public void RunLorenzian()
{
int npts=100;
//produce test data - a is a vecor with exact solution
double[] x = new double[npts];
for (int i = 0; i < npts; i++)
{
x[i] = -5 + 0.1 *i; // NR always counts from 1
}
double[] a = {1,0};
LMAFunction f = new LorenzianFunction();
double[][] dataPoints = f.GenerateData(a,x);
//initial guess should be close enough
LMA algorithm = new LMA(f,new double[] {5, 5},
dataPoints, null, new GeneralMatrix(2,2),1d-20,100);
algorithm.Fit();
for (int i=0; i<a.Length; i++)
{
Assert.IsTrue(System.Math.Abs(algorithm.Parameters[i]-a[i])<0.0001);
Trace.WriteLine("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
Trace.WriteLine("# of iterations =" + algorithm.Iterations.ToString());
}
public void RunGaussian()
{
int npts=100;
//produce test data - a is a vecor with exact solution
double[] x = new double[npts];
for (int i = 0; i < npts; i++)
{
x[i] = 0.1 * (i + 1); // NR always counts from 1
}
double[] a = {5, 2, 3, 2, 5, 3};
LMAFunction f = new GaussianFunction();
double[][] dataPoints = f.GenerateData(a,x);
LMA algorithm = new LMA(f,new double[] {4, 2, 2, 2, 5, 2},
dataPoints, null, new GeneralMatrix(6,6),1d-30,100);
algorithm.Fit();
for (int i=0; i<a.Length; i++)
{
Assert.IsTrue(System.Math.Abs(algorithm.Parameters[i]-a[i])<0.0001);
Trace.WriteLine("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
Trace.WriteLine("# of iterations =" + algorithm.Iterations.ToString());
}
public void RunSin()
{
//produce test data - a is a vecor with exact solution
double[] x = {0.0, 0.1, 0.2, 0.3, 0.5, 0.7};
double[] a = {2.2, 0.4};
LMAFunction f = new SinFunction();
double[][] dataPoints = f.GenerateData(a,x);
LMA algorithm = new LMA(f,new double[] {0.1, 10},
dataPoints, null, new GeneralMatrix(2,2),1d-20,100);
algorithm.Fit();
for (int i=0; i<a.Length; i++)
{
Assert.IsTrue(System.Math.Abs(algorithm.Parameters[i]-a[i])<0.0001);
Trace.WriteLine("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
Trace.WriteLine("# of iterations =" + algorithm.Iterations.ToString());
}
public void RunLine()
{
double[] x = {0, 2, 6, 8, 9};
double[] a = {2, 0.51};
LMAFunction f = new LineFunction();
double[][] dataPoints = f.GenerateData(a,x);
LMA algorithm = new LMA(f,new double[] {100, -100},
dataPoints, null, new GeneralMatrix(2,2),1d-20,100);
algorithm.Fit();
for (int i=0; i<a.Length; i++)
{
Assert.IsTrue(System.Math.Abs(algorithm.Parameters[i]-a[i])<0.0001);
Trace.WriteLine("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
Trace.WriteLine("# of iterations =" + algorithm.Iterations.ToString());
}
public void Phosphinate()
{
StreamWriter log = null;
IXRawfile2 raw = null;
StreamReader csv = null;
StreamWriter non_phospho_output = null;
StreamWriter localized_phospho_output = null;
StreamWriter unlocalized_phospho_output = null;
StreamWriter motifX = null;
try
{
onStarting(new EventArgs());
onUpdateProgress(new ProgressEventArgs(0));
StringBuilder fixed_modifications_sb = new StringBuilder();
foreach (Modification modification in fixedModifications)
{
fixed_modifications_sb.Append(modification.Name + ", ");
}
if (fixed_modifications_sb.Length > 0)
{
fixed_modifications_sb = fixed_modifications_sb.Remove(fixed_modifications_sb.Length - 2, 2);
}
string fixed_modifications = fixed_modifications_sb.ToString();
if (!Directory.Exists(outputFolder))
{
Directory.CreateDirectory(outputFolder);
}
log = new StreamWriter(Path.Combine(outputFolder, "Phosphinator_log.txt"));
log.AutoFlush = true;
log.WriteLine("Phosphinator PARAMETERS");
log.WriteLine("Fixed Modifications: " + fixed_modifications);
log.WriteLine("Fragment Intensity Threshold: " + intensityThreshold.ToString() + " (" + intensityThresholdType.ToString() + ')');
log.WriteLine("Fragment m/z Tolerance (Th): " + mzTolerance.ToString());
log.WriteLine("Ambiguity Score Threshold: " + ambiguityScoreThreshold.ToString());
log.WriteLine("Eliminate Precursor Interference: " + eliminatePrecursorInterference.ToString());
if (eliminatePrecursorInterference)
{
log.WriteLine("Precursor Interference Threshold: " + precursorInterferenceThreshold.ToString());
}
if (motifXOutput)
{
log.WriteLine("Motif-X Fasta Protein Database Filepath: " + motifXFastaProteinDatabaseFilepath);
log.WriteLine("Motif-X Window Size: " + motifXWindowSize.ToString());
}
log.WriteLine();
ProteinSiteCounter identified_sites_by_protein = new ProteinSiteCounter();
ProteinSiteCounter localized_sites_by_protein = new ProteinSiteCounter();
ProteinSiteCounter unlocalized_sites_by_protein = new ProteinSiteCounter();
Dictionary<string, Dictionary<KeyValuePair<int, string>, List<string>>> localized =
new Dictionary<string, Dictionary<KeyValuePair<int, string>, List<string>>>();
Dictionary<string, Dictionary<KeyValuePair<int, string>, List<string>>> unlocalized =
new Dictionary<string, Dictionary<KeyValuePair<int, string>, List<string>>>();
non_phospho_output = new StreamWriter(Path.Combine(outputFolder, "non_phospho.csv"));
localized_phospho_output = new StreamWriter(Path.Combine(outputFolder, "localized_phospho.csv"));
unlocalized_phospho_output = new StreamWriter(Path.Combine(outputFolder, "unlocalized_phospho.csv"));
ProteinDictionary proteins = null;
Dictionary<string, int> motifs = null;
if (motifXOutput)
{
proteins = new ProteinDictionary(motifXFastaProteinDatabaseFilepath);
motifs = new Dictionary<string, int>();
motifX = new StreamWriter(Path.Combine(outputFolder, "motif-x.txt"));
}
raw = (IXRawfile2) new MSFileReader_XRawfile();
string header_line = null;
string[] headers = null;
bool quant = false;
foreach (string csv_filepath in csvFilepaths)
{
onStartingFile(new FilepathEventArgs(csv_filepath));
csv = new StreamReader(csv_filepath);
using (CsvReader reader = new CsvReader(csv, true))
{
headers = reader.GetFieldHeaders();
header_line = string.Join(",", headers);
quant = headers.Contains("Channels Detected");
string[] lineData = new string[headers.Length];
//header_line = csv.ReadLine();
//quant = header_line.Contains("TQ_");
non_phospho_output.WriteLine(header_line);
localized_phospho_output.WriteLine(header_line +
", Number of Theoretical Fragments, Identified Phosphoisoform, Identified Phosphoisoform Number of Matching Fragments, Best Phosphoisoforms, Best Phosphoisoform, Best Phosphoisoform Number of Matching Fragments, Second-Best Phosphoisoform, Second-Best Phosphoisoform Number of Matching Fragments, Identified Phosphoisoform Correct?, Preliminary Localization of All Phosphorylations?, Peptide Phosphorylation Sites, Probability of Spurious Fragment Match, Number of Theoretical Site-Determining Fragment Ions, Number of Matching Site-Determining Fragment Ions, Matching Site-Determining Fragment Ions, Probability Values, Ambiguity Scores, Phosphorylation Sites Localized?, All Phosphorylation Sites Localized?");
unlocalized_phospho_output.WriteLine(header_line +
", Number of Theoretical Fragments, Identified Phosphoisoform, Identified Phosphoisoform Number of Matching Fragments, Best Phosphoisoforms, Best Phosphoisoform, Best Phosphoisoform Number of Matching Fragments, Second-Best Phosphoisoform, Second-Best Phosphoisoform Number of Matching Fragments, Identified Phosphoisoform Correct?, Preliminary Localization of All Phosphorylations?, Peptide Phosphorylation Sites, Probability of Spurious Fragment Match, Number of Theoretical Site-Determining Fragment Ions, Number of Matching Site-Determining Fragment Ions, Matching Site-Determining Fragment Ions, Probability Values, Ambiguity Scores, Phosphorylation Sites Localized?, All Phosphorylation Sites Localized?");
while (reader.ReadNextRecord())
{
//string line = csv.ReadLine();
//string[] fields = Regex.Split(line,
// @",(?!(?<=(?:^|,)\s*\x22(?:[^\x22]|\x22\x22|\\\x22)*,)(?:[^\x22]|\x22\x22|\\\x22)*\x22\s*(?:,|$))");
// // crazy regex to parse CSV with internal double quotes from http://regexlib.com/REDetails.aspx?regexp_id=621
string sequence = reader["Peptide"];
string dynamic_modifications = reader["Mods"];
if (!dynamic_modifications.Contains("phosphorylation"))
{
//non_phospho_output.WriteLine(line);
}
else
{
Peptide identified_phosphopeptide = new Peptide(sequence, fixedModifications,
dynamic_modifications);
int start_residue = int.Parse(reader["Start"]);
int stop_residue = int.Parse(reader["Stop"]);
string protein_description = reader["Defline"].Trim('"');
StringBuilder sb = new StringBuilder();
reader.CopyCurrentRecordTo(lineData);
foreach (string datum in lineData)
{
if (datum.Contains(','))
sb.Append("\"" + datum + "\"");
else
sb.Append(datum);
sb.Append(',');
}
sb.Remove(sb.Length - 1, 1);
string line = sb.ToString();
if (!identified_sites_by_protein.ContainsKey(protein_description))
{
identified_sites_by_protein.Add(protein_description, new Dictionary<string, int>());
}
foreach (KeyValuePair<int, string> kvp in identified_phosphopeptide.DynamicModifications)
{
if (kvp.Value.Contains("phosphorylation"))
{
string site = sequence[kvp.Key - 1] + (start_residue + kvp.Key).ToString();
if (!identified_sites_by_protein[protein_description].ContainsKey(site))
{
identified_sites_by_protein[protein_description].Add(site, 0);
}
identified_sites_by_protein[protein_description][site]++;
}
}
int scan_number = int.Parse(reader["Spectrum number"]);
string filenameID = reader["Filename/id"];
FragmentType[] fragment_types = null;
if (filenameID.Contains(".ETD.") || filenameID.Contains(".ECD."))
