NULL;
}
if (! treeNeedCh(fp, ')', "in"))
assert(0);
if(topologyOnly)
assert(!(tr->rooted && readNodeLabels));
(void) treeFlushLabel(fp);
if (! treeFlushLen(fp))
assert(0);
if (! treeNeedCh(fp, ';', "at end of"))
assert(0);
if (tr->rooted)
{
assert(!readNodeLabels);
p->next->next->back = (nodeptr) NULL;
tr->start = uprootTree(tr, p->next->next, FALSE, FALSE);
if (! tr->start)
{
printf("FATAL ERROR UPROOTING TREE\n");
assert(0);
}
}
else
tr->start = findAnyTip(p, tr->rdta->numsp);
if(!topologyOnly)
{
setupPointerMesh(tr);
assert(tr->ntips <= tr->mxtips);
if(tr->ntips < tr->mxtips)
{
if(completeTree)
{
printBothOpen("Hello this is your friendly RAxML tree parsing routine\n");
printBothOpen("The RAxML option you are uisng requires to read in only complete trees\n");
printBothOpen("with %d taxa, there is at least one tree with %d taxa though ... exiting\n", tr->mxtips, tr->ntips);
exit(-1);
}
else
{
if(adef->computeDistance)
{
printBothOpen("Error: pairwise distance computation only allows for complete, i.e., containing all taxa\n");
printBothOpen("bifurcating starting trees\n");
exit(-1);
}
if(adef->mode == CLASSIFY_ML)
{
printBothOpen("RAxML classifier Algo: You provided a reference tree with %d taxa; alignmnet has %d taxa\n", tr->ntips, tr->mxtips);
printBothOpen("%d query taxa will be classifed under ML\n", tr->mxtips - tr->ntips);
classifyML(tr, adef);
}
else
{
printBothOpen("You provided an incomplete starting tree %d alignmnet has %d taxa\n", tr->ntips, tr->mxtips);
makeParsimonyTreeIncomplete(tr, adef);
}
}
}
else
{
if(adef->mode == PARSIMONY_ADDITION)
{
printBothOpen("Error you want to add sequences to a trees via MP stepwise addition, but \n");
printBothOpen("you have provided an input tree that already contains all taxa\n");
exit(-1);
}
if(adef->mode == CLASSIFY_ML)
{
printBothOpen("Error you want to classify query sequences into a tree via ML, but \n");
printBothOpen("you have provided an input tree that already contains all taxa\n");
exit(-1);
}
}
onlyInitrav(tr, tr->start);
}
return lcount;
}
void computePlacementBias(tree *tr, analdef *adef)
{
int
windowSize = adef->slidingWindowSize,
k,
i,
tips,
numTraversalBranches = (2 * (tr->mxtips - 1)) - 3; /* compute number of branches into which we need to insert once we have removed a taxon */
char
fileName[1024];
FILE
*outFile;
/* data for each sliding window starting position */
positionData
*pd = (positionData *)malloc(sizeof(positionData) * (tr->cdta->endsite - windowSize));
double
*nodeDistances = (double*)calloc(tr->cdta->endsite, sizeof(double)), /* array to store node distnces ND for every sliding window position */
*distances = (double*)calloc(tr->cdta->endsite, sizeof(double)); /* array to store avg distances for every site */
strcpy(fileName, workdir);
strcat(fileName, "RAxML_SiteSpecificPlacementBias.");
strcat(fileName, run_id);
outFile = myfopen(fileName, "w");
printBothOpen("Likelihood of comprehensive tree %f\n\n", tr->likelihood);
if(windowSize > tr->cdta->endsite)
{
printBothOpen("The size of your sliding window is %d while the number of sites in the alignment is %d\n\n", windowSize, tr->cdta->endsite);
exit(-1);
}
if(windowSize >= (int)(0.9 * tr->cdta->endsite))
printBothOpen("WARNING: your sliding window of size %d is only slightly smaller than you alignment that has %d sites\n\n", windowSize, tr->cdta->endsite);
printBothOpen("Sliding window size: %d\n\n", windowSize);
/* prune and re-insert on tip at a time into all branches of the remaining tree */
for(tips = 1; tips <= tr->mxtips; tips++)
{
nodeptr
myStart,
p = tr->nodep[tips]->back, /* this is the node at which we are prunung */
p1 = p->next->back,
p2 = p->next->next->back;
double
pz[NUM_BRANCHES],
p1z[NUM_BRANCHES],
p2z[NUM_BRANCHES];
int
branchCounter = 0;
/* reset array values for this tip */
for(i = 0; i < tr->cdta->endsite; i++)
{
pd[i].lh = unlikely;
pd[i].p = (nodeptr)NULL;
}
/* store the three branch lengths adjacent to the position at which we prune */
for(i = 0; i < tr->numBranches; i++)
{
p1z[i] = p1->z[i];
p2z[i] = p2->z[i];
pz[i] = p->z[i];
}
/* prune the taxon, optimizing the branch between p1 and p2 */
removeNodeBIG(tr, p, tr->numBranches);
printBothOpen("Pruning taxon Number %d [%s]\n", tips, tr->nameList[tips]);
/* find any tip to start traversing the tree */
myStart = findAnyTip(p1, tr->mxtips);
/* insert taxon, compute likelihood and remove taxon again from all branches */
traverseBias(p, myStart->back, tr, &branchCounter, pd, windowSize);
assert(branchCounter == numTraversalBranches);
/* for every sliding window position calc ND to the true/correct position at p */
for(i = 0; i < tr->cdta->endsite - windowSize; i++)
nodeDistances[i] = getNodeDistance(p1, pd[i].p, tr->mxtips);
/* now analyze */
for(i = 0; i < tr->cdta->endsite; i++)
{
double
d = 0.0;
int
s = 0;
/*
check site position, i.e., doe we have windowSize data points available
or fewer because we are at the start or the end of the alignment
*/
/*
for each site just accumulate the node distances we have for all
sliding windows that passed over this site
*/
if(i < windowSize)
{
for(k = 0; k < i + 1; k++, s++)
d += nodeDistances[k];
}
else
{
if(i < tr->cdta->endsite - windowSize)
{
for(k = i - windowSize + 1; k <= i; k++, s++)
d += nodeDistances[k];
}
else
{
for(k = i - windowSize; k < (tr->cdta->endsite - windowSize); k++, s++)
d += nodeDistances[k + 1];
}
}
/*
now just divide the accumultaed ND distance by
the number of distances we have for this position and then add it to the acc
distances over all taxa.
I just realized that the version on which I did the tests
I sent to Simon I used
distances[i] = d / ((double)s);
instead of
distances[i] += d / ((double)s);
gamo tin poutana mou
*/
distances[i] += (d / ((double)s));
}
/*
re-connect taxon to its original position
*/
hookup(p->next, p1, p1z, tr->numBranches);
hookup(p->next->next, p2, p2z, tr->numBranches);
hookup(p, p->back, pz, tr->numBranches);
/*
fix likelihood vectors
*/
newviewGeneric(tr, p);
}
/*
now just compute the average ND over all taxa
*/
for(i = 0; i < tr->cdta->endsite; i++)
{
double
avg = distances[i] / ((double)tr->mxtips);
fprintf(outFile, "%d %f\n", i, avg);
}
printBothOpen("\nTime for EPA-based site-specific placement bias calculation: %f\n", gettime() - masterTime);
printBothOpen("Site-specific placement bias statistics written to file %s\n", fileName);
fclose(outFile);
exit(0);
}