static int Main(string[] args)
{
CanvasCommon.Utilities.LogCommandLine(args);
string inFile = null;
string outFile = null;
string variantFrequencyFile = null;
string referenceFolder = null;
string name = "SAMPLE";
string truthDataPath = null;
string somaticVCFPath = null;
bool needHelp = false;
string bedPath = null;
string ploidyVcfPath = null;
string localSdMetricFile = null;
string evennessMetricFile = null;
bool isEnrichment = false;
bool isDbsnpVcf = false;
double minimumCallSize;
int qualityFilterThreshold = 10; // Default quality filter threshold = 10, overridable via -q command-line argument
// Parameters, for parameter-sweep, somatic model training:
bool isTrainMode = false;
float?userPurity = null;
float?userPloidy = null;
CanvasCommon.CanvasSomaticClusteringMode somaticClusteringMode =
CanvasCommon.CanvasSomaticClusteringMode.MeanShift;
string parameterconfigPath = Path.Combine(Isas.Framework.Utilities.Utilities.GetAssemblyFolder(typeof(Program)),
"SomaticCallerParameters.json");
string qualityScoreConfigPath = Path.Combine(Isas.Framework.Utilities.Utilities.GetAssemblyFolder(typeof(Program)),
"QualityScoreParameters.json");
OptionSet p = new OptionSet()
{
{
"i|infile=",
"file containing bins, their counts, and assigned segments (obtained from CanvasPartition.exe)",
v => inFile = v
},
{
"v|varfile=", "file containing variant frequencies (obtained from CanvasSNV.exe)",
v => variantFrequencyFile = v
},
{ "o|outfile=", "file name prefix to ouput copy number calls to outfile.vcf", v => outFile = v },
{ "r|reference=", "folder that contains both genome.fa and GenomeSize.xml", v => referenceFolder = v },
{ "n|name=", "sample name for output VCF header (optional)", v => name = v },
{ "t|truth=", "path to vcf/bed with CNV truth data (optional)", v => truthDataPath = v },
{ "h|help", "show this message and exit", v => needHelp = v != null },
{ "e|enrichment", "flag indicating this is enrichment data", v => isEnrichment = v != null },
{ "s|somaticvcf=", "somatic vcf file - optionally used for purity estimation", v => somaticVCFPath = v },
{ "b|bedfile=", "bed file containing regions to exclude from calling", v => bedPath = v },
{
"p|ploidyVcfFile=", "vcf file specifying reference ploidy (e.g. for sex chromosomes) (optional)",
v => ploidyVcfPath = v
},
{
$"{CommandLineOptions.LocalSdMetricFile}=", "text file with local SD metric (calculate within CanvasClean) (optional)",
v => localSdMetricFile = v
},
{
$"{CommandLineOptions.EvennessMetricFile}=", "text file with evenness metric (calculated within CanvasPartition) (optional)",
v => evennessMetricFile = v
},
{
"d|dbsnpvcf", "flag indicating a dbSNP VCF file is used to generate the variant frequency file",
v => isDbsnpVcf = v != null
},
{ "M|minimumcall=", "INTERNAL: minimum call size", v => minimumCallSize = int.Parse(v) },
{
"q|qualitythreshold=", $"quality filter threshold (default {qualityFilterThreshold})",
v => qualityFilterThreshold = int.Parse(v)
},
{
"c|parameterconfig=", $"parameter configuration path (default {parameterconfigPath})",
v => parameterconfigPath = v
},
{
"g|qscoreconfig=", $"parameter configuration path (default {qualityScoreConfigPath})",
v => qualityScoreConfigPath = v
},
{ "u|definedpurity=", "INTERNAL: user pre-defined purity", v => userPurity = float.Parse(v) },