{
fragment_types = new FragmentType[] {FragmentType.c, FragmentType.zdot};
}
else
{
fragment_types = new FragmentType[] {FragmentType.b, FragmentType.y};
}
string raw_filename = filenameID.Substring(0, filenameID.IndexOf('.')) + ".raw";
int charge = int.Parse(reader["Charge"]);
string current_raw_filename = null;
raw.GetFileName(ref current_raw_filename);
if (current_raw_filename == null ||
!raw_filename.Equals(Path.GetFileName(current_raw_filename),
StringComparison.InvariantCultureIgnoreCase))
{
raw.Close();
string[] raw_filepaths = null;
if (!string.IsNullOrEmpty(rawFolder) && Directory.Exists(rawFolder))
{
raw_filepaths = Directory.GetFiles(rawFolder, raw_filename,
SearchOption.AllDirectories);
}
else
{
raw_filepaths = Directory.GetFiles(Path.GetDirectoryName(csv_filepath),
raw_filename, SearchOption.AllDirectories);
}
if (raw_filepaths.Length == 0)
{
throw new FileNotFoundException("No corresponding .raw file found for " +
csv_filepath);
}
if (raw_filepaths.Length > 1)
{
throw new Exception("Multiple corresponding .raw files found for " +
csv_filepath);
}
raw.Open(raw_filepaths[0]);
raw.SetCurrentController(0, 1);
}
string scan_filter = null;
raw.GetFilterForScanNum(scan_number, ref scan_filter);
string low_mz_scan_filter = scan_filter.Substring(scan_filter.IndexOf('[') + 1);
double low_mz =
double.Parse(low_mz_scan_filter.Substring(0, low_mz_scan_filter.IndexOf('-')));
string high_mz_scan_filter = scan_filter.Substring(scan_filter.LastIndexOf('-') + 1);
double high_mz =
double.Parse(high_mz_scan_filter.Substring(0, high_mz_scan_filter.IndexOf(']')));
double[,] spectrum = null;
if (scan_filter.Contains("FTMS"))
{
object labels_obj = null;
object flags_obj = null;
raw.GetLabelData(ref labels_obj, ref flags_obj, ref scan_number);
spectrum = (double[,]) labels_obj;
}
else
{
double centroid_width = double.NaN;
object spectrum_obj = null;
object flags = null;
int size = -1;
raw.GetMassListFromScanNum(ref scan_number, null, 0, -1, 0, 1, ref centroid_width,
ref spectrum_obj, ref flags, ref size);
spectrum = (double[,]) spectrum_obj;
}
double base_peak_mz = double.NaN;
double base_peak_intensity = double.NaN;
for (int i = spectrum.GetLowerBound(1); i <= spectrum.GetUpperBound(1); i++)
{
if (double.IsNaN(base_peak_mz) ||
spectrum[(int) RawLabelDataColumn.Intensity, i] > base_peak_intensity)
{
base_peak_mz = spectrum[(int) RawLabelDataColumn.MZ, i];
base_peak_intensity = spectrum[(int) RawLabelDataColumn.Intensity, i];
}
}
double intensity_threshold = intensityThreshold;
if (intensityThresholdType == IntensityThresholdType.Relative)
{
intensity_threshold = (intensityThreshold/100.0)*base_peak_intensity;
}
double[] parameters = new double[4];
if (!scan_filter.Contains("FTMS") &&
intensityThresholdType == IntensityThresholdType.SignalToNoiseRatio)
{
List<double> relative_intensities = new List<double>();
for (int i = spectrum.GetLowerBound(1); i <= spectrum.GetUpperBound(1); i++)
{
relative_intensities.Add(spectrum[(int) RawLabelDataColumn.Intensity, i]/
base_peak_intensity);
}
double bin_width = 0.001;
int bins = 101;
double[][] relative_intensity_histogram = new double[2][];
relative_intensity_histogram[0] = new double[bins];
relative_intensity_histogram[1] = new double[bins];
for (int i = relative_intensity_histogram[0].GetLowerBound(0);
i <= relative_intensity_histogram[0].GetUpperBound(0);
i++)
{
relative_intensity_histogram[0][i] = i*bin_width;
}
foreach (double relative_intensity in relative_intensities)
{
int bin_number = (int) Math.Floor(relative_intensity/bin_width);
if (bin_number < bins)
{
relative_intensity_histogram[1][bin_number]++;
}
}
parameters[0] = 0.0;
parameters[1] = 100.0;
parameters[2] = 0.0;
parameters[3] = 0.001;
double[] weights = new double[relative_intensity_histogram[1].Length];
for (int i = weights.GetLowerBound(0); i <= weights.GetUpperBound(0); i++)
{
weights[i] = 1.0;
}
LMA lma = new LMA(new GaussianFunctionWithPartials(), parameters,
relative_intensity_histogram, weights, new DotNetMatrix.GeneralMatrix(4, 4),
0.001, 5000);
lma.Fit();
}
List<Peptide> peptides = GetAlternativePhosphoisoformPeptides(
identified_phosphopeptide, fixedModifications);
List<PhosphopeptideStatistics> all_phosphopeptide_stats =
new List<PhosphopeptideStatistics>(peptides.Count);
PhosphopeptideStatistics identified_phosphoisoform = null;
List<double> ms2_mz_peaks = new List<double>(spectrum.GetLength(1));
for (int i = spectrum.GetLowerBound(1); i <= spectrum.GetUpperBound(1); i++)
{
double signal_to_noise = scan_filter.Contains("FTMS")
? (spectrum[(int) RawLabelDataColumn.Intensity, i] -
spectrum[(int) RawLabelDataColumn.NoiseBaseline, i])/
spectrum[(int) RawLabelDataColumn.NoiseLevel, i]
: ((spectrum[(int) RawLabelDataColumn.Intensity, i]/base_peak_intensity) -
parameters[2])/parameters[3];
if ((intensityThresholdType == IntensityThresholdType.SignalToNoiseRatio
&& signal_to_noise >= intensity_threshold)
|| (intensityThresholdType != IntensityThresholdType.SignalToNoiseRatio
&& spectrum[(int) RawLabelDataColumn.Intensity, i] >= intensity_threshold))
{
ms2_mz_peaks.Add(spectrum[(int) RawLabelDataColumn.MZ, i]);
}
}
double mz_range = high_mz - low_mz;
Dictionary<double, bool> searched_fragment_mzs = new Dictionary<double, bool>();
foreach (Peptide peptide in peptides)
{
PhosphopeptideStatistics phosphopeptide_stats = new PhosphopeptideStatistics(peptide);
if (peptide.Sequence == identified_phosphopeptide.Sequence)
{
identified_phosphoisoform = phosphopeptide_stats;
}
FragmentDictionary fragments = peptide.CalculateFragments(fragment_types);
foreach (KeyValuePair<string, Fragment> kvp in fragments)
{
phosphopeptide_stats.Fragments.Add(kvp.Key, new Dictionary<int, bool>());
for (int fragment_charge = 1;
fragment_charge <= (charge >= 3 ? 2 : 1);
fragment_charge++)
{
if (fragment_charge > 1 &&
fragment_charge >
(double) kvp.Value.Number/peptide.Sequence.Length*charge)
{
break;
}
double mz = MZFromMassAndCharge(kvp.Value.Mass, fragment_charge);
if (mz < low_mz || mz > high_mz)
{
continue;
}
if (!searched_fragment_mzs.ContainsKey(mz))
{
bool found = false;
foreach (double ms2_mz_peak in ms2_mz_peaks)
{
if (Math.Abs(ms2_mz_peak - mz) <= mzTolerance)
{
found = true;
break;
}
else if (ms2_mz_peak > mz + mzTolerance)
{
break;
}
}
searched_fragment_mzs.Add(mz, found);
}
phosphopeptide_stats.Fragments[kvp.Key].Add(fragment_charge,
searched_fragment_mzs[mz]);
}
}
all_phosphopeptide_stats.Add(phosphopeptide_stats);
}
