public void TestDoubleAverage()
{
List <TopDownHit> tdhList = new List <TopDownHit>();
for (int i = 0; i < 10; i++)
{
TopDownHit t = new TopDownHit();
t.score = (10 + Convert.ToDouble(i));
t.ms2_retention_time = 50;
t.accession = "accession";
t.sequence = "sequence";
t.pscore = (double)1 / (i + 1);
t.ptm_list = new List <Ptm>();
t.tdResultType = TopDownResultType.TightAbsoluteMass;
tdhList.Add(t);
}
tdhList[9].ms2_retention_time = 52;
Sweet.lollipop.top_down_hits = tdhList;
Sweet.lollipop.topdown_proteoforms = Sweet.lollipop.aggregate_td_hits(Sweet.lollipop.top_down_hits, Sweet.lollipop.min_score_td, Sweet.lollipop.biomarker, Sweet.lollipop.tight_abs_mass);
int count = Sweet.lollipop.topdown_proteoforms.Count();
Assert.AreEqual(1, count); //all topdown hits should aggregate to a single proteoform
Assert.AreEqual(19, Sweet.lollipop.topdown_proteoforms[0].topdown_hits[0].score); //higher scoring topdown hit should be root.
Assert.AreEqual(10, Sweet.lollipop.topdown_proteoforms[0].topdown_hits.Count()); //higher scoring topdown hit should be root.
Assert.IsTrue(Sweet.lollipop.topdown_proteoforms[0].agg_rt < 52);
}
public LabeledMs1DataPoint(double mz, double retentionTime, double logTotalIonCurrent, double logInjectionTime, double massError, TopDownHit identification)
{
this.mz = mz;
this.retentionTime = retentionTime;
this.logTotalIonCurrent = logTotalIonCurrent;
this.logInjectionTime = logInjectionTime;
this.massError = massError;
this.identification = identification;
Inputs = new double[] { mz, retentionTime };
}
public void TestSimpleAggregation()
{
List <TopDownHit> tdhList = new List <TopDownHit>();
for (int i = 0; i < 2; i++)
{
TopDownHit t = new TopDownHit();
t.score = (10 + Convert.ToDouble(i));
t.ms2_retention_time = 50d;
t.ptm_list = new List <Ptm>();
t.pfr_accession = "12345";
t.sequence = "SEQUENCE";
t.tdResultType = TopDownResultType.TightAbsoluteMass;
tdhList.Add(t);
t.pscore = 1 / (i + 1);
}
Sweet.lollipop.clear_td();
Sweet.lollipop.top_down_hits = tdhList;
Sweet.lollipop.topdown_proteoforms = Sweet.lollipop.aggregate_td_hits(Sweet.lollipop.top_down_hits, Sweet.lollipop.min_score_td, Sweet.lollipop.biomarker, Sweet.lollipop.tight_abs_mass);
int count = Sweet.lollipop.topdown_proteoforms.Count();
Assert.AreEqual(1, count); //both topdown hits should aggregate to a single proteoform
Assert.AreEqual(11, Sweet.lollipop.topdown_proteoforms[0].topdown_hits[0].score); //higher scoring topdown hit should be root.
Assert.AreEqual(2, Sweet.lollipop.topdown_proteoforms[0].topdown_hits.Count()); //higher scoring topdown hit should be root.
//Test no aggregation outside retention time range
tdhList[1].ms2_retention_time += Convert.ToDouble(Sweet.lollipop.td_retention_time_tolerance + 1);
Sweet.lollipop.top_down_hits = tdhList;
Sweet.lollipop.topdown_proteoforms = Sweet.lollipop.aggregate_td_hits(Sweet.lollipop.top_down_hits, Sweet.lollipop.min_score_td, Sweet.lollipop.biomarker, Sweet.lollipop.tight_abs_mass);
Assert.AreEqual(2, Sweet.lollipop.topdown_proteoforms.Count());
//Test no aggregation different pfr
tdhList[1].ms2_retention_time = tdhList[0].ms2_retention_time;
tdhList[1].pfr_accession = "12346";
Sweet.lollipop.top_down_hits = tdhList;
Sweet.lollipop.topdown_proteoforms = Sweet.lollipop.aggregate_td_hits(Sweet.lollipop.top_down_hits, Sweet.lollipop.min_score_td, Sweet.lollipop.biomarker, Sweet.lollipop.tight_abs_mass);
Assert.AreEqual(2, Sweet.lollipop.topdown_proteoforms.Count()); //both topdown hits should aggregate to a single proteoform
//if hit score below threshold, don't aggregate
tdhList[1].pfr_accession = "12345";
tdhList[1].score = 1;
Sweet.lollipop.min_score_td = 3;
Sweet.lollipop.top_down_hits = tdhList;
Sweet.lollipop.topdown_proteoforms = Sweet.lollipop.aggregate_td_hits(Sweet.lollipop.top_down_hits, Sweet.lollipop.min_score_td, Sweet.lollipop.biomarker, Sweet.lollipop.tight_abs_mass);
Assert.AreEqual(1, Sweet.lollipop.topdown_proteoforms.Count());
Assert.AreEqual(1, Sweet.lollipop.topdown_proteoforms[0].topdown_hits.Count());
}
public void get_topdown_hit_sequence()
{
Sweet.lollipop = new Lollipop();
Sweet.lollipop.carbamidomethylation = false;
Sweet.lollipop.enter_input_files(new string[] { Path.Combine(TestContext.CurrentContext.TestDirectory, "uniprot_yeast_test_12entries.xml") }, Lollipop.acceptable_extensions[2], Lollipop.file_types[2], Sweet.lollipop.input_files, false);
Sweet.lollipop.enter_input_files(new string[] { Path.Combine(TestContext.CurrentContext.TestDirectory, "ptmlist.txt") }, Lollipop.acceptable_extensions[2], Lollipop.file_types[2], Sweet.lollipop.input_files, false);
Sweet.lollipop.theoretical_database.get_theoretical_proteoforms(TestContext.CurrentContext.TestDirectory);
//make theo database so have ptm's and sequences...
