public void ProcessData(IMatrixData mdata, Parameters param, ref IMatrixData[] supplTables,
ref IDocumentData[] documents, ProcessInfo processInfo)
{
ParameterWithSubParams <int> access = param.GetParamWithSubParams <int>("Matrix access");
bool rows = access.Value == 0;
int groupInd;
if (rows)
{
groupInd = access.GetSubParameters().GetParam <int>("Grouping").Value - 1;
}
else
{
groupInd = -1;
}
bool report = param.GetParam <bool>("Report mean and std. dev.").Value;
bool median = param.GetParam <bool>("Use median").Value;
if (groupInd < 0)
{
Zscore(rows, mdata, processInfo.NumThreads, report, median, out double[] means, out double[] stddevs);
if (report)
{
if (rows)
{
mdata.AddNumericColumn("Mean", "Mean", means);
mdata.AddNumericColumn("Std. dev.", "Std. dev.", stddevs);
}
else
{
mdata.AddNumericRow("Mean", "Mean", means);
mdata.AddNumericRow("Std. dev.", "Std. dev.", stddevs);
}
}
}
else
{
string[][] catRow = mdata.GetCategoryRowAt(groupInd);
foreach (string[] t in catRow)
{
if (t.Length > 1)
{
processInfo.ErrString = "The groups are overlapping.";
return;
}
}
string[] groupVals = ArrayUtils.UniqueValuesPreserveOrder(catRow);
ZscoreGroups(mdata, catRow, processInfo.NumThreads, report, median, groupVals, out double[][] means, out double[][] stddevs);
if (report)
{
for (int i = 0; i < groupVals.Length; i++)
{
mdata.AddNumericColumn("Mean " + groupVals[i], "Mean", means[i]);
mdata.AddNumericColumn("Std. dev. " + groupVals[i], "Std. dev.", stddevs[i]);
}
}
}
}
public void WriteMatrixTest()
{
// main data
IMatrixData mdata = PerseusFactory.CreateMatrixData(new double[, ] {
{ 1, 2, 3 }, { 3, 4, 5 }
},
new List <string> {
"col1", "col2", "col3"
});
// annotation rows
mdata.AddCategoryRow("catrow", "this is catrow", new[] { new[] { "cat1" }, new[] { "cat1", "cat2" }, new[] { "cat2" } });
mdata.AddNumericRow("numrow", "this is numrow", new[] { -1.0, 1, 2 });
// annotation columns
mdata.AddStringColumn("strcol1", "this is stringcol1", new[] { "1", "2" });
mdata.AddStringColumn("strcol2", "", new[] { "", "hallo" });
mdata.AddNumericColumn("numcol", "", new[] { 1.0, 2.0 });
mdata.AddMultiNumericColumn("multnumcol", "this is multnumcol", new[] { new[] { -2.0, 2.0 }, new double[] {} });
mdata.AddCategoryColumn("catcol", "", new[] { new[] { "cat1", "cat1.1" }, new[] { "cat2", "cat1" } });
string mdataStr;
using (MemoryStream memstream = new MemoryStream())
using (StreamWriter writer = new StreamWriter(memstream)) {
PerseusUtils.WriteMatrix(mdata, writer);
writer.Flush();
mdataStr = Encoding.UTF8.GetString(memstream.ToArray());
}
IMatrixData mdata2 = PerseusFactory.CreateMatrixData();
PerseusUtils.ReadMatrix(mdata2, new ProcessInfo(new Settings(), status => { }, progress => { }, 1), () => {
StreamReader tmpStream = new StreamReader(new MemoryStream(Encoding.UTF8.GetBytes(mdataStr)));
return(tmpStream);
}, "matrix1", '\t');
Assert.AreEqual(2, mdata2.RowCount);
Assert.AreEqual(3, mdata2.ColumnCount);
Assert.AreEqual(2, mdata2.StringColumnCount);
Assert.AreEqual(1, mdata2.NumericColumnCount);
Assert.AreEqual(1, mdata2.CategoryColumnCount);
Assert.AreEqual(1, mdata2.MultiNumericColumnCount);
Assert.AreEqual("hallo", mdata2.StringColumns[mdata2.StringColumnNames.FindIndex(col => col.Equals("strcol2"))][1]);
Assert.AreEqual(1, mdata2.CategoryRowCount);
Assert.AreEqual(1, mdata2.NumericRowCount);
}
private static void LoadMatrixData(IList<string> colNames, IList<string> colDescriptions, IList<int> mainColIndices,
IList<int> catColIndices, IList<int> numColIndices, IList<int> textColIndices, IList<int> multiNumColIndices,