all_phosphopeptide_stats.Sort(ComparePhosphopeptidesByDescendingMatchingFragments);
PhosphopeptideStatistics best_phosphoisoform = all_phosphopeptide_stats[0];
PhosphopeptideStatistics second_best_phosphoisoform = all_phosphopeptide_stats.Count > 1
? all_phosphopeptide_stats[1]
: null;
List<string> best_sequences = new List<string>();
foreach (PhosphopeptideStatistics phosphopeptide_stats in all_phosphopeptide_stats)
{
if (phosphopeptide_stats.NumberOfMatchingFragments ==
best_phosphoisoform.NumberOfMatchingFragments)
{
best_sequences.Add(phosphopeptide_stats.Peptide.Sequence);
}
else
{
break;
}
}
bool preliminary_localization = second_best_phosphoisoform == null
||
best_phosphoisoform.NumberOfMatchingFragments >
second_best_phosphoisoform.NumberOfMatchingFragments;
bool all_sites_localized = preliminary_localization;
Dictionary<string, bool> peptide_sites = new Dictionary<string, bool>();
Dictionary<string, bool> protein_sites = new Dictionary<string, bool>();
string best_sequence = best_phosphoisoform.Peptide.Sequence;
for (int i = 0; i < best_sequence.Length; i++)
{
if (char.IsLower(best_sequence[i]))
{
if (preliminary_localization && second_best_phosphoisoform == null)
{
peptide_sites.Add(best_sequence[i] + (i + 1).ToString(), true);
protein_sites.Add(best_sequence[i] + (start_residue + i).ToString(), true);
if (!localized_sites_by_protein.ContainsKey(protein_description))
{
localized_sites_by_protein.Add(protein_description,
new Dictionary<string, int>());
}
string site = best_sequence[i] + (start_residue + i).ToString();
if (!localized_sites_by_protein[protein_description].ContainsKey(site))
{
localized_sites_by_protein[protein_description].Add(site, 0);
}
localized_sites_by_protein[protein_description][site]++;
if (motifXOutput)
{
ExtractMotifs(motifs, proteins, protein_description, best_sequence,
start_residue, i);
}
}
else
{
peptide_sites.Add(best_sequence[i] + (i + 1).ToString(), false);
protein_sites.Add(best_sequence[i] + (start_residue + i).ToString(), false);
}
}
}
double probability_of_success = double.NaN;
List<string> theoretical_site_determining_fragment_ions = new List<string>();
List<string> matching_site_determining_fragment_ions = new List<string>();
List<string> left_site_determining_fragments = new List<string>();
List<string> right_site_determining_fragments = new List<string>();
List<string> site_determining_fragments = new List<string>();
List<string> p_values = new List<string>();
List<string> a_scores = new List<string>();
List<string> sites_localized = new List<string>();
if (preliminary_localization && second_best_phosphoisoform != null)
{
probability_of_success = (ms2_mz_peaks.Count*2*mzTolerance)/mz_range;
for (int i = 0; i < best_sequence.Length; i++)
{
if (char.IsLower(best_sequence[i]))
{
int first_phosphorylatable_residue = i - 1;
while (first_phosphorylatable_residue >= 0)
{
if (best_sequence[first_phosphorylatable_residue] == 'S'
|| best_sequence[first_phosphorylatable_residue] == 'T'
|| best_sequence[first_phosphorylatable_residue] == 'Y')
{
break;
}
else
{
first_phosphorylatable_residue--;
}
}
int? num_left_theoretical_site_determining_fragment_ions = null;
int? num_left_matching_site_determining_fragment_ions = null;
double left_p_value = double.NaN;
double left_a_score = double.NaN;
if (first_phosphorylatable_residue >= 0)
{
num_left_theoretical_site_determining_fragment_ions = 0;
num_left_matching_site_determining_fragment_ions = 0;
for (int j = first_phosphorylatable_residue + 1; j <= i; j++)
{
string n_terminal_fragment = fragment_types[0].ToString() +
j.ToString();
if (best_phosphoisoform.Fragments.ContainsKey(n_terminal_fragment))
{
foreach (
KeyValuePair<int, bool> kvp in
best_phosphoisoform.Fragments[n_terminal_fragment])
{
num_left_theoretical_site_determining_fragment_ions++;
if (kvp.Value)
{
num_left_matching_site_determining_fragment_ions++;
string n_terminal_fragment_string =
n_terminal_fragment + "(+" + kvp.Key.ToString() +
')';
if (
!left_site_determining_fragments.Contains(
n_terminal_fragment_string))
{
left_site_determining_fragments.Add(
n_terminal_fragment_string);
}
}
}
}
string c_terminal_fragment = fragment_types[1].ToString() +
(best_sequence.Length - j).ToString();
if (best_phosphoisoform.Fragments.ContainsKey(c_terminal_fragment))
{
foreach (
KeyValuePair<int, bool> kvp in
best_phosphoisoform.Fragments[c_terminal_fragment])
{
num_left_theoretical_site_determining_fragment_ions++;
if (kvp.Value)
{
num_left_matching_site_determining_fragment_ions++;
string c_terminal_fragment_string =
c_terminal_fragment + "(+" + kvp.Key.ToString() +
')';
if (
!left_site_determining_fragments.Contains(
c_terminal_fragment_string))
{
left_site_determining_fragments.Add(
c_terminal_fragment_string);
}
}
}
}
}
left_p_value =
alglib.binomialdistr.binomialcdistribution(
num_left_matching_site_determining_fragment_ions.Value - 1,
num_left_theoretical_site_determining_fragment_ions.Value,
probability_of_success);
left_a_score = -10*Math.Log10(left_p_value);
}
int last_phosphorylatable_residue = i + 1;
while (last_phosphorylatable_residue < best_sequence.Length)
{
if (best_sequence[last_phosphorylatable_residue] == 'S'
|| best_sequence[last_phosphorylatable_residue] == 'T'
|| best_sequence[last_phosphorylatable_residue] == 'Y')
{
break;
}
else
{
last_phosphorylatable_residue++;
}
}
int? num_right_theoretical_site_determining_fragment_ions = null;
int? num_right_matching_site_determining_fragment_ions = null;
double right_p_value = double.NaN;
double right_a_score = double.NaN;
if (last_phosphorylatable_residue < best_sequence.Length)
{
num_right_theoretical_site_determining_fragment_ions = 0;
num_right_matching_site_determining_fragment_ions = 0;
for (int j = last_phosphorylatable_residue; j > i; j--)
{
string n_terminal_fragment = fragment_types[0].ToString() +
j.ToString();
if (best_phosphoisoform.Fragments.ContainsKey(n_terminal_fragment))
{
foreach (
KeyValuePair<int, bool> kvp in
best_phosphoisoform.Fragments[n_terminal_fragment])
{
num_right_theoretical_site_determining_fragment_ions++;
if (kvp.Value)
{
num_right_matching_site_determining_fragment_ions++;
string n_terminal_fragment_string =
n_terminal_fragment + "(+" + kvp.Key.ToString() +
')';
if (
!right_site_determining_fragments.Contains(
n_terminal_fragment_string))
{
right_site_determining_fragments.Add(
n_terminal_fragment_string);
}
}
}
}
string c_terminal_fragment = fragment_types[1].ToString() +