TopDownHit hit = new TopDownHit();
hit.sequence = "ASDACSDASD";
hit.ptm_list = new List <Ptm>();
Modification mod = Sweet.lollipop.theoretical_database.uniprotModifications.Values.SelectMany(m => m).Where(m => m.DatabaseReference != null && m.DatabaseReference.ContainsKey("RESID")).Where(m => m.DatabaseReference["RESID"].Contains("AA0502")).FirstOrDefault();
hit.ptm_list.Add(new Ptm(hit.sequence.Length, mod));
Modification mod2 = Sweet.lollipop.theoretical_database.uniprotModifications.Values.SelectMany(m => m).Where(m => m.DatabaseReference != null && m.DatabaseReference.ContainsKey("RESID")).Where(m => m.DatabaseReference["RESID"].Contains("AA0170")).FirstOrDefault();
hit.ptm_list.Add(new Ptm(3, mod2));
Modification mod3 = Sweet.lollipop.theoretical_database.uniprotModifications.Values.SelectMany(m => m).Where(m => m.DatabaseReference != null && m.DatabaseReference.ContainsKey("RESID")).Where(m => m.DatabaseReference["RESID"].Contains("AA0433")).FirstOrDefault();
hit.ptm_list.Add(new Ptm(1, mod3));
string sequencewithchemicalformula = hit.GetChemicalFormula().Formula;
Assert.AreEqual("C46H77N12O28PS", sequencewithchemicalformula);
//should add carbamidomethylation to C...
Sweet.lollipop.carbamidomethylation = true;
sequencewithchemicalformula = hit.GetChemicalFormula().Formula;
Assert.AreEqual("C46H77N12O28PS", sequencewithchemicalformula);
//should return null if N term formula wrong or doesn't match mass
Modification badNtermMod = new Modification("badNtermMod", _locationRestriction: "N-terminal.", _chemicalFormula: null, _monoisotopicMass: -1000);
hit = new TopDownHit();
hit.sequence = "ASDACSDASD";
hit.ptm_list = new List <Ptm>()
{
new Ptm(1, badNtermMod)
};
Assert.IsNull(hit.GetChemicalFormula());
}
//TOPDOWN pROTEOFORM
public static TopDownProteoform TopDownProteoform(string accession, double modified_mass, double retention_time)
{
TopDownHit h = new TopDownHit();
h.reported_mass = modified_mass;
h.theoretical_mass = modified_mass;
h.ms2_retention_time = retention_time;
h.sequence = "MSSSSSSSSSS";
h.begin = 10;
h.end = 20;
TopDownProteoform td = new TopDownProteoform(accession, new List <TopDownHit>()
{
h
});
(td as ExperimentalProteoform).topdown_id = true;
td.accepted = true;
return(td);
}
public void TestCopyTopDown()
{
TopDownHit hit = new TopDownHit();
hit.name = "name";
hit.uniprot_id = "id";
hit.sequence = "sequence";
hit.begin = 0;
hit.end = 20;
hit.theoretical_mass = 1000;
hit.reported_mass = 1000;
hit.ms2_retention_time = 10;
hit.pfr_accession = "PFR";
TopDownProteoform td1 = new TopDownProteoform("accession", new List <TopDownHit>()
{
hit
});
TopDownProteoform td2 = new TopDownProteoform(td1);
Assert.AreNotEqual(td1, td2);
Assert.AreEqual(td1.root, td2.root);
Assert.AreEqual(td1.name, td2.name);
Assert.AreEqual(td1.ptm_set.ptm_combination.Count, td2.ptm_set.ptm_combination.Count);
Assert.AreEqual(td1.uniprot_id, td2.uniprot_id);
Assert.AreEqual(td1.sequence, td2.sequence);
Assert.AreEqual(td1.begin, td2.begin);
Assert.AreEqual(td1.end, td2.end);
Assert.AreEqual(td1.theoretical_mass, td2.theoretical_mass);
Assert.AreEqual(td1.topdown_hits, td2.topdown_hits);
Assert.AreEqual(td1.modified_mass, td2.modified_mass);
Assert.AreEqual(td1.matching_experimental, td2.matching_experimental);
Assert.AreEqual(td1.accession, td2.accession);
Assert.AreEqual(td1.agg_rt, td2.agg_rt);
Assert.AreEqual(td1.lysine_count, td2.lysine_count);
Assert.AreEqual(td1.topdown_id, td2.topdown_id);