string origin, IMatrixData matrixData, IDictionary<string, string[]> annotationRows, Action<int> progress,
Action<string> status, char separator, TextReader reader, StreamReader auxReader, int nrows,
bool shortenExpressionNames, List<Tuple<Relation[], int[], bool>> filters)
{
Dictionary<string, string[]> catAnnotatRows;
Dictionary<string, string[]> numAnnotatRows;
status("Reading data");
SplitAnnotRows(annotationRows, out catAnnotatRows, out numAnnotatRows);
List<string[][]> categoryAnnotation = new List<string[][]>();
for (int i = 0; i < catColIndices.Count; i++){
categoryAnnotation.Add(new string[nrows][]);
}
List<double[]> numericAnnotation = new List<double[]>();
for (int i = 0; i < numColIndices.Count; i++){
numericAnnotation.Add(new double[nrows]);
}
List<double[][]> multiNumericAnnotation = new List<double[][]>();
for (int i = 0; i < multiNumColIndices.Count; i++){
multiNumericAnnotation.Add(new double[nrows][]);
}
List<string[]> stringAnnotation = new List<string[]>();
for (int i = 0; i < textColIndices.Count; i++){
stringAnnotation.Add(new string[nrows]);
}
float[,] mainValues = new float[nrows, mainColIndices.Count];
float[,] qualityValues = null;
bool[,] isImputedValues = null;
bool hasAddtlMatrices = auxReader != null && GetHasAddtlMatrices(auxReader, mainColIndices, separator);
if (hasAddtlMatrices){
qualityValues = new float[nrows, mainColIndices.Count];
isImputedValues = new bool[nrows, mainColIndices.Count];
}
reader.ReadLine();
int count = 0;
string line;
while ((line = reader.ReadLine()) != null){
progress(100*(count + 1)/nrows);
if (TabSep.IsCommentLine(line, commentPrefix, commentPrefixExceptions)){
continue;
}
string[] w;
if (!IsValidLine(line, separator, filters, out w, hasAddtlMatrices)){
continue;
}
for (int i = 0; i < mainColIndices.Count; i++){
if (mainColIndices[i] >= w.Length){
mainValues[count, i] = float.NaN;
} else{
string s = StringUtils.RemoveWhitespace(w[mainColIndices[i]]);
if (hasAddtlMatrices){
ParseExp(s, out mainValues[count, i], out isImputedValues[count, i], out qualityValues[count, i]);
} else{
if (count < mainValues.GetLength(0)){
bool success = float.TryParse(s, out mainValues[count, i]);
if (!success){
mainValues[count, i] = float.NaN;
}
}
}
}
}
for (int i = 0; i < numColIndices.Count; i++){
if (numColIndices[i] >= w.Length){
numericAnnotation[i][count] = double.NaN;
} else{
double q;
bool success = double.TryParse(w[numColIndices[i]].Trim(), out q);
if (numericAnnotation[i].Length > count){
numericAnnotation[i][count] = success ? q : double.NaN;
}
}
}
for (int i = 0; i < multiNumColIndices.Count; i++){
if (multiNumColIndices[i] >= w.Length){
multiNumericAnnotation[i][count] = new double[0];
} else{
string q = w[multiNumColIndices[i]].Trim();
if (q.Length >= 2 && q[0] == '\"' && q[q.Length - 1] == '\"'){
q = q.Substring(1, q.Length - 2);
}
if (q.Length >= 2 && q[0] == '\'' && q[q.Length - 1] == '\''){
q = q.Substring(1, q.Length - 2);
}
string[] ww = q.Length == 0 ? new string[0] : q.Split(';');
multiNumericAnnotation[i][count] = new double[ww.Length];
for (int j = 0; j < ww.Length; j++){
double q1;
bool success = double.TryParse(ww[j], out q1);
multiNumericAnnotation[i][count][j] = success ? q1 : double.NaN;
}
}
}
for (int i = 0; i < catColIndices.Count; i++){
if (catColIndices[i] >= w.Length){
categoryAnnotation[i][count] = new string[0];
} else{
string q = w[catColIndices[i]].Trim();
if (q.Length >= 2 && q[0] == '\"' && q[q.Length - 1] == '\"'){
q = q.Substring(1, q.Length - 2);
}