(best_sequence.Length - j).ToString();
if (best_phosphoisoform.Fragments.ContainsKey(c_terminal_fragment))
{
foreach (
KeyValuePair<int, bool> kvp in
best_phosphoisoform.Fragments[c_terminal_fragment])
{
num_right_theoretical_site_determining_fragment_ions++;
if (kvp.Value)
{
num_right_matching_site_determining_fragment_ions++;
string c_terminal_fragment_string =
c_terminal_fragment + "(+" + kvp.Key.ToString() +
')';
if (
!right_site_determining_fragments.Contains(
c_terminal_fragment_string))
{
right_site_determining_fragments.Add(
c_terminal_fragment_string);
}
}
}
}
}
right_p_value =
alglib.binomialdistr.binomialcdistribution(
num_right_matching_site_determining_fragment_ions.Value - 1,
num_right_theoretical_site_determining_fragment_ions.Value,
probability_of_success);
right_a_score = -10*Math.Log10(right_p_value);
}
theoretical_site_determining_fragment_ions.Add(
(num_left_theoretical_site_determining_fragment_ions.HasValue
? num_left_theoretical_site_determining_fragment_ions.ToString()
: "n/a") + " | " +
(num_right_theoretical_site_determining_fragment_ions.HasValue
? num_right_theoretical_site_determining_fragment_ions.ToString()
: "n/a"));
matching_site_determining_fragment_ions.Add(
(num_left_matching_site_determining_fragment_ions.HasValue
? num_left_matching_site_determining_fragment_ions.ToString()
: "n/a") + " | " +
(num_right_matching_site_determining_fragment_ions.HasValue
? num_right_matching_site_determining_fragment_ions.ToString()
: "n/a"));
site_determining_fragments.Add((left_site_determining_fragments.Count > 0
? string.Join(",", left_site_determining_fragments.ToArray())
: "n/a") + " | " +
(right_site_determining_fragments.Count > 0
? string.Join(",",
right_site_determining_fragments
.ToArray())
: "n/a"));
p_values.Add((double.IsNaN(left_p_value) ? "n/a" : left_p_value.ToString()) +
" | " +
(double.IsNaN(right_p_value) ? "n/a" : right_p_value.ToString()));
a_scores.Add((double.IsNaN(left_a_score) ? "n/a" : left_a_score.ToString()) +
" | " +
(double.IsNaN(right_a_score) ? "n/a" : right_a_score.ToString()));
bool site_localized = (double.IsNaN(left_a_score) ||
left_a_score >= ambiguityScoreThreshold) &&
(double.IsNaN(right_a_score) ||
right_a_score >= ambiguityScoreThreshold);
sites_localized.Add(site_localized.ToString().ToUpper());
if (site_localized)
{
peptide_sites[best_sequence[i] + (i + 1).ToString()] = true;
protein_sites[best_sequence[i] + (start_residue + i).ToString()] = true;
if (!localized_sites_by_protein.ContainsKey(protein_description))
{
localized_sites_by_protein.Add(protein_description,
new Dictionary<string, int>());
}
string site = best_sequence[i] + (start_residue + i).ToString();
if (!localized_sites_by_protein[protein_description].ContainsKey(site))
{
localized_sites_by_protein[protein_description].Add(site, 0);
}
localized_sites_by_protein[protein_description][site]++;
if (motifXOutput)
{
ExtractMotifs(motifs, proteins, protein_description, best_sequence,
start_residue, i);
}
}
if (!site_localized)
{
all_sites_localized = false;
}
}
}
}
int phosphorylations = 0;
foreach (
string dynamic_modification in
best_phosphoisoform.Peptide.DynamicModifications.Values)
{
if (dynamic_modification.Contains("phosphorylation"))
{
phosphorylations++;
}
}
string isoform = null;
if (all_sites_localized)
{
foreach (KeyValuePair<string, bool> kvp in protein_sites)
{
isoform += kvp.Key + ',';
}
isoform = isoform.Substring(0, isoform.Length - 1);
KeyValuePair<int, string> isoform_kvp =
new KeyValuePair<int, string>(phosphorylations, isoform);
if (!localized.ContainsKey(protein_description))
{
localized.Add(protein_description,
new Dictionary<KeyValuePair<int, string>, List<string>>());
}
if (!localized[protein_description].ContainsKey(isoform_kvp))
{
localized[protein_description].Add(isoform_kvp, new List<string>());
}
localized[protein_description][isoform_kvp].Add(line);
}
else
{
if (preliminary_localization)
{
foreach (KeyValuePair<string, bool> kvp in protein_sites)
{
isoform += kvp.Key;
if (!kvp.Value)
{
isoform += '?';
}
isoform += ',';
}
}
else
{
for (int i = 0; i < best_sequence.Length; i++)
{
bool phospho = false;
for (int j = 0; j < all_phosphopeptide_stats.Count; j++)
{
if (all_phosphopeptide_stats[j].NumberOfMatchingFragments <
best_phosphoisoform.NumberOfMatchingFragments)
{
break;
}
if (char.IsLower(all_phosphopeptide_stats[j].Peptide.Sequence[i]))
{
phospho = true;
}
}
if (phospho)
{
isoform += char.ToLower(best_sequence[i]) +
(start_residue + i).ToString() + "?,";
}
}
}
isoform = isoform.Substring(0, isoform.Length - 1);
KeyValuePair<int, string> isoform_kvp =
new KeyValuePair<int, string>(phosphorylations, isoform);
if (!unlocalized.ContainsKey(protein_description))
{
unlocalized.Add(protein_description,
new Dictionary<KeyValuePair<int, string>, List<string>>());
}
if (!unlocalized[protein_description].ContainsKey(isoform_kvp))
{
unlocalized[protein_description].Add(isoform_kvp, new List<string>());
}
unlocalized[protein_description][isoform_kvp].Add(line);
}
StreamWriter output = all_sites_localized
? localized_phospho_output
: unlocalized_phospho_output;
output.Write(line + ',');
output.Write(identified_phosphoisoform.NumberOfTotalFragments.ToString() + ',');
output.Write(identified_phosphoisoform.Peptide.Sequence + ',');
output.Write(identified_phosphoisoform.NumberOfMatchingFragments.ToString() + ',');
for (int s = 0; s < best_sequences.Count; s++)
{
output.Write(best_sequences[s]);
if (s < best_sequences.Count - 1)
{
output.Write('/');
}
}
output.Write(',');
output.Write(best_phosphoisoform.Peptide.Sequence + ',');
output.Write(best_phosphoisoform.NumberOfMatchingFragments.ToString() + ',');
if (second_best_phosphoisoform != null)
{
output.Write(second_best_phosphoisoform.Peptide.Sequence + ',');
output.Write(second_best_phosphoisoform.NumberOfMatchingFragments.ToString() + ',');
}
else
{
output.Write("n/a,n/a,");
}
output.Write(
(identified_phosphoisoform.NumberOfMatchingFragments ==
best_phosphoisoform.NumberOfMatchingFragments).ToString() + ',');
output.Write(preliminary_localization.ToString() + ',');
string[] peptide_sites_array = new string[peptide_sites.Count];
peptide_sites.Keys.CopyTo(peptide_sites_array, 0);
string peptide_sites_array_string = string.Join("; ", peptide_sites_array);
AppendFieldToCsv(peptide_sites_array_string, output);
output.Write((!double.IsNaN(probability_of_success)
? probability_of_success.ToString()
: string.Empty) + ',');
