def test_alignAllCluster_1(self):
"""Test the best cluster align
This is using the best possible conditions with only 7 seconds retention time cutoff
- Run1 : 100s [threadRT = 100s]
- Run2 : 112s [threadRT = 106s]
- Run3 : 120s [threadRT = 118s]
- Run4 : xxx [threadRT = 126s] (should be around 130s)
- Run5 : 139s [threadRT = 133s]
"""
spl_aligner = SplineAligner(self.initial_alignment_cutoff)
tree = MinimumSpanningTree(
algo.getDistanceMatrix(self.exp, self.multipeptides, spl_aligner))
tree_mapped = [(self.exp.runs[a].get_id(), self.exp.runs[b].get_id())
for a, b in tree]
alignment = algo.TreeConsensusAlignment(max_rt_diff=6,
fdr_cutoff=0.1,
aligned_fdr_cutoff=0.25,
correctRT_using_pg=True,
verbose=True)
alignment.alignAllCluster(self.multipeptides, tree_mapped,
self.tr_data)
# We should have 4 peakgroups
prec1 = self.mpep
self.assertEqual(len(prec1.get_selected_peakgroups()), 4)
# Check that we have all the correct ones (1,2,4,8)
self.assertEqual(
set(['peakgroup8', 'peakgroup2', 'peakgroup4', 'peakgroup1']),
set([p.get_feature_id() for p in prec1.get_selected_peakgroups()]))
def test_alignBestCluster_1(self):
"""Test the best cluster align
This is now using no correction of the alignment thread by using the
found peakgroup. In this case it means that after finding the second
peakgroup at 112 s, the search RT for run 2 is still at 106 seconds
which gets mapped to 112 seconds in run 3 (but the next pg is at 120s,
too far for 7 seconds tolerance).
"""
spl_aligner = SplineAligner(self.initial_alignment_cutoff)
tree = MinimumSpanningTree(
algo.getDistanceMatrix(self.exp, self.multipeptides, spl_aligner))
tree_mapped = [(self.exp.runs[a].get_id(), self.exp.runs[b].get_id())
for a, b in tree]
alignment = algo.TreeConsensusAlignment(max_rt_diff=6,
fdr_cutoff=0.1,
aligned_fdr_cutoff=0.25,
correctRT_using_pg=False)
alignment.alignBestCluster_legacy(self.multipeptides, tree_mapped,
self.tr_data)
# Now only 2 peakgroups should be selected
prec1 = self.mpep
self.assertEqual(len(prec1.get_selected_peakgroups()), 2)
# Check that we have all the correct ones (only 1,2)
self.assertEqual(
set(['peakgroup2', 'peakgroup1']),
set([p.get_feature_id() for p in prec1.get_selected_peakgroups()]))
def test_alignBestCluster_2(self):
"""Test the best cluster align
This is now using no correction of the alignment thread by using the
found peakgroup (e.g. no correction of the threading).
- Run1 : 100s [threadRT = 100s]
- Run2 : 112s [threadRT = 106s]
- Run3 : 120s [threadRT = 112s]
- Run4 : xxx [threadRT = 118s]
- Run5 : 139s [threadRT = 124s]
By using a larger tolerance of 15s, we can still manage to find all the correct peakgroups
"""
spl_aligner = SplineAligner(self.initial_alignment_cutoff)
tree = MinimumSpanningTree(
algo.getDistanceMatrix(self.exp, self.multipeptides, spl_aligner))
tree_mapped = [(self.exp.runs[a].get_id(), self.exp.runs[b].get_id())
for a, b in tree]
alignment = algo.TreeConsensusAlignment(max_rt_diff=15,
fdr_cutoff=0.1,
aligned_fdr_cutoff=0.25,
correctRT_using_pg=False)
alignment.alignBestCluster_legacy(self.multipeptides, tree_mapped,
self.tr_data)
# Now only 2 peakgroups should be selected
prec1 = self.mpep
self.assertEqual(len(prec1.get_selected_peakgroups()), 4)
# Check that we have all the correct ones (1,2,4,8)
self.assertEqual(
set(['peakgroup8', 'peakgroup2', 'peakgroup4', 'peakgroup1']),
set([p.get_feature_id() for p in prec1.get_selected_peakgroups()]))