if (q.Length >= 2 && q[0] == '\'' && q[q.Length - 1] == '\''){
q = q.Substring(1, q.Length - 2);
}
string[] ww = q.Length == 0 ? new string[0] : q.Split(';');
List<int> valids = new List<int>();
for (int j = 0; j < ww.Length; j++){
ww[j] = ww[j].Trim();
if (ww[j].Length > 0){
valids.Add(j);
}
}
ww = ArrayUtils.SubArray(ww, valids);
Array.Sort(ww);
if (categoryAnnotation[i].Length > count){
categoryAnnotation[i][count] = ww;
}
}
}
for (int i = 0; i < textColIndices.Count; i++){
if (textColIndices[i] >= w.Length){
stringAnnotation[i][count] = "";
} else{
string q = w[textColIndices[i]].Trim();
if (stringAnnotation[i].Length > count){
stringAnnotation[i][count] = RemoveSplitWhitespace(RemoveQuotes(q));
}
}
}
count++;
}
reader.Close();
string[] columnNames = ArrayUtils.SubArray(colNames, mainColIndices);
if (shortenExpressionNames){
columnNames = StringUtils.RemoveCommonSubstrings(columnNames, true);
}
string[] catColnames = ArrayUtils.SubArray(colNames, catColIndices);
string[] numColnames = ArrayUtils.SubArray(colNames, numColIndices);
string[] multiNumColnames = ArrayUtils.SubArray(colNames, multiNumColIndices);
string[] textColnames = ArrayUtils.SubArray(colNames, textColIndices);
matrixData.Name = origin;
matrixData.ColumnNames = RemoveQuotes(columnNames);
matrixData.Values.Set(mainValues);
if (hasAddtlMatrices){
matrixData.Quality.Set(qualityValues);
matrixData.IsImputed.Set(isImputedValues);
} else{
matrixData.Quality.Set(new float[mainValues.GetLength(0), mainValues.GetLength(1)]);
matrixData.IsImputed.Set(new bool[mainValues.GetLength(0), mainValues.GetLength(1)]);
}
matrixData.SetAnnotationColumns(RemoveQuotes(textColnames), stringAnnotation, RemoveQuotes(catColnames),
categoryAnnotation, RemoveQuotes(numColnames), numericAnnotation, RemoveQuotes(multiNumColnames),
multiNumericAnnotation);
if (colDescriptions != null){
string[] columnDesc = ArrayUtils.SubArray(colDescriptions, mainColIndices);
string[] catColDesc = ArrayUtils.SubArray(colDescriptions, catColIndices);
string[] numColDesc = ArrayUtils.SubArray(colDescriptions, numColIndices);
string[] multiNumColDesc = ArrayUtils.SubArray(colDescriptions, multiNumColIndices);
string[] textColDesc = ArrayUtils.SubArray(colDescriptions, textColIndices);
matrixData.ColumnDescriptions = new List<string>(columnDesc);
matrixData.NumericColumnDescriptions = new List<string>(numColDesc);
matrixData.CategoryColumnDescriptions = new List<string>(catColDesc);
matrixData.StringColumnDescriptions = new List<string>(textColDesc);
matrixData.MultiNumericColumnDescriptions = new List<string>(multiNumColDesc);
}
foreach (string key in catAnnotatRows.Keys){
string name = key;
string[] svals = ArrayUtils.SubArray(catAnnotatRows[key], mainColIndices);
string[][] cat = new string[svals.Length][];
for (int i = 0; i < cat.Length; i++){
string s = svals[i].Trim();
cat[i] = s.Length > 0 ? s.Split(';') : new string[0];
List<int> valids = new List<int>();
for (int j = 0; j < cat[i].Length; j++){
cat[i][j] = cat[i][j].Trim();
if (cat[i][j].Length > 0){
valids.Add(j);
}
}
cat[i] = ArrayUtils.SubArray(cat[i], valids);
Array.Sort(cat[i]);
}
matrixData.AddCategoryRow(name, name, cat);
}
foreach (string key in numAnnotatRows.Keys){
string name = key;
string[] svals = ArrayUtils.SubArray(numAnnotatRows[key], mainColIndices);
double[] num = new double[svals.Length];
for (int i = 0; i < num.Length; i++){
string s = svals[i].Trim();
num[i] = double.NaN;
double.TryParse(s, out num[i]);
}
matrixData.AddNumericRow(name, name, num);
}
matrixData.Origin = origin;
progress(0);
status("");
}