string theoretical_site_determining_fragment_ions_string = string.Join("; ",
theoretical_site_determining_fragment_ions.ToArray());
AppendFieldToCsv(theoretical_site_determining_fragment_ions_string, output);
string matching_site_determining_fragment_ions_string = string.Join("; ",
matching_site_determining_fragment_ions.ToArray());
AppendFieldToCsv(matching_site_determining_fragment_ions_string, output);
string site_determining_fragments_string = string.Join("; ",
site_determining_fragments.ToArray());
AppendFieldToCsv(site_determining_fragments_string, output);
string p_values_string = string.Join("; ", p_values.ToArray());
AppendFieldToCsv(p_values_string, output);
string a_scores_string = string.Join("; ", a_scores.ToArray());
AppendFieldToCsv(a_scores_string, output);
string sites_localized_string = string.Join("; ", sites_localized.ToArray());
AppendFieldToCsv(sites_localized_string, output);
output.Write(all_sites_localized.ToString().ToUpper());
output.WriteLine();
}
double progress = (double) csv.BaseStream.Position/csv.BaseStream.Length;
onUpdateProgress(new ProgressEventArgs((int) Math.Round(progress*100.0)));
}
}
csv.Close();
onFinishedFile(new EventArgs());
}
raw.Close();
non_phospho_output.Close();
localized_phospho_output.Close();
unlocalized_phospho_output.Close();
log.WriteLine("Identified Phosphoproteins: " + identified_sites_by_protein.Proteins.ToString());
log.WriteLine("Identified Phosphosites: " + identified_sites_by_protein.Sites.ToString());
log.WriteLine();
log.WriteLine("Localized Phosphoproteins: " + localized_sites_by_protein.Proteins.ToString());
log.WriteLine("Localized Phosphosites: " + localized_sites_by_protein.Sites.ToString());
log.WriteLine();
int localized_phosphoisoforms = 0;
foreach (KeyValuePair<string, Dictionary<KeyValuePair<int, string>, List<string>>> kvp in localized)
{
foreach (KeyValuePair<KeyValuePair<int, string>, List<string>> kvp2 in kvp.Value)
{
localized_phosphoisoforms++;
}
}
int unlocalized_phosphoisoforms = 0;
foreach (KeyValuePair<string, Dictionary<KeyValuePair<int, string>, List<string>>> kvp in unlocalized)
{
foreach (KeyValuePair<KeyValuePair<int, string>, List<string>> kvp2 in kvp.Value)
{
unlocalized_phosphoisoforms++;
}
}
log.WriteLine("Localized Phosphoisoforms: " + localized_phosphoisoforms.ToString());
log.WriteLine("Unlocalized Phosphoisoforms: " + unlocalized_phosphoisoforms.ToString());
log.Close();
using (StreamWriter protein_sites = new StreamWriter(Path.Combine(outputFolder, "localized_protein_phosphosites.csv")))
{
protein_sites.WriteLine("Protein Description, Number of Localized Phosphosites");
protein_sites.WriteLine(", Localized Phosphosite");
foreach (KeyValuePair<string, Dictionary<string, int>> kvp in localized_sites_by_protein)
{
protein_sites.WriteLine((kvp.Key.Contains(",") ? '"' + kvp.Key + '"' : kvp.Key) + ',' + kvp.Value.Count.ToString());
foreach (KeyValuePair<string, int> kvp2 in kvp.Value)
{
protein_sites.WriteLine(',' + kvp2.Key);
}
}
}
using (StreamWriter full_localized_output = new StreamWriter(Path.Combine(outputFolder, "full_localized_phosphoisoforms.csv")))
{
//int interference_index = -1;
int first_quant_index = -1;
int last_quant_index = -1;
if (!quant)
{
full_localized_output.Write("Protein Description, Phosphoisoform, Phosphoisoform Sites, PSMs Identified, Peptides Identified");
}
else
{
full_localized_output.Write("Protein Description, Phosphoisoform, Phosphoisoform Sites, PSMs Identified, PSMs Quantified, Peptides Identified, Peptides Quantified,");
for (int i = 0; i < headers.Length; i++)
{
if (headers[i].EndsWith("NL)"))
{
if (first_quant_index < 0)
{
first_quant_index = i;
}
}
if (first_quant_index >= 0)
full_localized_output.Write(' ' + headers[i] + ',');
if (headers[i].Equals("Channels Detected"))
{
last_quant_index = i;
}
}
full_localized_output.Write(" Phosphoisoform Quantified?");
}
full_localized_output.WriteLine();
full_localized_output.WriteLine(", " + header_line);
using (StreamWriter reduced_localized_output = new StreamWriter(Path.Combine(outputFolder, "reduced_localized_phosphoisoforms.csv")))
{
if (!quant)
{
reduced_localized_output.Write("Protein Description, Phosphoisoform, Phosphoisoform Sites,Peptides , PSMs Identified, Peptides Identified");
}
else
{
reduced_localized_output.Write("Protein Description, Phosphoisoform, Phosphoisoform Sites,Peptides , PSMs Identified, PSMs Quantified, Peptides Identified, Peptides Quantified,");
for (int i = first_quant_index; i <= last_quant_index; i++)
{
reduced_localized_output.Write(' ' + headers[i] + ',');
}
reduced_localized_output.Write(" Phosphoisoform Quantified?");
}
reduced_localized_output.WriteLine();
foreach (KeyValuePair<string, Dictionary<KeyValuePair<int, string>, List<string>>> kvp in localized)
{
foreach (KeyValuePair<KeyValuePair<int, string>, List<string>> kvp2 in kvp.Value)
{
full_localized_output.Write((kvp.Key.Contains(",") ? '"' + kvp.Key + '"' : kvp.Key) + ',');
reduced_localized_output.Write((kvp.Key.Contains(",") ? '"' + kvp.Key + '"' : kvp.Key) + ',');
full_localized_output.Write((kvp2.Key.Value.Contains(",") ? '"' + kvp2.Key.Value + '"' : kvp2.Key.Value) + ',');
reduced_localized_output.Write((kvp2.Key.Value.Contains(",") ? '"' + kvp2.Key.Value + '"' : kvp2.Key.Value) + ',');
full_localized_output.Write(kvp2.Key.Key.ToString() + ',');
reduced_localized_output.Write(kvp2.Key.Key.ToString() + ',');
double[] isoform_quantitation = new double[last_quant_index - first_quant_index + 1];
isoform_quantitation = Array.ConvertAll<double, double>(isoform_quantitation, SET_DOUBLE_VALUE_TO_NAN);
int spectra_identified = 0;
int spectra_quantified = 0;
Dictionary<string, int> unique_peptides_identified = new Dictionary<string, int>();
Dictionary<string, int> unique_peptides_quantified = new Dictionary<string, int>();
StringBuilder peptides = new StringBuilder();
foreach (string line in kvp2.Value)
{
string[] fields = Regex.Split(line, @",(?!(?<=(?:^|,)\s*\x22(?:[^\x22]|\x22\x22|\\\x22)*,)(?:[^\x22]|\x22\x22|\\\x22)*\x22\s*(?:,|$))"); // crazy regex to parse CSV with internal double quotes from http://regexlib.com/REDetails.aspx?regexp_id=621
spectra_identified++;
string peptide_sequence = fields[2];
peptides.Append(peptide_sequence + " ");
if (!unique_peptides_identified.ContainsKey(peptide_sequence))
{
unique_peptides_identified.Add(peptide_sequence, 0);
}
unique_peptides_identified[peptide_sequence]++;
if (quant)
{
spectra_quantified++;