Assert.AreEqual(td1.agg_mass, td2.agg_mass);
Assert.AreEqual(td1.is_target, td2.is_target);
}
public DisplayTopDownHit(TopDownHit h)
: base(h)
{
this.h = h;
}
public void TestRelateTD()
{
Sweet.lollipop = new Lollipop();
Sweet.lollipop.neucode_labeled = false;
Sweet.lollipop.maximum_missed_monos = 1;
Sweet.lollipop.agg_minBiorepsWithObservations = 0;
InputFile f = new InputFile("path", Purpose.Identification);
Sweet.lollipop.input_files.Add(f);
// Two proteoforms; lysine count equal; mass difference < 250 -- return 1
Component c1 = new Component();
c1.weighted_monoisotopic_mass = 1000.0;
c1.rt_apex = 45;
c1.accepted = true;
c1.id = 1.ToString();
c1.intensity_sum = 1e6;
c1.input_file = f;
c1.charge_states = new List <ChargeState>()
{
new ChargeState(1, c1.intensity_sum, c1.weighted_monoisotopic_mass)
};
Component c2 = new Component();
c2.weighted_monoisotopic_mass = 1000.0;
c2.rt_apex = 85;
c2.accepted = true;
c2.input_file = f;
c2.intensity_sum = 1e6;
c2.charge_states = new List <ChargeState>()
{
new ChargeState(1, c2.intensity_sum, c2.weighted_monoisotopic_mass)
};
c2.id = 2.ToString();
Component c3 = new Component();
c3.weighted_monoisotopic_mass = 1131.04;
c3.rt_apex = 45;
c3.accepted = true;
c3.input_file = f;
c3.intensity_sum = 1e6;
c3.charge_states = new List <ChargeState>()
{
new ChargeState(1, c3.intensity_sum, c3.weighted_monoisotopic_mass)
};
c3.id = 3.ToString();
Component c4 = new Component();
c4.weighted_monoisotopic_mass = 2000.00;
c4.rt_apex = 45;
c4.accepted = true;
c4.input_file = new InputFile("path", Purpose.Identification);
c4.intensity_sum = 1e6;
c4.charge_states = new List <ChargeState>()
{
new ChargeState(1, c4.intensity_sum, c4.weighted_monoisotopic_mass)
};
c4.id = 4.ToString();
Component c5 = new Component();
c5.weighted_monoisotopic_mass = 1001.0;
c5.rt_apex = 45;
c5.accepted = true;
c5.input_file = f;
c5.intensity_sum = 1e6;
c5.charge_states = new List <ChargeState>()
{
new ChargeState(1, c5.intensity_sum, c5.weighted_monoisotopic_mass)
};
c5.id = 2.ToString();
List <IAggregatable> components = new List <IAggregatable>()
{
c1, c2, c3, c4, c5
};
Sweet.lollipop.raw_experimental_components = components.OfType <Component>().ToList();
TopDownProteoform td1 = ConstructorsForTesting.TopDownProteoform("ACCESSION_1", 1000.0, 45);
TopDownProteoform td2 = ConstructorsForTesting.TopDownProteoform("ACCESSION_2", 1001.0, 85);
TopDownProteoform td3 = ConstructorsForTesting.TopDownProteoform("ACCESSION_3", 1131.04, 45);
TheoreticalProteoform t1 = ConstructorsForTesting.make_a_theoretical("ACCESSION", 1000.0, 1);
//need to make theoretical accession database
TestProteoformCommunityRelate.prepare_for_et(new List <double>()
{
0
});
Sweet.lollipop.target_proteoform_community.community_number = -100;
Sweet.lollipop.theoretical_database.theoreticals_by_accession = new Dictionary <int, Dictionary <string, List <TheoreticalProteoform> > >();
Sweet.lollipop.theoretical_database.theoreticals_by_accession.Add(-100, new Dictionary <string, List <TheoreticalProteoform> >());
Sweet.lollipop.theoretical_database.theoreticals_by_accession[-100].Add(t1.accession, new List <TheoreticalProteoform>()
{
t1
});
//need to make decon error top "deconvolution error"
ModificationMotif motif;
ModificationMotif.TryGetMotif("S", out motif);
Modification m = new Modification("id", _modificationType: "modtype", _target: motif, _locationRestriction: "Anywhere.", _monoisotopicMass: 1);
Sweet.lollipop.theoretical_database.all_mods_with_mass.Add(m);