private static void ProcessDataCreate(IMatrixData mdata, Parameters param)
{
string name = param.GetStringParam("Row name").Value;
double[] groupCol = new double[mdata.ExpressionColumnCount];
for (int i = 0; i < mdata.ExpressionColumnCount; i++){
string ename = mdata.ExpressionColumnNames[i];
double value = param.GetDoubleParam(ename).Value;
groupCol[i] = value;
}
mdata.AddNumericRow(name, name, groupCol);
}
private static void LoadMatrixData(IList <string> colNames, IList <string> colDescriptions, IList <int> mainColIndices,
IList <int> catColIndices, IList <int> numColIndices, IList <int> textColIndices, IList <int> multiNumColIndices,
string origin, IMatrixData matrixData, IDictionary <string, string[]> annotationRows, Action <int> progress,
Action <string> status, char separator, TextReader reader, StreamReader auxReader, int nrows,
bool shortenExpressionNames, List <Tuple <Relation[], int[], bool> > filters)
{
Dictionary <string, string[]> catAnnotatRows;
Dictionary <string, string[]> numAnnotatRows;
status("Reading data");
SplitAnnotRows(annotationRows, out catAnnotatRows, out numAnnotatRows);
List <string[][]> categoryAnnotation = new List <string[][]>();
for (int i = 0; i < catColIndices.Count; i++)
{
categoryAnnotation.Add(new string[nrows][]);
}
List <double[]> numericAnnotation = new List <double[]>();
for (int i = 0; i < numColIndices.Count; i++)
{
numericAnnotation.Add(new double[nrows]);
}
List <double[][]> multiNumericAnnotation = new List <double[][]>();
for (int i = 0; i < multiNumColIndices.Count; i++)
{
multiNumericAnnotation.Add(new double[nrows][]);
}
List <string[]> stringAnnotation = new List <string[]>();
for (int i = 0; i < textColIndices.Count; i++)
{
stringAnnotation.Add(new string[nrows]);
}
float[,] mainValues = new float[nrows, mainColIndices.Count];
float[,] qualityValues = null;
bool[,] isImputedValues = null;
bool hasAddtlMatrices = auxReader != null && GetHasAddtlMatrices(auxReader, mainColIndices, separator);
if (hasAddtlMatrices)
{
qualityValues = new float[nrows, mainColIndices.Count];
isImputedValues = new bool[nrows, mainColIndices.Count];
}
reader.ReadLine();
int count = 0;
string line;
while ((line = reader.ReadLine()) != null)
{
progress(100 * (count + 1) / nrows);
if (TabSep.IsCommentLine(line, commentPrefix, commentPrefixExceptions))
{
continue;
}
string[] w;
if (!IsValidLine(line, separator, filters, out w, hasAddtlMatrices))
{
continue;
}
for (int i = 0; i < mainColIndices.Count; i++)
{
if (mainColIndices[i] >= w.Length)
{
mainValues[count, i] = float.NaN;
}
else
{
string s = StringUtils.RemoveWhitespace(w[mainColIndices[i]]);
if (hasAddtlMatrices)
{
ParseExp(s, out mainValues[count, i], out isImputedValues[count, i], out qualityValues[count, i]);
}
else
{
if (count < mainValues.GetLength(0))
{
bool success = float.TryParse(s, out mainValues[count, i]);
if (!success)
{
mainValues[count, i] = float.NaN;
}
}
}
}
}
for (int i = 0; i < numColIndices.Count; i++)
{
if (numColIndices[i] >= w.Length)
{
numericAnnotation[i][count] = double.NaN;
}
else
{
double q;
bool success = double.TryParse(w[numColIndices[i]].Trim(), out q);
if (numericAnnotation[i].Length > count)
{
numericAnnotation[i][count] = success ? q : double.NaN;
}
}
}
for (int i = 0; i < multiNumColIndices.Count; i++)
{
if (multiNumColIndices[i] >= w.Length)
{
multiNumericAnnotation[i][count] = new double[0];
}
else
{
string q = w[multiNumColIndices[i]].Trim();
if (q.Length >= 2 && q[0] == '\"' && q[q.Length - 1] == '\"')
{
q = q.Substring(1, q.Length - 2);
}