if (double.IsNaN(isoform_quantitation[0]))
{
isoform_quantitation = Array.ConvertAll<double, double>(isoform_quantitation, SET_DOUBLE_VALUE_TO_ZERO);
}
if (!unique_peptides_quantified.ContainsKey(peptide_sequence))
{
unique_peptides_quantified.Add(peptide_sequence, 0);
}
unique_peptides_quantified[peptide_sequence]++;
for (int i = first_quant_index; i <= last_quant_index; i++)
{
double val = 0;
double.TryParse(fields[i], out val);
isoform_quantitation[i - first_quant_index] += val;
}
}
}
full_localized_output.Write(peptides.ToString() + ',');
reduced_localized_output.Write(peptides.ToString() + ',');
full_localized_output.Write(spectra_identified.ToString() + ',');
reduced_localized_output.Write(spectra_identified.ToString() + ',');
if (quant)
{
full_localized_output.Write(spectra_quantified.ToString() + ',');
reduced_localized_output.Write(spectra_quantified.ToString() + ',');
}
full_localized_output.Write(unique_peptides_identified.Count.ToString() + ',');
reduced_localized_output.Write(unique_peptides_identified.Count.ToString() + ',');
if (quant)
{
full_localized_output.Write(unique_peptides_quantified.Count.ToString() + ',');
reduced_localized_output.Write(unique_peptides_quantified.Count.ToString() + ',');
for (int i = isoform_quantitation.GetLowerBound(0); i <= isoform_quantitation.GetUpperBound(0); i++)
{
full_localized_output.Write(isoform_quantitation[i].ToString() + ',');
reduced_localized_output.Write(isoform_quantitation[i].ToString() + ',');
}
full_localized_output.Write((spectra_quantified > 0).ToString());
reduced_localized_output.Write((spectra_quantified > 0).ToString());
}
full_localized_output.WriteLine();
reduced_localized_output.WriteLine();
foreach (string line in kvp2.Value)
{
full_localized_output.WriteLine(',' + line);
}
}
}
}
}
using (StreamWriter full_unlocalized_output = new StreamWriter(Path.Combine(outputFolder, "full_unlocalized_phosphoisoforms.csv")))
{
int first_quant_index = -1;
int last_quant_index = -1;
if (!quant)
{
full_unlocalized_output.Write("Protein Description, Phosphoisoform, Phosphoisoform Sites,Peptides, PSMs Identified, Peptides Identified");
}
else
{
full_unlocalized_output.Write("Protein Description, Phosphoisoform, Phosphoisoform Sites,Peptides, PSMs Identified, PSMs Quantified, Peptides Identified, Peptides Quantified,");
for (int i = 0; i < headers.Length; i++)
{
if (headers[i].EndsWith("NL)"))
{
if (first_quant_index < 0)
{
first_quant_index = i;
}
}
if (first_quant_index >= 0)
full_unlocalized_output.Write(' ' + headers[i] + ',');
if (headers[i].Equals("Channels Detected"))
{
last_quant_index = i;
}
}
full_unlocalized_output.Write(" Phosphoisoform Quantified?");
}
full_unlocalized_output.WriteLine();
full_unlocalized_output.WriteLine(", " + header_line);
using (StreamWriter reduced_unlocalized_output = new StreamWriter(Path.Combine(outputFolder, "reduced_unlocalized_phosphoisoforms.csv")))
{
if (!quant)
{
reduced_unlocalized_output.Write("Protein Description, Phosphoisoform, Phosphoisoform Sites,Peptides, PSMs Identified, Peptides Identified");
}
else
{
reduced_unlocalized_output.Write("Protein Description, Phosphoisoform, Phosphoisoform Sites,Peptides, PSMs Identified, PSMs Quantified, Peptides Identified, Peptides Quantified,");
for (int i = first_quant_index; i <= last_quant_index; i++)
{
reduced_unlocalized_output.Write(' ' + headers[i] + ',');
}
reduced_unlocalized_output.Write(" Phosphoisoform Quantified?");
}
reduced_unlocalized_output.WriteLine();
foreach (KeyValuePair<string, Dictionary<KeyValuePair<int, string>, List<string>>> kvp in unlocalized)
{
foreach (KeyValuePair<KeyValuePair<int, string>, List<string>> kvp2 in kvp.Value)
{
full_unlocalized_output.Write((kvp.Key.Contains(",") ? '"' + kvp.Key + '"' : kvp.Key) + ',');
reduced_unlocalized_output.Write((kvp.Key.Contains(",") ? '"' + kvp.Key + '"' : kvp.Key) + ',');
full_unlocalized_output.Write((kvp2.Key.Value.Contains(",") ? '"' + kvp2.Key.Value + '"' : kvp2.Key.Value) + ',');
reduced_unlocalized_output.Write((kvp2.Key.Value.Contains(",") ? '"' + kvp2.Key.Value + '"' : kvp2.Key.Value) + ',');
full_unlocalized_output.Write(kvp2.Key.Key.ToString() + ',');
reduced_unlocalized_output.Write(kvp2.Key.Key.ToString() + ',');
double[] isoform_quantitation = new double[last_quant_index - first_quant_index + 1];
isoform_quantitation = Array.ConvertAll<double, double>(isoform_quantitation, SET_DOUBLE_VALUE_TO_NAN);
int spectra_identified = 0;
int spectra_quantified = 0;
Dictionary<string, int> unique_peptides_identified = new Dictionary<string, int>();
Dictionary<string, int> unique_peptides_quantified = new Dictionary<string, int>();
StringBuilder peptides = new StringBuilder();
foreach (string line in kvp2.Value)
{
string[] fields = Regex.Split(line, @",(?!(?<=(?:^|,)\s*\x22(?:[^\x22]|\x22\x22|\\\x22)*,)(?:[^\x22]|\x22\x22|\\\x22)*\x22\s*(?:,|$))"); // crazy regex to parse CSV with internal double quotes from http://regexlib.com/REDetails.aspx?regexp_id=621
spectra_identified++;
string peptide_sequence = fields[2];
peptides.Append(peptide_sequence + " ");
if (!unique_peptides_identified.ContainsKey(peptide_sequence))
{
unique_peptides_identified.Add(peptide_sequence, 0);
}
unique_peptides_identified[peptide_sequence]++;
if (quant)
{
spectra_quantified++;
if (double.IsNaN(isoform_quantitation[0]))
{
isoform_quantitation = Array.ConvertAll<double, double>(isoform_quantitation, SET_DOUBLE_VALUE_TO_ZERO);
}
if (!unique_peptides_quantified.ContainsKey(peptide_sequence))
{
unique_peptides_quantified.Add(peptide_sequence, 0);
}
unique_peptides_quantified[peptide_sequence]++;
for (int i = first_quant_index; i <= last_quant_index; i++)
{
double val = 0;
double.TryParse(fields[i], out val);
isoform_quantitation[i - first_quant_index] += val;
}
}
}
full_unlocalized_output.Write(peptides.ToString() + ',');
reduced_unlocalized_output.Write(peptides.ToString() + ',');
full_unlocalized_output.Write(spectra_identified.ToString() + ',');
reduced_unlocalized_output.Write(spectra_identified.ToString() + ',');
if (quant)
{
full_unlocalized_output.Write(spectra_quantified.ToString() + ',');
reduced_unlocalized_output.Write(spectra_quantified.ToString() + ',');
}
full_unlocalized_output.Write(unique_peptides_identified.Count.ToString() + ',');
reduced_unlocalized_output.Write(unique_peptides_identified.Count.ToString() + ',');
if (quant)
{
full_unlocalized_output.Write(unique_peptides_quantified.Count.ToString() + ',');
