public void ProcessData(IMatrixData mdata, Parameters param, ref IMatrixData[] supplTables,
ref IDocumentData[] documents, ProcessInfo processInfo)
{
int[] outputColumns = param.GetMultiChoiceParam("Output").Value;
int proteinIdColumnInd = param.GetSingleChoiceParam("Protein IDs").Value;
string[] proteinIds = mdata.StringColumns[proteinIdColumnInd];
int[] intensityCols = param.GetMultiChoiceParam("Intensities").Value;
if (intensityCols.Length == 0){
processInfo.ErrString = "Please select at least one column containing protein intensities.";
return;
}
// variable to hold all intensity values
List<double[]> columns = new List<double[]>();
string[] sampleNames = new string[intensityCols.Length];
for (int col = 0; col < intensityCols.Length; col++){
double[] values;
if (intensityCols[col] < mdata.ExpressionColumnCount){
values = ArrayUtils.ToDoubles(mdata.GetExpressionColumn(intensityCols[col]));
sampleNames[col] = mdata.ExpressionColumnNames[intensityCols[col]];
} else{
values = mdata.NumericColumns[intensityCols[col] - mdata.ExpressionColumnCount];
sampleNames[col] = mdata.NumericColumnNames[intensityCols[col] - mdata.ExpressionColumnCount];
}
sampleNames[col] = new Regex(@"^(?:(?:LFQ )?[Ii]ntensity )?(.*)$").Match(sampleNames[col]).Groups[1].Value;
columns.Add(values);
}
// average over columns if this option is selected
if (param.GetSingleChoiceWithSubParams("Averaging mode").Value == 3){
double[] column = new double[mdata.RowCount];
for (int row = 0; row < mdata.RowCount; row++){
double[] values = new double[intensityCols.Length];
for (int col = 0; col < intensityCols.Length; col++){
values[col] = columns[col][row];
}
column[row] = ArrayUtils.Median(ExtractValidValues(values, false));
}
// delete the original list of columns
columns = new List<double[]>{column};
sampleNames = new[]{""};
}
// revert logarithm if necessary
if (param.GetBoolWithSubParams("Logarithmized").Value){
double[] logBases = new[]{2, Math.E, 10};
double logBase =
logBases[param.GetBoolWithSubParams("Logarithmized").GetSubParameters().GetSingleChoiceParam("log base").Value];
foreach (double[] t in columns){
for (int row = 0; row < mdata.RowCount; row++){
if (t[row] == 0){
processInfo.ErrString = "Are the columns really logarithmized?\nThey contain zeroes!";
}
t[row] = Math.Pow(logBase, t[row]);
}
}
}
double[] mw = mdata.NumericColumns[param.GetSingleChoiceParam("Molecular masses").Value];
// detect whether the molecular masses are given in Da or kDa
if (ArrayUtils.Median(mw) < 250) // likely kDa
{
for (int i = 0; i < mw.Length; i++){
mw[i] *= 1000;
}
}
double[] detectabilityNormFactor = mw;
if (param.GetBoolWithSubParams("Detectability correction").Value){
detectabilityNormFactor =
mdata.NumericColumns[
param.GetBoolWithSubParams("Detectability correction")
.GetSubParameters()
.GetSingleChoiceParam("Correction factor")
.Value];
}
// the normalization factor needs to be nonzero for all proteins
// check and replace with 1 for all relevant cases
for (int row = 0; row < mdata.RowCount; row++){
if (detectabilityNormFactor[row] == 0 || detectabilityNormFactor[row] == double.NaN){
detectabilityNormFactor[row] = 1;
}
}
// detect the organism
Organism organism = DetectOrganism(proteinIds);
// c value the amount of DNA per cell, see: http://en.wikipedia.org/wiki/C-value
double cValue = (organism.genomeSize*basePairWeight)/avogadro;
// find the histones
int[] histoneRows = FindHistones(proteinIds, organism);
// write a categorical column indicating the histones
string[][] histoneCol = new string[mdata.RowCount][];
for (int row = 0; row < mdata.RowCount; row++){
histoneCol[row] = (ArrayUtils.Contains(histoneRows, row)) ? new[]{"+"} : new[]{""};
}
mdata.AddCategoryColumn("Histones", "", histoneCol);
