private ModelAndFeatures CreateScoringModel(string modelName, bool decoys, bool secondBest)
{
_out.WriteLine(Resources.CommandLine_CreateScoringModel_Creating_scoring_model__0_, modelName);
try
{
// Create new scoring model using the default calculators.
var scoringModel = new MProphetPeakScoringModel(modelName, null as LinearModelParams, null, decoys, secondBest);
var progressMonitor = new CommandProgressMonitor(_out, new ProgressStatus(String.Empty));
var targetDecoyGenerator = new TargetDecoyGenerator(_doc, scoringModel, progressMonitor);
// Get scores for target and decoy groups.
List<IList<float[]>> targetTransitionGroups;
List<IList<float[]>> decoyTransitionGroups;
targetDecoyGenerator.GetTransitionGroups(out targetTransitionGroups, out decoyTransitionGroups);
// If decoy box is checked and no decoys, throw an error
if (decoys && decoyTransitionGroups.Count == 0)
{
_out.WriteLine(Resources.CommandLine_CreateScoringModel_Error__There_are_no_decoy_peptides_in_the_document__Failed_to_create_scoring_model_);
return null;
}
// Use decoys for training only if decoy box is checked
if (!decoys)
decoyTransitionGroups = new List<IList<float[]>>();
// Set intial weights based on previous model (with NaN's reset to 0)
var initialWeights = new double[scoringModel.PeakFeatureCalculators.Count];
// But then set to NaN the weights that have unknown values for this dataset
for (int i = 0; i < initialWeights.Length; ++i)
{
if (!targetDecoyGenerator.EligibleScores[i])
initialWeights[i] = double.NaN;
}
var initialParams = new LinearModelParams(initialWeights);
// Train the model.
scoringModel = (MProphetPeakScoringModel)scoringModel.Train(targetTransitionGroups,
decoyTransitionGroups, initialParams, secondBest, true, progressMonitor);
Settings.Default.PeakScoringModelList.SetValue(scoringModel);
return new ModelAndFeatures(scoringModel, targetDecoyGenerator.PeakGroupFeatures);
}
catch (Exception x)
{
_out.WriteLine(Resources.CommandLine_CreateScoringModel_Error__Failed_to_create_scoring_model_);
_out.WriteLine(x.Message);
return null;
}
}
public override IPeakScoringModel Train(IList <IList <float[]> > targets, IList <IList <float[]> > decoys, TargetDecoyGenerator targetDecoyGenerator, LinearModelParams initParameters,
int?iterations = null, bool includeSecondBest = false, bool preTrain = true, IProgressMonitor progressMonitor = null, string documentPath = null)
{
return(ChangeProp(ImClone(this), im =>
{
int nWeights = initParameters.Weights.Count;
var weights = new double [nWeights];
for (int i = 0; i < initParameters.Weights.Count; ++i)
{
weights[i] = double.IsNaN(initParameters.Weights[i]) ? double.NaN : DEFAULT_WEIGHTS[i];
}
var parameters = new LinearModelParams(weights);
ScoredGroupPeaksSet decoyTransitionGroups = new ScoredGroupPeaksSet(decoys, decoys.Count);
ScoredGroupPeaksSet targetTransitionGroups = new ScoredGroupPeaksSet(targets, targets.Count);
targetTransitionGroups.ScorePeaks(parameters.Weights);
if (includeSecondBest)
{
ScoredGroupPeaksSet secondBestTransitionGroups;
targetTransitionGroups.SelectTargetsAndDecoys(out targetTransitionGroups, out secondBestTransitionGroups);
foreach (var secondBestGroup in secondBestTransitionGroups.ScoredGroupPeaksList)
{
decoyTransitionGroups.Add(secondBestGroup);
}
}
decoyTransitionGroups.ScorePeaks(parameters.Weights);
im.UsesDecoys = decoys.Count > 0;
im.UsesSecondBest = includeSecondBest;
im.Parameters = parameters.RescaleParameters(decoyTransitionGroups.Mean, decoyTransitionGroups.Stdev);
im.Parameters = im.Parameters.CalculatePercentContributions(im, targetDecoyGenerator);
}));
}
public abstract IPeakScoringModel Train(IList <IList <float[]> > targets, IList <IList <float[]> > decoys, TargetDecoyGenerator targetDecoyGenerator, LinearModelParams initParameters,
IList <double> cutoffs, int?iterations = null, bool includeSecondBest = false, bool preTrain = true, IProgressMonitor progressMonitor = null, string documentPath = null);
public LinearModelParams CalculatePercentContributions(IPeakScoringModel model, TargetDecoyGenerator targetDecoyGenerator)
{
var percentContributions = new double[_percentContributions.Count];
for (var i = 0; i < _percentContributions.Count; ++i)
{
percentContributions[i] = (targetDecoyGenerator != null ? targetDecoyGenerator.GetPercentContribution(model, i) : null) ?? double.NaN;
}
return(ChangeProp(ImClone(this), im =>
{
im.PercentContributions = percentContributions;
}));
}
/// <summary>
/// Train the model by iterative calculating weights to separate target and decoy transition groups.