reduced_unlocalized_output.Write(unique_peptides_quantified.Count.ToString() + ',');
for (int i = isoform_quantitation.GetLowerBound(0); i <= isoform_quantitation.GetUpperBound(0); i++)
{
full_unlocalized_output.Write(isoform_quantitation[i].ToString() + ',');
reduced_unlocalized_output.Write(isoform_quantitation[i].ToString() + ',');
}
full_unlocalized_output.Write((spectra_quantified > 0).ToString());
reduced_unlocalized_output.Write((spectra_quantified > 0).ToString());
}
full_unlocalized_output.WriteLine();
reduced_unlocalized_output.WriteLine();
foreach (string line in kvp2.Value)
{
full_unlocalized_output.WriteLine(',' + line);
}
}
}
}
}
if (motifXOutput)
{
foreach (string motif in motifs.Keys)
{
motifX.WriteLine(motif);
}
motifX.Close();
using (StreamWriter motif_fasta = new StreamWriter(Path.Combine(outputFolder, "motif-x.fasta")))
{
foreach (KeyValuePair<string, string> kvp in proteins)
{
if (!kvp.Key.Contains("DECOY") && !kvp.Key.Contains("REVERSED"))
{
motif_fasta.WriteLine('>' + kvp.Key);
motif_fasta.WriteLine(kvp.Value);
}
}
}
}
onFinished(new EventArgs());
//}
//catch(Exception ex)
//{
// onThrowException(new ExceptionEventArgs(ex));
//}
//finally
//{
if (log != null)
{
log.Close();
}
if (raw != null)
{
raw.Close();
}
if (csv != null)
{
csv.Close();
}
if (non_phospho_output != null)
{
non_phospho_output.Close();
}
if (localized_phospho_output != null)
{
localized_phospho_output.Close();
}
if (unlocalized_phospho_output != null)
{
unlocalized_phospho_output.Close();
}
if (motifX != null)
{
motifX.Close();
}
}
catch (Exception e)
{
MessageBox.Show(e.Message + " " + e.StackTrace);
}
}
public void Produto2500Teste()
{
LMAFunction f = new FuncaoGaussianaAcumulada();
double[] parametrosEstimados = new[] { 0.111989183, 0.735 };
#region Dados Experimentais
double[] xExperimental = new[]
{
0,
0.02,
0.04,
0.06,
0.08,
0.1,
0.12,
0.14,
0.16,
0.18,
0.2,
0.22,
0.24,
0.26,
0.28,
0.3,
0.32,
0.34,
0.36,
0.38,
0.4,
0.42,
0.44,
0.46,
0.48,
0.5,
0.52,
0.54,
0.56,
0.58,
0.6,
0.62,
0.64,
0.66,
0.68,
0.7,
0.72,
0.74,
0.76,
0.78,
0.8,
0.82,
0.84,
0.86,
0.88,
0.9,
0.92,
0.94,
0.96
};
double[] yExperimental = new[]
{
0,
0,
0.03472,
0.06644,
0.09601,
0.12272,
0.14793,
0.17208,
0.19535,
0.21753,
0.23669,
0.25444,
0.27351,
0.29654,
0.32522,
0.35796,
0.39288,
0.42818,
0.46214,
0.4953,
0.52848,
0.56211,
0.59659,
0.63314,
0.67136,
0.70917,
0.74448,
0.77573,
0.80428,
0.83035,
0.85386,
0.87476,
0.89255,
0.90755,
0.92063,
0.93257,
0.94395,
0.95415,
0.96302,
0.97057,
0.97682,
0.98124,
0.98433,
0.98668,
0.98884,
0.9908,
0.9916,
0.99404,
0.99706
};
#endregion
double[][] dataPoints = new double[2][];
dataPoints[0] = xExperimental;
dataPoints[1] = yExperimental;
Net.Kniaz.LMA.LMA algorithm = new Net.Kniaz.LMA.LMA(f, parametrosEstimados,
dataPoints, null, new GeneralMatrix(2, 2), 1d - 30, 100);
algorithm.Fit();
for (int i = 0; i < parametrosEstimados.Length; i++)
{
Trace.WriteLine("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
}
public void Produto1724Teste()
{
LMAFunction f = new FuncaoGaussianaAcumulada();
double[] parametrosEstimados = new[] { 0.111989183, 0.735 };
#region Dados Experimentais
double[] xExperimental = new[]
{
0,
0.02,
0.04,
0.06,
0.08,
0.1,
0.12,
0.14,
0.16,
0.18,
0.2,
0.22,
0.24,
0.26,
0.28,
0.3,
0.32,
0.34,
0.36,
0.38,
0.4,
0.42,
0.44,
0.46,
0.48,
0.5,
0.52,
0.54,
0.56,
0.58,
0.6,
0.62,
0.64,
0.66,
0.68,
0.7,
0.72,
0.74,
0.76,
0.78,
0.8,
0.82,
0.84,
0.86,
0.88,
0.9,
0.92,
0.94,
0.96
};
double[] yExperimental = new[]
{
0,
0,
0.01558,
0.02839,
0.04047,
0.05091,
0.05979,
0.06895,
0.07986,
0.09401,
0.11091,
0.12986,
0.15061,
0.17297,
0.19653,
0.22114,
0.2478,
0.27755,
0.31163,
0.35184,
0.396,
0.44082,
0.48298,
0.52204,
0.55988,
0.59661,
0.63235,
0.66734,
0.70202,
0.73575,
0.7677,
0.79702,
0.82366,
0.84807,
0.87005,
0.88941,
0.90594,
0.91933,
0.92999,
0.93881,
0.94672,
0.95361,
0.95951,
0.96473,
0.96941,
0.97359,
0.97704,
0.97868,
0.97878
};
#endregion
double[][] dataPoints = new double[2][];
dataPoints[0] = xExperimental;
dataPoints[1] = yExperimental;
Net.Kniaz.LMA.LMA algorithm = new Net.Kniaz.LMA.LMA(f, parametrosEstimados,
dataPoints, null, new GeneralMatrix(2, 2), 1d - 30, 100);
algorithm.Fit();
for (int i = 0; i < parametrosEstimados.Length; i++)
{
Trace.WriteLine("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
}
public void Produto0952Teste()
{
LMAFunction f = new FuncaoGaussianaAcumulada();
double[] parametrosEstimados = new[] { 0.111989183, 0.735 };
#region Dados Experimentais
double[] xExperimental = new[]
{
0,
0.02,
0.04,
0.06,
0.08,
0.1,
0.12,
0.14,
0.16,
0.18,
0.2,
0.22,
0.24,
0.26,
0.28,
0.3,
0.32,
0.34,
0.36,
0.38,
0.4,
0.42,
0.44,
0.46,
0.48,
0.5,
0.52,
0.54,
0.56,
0.58,
0.6,
0.62,
0.64,
0.66,
0.68,
0.7,
0.72,
0.74,
0.76,
0.78,
0.8,
0.82,
0.84,
0.86,
0.88,
0.9,
0.92,
0.94,
0.96
};
double[] yExperimental = new[]
{
0,
0.00608,
0.01391,
0.02146,
0.02825,
0.03357,
0.03764,
0.04171,
0.04676,
0.05379,
0.06234,
0.07212,
0.08319,
0.09557,
0.10882,
0.12271,
0.13817,
0.15615,
0.17769,
0.20325,
0.23188,
0.2624,
0.29354,
0.32523,
0.35833,
0.39221,
0.42622,
0.45978,
0.49319,
0.52665,
0.56012,
0.59358,
0.62763,
0.66244,
0.69672,
0.72918,
0.75868,
0.78573,
0.81087,
0.83445,
0.85676,
0.87774,
0.89717,
0.91506,
0.93141,
0.94569,
0.95773,
0.96857,
0.97905
};
#endregion
double[][] dataPoints = new double[2][];
dataPoints[0] = xExperimental;
dataPoints[1] = yExperimental;
Net.Kniaz.LMA.LMA algorithm = new Net.Kniaz.LMA.LMA(f, parametrosEstimados,
dataPoints, null, new GeneralMatrix(2, 2), 1d - 30, 100);
algorithm.Fit();
for (int i = 0; i < parametrosEstimados.Length; i++)
{
Trace.WriteLine("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
}
public void FeedTeste()
{
LMAFunction f = new FuncaoGaussianaAcumulada();
double[] parametrosEstimados = new[] { 0.111989183, 0.735 };
#region Dados Experimentais
double[] xExperimental = new[]
{
0,
0.02,
0.04,
0.06,
0.08,
0.1,
0.12,
0.14,
0.16,
0.18,
0.2,
0.22,
0.24,
0.26,
0.28,
0.3,
0.32,
0.34,
0.36,
0.38,
0.4,
0.42,
0.44,
0.46,
0.48,
0.5,
0.52,
0.54,
0.56,
0.58,
0.6,
0.62,
0.64,
0.66,
0.68,
0.7,
0.72,
0.74,
0.76,
0.78,
0.8,
0.82,
0.84,
0.86,
0.88,
0.9,
0.92,
0.94,
0.96
};
double[] yExperimental = new[]
{
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0.02532,
0.03191,
0.03557,
0.03855,
0.04199,
0.05473,
0.07439,
0.09963,
0.1324,
0.17218,
0.222,
0.2795,
0.34357,
0.41488,
0.48759,
0.55907,
0.62985,
0.69556,
0.75486,
0.8067,
0.85443,
0.89529,