// initialize the variables for the annotation rows
double[] totalProteinRow = new double[mdata.ExpressionColumnCount];
double[] totalMoleculesRow = new double[mdata.ExpressionColumnCount];
string[][] organismRow = new string[mdata.ExpressionColumnCount][];
double[] histoneMassRow = new double[mdata.ExpressionColumnCount];
double[] ploidyRow = new double[mdata.ExpressionColumnCount];
double[] cellVolumeRow = new double[mdata.ExpressionColumnCount];
double[] normalizationFactors = new double[columns.Count];
// calculate normalization factors for each column
for (int col = 0; col < columns.Count; col++){
string sampleName = sampleNames[col];
double[] column = columns[col];
// normalization factor to go from intensities to copies,
// needs to be determined either using the total protein or the histone scaling approach
double factor;
switch (param.GetSingleChoiceWithSubParams("Scaling mode").Value){
case 0: // total protein amount
double mwWeightedNormalizedSummedIntensities = 0;
for (int row = 0; row < mdata.RowCount; row++){
if (!double.IsNaN(column[row]) && !double.IsNaN(mw[row])){
mwWeightedNormalizedSummedIntensities += (column[row]/detectabilityNormFactor[row])*mw[row];
}
}
factor =
(param.GetSingleChoiceWithSubParams("Scaling mode")
.GetSubParameters()
.GetDoubleParam("Protein amount per cell [pg]")
.Value*1e-12*avogadro)/mwWeightedNormalizedSummedIntensities;
break;
case 1: // histone mode
double mwWeightedNormalizedSummedHistoneIntensities = 0;
foreach (int row in histoneRows){
if (!double.IsNaN(column[row]) && !double.IsNaN(mw[row])){
mwWeightedNormalizedSummedHistoneIntensities += (column[row]/detectabilityNormFactor[row])*mw[row];
}
}
double ploidy =
param.GetSingleChoiceWithSubParams("Scaling mode").GetSubParameters().GetDoubleParam("Ploidy").Value;
factor = (cValue*ploidy*avogadro)/mwWeightedNormalizedSummedHistoneIntensities;
break;
default:
factor = 1;
break;
}
normalizationFactors[col] = factor;
}
// check averaging mode
if (param.GetSingleChoiceWithSubParams("Averaging mode").Value == 1) // same factor for all
{
double factor = ArrayUtils.Mean(normalizationFactors);
for (int i = 0; i < normalizationFactors.Length; i++){
normalizationFactors[i] = factor;
}
}
if (param.GetSingleChoiceWithSubParams("Averaging mode").Value == 2) // same factor in each group
{
if (
param.GetSingleChoiceWithSubParams("Averaging mode").GetSubParameters().GetSingleChoiceParam("Grouping").Value ==
-1){
processInfo.ErrString = "No grouping selected.";
return;
}
string[][] groupNames =
mdata.GetCategoryRowAt(
param.GetSingleChoiceWithSubParams("Averaging mode").GetSubParameters().GetSingleChoiceParam("Grouping").Value);
string[] uniqueGroupNames = Unique(groupNames);
int[] grouping = new int[columns.Count];
for (int i = 0; i < columns.Count; i++){
if (intensityCols[i] >= mdata.ExpressionColumnCount){ // Numeric annotation columns cannot be grouped
grouping[i] = i;
continue;
}
if (ArrayUtils.Contains(uniqueGroupNames, groupNames[i][0])){
grouping[i] = ArrayUtils.IndexOf(uniqueGroupNames, groupNames[i][0]);
continue;
}
grouping[i] = i;
}
Dictionary<int, List<double>> factors = new Dictionary<int, List<double>>();
for (int i = 0; i < columns.Count; i++){
if (factors.ContainsKey(grouping[i])){
factors[grouping[i]].Add(normalizationFactors[i]);
} else{
factors.Add(grouping[i], new List<double>{normalizationFactors[i]});
}
}
double[] averagedNormalizationFactors = new double[columns.Count];
for (int i = 0; i < columns.Count; i++){
List<double> factor;
factors.TryGetValue(grouping[i], out factor);
averagedNormalizationFactors[i] = ArrayUtils.Mean(factor);
}
normalizationFactors = averagedNormalizationFactors;
}
// loop over all selected columns and calculate copy numbers
for (int col = 0; col < columns.Count; col++){