if (q.Length >= 2 && q[0] == '\'' && q[q.Length - 1] == '\'')
{
q = q.Substring(1, q.Length - 2);
}
string[] ww = q.Length == 0 ? new string[0] : q.Split(';');
multiNumericAnnotation[i][count] = new double[ww.Length];
for (int j = 0; j < ww.Length; j++)
{
double q1;
bool success = double.TryParse(ww[j], out q1);
multiNumericAnnotation[i][count][j] = success ? q1 : double.NaN;
}
}
}
for (int i = 0; i < catColIndices.Count; i++)
{
if (catColIndices[i] >= w.Length)
{
categoryAnnotation[i][count] = new string[0];
}
else
{
string q = w[catColIndices[i]].Trim();
if (q.Length >= 2 && q[0] == '\"' && q[q.Length - 1] == '\"')
{
q = q.Substring(1, q.Length - 2);
}
if (q.Length >= 2 && q[0] == '\'' && q[q.Length - 1] == '\'')
{
q = q.Substring(1, q.Length - 2);
}
string[] ww = q.Length == 0 ? new string[0] : q.Split(';');
List <int> valids = new List <int>();
for (int j = 0; j < ww.Length; j++)
{
ww[j] = ww[j].Trim();
if (ww[j].Length > 0)
{
valids.Add(j);
}
}
ww = ArrayUtils.SubArray(ww, valids);
Array.Sort(ww);
if (categoryAnnotation[i].Length > count)
{
categoryAnnotation[i][count] = ww;
}
}
}
for (int i = 0; i < textColIndices.Count; i++)
{
if (textColIndices[i] >= w.Length)
{
stringAnnotation[i][count] = "";
}
else
{
string q = w[textColIndices[i]].Trim();
if (stringAnnotation[i].Length > count)
{
stringAnnotation[i][count] = RemoveSplitWhitespace(RemoveQuotes(q));
}
}
}
count++;
}
reader.Close();
string[] columnNames = ArrayUtils.SubArray(colNames, mainColIndices);
if (shortenExpressionNames)
{
columnNames = StringUtils.RemoveCommonSubstrings(columnNames, true);
}
string[] catColnames = ArrayUtils.SubArray(colNames, catColIndices);
string[] numColnames = ArrayUtils.SubArray(colNames, numColIndices);
string[] multiNumColnames = ArrayUtils.SubArray(colNames, multiNumColIndices);
string[] textColnames = ArrayUtils.SubArray(colNames, textColIndices);
matrixData.Name = origin;
matrixData.ColumnNames = RemoveQuotes(columnNames);
matrixData.Values.Set(mainValues);
if (hasAddtlMatrices)
{
matrixData.Quality.Set(qualityValues);
matrixData.IsImputed.Set(isImputedValues);
}
else
{
matrixData.Quality.Set(new float[mainValues.GetLength(0), mainValues.GetLength(1)]);
matrixData.IsImputed.Set(new bool[mainValues.GetLength(0), mainValues.GetLength(1)]);
}
matrixData.SetAnnotationColumns(RemoveQuotes(textColnames), stringAnnotation, RemoveQuotes(catColnames),
categoryAnnotation, RemoveQuotes(numColnames), numericAnnotation, RemoveQuotes(multiNumColnames),
multiNumericAnnotation);
if (colDescriptions != null)
{
string[] columnDesc = ArrayUtils.SubArray(colDescriptions, mainColIndices);
string[] catColDesc = ArrayUtils.SubArray(colDescriptions, catColIndices);
string[] numColDesc = ArrayUtils.SubArray(colDescriptions, numColIndices);
string[] multiNumColDesc = ArrayUtils.SubArray(colDescriptions, multiNumColIndices);
string[] textColDesc = ArrayUtils.SubArray(colDescriptions, textColIndices);
matrixData.ColumnDescriptions = new List <string>(columnDesc);
matrixData.NumericColumnDescriptions = new List <string>(numColDesc);
matrixData.CategoryColumnDescriptions = new List <string>(catColDesc);
matrixData.StringColumnDescriptions = new List <string>(textColDesc);
matrixData.MultiNumericColumnDescriptions = new List <string>(multiNumColDesc);
}
foreach (string key in catAnnotatRows.Keys)
{
string name = key;
string[] svals = ArrayUtils.SubArray(catAnnotatRows[key], mainColIndices);
string[][] cat = new string[svals.Length][];
for (int i = 0; i < cat.Length; i++)
{
string s = svals[i].Trim();
cat[i] = s.Length > 0 ? s.Split(';') : new string[0];