/// </summary>
/// <param name="targetsIn">Target transition groups.</param>
/// <param name="decoysIn">Decoy transition groups.</param>
/// <param name="targetDecoyGenerator">Target decoy generator used to calculate contribution percentages</param>
/// <param name="initParameters">Initial model parameters (weights and bias)</param>
/// <param name="iterations">Optional specific number of iterations to use in training</param>
/// <param name="includeSecondBest">Include the second best peaks in the targets as decoys?</param>
/// <param name="preTrain">Use a pre-trained model to bootstrap the learning.</param>
/// <param name="progressMonitor">Used to report progress to the calling context</param>
/// <param name="documentPath">The path to the current document for writing score distributions</param>
/// <returns>Immutable model with new weights.</returns>
public override IPeakScoringModel Train(IList <IList <float[]> > targetsIn,
IList <IList <float[]> > decoysIn,
TargetDecoyGenerator targetDecoyGenerator,
LinearModelParams initParameters,
int?iterations = null,
bool includeSecondBest = false,
bool preTrain = true,
IProgressMonitor progressMonitor = null,
string documentPath = null)
{
if (initParameters == null)
{
initParameters = new LinearModelParams(_peakFeatureCalculators.Count);
}
return(ChangeProp(ImClone(this), im =>
{
// This may take a long time between progress updates, but just measure progress by cycles through the training
IProgressStatus status = new ProgressStatus(Resources.MProphetPeakScoringModel_Train_Training_peak_scoring_model);
if (progressMonitor != null)
{
progressMonitor.UpdateProgress(status);
}
var targets = targetsIn.Where(list => list.Count > 0);
var decoys = decoysIn.Where(list => list.Count > 0);
var targetTransitionGroups = new ScoredGroupPeaksSet(targets, targetsIn.Count);
var decoyTransitionGroups = new ScoredGroupPeaksSet(decoys, decoysIn.Count);
// Iteratively refine the weights through multiple iterations.