string sampleName = sampleNames[col];
double[] column = columns[col];
double factor = normalizationFactors[col];
double[] copyNumbers = new double[mdata.RowCount];
double[] concentrations = new double[mdata.RowCount]; // femtoliters
double[] massFraction = new double[mdata.RowCount];
double[] moleFraction = new double[mdata.RowCount];
double totalProtein = 0; // picograms
double histoneMass = 0; // picograms
double totalMolecules = 0;
for (int row = 0; row < mdata.RowCount; row++){
if (!double.IsNaN(column[row]) && !double.IsNaN(mw[row])){
copyNumbers[row] = (column[row]/detectabilityNormFactor[row])*factor;
totalMolecules += copyNumbers[row];
totalProtein += (copyNumbers[row]*mw[row]*1e12)/avogadro; // picograms
if (ArrayUtils.Contains(histoneRows, row)){
histoneMass += (copyNumbers[row]*mw[row]*1e12)/avogadro; // picograms
}
}
}
double totalVolume = (totalProtein/(param.GetDoubleParam("Total cellular protein concentration [g/l]").Value))*1000;
// femtoliters
for (int row = 0; row < mdata.RowCount; row++){
if (!double.IsNaN(column[row]) && !double.IsNaN(mw[row])){
concentrations[row] = ((copyNumbers[row]/(totalVolume*1e-15))/avogadro)*1e9; // nanomolar
massFraction[row] = (((copyNumbers[row]*mw[row]*1e12)/avogadro)/totalProtein)*1e6; // ppm
moleFraction[row] = (copyNumbers[row]/totalMolecules)*1e6; // ppm
}
}
string suffix = (sampleName == "") ? "" : " " + sampleName;
if (ArrayUtils.Contains(outputColumns, 0)){
mdata.AddNumericColumn("Copy number" + suffix, "", copyNumbers);
}
if (ArrayUtils.Contains(outputColumns, 1)){
mdata.AddNumericColumn("Concentration [nM]" + suffix, "", concentrations);
}
if (ArrayUtils.Contains(outputColumns, 2)){
mdata.AddNumericColumn("Abundance (mass/total mass) [*10^-6]" + suffix, "", massFraction);
}
if (ArrayUtils.Contains(outputColumns, 3)){
mdata.AddNumericColumn("Abundance (molecules/total molecules) [*10^-6]" + suffix, "", moleFraction);
}
double[] rank = ArrayUtils.Rank(copyNumbers);
double[] relativeRank = new double[mdata.RowCount];
double validRanks = mdata.RowCount;
for (int row = 0; row < mdata.RowCount; row++){
// remove rank for protein with no copy number information
if (double.IsNaN((copyNumbers[row])) || copyNumbers[row] == 0){
rank[row] = double.NaN;
validRanks--; // do not consider as valid
}
// invert ranking, so that rank 0 is the most abundant protein
rank[row] = mdata.RowCount - rank[row];
}
for (int row = 0; row < mdata.RowCount; row++){
relativeRank[row] = rank[row]/validRanks;
}
if (ArrayUtils.Contains(outputColumns, 4)){
mdata.AddNumericColumn("Copy number rank" + suffix, "", rank);
}
if (ArrayUtils.Contains(outputColumns, 5)){
mdata.AddNumericColumn("Relative copy number rank" + suffix, "", relativeRank);
}
if (intensityCols[col] < mdata.ExpressionColumnCount &&
param.GetSingleChoiceWithSubParams("Averaging mode").Value != 3){
totalProteinRow[intensityCols[col]] = Math.Round(totalProtein, 2);
totalMoleculesRow[intensityCols[col]] = Math.Round(totalMolecules, 0);
organismRow[intensityCols[col]] = new string[]{organism.name};
histoneMassRow[intensityCols[col]] = Math.Round(histoneMass, 4);
ploidyRow[intensityCols[col]] = Math.Round((histoneMass*1e-12)/cValue, 2);
cellVolumeRow[intensityCols[col]] = Math.Round(totalVolume, 2); // femtoliters
}
}
if (param.GetSingleChoiceWithSubParams("Averaging mode").Value != 3 && ArrayUtils.Contains(outputColumns, 6)){
mdata.AddNumericRow("Total protein [pg/cell]", "", totalProteinRow);
mdata.AddNumericRow("Total molecules per cell", "", totalMoleculesRow);
mdata.AddCategoryRow("Organism", "", organismRow);
mdata.AddNumericRow("Histone mass [pg/cell]", "", histoneMassRow);
mdata.AddNumericRow("Ploidy", "", ploidyRow);
mdata.AddNumericRow("Cell volume [fl]", "", cellVolumeRow);
}
}