{ "l|definedploidy=", "INTERNAL: user pre-defined ploidy", v => userPloidy = float.Parse(v) },
{ "a|trainmodel=", "INTERNAL: user pre-defined ploidy", v => isTrainMode = v != null }
};
List <string> extraArgs = p.Parse(args);
if (extraArgs.Count > 0)
{
Console.WriteLine("Error: Argument '{0}' not understood", extraArgs[0]);
needHelp = true;
}
if (needHelp)
{
ShowHelp(p);
return(0);
}
if (inFile == null || outFile == null || referenceFolder == null)
{
ShowHelp(p);
return(0);
}
if (!File.Exists(inFile))
{
Console.WriteLine("Canvas error: File {0} does not exist! Exiting.", inFile);
return(1);
}
if (!File.Exists(variantFrequencyFile))
{
Console.WriteLine("Canvas error: File {0} does not exist! Exiting.", variantFrequencyFile);
return(1);
}
if (!File.Exists(Path.Combine(referenceFolder, "GenomeSize.xml")))
{
Console.WriteLine("Canvas error: File {0} does not exist! Exiting.",
Path.Combine(referenceFolder, "GenomeSize.xml"));
return(1);
}
if (qualityFilterThreshold < 0)
{
throw new ArgumentException(
$"Quality filter threshold must be greater than or equal to zero. Value was {qualityFilterThreshold}");
}
if (!File.Exists(parameterconfigPath))
{
Console.WriteLine("Canvas error: File {0} does not exist! Exiting.", parameterconfigPath);
return(1);
}
FileLocation parameterconfigFile = new FileLocation(parameterconfigPath);
SomaticCallerParameters somaticCallerParametersJSON = Deserialize <SomaticCallerParameters>(parameterconfigFile);
FileLocation qscoreConfigFile = new FileLocation(qualityScoreConfigPath);
CanvasCommon.QualityScoreParameters qscoreParametersJSON = Deserialize <CanvasCommon.QualityScoreParameters>(qscoreConfigFile);
var logger = new Logger(new[] { Console.Out }, new[] { Console.Error });
SomaticCaller caller = new SomaticCaller(logger);
caller.somaticCallerParameters = somaticCallerParametersJSON;
caller.somaticCallerQscoreParameters = qscoreParametersJSON;
caller.TruthDataPath = truthDataPath;
caller.SomaticVcfPath = somaticVCFPath;
caller.IsEnrichment = isEnrichment;
caller.IsDbsnpVcf = isDbsnpVcf;
caller.userPurity = userPurity;
caller.userPloidy = userPloidy;
caller.IsTrainingMode = truthDataPath != null || isTrainMode;
caller.IsTrainingMode = isTrainMode;
caller.QualityFilterThreshold = qualityFilterThreshold;
// Set parameters:
if (!string.IsNullOrEmpty(ploidyVcfPath))
{
caller.LoadReferencePloidy(ploidyVcfPath);
}
double?localSDmetric = null;
double?evennessMetric = null;
if (!string.IsNullOrEmpty(localSdMetricFile))
{
localSDmetric = CanvasCommon.CanvasIO.ReadLocalSdMetricFromTextFile(localSdMetricFile);
}
if (!string.IsNullOrEmpty(evennessMetricFile))
{
evennessMetric = CanvasCommon.CanvasIO.ReadEvennessMetricFromTextFile(evennessMetricFile);
}
caller.LoadBedFile(bedPath);
return(caller.CallVariants(inFile, variantFrequencyFile, outFile, referenceFolder, name, localSDmetric, evennessMetric, somaticClusteringMode));
}
public int ComputeQScore(QScoreMethod qscoreMethod, QualityScoreParameters qscoreParameters)
{
double score;
int qscore;
switch (qscoreMethod)
{
case QScoreMethod.LogisticGermline:
// Logistic model using a new selection of features. Gives ROC curve area 0.921
score = qscoreParameters.LogisticGermlineIntercept;