PtmSet set = new PtmSet(new List <Ptm> {
new Ptm(-1, m)
});
Sweet.lollipop.theoretical_database.all_possible_ptmsets.Add(set);
Sweet.lollipop.modification_ranks.Add(-1.0023, 2);
Sweet.lollipop.theoretical_database.possible_ptmset_dictionary.Add(-1.0, new List <PtmSet>()
{
set
});
//need missing error
Modification m2 = new Modification("id", _modificationType: "modtype", _target: motif, _locationRestriction: "Anywhere.", _monoisotopicMass: 1);
Sweet.lollipop.theoretical_database.all_mods_with_mass.Add(m2);
PtmSet set2 = new PtmSet(new List <Ptm> {
new Ptm(-1, m2)
});
Sweet.lollipop.theoretical_database.all_possible_ptmsets.Add(set2);
Sweet.lollipop.modification_ranks.Add(-87.03, 2);
Sweet.lollipop.theoretical_database.possible_ptmset_dictionary.Add(-87.0, new List <PtmSet>()
{
set2
});
Sweet.lollipop.target_proteoform_community.theoretical_proteoforms = new List <TheoreticalProteoform>()
{
t1
}.ToArray();
Sweet.lollipop.topdown_proteoforms = new List <TopDownProteoform> {
td1, td2, td3
};
Sweet.lollipop.add_td_proteoforms = true;
Sweet.lollipop.aggregate_proteoforms(Sweet.lollipop.validate_proteoforms, Sweet.lollipop.raw_neucode_pairs, Sweet.lollipop.raw_experimental_components, Sweet.lollipop.raw_quantification_components, 0);
List <ProteoformRelation> relations = Sweet.lollipop.target_proteoform_community.relate(Sweet.lollipop.target_proteoform_community.experimental_proteoforms, Sweet.lollipop.target_proteoform_community.theoretical_proteoforms, ProteoformComparison.ExperimentalTheoretical, true, Environment.CurrentDirectory, true);
List <DeltaMassPeak> peaks = Sweet.lollipop.target_proteoform_community.accept_deltaMass_peaks(relations, new Dictionary <string, List <ProteoformRelation> >());
//should have 4 experimental proteoforms -- 3 topdown, 1 not topdown experimental
Assert.AreEqual(3, Sweet.lollipop.target_proteoform_community.experimental_proteoforms.Count(e => e.topdown_id));
Assert.AreEqual(4, Sweet.lollipop.target_proteoform_community.experimental_proteoforms.Count());
Assert.AreEqual(1, relations.Count);
Assert.AreEqual(1, relations.Count(r => r.RelationType == ProteoformComparison.ExperimentalTheoretical && (r.connected_proteoforms[0] as ExperimentalProteoform).topdown_id));
Assert.AreEqual(1, td1.relationships.Count(r => r.RelationType == ProteoformComparison.ExperimentalTheoretical && (r.connected_proteoforms[0] as ExperimentalProteoform).topdown_id));
Assert.AreEqual(0, td2.relationships.Count());
Assert.AreEqual(0, td3.relationships.Count());
//accession 3 has higher score... gets td
Sweet.lollipop.clear_td();
td3 = ConstructorsForTesting.TopDownProteoform("ACCESSION_3", 1000.0, 45);
TopDownHit h3 = new TopDownHit();
h3.score = 100;
td3.topdown_hits = new List <TopDownHit>()
{
h3
};
TopDownHit h4 = new TopDownHit();
h4.score = 1;
TopDownProteoform td4 = ConstructorsForTesting.TopDownProteoform("ACCESSION_4", 1001.0, 45);
td4.topdown_hits = new List <TopDownHit>()
{
h4
};
Sweet.lollipop.topdown_proteoforms = new List <TopDownProteoform> {
td4, td3
};
Sweet.lollipop.topdown_proteoforms.OrderBy(p => p.modified_mass);
Sweet.lollipop.aggregate_proteoforms(Sweet.lollipop.validate_proteoforms, Sweet.lollipop.raw_neucode_pairs, Sweet.lollipop.raw_experimental_components, Sweet.lollipop.raw_quantification_components, 0);
Assert.AreEqual(0, Math.Round(td3.modified_mass - td3.matching_experimental.modified_mass, 0));
Assert.IsNull(td4.matching_experimental);
}