var calcWeights = new double[initParameters.Weights.Count];
Array.Copy(initParameters.Weights.ToArray(), calcWeights, initParameters.Weights.Count);
double qValueCutoff = 0.01; // First iteration cut-off - if not pretraining, just start at 0.01
// Start with scores calculated from the initial weights
if (!preTrain)
{
targetTransitionGroups.ScorePeaks(calcWeights);
decoyTransitionGroups.ScorePeaks(calcWeights);
}
// Bootstrap from the pre-trained legacy model
else
{
qValueCutoff = 0.15;
var preTrainedWeights = new double[initParameters.Weights.Count];
for (int i = 0; i < preTrainedWeights.Length; ++i)
{
if (double.IsNaN(initParameters.Weights[i]))
{
preTrainedWeights[i] = double.NaN;
}
}
int standardEnabledCount = GetEnabledCount(LegacyScoringModel.StandardFeatureCalculators, initParameters.Weights);
int analyteEnabledCount = GetEnabledCount(LegacyScoringModel.AnalyteFeatureCalculators, initParameters.Weights);
bool hasStandards = standardEnabledCount >= analyteEnabledCount;
var calculators = hasStandards ? LegacyScoringModel.StandardFeatureCalculators : LegacyScoringModel.AnalyteFeatureCalculators;
for (int i = 0; i < calculators.Length; ++i)
{
if (calculators[i].GetType() == typeof(MQuestRetentionTimePredictionCalc))
{
continue;
}
SetCalculatorValue(calculators[i].GetType(), LegacyScoringModel.DEFAULT_WEIGHTS[i], preTrainedWeights);
}
targetTransitionGroups.ScorePeaks(preTrainedWeights);
decoyTransitionGroups.ScorePeaks(preTrainedWeights);
}
double decoyMean = 0;
double decoyStdev = 0;
bool colinearWarning = false;
int iterationCount = iterations ?? MAX_ITERATIONS;
int truePeaksCount = 0;
var lastWeights = new double[calcWeights.Length];
for (int i = 0; i < iterationCount; i++)
{
int percentComplete = 0;
double decoyMeanNew, decoyStdevNew;
bool colinearWarningNew = colinearWarning;
int truePeaksCountNew = im.CalculateWeights(documentPath,
targetTransitionGroups,
decoyTransitionGroups,
includeSecondBest,
i == 0, // Use non-parametric q values for first round, when normality assumption may not hold
qValueCutoff,
calcWeights,
out decoyMeanNew,
out decoyStdevNew,
ref colinearWarningNew);
if (progressMonitor != null)
{
if (progressMonitor.IsCanceled)
{
throw new OperationCanceledException();
}
// Calculate progress, but wait to make sure convergence has not occurred before setting it
string formatText = qValueCutoff > 0.02
? Resources.MProphetPeakScoringModel_Train_Training_scoring_model__iteration__0__of__1__
: Resources.MProphetPeakScoringModel_Train_Training_scoring_model__iteration__0__of__1_____2______peaks_at__3_0_____FDR_;
percentComplete = (i + 1) * 100 / (iterationCount + 1);
status = status.ChangeMessage(string.Format(formatText, i + 1, iterationCount, truePeaksCountNew, qValueCutoff))
.ChangePercentComplete(percentComplete);
}
if (qValueCutoff > 0.02)
{
// Tighten the q value cut-off for "truth" to 2% FDR
qValueCutoff = 0.02;
// And allow the true peaks count to go down in the next iteration
// Though it rarely will
truePeaksCountNew = 0;
}
// Decided in 2018 that equal should be counted as converging, since otherwise training can just get stuck,
// and go to full iteration count without progressing
else if (truePeaksCountNew <= truePeaksCount)
{
// The model has leveled off enough to begin losing discriminant value
if (qValueCutoff > 0.01)
{
// Tighten the q value cut-off for "truth" to 1% FDR
qValueCutoff = 0.01;
// And allow the true peaks count to go down in the next iteration
truePeaksCountNew = 0;
}
else
{
if (progressMonitor != null)
{
progressMonitor.UpdateProgress(status =
status.ChangeMessage(string.Format(Resources.MProphetPeakScoringModel_Train_Scoring_model_converged__iteration__0_____1______peaks_at__2_0_____FDR_, i + 1, truePeaksCount, qValueCutoff))
.ChangePercentComplete(Math.Max(95, percentComplete)));
}
calcWeights = lastWeights;
break;
}
}
truePeaksCount = truePeaksCountNew;
Array.Copy(calcWeights, lastWeights, calcWeights.Length);
decoyMean = decoyMeanNew;
decoyStdev = decoyStdevNew;
colinearWarning = colinearWarningNew;
if (progressMonitor != null)
{
progressMonitor.UpdateProgress(status);
}
}
if (progressMonitor != null)
{
progressMonitor.UpdateProgress(status.ChangePercentComplete(100));
}
var parameters = new LinearModelParams(calcWeights);
parameters = parameters.RescaleParameters(decoyMean, decoyStdev);
im.Parameters = parameters;
im.ColinearWarning = colinearWarning;
im.UsesSecondBest = includeSecondBest;
im.UsesDecoys = decoysIn.Count > 0;
im.Parameters = parameters.CalculatePercentContributions(im, targetDecoyGenerator);
}));
}