List <int> valids = new List <int>();
for (int j = 0; j < cat[i].Length; j++)
{
cat[i][j] = cat[i][j].Trim();
if (cat[i][j].Length > 0)
{
valids.Add(j);
}
}
cat[i] = ArrayUtils.SubArray(cat[i], valids);
Array.Sort(cat[i]);
}
matrixData.AddCategoryRow(name, name, cat);
}
foreach (string key in numAnnotatRows.Keys)
{
string name = key;
string[] svals = ArrayUtils.SubArray(numAnnotatRows[key], mainColIndices);
double[] num = new double[svals.Length];
for (int i = 0; i < num.Length; i++)
{
string s = svals[i].Trim();
num[i] = double.NaN;
double.TryParse(s, out num[i]);
}
matrixData.AddNumericRow(name, name, num);
}
matrixData.Origin = origin;
progress(0);
status("");
}
public void ProcessData(IMatrixData mdata, Parameters param, ref IMatrixData[] supplTables,
ref IDocumentData[] documents, ProcessInfo processInfo)
{
int[] outputColumns = param.GetParam <int[]>("Output").Value;
int proteinIdColumnInd = param.GetParam <int>("Protein IDs").Value;
string[] proteinIds = mdata.StringColumns[proteinIdColumnInd];
int[] intensityCols = param.GetParam <int[]>("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[] inputNames = new string[intensityCols.Length];
string[] sampleNames = new string[intensityCols.Length];
for (int col = 0; col < intensityCols.Length; col++)
{
double[] values;
if (intensityCols[col] < mdata.ColumnCount)
{
values = ArrayUtils.ToDoubles(mdata.Values.GetColumn(intensityCols[col]));
inputNames[col] = mdata.ColumnNames[intensityCols[col]];
}
else
{
values = mdata.NumericColumns[intensityCols[col] - mdata.ColumnCount];
inputNames[col] = mdata.NumericColumnNames[intensityCols[col] - mdata.ColumnCount];
}
sampleNames[col] = new Regex(@"^(?:(?:LFQ )?[Ii]ntensity )?(.*)$").Match(inputNames[col]).Groups[1].Value;
columns.Add(values);
}
// average over columns if this option is selected
if (param.GetParamWithSubParams <int>("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.GetParamWithSubParams <bool>("Logarithmized").Value)
{
double[] logBases = new[] { 2, Math.E, 10 };
double logBase =
logBases[param.GetParamWithSubParams <bool>("Logarithmized").GetSubParameters().GetParam <int>("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.GetParam <int>("Molecular masses").Value];
// define whether the molecular masses are given in Da or kDa
if (ArrayUtils.Median(mw) < 250) // most likely kDa
{
for (int i = 0; i < mw.Length; i++)
{
mw[i] *= 1000;
}
}
double[] detectabilityNormFactor = mw;
if (param.GetParamWithSubParams <bool>("Detectability correction").Value)
{
detectabilityNormFactor =
mdata.NumericColumns[
param.GetParamWithSubParams <bool>("Detectability correction").GetSubParameters().GetParam <int>("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 || double.IsNaN(detectabilityNormFactor[row]))
{
detectabilityNormFactor[row] = 1;
}
}
// detect the organism
Organism organism = DetectOrganism(proteinIds);
// c value the amount of DNA per haploid genome, 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 string[0];
}
mdata.AddCategoryColumn("Histones", "", histoneCol);
// initialize the variables for the annotation rows
string[] sampleNameRow = new string[mdata.ColumnCount];
string[] inputNameRow = new string[mdata.ColumnCount];
double[] totalProteinRow = new double[mdata.ColumnCount];
double[] totalMoleculesRow = new double[mdata.ColumnCount];
string[][] organismRow = new string[mdata.ColumnCount][];
// populate the organismRow variable with empty strings as defaults (not null, which may cause errors when writing the annotations in the end.)