score += GetQScorePredictor(QScorePredictor.LogBinCount) * qscoreParameters.LogisticGermlineLogBinCount;
score += GetQScorePredictor(QScorePredictor.ModelDistance) * qscoreParameters.LogisticGermlineModelDistance;
score += GetQScorePredictor(QScorePredictor.DistanceRatio) * qscoreParameters.LogisticGermlineDistanceRatio;
score = Math.Exp(score);
score = score / (score + 1);
// Transform probability into a q-score:
qscore = (int)(Math.Round(-10 * Math.Log10(1 - score)));
qscore = Math.Min(40, qscore);
qscore = Math.Max(2, qscore);
return(qscore);
case QScoreMethod.Logistic:
// Logistic model using a new selection of features. Gives ROC curve area 0.8289
score = qscoreParameters.LogisticIntercept;
score += GetQScorePredictor(QScorePredictor.LogBinCount) * qscoreParameters.LogisticLogBinCount;
score += GetQScorePredictor(QScorePredictor.ModelDistance) * qscoreParameters.LogisticModelDistance;
score += GetQScorePredictor(QScorePredictor.DistanceRatio) * qscoreParameters.LogisticDistanceRatio;
score += GetQScorePredictor(QScorePredictor.BinCountAmpDistance);
score = Math.Exp(score);
score = score / (score + 1);
// Transform probability into a q-score:
qscore = (int)Math.Round(-10 * Math.Log10(1 - score));
qscore = Math.Min(60, qscore);
qscore = Math.Max(2, qscore);
return(qscore);
case QScoreMethod.BinCountLinearFit:
if (this.BinCount >= 100)
{
return(61);
}
else
{
return((int)Math.Round(-10 * Math.Log10(1 - 1 / (1 + Math.Exp(0.5532 - this.BinCount * 0.147))), 0, MidpointRounding.AwayFromZero));
}
case QScoreMethod.GeneralizedLinearFit: // Generalized linear fit with linear transformation to QScore
double linearFit = qscoreParameters.GeneralizedLinearFitIntercept;
linearFit += qscoreParameters.GeneralizedLinearFitLogBinCount *
GetQScorePredictor(QScorePredictor.LogBinCount);
linearFit += qscoreParameters.GeneralizedLinearFitModelDistance *
GetQScorePredictor(QScorePredictor.ModelDistance);
linearFit += qscoreParameters.GeneralizedLinearFitMajorChromosomeCount *
GetQScorePredictor(QScorePredictor.MajorChromosomeCount);
linearFit += qscoreParameters.GeneralizedLinearFitMafMean *
GetQScorePredictor(QScorePredictor.MafMean);
linearFit += qscoreParameters.GeneralizedLinearFitLogMafCv * GetQScorePredictor(QScorePredictor.LogMafCv);
linearFit += GetQScorePredictor(QScorePredictor.BinCountAmpDistance);
score = -11.9 - 11.4 * linearFit; // Scaling to achieve 2 <= qscore <= 61
score = Math.Max(2, score);
score = Math.Min(61, score);
return((int)Math.Round(score, 0, MidpointRounding.AwayFromZero));
default:
throw new Exception("Unhandled qscore method");
}
}
public int ComputeQScore(QScoreMethod qscoreMethod, QualityScoreParameters qscoreParameters)
{
double score;
int qscore;
switch (qscoreMethod)
{
case QScoreMethod.LogisticGermline:
// Logistic model using a new selection of features. Gives ROC curve area 0.921
score = qscoreParameters.LogisticGermlineIntercept;
score += GetQScorePredictor(QScorePredictor.LogBinCount) *
qscoreParameters.LogisticGermlineLogBinCount;
score += GetQScorePredictor(QScorePredictor.ModelDistance) *
qscoreParameters.LogisticGermlineModelDistance;
score += GetQScorePredictor(QScorePredictor.DistanceRatio) *
qscoreParameters.LogisticGermlineDistanceRatio;
score = Math.Exp(score);
score = score / (score + 1);
// Transform probability into a q-score:
qscore = (int)(Math.Round(-10 * Math.Log10(1 - score)));
qscore = Math.Min(40, qscore);
qscore = Math.Max(2, qscore);
return(qscore);
case QScoreMethod.Logistic:
// Logistic model using a new selection of features. Gives ROC curve area 0.8289
score = qscoreParameters.LogisticIntercept;
score += GetQScorePredictor(QScorePredictor.LogBinCount) * qscoreParameters.LogisticLogBinCount;
score += GetQScorePredictor(QScorePredictor.ModelDistance) * qscoreParameters.LogisticModelDistance;
score += GetQScorePredictor(QScorePredictor.DistanceRatio) * qscoreParameters.LogisticDistanceRatio;
score += GetQScorePredictor(QScorePredictor.BinCountAmpDistance);
double coreScore = score;
score = Math.Exp(score);
score = score / (score + 1);
// Transform probability into a q-score:
qscore = (int)Math.Round(-10 * Math.Log10(1 - score));
qscore = Math.Min(60, qscore);
qscore = Math.Max(2, qscore);
//if (CopyNumber>20)
//{
// Console.WriteLine($"HiCN: {CopyNumber} from {this.MedianCount} distance {ModelDistance} next {RunnerUpModelDistance} bins {BinCount}");
// Console.WriteLine($" Prelogit {coreScore} = intercept {qscoreParameters.LogisticIntercept} + bins { GetQScorePredictor(QScorePredictor.LogBinCount) * qscoreParameters.LogisticLogBinCount} + dist {GetQScorePredictor(QScorePredictor.ModelDistance) * qscoreParameters.LogisticModelDistance} + ratio { GetQScorePredictor(QScorePredictor.DistanceRatio) * qscoreParameters.LogisticDistanceRatio} + amp {GetQScorePredictor(QScorePredictor.BinCountAmpDistance)}");
// Console.WriteLine($" Logit {score} --> init qscore {(int)Math.Round(-10 * Math.Log10(1 - score))} --> qscore");
//}
return(qscore);
case QScoreMethod.BinCountLinearFit:
if (this.BinCount >= 100)
{
return(61);
}
else
{
return
((int)
Math.Round(-10 * Math.Log10(1 - 1 / (1 + Math.Exp(0.5532 - this.BinCount * 0.147))), 0,
MidpointRounding.AwayFromZero));
}
case QScoreMethod.GeneralizedLinearFit: // Generalized linear fit with linear transformation to QScore
double linearFit = qscoreParameters.GeneralizedLinearFitIntercept;
linearFit += qscoreParameters.GeneralizedLinearFitLogBinCount *
GetQScorePredictor(QScorePredictor.LogBinCount);
linearFit += qscoreParameters.GeneralizedLinearFitModelDistance *
GetQScorePredictor(QScorePredictor.ModelDistance);
linearFit += qscoreParameters.GeneralizedLinearFitMajorChromosomeCount *
GetQScorePredictor(QScorePredictor.MajorChromosomeCount);
linearFit += qscoreParameters.GeneralizedLinearFitMafMean *
GetQScorePredictor(QScorePredictor.MafMean);
linearFit += qscoreParameters.GeneralizedLinearFitLogMafCv *
GetQScorePredictor(QScorePredictor.LogMafCv);
linearFit += GetQScorePredictor(QScorePredictor.BinCountAmpDistance);
score = -11.9 - 11.4 * linearFit; // Scaling to achieve 2 <= qscore <= 61
score = Math.Max(2, score);
score = Math.Min(61, score);
return((int)Math.Round(score, 0, MidpointRounding.AwayFromZero));
default:
throw new Exception("Unhandled qscore method");
}
}
/// <summary>
/// Apply quality scores.
/// </summary>
public static void AssignQualityScores(List <CanvasSegment> segments, QScoreMethod qscoreMethod, QualityScoreParameters qscoreParameters)
{
foreach (CanvasSegment segment in segments)
{
segment.QScore = segment.ComputeQScore(qscoreMethod, qscoreParameters);
}
}