def testPeptideHit():
"""
@tests:
PeptideHit.__init__
PeptideHit.addProteinAccession
PeptideHit.clearMetaInfo
PeptideHit.getAAAfter
PeptideHit.getAABefore
PeptideHit.getKeys
PeptideHit.getMetaValue
PeptideHit.getProteinAccessions
PeptideHit.getRank
PeptideHit.getScore
PeptideHit.getSequence
PeptideHit.isMetaEmpty
PeptideHit.metaValueExists
PeptideHit.removeMetaValue
PeptideHit.setAAAfter
PeptideHit.setAABefore
PeptideHit.setCharge
PeptideHit.setMetaValue
PeptideHit.setProteinAccessions
PeptideHit.setRank
PeptideHit.setScore
PeptideHit.setSequence
PeptideHit.__eq__
PeptideHit.__ge__
PeptideHit.__gt__
PeptideHit.__le__
PeptideHit.__lt__
PeptideHit.__ne__
"""
ph = pyopenms.PeptideHit()
assert ph == ph
assert not ph != ph
ph = pyopenms.PeptideHit(1.0, 1, 0, pyopenms.AASequence("A"))
_testMetaInfoInterface(ph)
ph.addProteinAccession("A")
assert ph.getProteinAccessions() == ["A"]
assert ph.getScore() == 1.0
assert ph.getRank() == 1
assert ph.getSequence().toString() == "A"
ph.setScore(2.0)
assert ph.getScore() == 2.0
ph.setRank(30)
assert ph.getRank() == 30
ph.setSequence(pyopenms.AASequence("AAA"))
assert ph.getSequence().toString() == "AAA"
ph.setAABefore('B')
assert ph.getAABefore() == "B"
ph.setAAAfter('C')
assert ph.getAAAfter() == 'C'
assert ph == ph
assert not ph != ph
import pyopenms
"""
Producing the test data for TOPP_FeatureLinkerUnlabeledQT_5 and TOPP_FeatureLinkerUnlabeledQT_6
"""
fmaps = [pyopenms.FeatureMap() for i in range(3)]
pepids = []
pepseq = ["PEPTIDEA", "PEPTIDEK", "PEPTIDER"]
for s in pepseq:
pepid = pyopenms.PeptideIdentification()
hit = pyopenms.PeptideHit()
hit.setSequence(pyopenms.AASequence.fromString(s, True))
pepid.insertHit(hit)
pepid.setIdentifier("Protein0")
pepids.append(pepid)
protid = pyopenms.ProteinIdentification()
protid.setIdentifier("Protein0")
for i, fmap in enumerate(fmaps):
fmap.setProteinIdentifications([protid])
# add 3 features to each map, but with a twist (adding different peptide ids to different maps)
for k in range(3):
f = pyopenms.Feature()
f.setRT(300 + k * 100 + i * 10)
f.setMZ(500 + k * 0.001 + i * 0.01)
f.setIntensity(500 + i * 100)
f.setMetaValue("sequence",
pepseq[(i + k) % 3]) # easier viewing in TOPPView
f.setPeptideIdentifications([pepids[(i + k) % 3]])
fmap.push_back(f)
pyopenms.FeatureXMLFile().store("output_%s.featureXML" % i, fmap)
def testPeptideIdentification():
"""
@tests:
PeptideIdentification.__init__
PeptideIdentification.assignRanks
PeptideIdentification.clearMetaInfo
PeptideIdentification.empty
PeptideIdentification.getHits
PeptideIdentification.getIdentifier
PeptideIdentification.getKeys
PeptideIdentification.getMetaValue
PeptideIdentification.getNonReferencingHits
PeptideIdentification.getReferencingHits
PeptideIdentification.getScoreType
PeptideIdentification.getSignificanceThreshold
PeptideIdentification.insertHit
PeptideIdentification.isHigherScoreBetter
PeptideIdentification.isMetaEmpty
PeptideIdentification.metaValueExists
PeptideIdentification.removeMetaValue
PeptideIdentification.setHigherScoreBetter
PeptideIdentification.setHits
PeptideIdentification.setIdentifier
PeptideIdentification.setMetaValue
PeptideIdentification.setScoreType
PeptideIdentification.sort
PeptideIdentification.__eq__
PeptideIdentification.__ge__
PeptideIdentification.__gt__
PeptideIdentification.__le__
PeptideIdentification.__lt__
PeptideIdentification.__ne__
"""
pi = pyopenms.PeptideIdentification()
_testMetaInfoInterface(pi)
assert pi == pi
assert not pi != pi
ph = pyopenms.PeptideHit(1.0, 1, 0, pyopenms.AASequence("A"))
pi.insertHit(ph)
phx, = pi.getHits()
assert phx == ph
pi.setHits([ph])
phx, = pi.getHits()
assert phx == ph
assert isinstance(pi.getSignificanceThreshold(), float)
assert isinstance(pi.getScoreType(), str)
pi.setScoreType("A")
assert isinstance(pi.isHigherScoreBetter(), int)
assert isinstance(pi.getIdentifier(), str)
pi.setIdentifier("id")
pi.assignRanks()
pi.sort()
assert not pi.empty()
rv = []
pi.getReferencingHits("A", rv)
assert rv == []
pi.getNonReferencingHits("A", rv)
hit, = rv
assert hit.getSequence().toString() == "A"
assert hit.getScore() == 1.0
assert hit.getRank() == 1
rv = []
pi.getReferencingHits(["A"], rv)
assert rv == []
pi.getNonReferencingHits(["A"], rv)
hit, = rv
assert hit.getSequence().toString() == "A"
assert hit.getScore() == 1.0
assert hit.getRank() == 1
ph = pyopenms.ProteinHit()
pi.getReferencingHits([ph], rv)
hit, = rv
assert hit.getSequence().toString() == "A"
assert hit.getScore() == 1.0
assert hit.getRank() == 1
rv = []
pi.getNonReferencingHits([ph], rv)
hit, = rv
assert hit.getSequence().toString() == "A"
assert hit.getScore() == 1.0
assert hit.getRank() == 1
run_name = 'unknown'
skiplines = 0
with open(args.mztab) as f_in:
line = next(f_in)
while line.split('\t', 1)[0] != 'PSH':
if 'ms_run[1]-location' in line:
run_name = line.split('\t')[2]
line = next(f_in)
skiplines += 1
psms = pd.read_csv(args.mztab, sep='\t', header=skiplines, index_col='PSM_ID')
peptide_ids = []
for _, psm in psms.iterrows():
peptide_id = pyms.PeptideIdentification()
peptide_id.setRT(psm['retention_time'])
peptide_id.setMZ(psm['exp_mass_to_charge'])
peptide_id.setScoreType('q-value')
peptide_id.setHigherScoreBetter(False)
peptide_id.setIdentifier(run_name)
peptide_hit = pyms.PeptideHit()
peptide_hit.setScore(psm['search_engine_score[2]'])
peptide_hit.setRank(1)
peptide_hit.setCharge(psm['charge'])
peptide_hit.setSequence(pyms.AASequence.fromString(psm['sequence']))
peptide_id.setHits([peptide_hit])
peptide_ids.append(peptide_id)
protein_id = pyms.ProteinIdentification()
protein_id.setIdentifier(run_name)
pyms.IdXMLFile().store(output_path, [protein_id], peptide_ids)