for (int i = 0; i < organismRow.Length; i++)
{
organismRow[i] = new[] { "N/A" };
}
double[] histoneMassRow = new double[mdata.ColumnCount];
double[] ploidyRow = new double[mdata.ColumnCount];
double[] cellVolumeRow = new double[mdata.ColumnCount];
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.GetParamWithSubParams <int>("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.GetParamWithSubParams <int>("Scaling mode").GetSubParameters().GetParam <double>(
"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.GetParamWithSubParams <int>("Scaling mode").GetSubParameters().GetParam <double>("Ploidy").Value;
factor = cValue * ploidy * avogadro / mwWeightedNormalizedSummedHistoneIntensities;
break;
default:
factor = 1;
break;
}
normalizationFactors[col] = factor;
}
// check averaging mode
if (param.GetParamWithSubParams <int>("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.GetParamWithSubParams <int>("Averaging mode").Value == 2) // same factor in each group
{
if (param.GetParamWithSubParams <int>("Averaging mode").GetSubParameters().GetParam <int>("Grouping").Value == -1)
{
processInfo.ErrString = "No grouping selected.";
return;
}
string[][] groupNames =
mdata.GetCategoryRowAt(
param.GetParamWithSubParams <int>("Averaging mode").GetSubParameters().GetParam <int>("Grouping").Value);
string[] uniqueGroupNames = Unique(groupNames);
int[] grouping = new int[columns.Count];
for (int i = 0; i < columns.Count; i++)
{
if (intensityCols[i] >= mdata.ColumnCount) // 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.GetParam <double>("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.ColumnCount && param.GetParamWithSubParams <int>("Averaging mode").Value != 3)
{
inputNameRow[intensityCols[col]] = inputNames[col];
sampleNameRow[intensityCols[col]] = sampleNames[col];
totalProteinRow[intensityCols[col]] = Math.Round(totalProtein, 2);
totalMoleculesRow[intensityCols[col]] = Math.Round(totalMolecules, 0);
organismRow[intensityCols[col]] = new[] { 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
}
}
// Summary annotation row
if (param.GetParamWithSubParams <int>("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);
}
// Summary matrix
if (param.GetParamWithSubParams <int>("Averaging mode").Value != 3 && ArrayUtils.Contains(outputColumns, 7))
{
supplTables = new IMatrixData[1];
IMatrixData supplTab = PerseusFactory.CreateMatrixData();
supplTab.ColumnNames = new List <string>();
supplTab.Values.Init(totalProteinRow.Length, 0);
supplTab.SetAnnotationColumns(new List <string> {
"Sample", "Input Column"
},
new List <string[]>()
{
sampleNameRow, inputNameRow
}, new List <string>()
{
"Organism"
},
new List <string[][]>()
{
organismRow
},
new List <string>()
{
"Total protein [pg/cell]",
"Total molecules per cell",
"Histone mass [pg/cell]",
"Ploidy",
"Cell volume [fl]"
},
new List <double[]>()
{
totalProteinRow, totalMoleculesRow, histoneMassRow, ploidyRow, cellVolumeRow
},
new List <string>(), new List <double[][]>());
supplTables[0] = supplTab;
}
}
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);
}
}
private static void LoadData(IList<string> colNames, IList<string> colDescriptions, IList<int> expressionColIndices,
IList<int> catColIndices, IList<int> numColIndices, IList<int> textColIndices, IList<int> multiNumColIndices,
string filename, IMatrixData matrixData, IDictionary<string, string[]> annotationRows, Action<int> progress,
Action<string> status)
{
Dictionary<string, string[]> catAnnotatRows;
Dictionary<string, string[]> numAnnotatRows;
status("Reading data");
SplitAnnotRows(annotationRows, out catAnnotatRows, out numAnnotatRows);
int nrows = TabSep.GetRowCount(filename, 0, commentPrefix, commentPrefixExceptions);
float[,] expressionValues = new float[nrows,expressionColIndices.Count];
List<string[][]> categoryAnnotation = new List<string[][]>();
foreach (int t in catColIndices){
categoryAnnotation.Add(new string[nrows][]);
}
List<double[]> numericAnnotation = new List<double[]>();
foreach (int t in numColIndices){
numericAnnotation.Add(new double[nrows]);
}
List<double[][]> multiNumericAnnotation = new List<double[][]>();
foreach (int t in multiNumColIndices){
multiNumericAnnotation.Add(new double[nrows][]);
}
List<string[]> stringAnnotation = new List<string[]>();
foreach (int t in textColIndices){
stringAnnotation.Add(new string[nrows]);
}
StreamReader reader = new StreamReader(filename);
reader.ReadLine();
int count = 0;
string line;
while ((line = reader.ReadLine()) != null){
progress((100*(count + 1))/nrows);
if (TabSep.IsCommentLine(line, commentPrefix, commentPrefixExceptions)){
continue;
}
string[] w = line.Split('\t');
for (int i = 0; i < expressionColIndices.Count; i++){
if (expressionColIndices[i] >= w.Length){
expressionValues[count, i] = float.NaN;
} else{
string s = StringUtils.RemoveWhitespace(w[expressionColIndices[i]]);
bool success = float.TryParse(s, out expressionValues[count, i]);
if (!success){
expressionValues[count, i] = float.NaN;
}
}
}
for (int i = 0; i < multiNumColIndices.Count; i++){
if (multiNumColIndices[i] >= w.Length){
multiNumericAnnotation[i][count] = new double[0];
} else{
string q = w[multiNumColIndices[i]].Trim();
if (q.Length >= 2 && q[0] == '\"' && q[q.Length - 1] == '\"'){
q = q.Substring(1, q.Length - 2);
}
if (q.Length >= 2 && q[0] == '\'' && q[q.Length - 1] == '\''){
q = q.Substring(1, q.Length - 2);
}
string[] ww = q.Length == 0 ? new string[0] : q.Split(';');
multiNumericAnnotation[i][count] = new double[ww.Length];
for (int j = 0; j < ww.Length; j++){
double q1;
bool success = double.TryParse(ww[j], out q1);
multiNumericAnnotation[i][count][j] = success ? q1 : double.NaN;
}
}
}
for (int i = 0; i < catColIndices.Count; i++){
if (catColIndices[i] >= w.Length){
categoryAnnotation[i][count] = new string[0];
} else{
string q = w[catColIndices[i]].Trim();
if (q.Length >= 2 && q[0] == '\"' && q[q.Length - 1] == '\"'){
q = q.Substring(1, q.Length - 2);
}
if (q.Length >= 2 && q[0] == '\'' && q[q.Length - 1] == '\''){
q = q.Substring(1, q.Length - 2);
}
string[] ww = q.Length == 0 ? new string[0] : q.Split(';');
Array.Sort(ww);
categoryAnnotation[i][count] = ww;
}
}
for (int i = 0; i < numColIndices.Count; i++){
if (numColIndices[i] >= w.Length){
numericAnnotation[i][count] = double.NaN;
} else{
double q;
bool success = double.TryParse(w[numColIndices[i]].Trim(), out q);
numericAnnotation[i][count] = success ? q : double.NaN;
}
}
for (int i = 0; i < textColIndices.Count; i++){
if (textColIndices[i] >= w.Length){
stringAnnotation[i][count] = "";
} else{
string q = w[textColIndices[i]].Trim();
stringAnnotation[i][count] = RemoveSplitWhitespace(RemoveQuotes(q));
}
}
count++;
}
reader.Close();
string[] columnNames = ArrayUtils.SubArray(colNames, expressionColIndices);
string[] catColnames = ArrayUtils.SubArray(colNames, catColIndices);
string[] numColnames = ArrayUtils.SubArray(colNames, numColIndices);
string[] multiNumColnames = ArrayUtils.SubArray(colNames, multiNumColIndices);
string[] textColnames = ArrayUtils.SubArray(colNames, textColIndices);
matrixData.SetData(filename, RemoveQuotes(columnNames), expressionValues, RemoveQuotes(textColnames),
stringAnnotation, RemoveQuotes(catColnames), categoryAnnotation, RemoveQuotes(numColnames), numericAnnotation,
RemoveQuotes(multiNumColnames), multiNumericAnnotation);
if (colDescriptions != null){
string[] columnDesc = ArrayUtils.SubArray(colDescriptions, expressionColIndices);
string[] catColDesc = ArrayUtils.SubArray(colDescriptions, catColIndices);
string[] numColDesc = ArrayUtils.SubArray(colDescriptions, numColIndices);
string[] multiNumColDesc = ArrayUtils.SubArray(colDescriptions, multiNumColIndices);
string[] textColDesc = ArrayUtils.SubArray(colDescriptions, textColIndices);
matrixData.ExpressionColumnDescriptions = new List<string>(columnDesc);
matrixData.NumericColumnDescriptions = new List<string>(numColDesc);
matrixData.CategoryColumnDescriptions = new List<string>(catColDesc);
matrixData.StringColumnDescriptions = new List<string>(textColDesc);
matrixData.MultiNumericColumnDescriptions = new List<string>(multiNumColDesc);
}
foreach (string key in ArrayUtils.GetKeys(catAnnotatRows)){
string name = key;
string[] svals = ArrayUtils.SubArray(catAnnotatRows[key], expressionColIndices);
string[][] cat = new string[svals.Length][];
for (int i = 0; i < cat.Length; i++){
string s = svals[i].Trim();
cat[i] = s.Length > 0 ? s.Split(';') : new string[0];
}
matrixData.AddCategoryRow(name, name, cat);
}
foreach (string key in ArrayUtils.GetKeys(numAnnotatRows)){
string name = key;
string[] svals = ArrayUtils.SubArray(numAnnotatRows[key], expressionColIndices);
double[] num = new double[svals.Length];
for (int i = 0; i < num.Length; i++){
string s = svals[i].Trim();
num[i] = double.NaN;
double.TryParse(s, out num[i]);
}
matrixData.AddNumericRow(name, name, num);
}
matrixData.Origin = filename;
status("");
}