0.9253,
0.94629,
0.96257,
0.97404,
0.98309
};
#endregion
double[][] dataPoints = new double[2][];
dataPoints[0] = xExperimental;
dataPoints[1] = yExperimental;
Net.Kniaz.LMA.LMA algorithm = new Net.Kniaz.LMA.LMA(f, parametrosEstimados,
dataPoints, null, new GeneralMatrix(parametrosEstimados.Length, parametrosEstimados.Length), 1d - 30, 100);
algorithm.Fit();
for (int i = 0; i < parametrosEstimados.Length; i++)
{
Trace.WriteLine("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
}
public void Produto0383Teste()
{
LMAFunction f = new FuncaoGaussianaAcumulada();
double[] parametrosEstimados = new[] { 0.111989183, 0.735 };
#region Dados Experimentais
double[] xExperimental = new[]
{
0,
0.02,
0.04,
0.06,
0.08,
0.1,
0.12,
0.14,
0.16,
0.18,
0.2,
0.22,
0.24,
0.26,
0.28,
0.3,
0.32,
0.34,
0.36,
0.38,
0.4,
0.42,
0.44,
0.46,
0.48,
0.5,
0.52,
0.54,
0.56,
0.58,
0.6,
0.62,
0.64,
0.66,
0.68,
0.7,
0.72,
0.74,
0.76,
0.78,
0.8,
0.82,
0.84,
0.86,
0.88,
0.9,
0.92,
0.94,
0.96
};
double[] yExperimental = new[]
{
0,
0,
0.00874,
0.0121,
0.01537,
0.01847,
0.02116,
0.02346,
0.02575,
0.02838,
0.03166,
0.0356,
0.03978,
0.04442,
0.04979,
0.05615,
0.06377,
0.07248,
0.08224,
0.09298,
0.10462,
0.11696,
0.12955,
0.14288,
0.15755,
0.17419,
0.1933,
0.21393,
0.23625,
0.26089,
0.28852,
0.31983,
0.35482,
0.39311,
0.43451,
0.47878,
0.52576,
0.57747,
0.63319,
0.69075,
0.74798,
0.802,
0.85845,
0.91109,
0.94528,
0.96223,
0.97008,
0.97396,
0.97589
};
#endregion
double[][] dataPoints = new double[2][];
dataPoints[0] = xExperimental;
dataPoints[1] = yExperimental;
Net.Kniaz.LMA.LMA algorithm = new Net.Kniaz.LMA.LMA(f, parametrosEstimados,
dataPoints, null, new GeneralMatrix(2, 2), 1d - 30, 100);
algorithm.Fit();
for (int i = 0; i < parametrosEstimados.Length; i++)
{
Trace.WriteLine("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
}
public void Produto0383Teste()
{
var tempo = Math.Exp(0.383);
FuncaoHidrocraqueamento f = new FuncaoHidrocraqueamento(8, 0.688622664823698, 0.186665545625228);
f.mensagens = escreverMensagens;
double alfa = 1.35;
double kMax = 1.35; //1/hora;
double a0 = 6.41;
double a1 = 28.15;
double delta = 2.6667e-5;
double[] parametrosSugeridos = new[] {a0,a1};
#region dmom/dt Calculados a partir da média e desvio padrão conhecidos (calculados)
double[] xExperimental = new[] //Ordem do polinomio
{
0.0,
1.0,
2.0,
3.0,
4.0,
5.0,
6.0,
7.0,
8.0,
9.0,
10.0,
11.0,
12.0,
13.0,
14.0,
15.0
};
double[] yExperimental = new[]
{
0.0,
-0.169853777,
-0.193208729,
-0.169711401,
-0.134584682,
-0.100332106,
-0.070889307,
-0.046939058,
-0.02800316,
-0.013274678,
-0.001938629,
0.006717949,
0.013281326,
0.018218895,
0.021897241,
0.024601441
};
#endregion
double[][] dataPoints = new double[2][];
dataPoints[0] = xExperimental;
dataPoints[1] = yExperimental;
Net.Kniaz.LMA.LMA algorithm = new Net.Kniaz.LMA.LMA(escreverMensagens, f, parametrosSugeridos,
dataPoints, null, new GeneralMatrix(parametrosSugeridos.Length, parametrosSugeridos.Length), 1d - 30, 100);
algorithm.Fit();
for (int i = 0; i < parametrosSugeridos.Length; i++)
{
escreverMensagens("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
}
public void LaxminaraEstimationTeste()
{
LaxminaraTeste f = new LaxminaraTeste(null);
double alfa = 1.35;
double kMax = 1.35; //1/hora;
double a0 = 6.41;
double a1 = 28.15;
double delta = 2.6667e-5;
double[] parametrosSugeridos = new[] {alfa, kMax,a0,a1};
#region Dados Experimentais
double[] xExperimental = new[] //Ordem do polinomio
{
0.0,
1.0,
2.0,
3.0,
4.0,
5.0,
6.0,
7.0,
8.0,
9.0,
10.0,
11.0
};
double[] yExperimental = new[]
{
1.0,
0.72317444741327097,
0.53437823495320125,
0.40292206645505568 ,
0.30958307055555123,
0.24207872555219578 ,
0.192409225454721 ,
0.15526760641360315 ,
0.12707117279007443 ,
0.10536080255783097 ,
0.088421883423926081,
0.075041064810312863
};
#endregion
double[][] dataPoints = new double[2][];
dataPoints[0] = xExperimental;
dataPoints[1] = yExperimental;
Net.Kniaz.LMA.LMA algorithm = new Net.Kniaz.LMA.LMA(escreverMensagens, f, parametrosSugeridos,
dataPoints, null, new GeneralMatrix(parametrosSugeridos.Length, parametrosSugeridos.Length), 1d - 30,
100);
algorithm.Fit();
for (int i = 0; i < parametrosSugeridos.Length; i++)
{
escreverMensagens("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
}
public void FeedTeste()
{
LMAFunction f = new FuncaoGama();
double[] parametrosEstimados = new[] { 1.0, 10, 0.3 };
#region Dados Experimentais
double[] xExperimental = new[]
{
0,
0.05,
0.1,
0.15,
0.2,
0.25,
0.3,
0.35,
0.4,
0.43,
0.45,
0.47,
0.49,
0.51,
0.53,
0.55,
0.57,
0.59,
0.61,
0.63,
0.65,
0.67,
0.69,
0.71,
0.73,
0.75,
0.77,
0.79,
0.81,
0.83,
0.85,
0.87,
0.89,
0.91,
0.93,
0.95,
0.97,
1
};
double[] yExperimental = new[]
{
0,
0.000477354,
0.000954709,
0.001432063,
0.001909417,
0.002386771,
0.002864126,
0.00334148,
0.003818834,
0.004105247,
0.00777,
0.00485,
0.0031,
0.00267,
0.00787,
0.01618,
0.02244,
0.02912,
0.03585,
0.04481,
0.05397,
0.0607,
0.06801,
0.07284,
0.0717,
0.07164,
0.0687,
0.0627,
0.05525,
0.04971,
0.04483,
0.03567,
0.02498,
0.01816,
0.01397,
0.00995,
0.00872,
0.01255
};
#endregion
double[][] dataPoints = new double[2][];
dataPoints[0] = xExperimental;
dataPoints[1] = yExperimental;
Net.Kniaz.LMA.LMA algorithm = new Net.Kniaz.LMA.LMA(f, parametrosEstimados,
dataPoints, null, new GeneralMatrix(3, 3), 1d - 30, 100);
algorithm.Fit();
for (int i = 0; i < parametrosEstimados.Length; i++)
{
Trace.WriteLine("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
}
public void FeedAdam2012Teste()
{
LMAFunction f = new FuncaoGama();
double[] parametrosEstimados = new[] {110 ,6.0, 2.0, 10.0 };
#region Dados Experimentais
double[] xExperimental = new[]
{
6,
6.5,
7,
7.5,
8,
8.5,
9,
9.5,
10,
10.5,
11,
11.5,
12,
12.5,
13,
13.5,
14,
14.5,
15,
15.5,
16,
16.5,
17,
17.5,
18,
18.5,
19,
19.5,
20,
20.5,
21,
21.5,
22,
22.5,
23,
23.5,
24,
24.5,
25,
25.5,
26,
26.5,
27,
27.5,
28,
28.5,
29,
29.5,
30,
30.5,
31,
31.5,
32,
32.5,
33,
33.5,
34,
34.5,
35,
35.5,
36,
36.5,
37,
37.5,
38,
38.5,
39,
39.5,
40,
40.5,
41,
41.5,
42,
42.5,
43,
43.5,
44,
44.5,
45,
45.5,
46,
46.5,
47,
47.5,
48,
48.5,
49,
49.5,
50,
50.5,
51,
51.5,
52,
52.5,
53,
53.5,
54,
54.5,
55,
55.5,
56,
56.5,
57,
57.5,
58,
58.5,
59,
59.5,
60,
60.5,
61,
61.5,
62,
62.5,
63,
63.5,
64,
64.5,
65,
65.5,
66,
66.5,
67,
67.5,
68,
68.5,
69,
69.5
};
double[] yExperimental = new[]
{
0.05038,
0.26068,
0.63623,
0.98765,
1.34988,
1.70814,
2.07049,
2.46031,
2.8452,
3.13967,
3.36847,
3.54668,
3.69239,
3.81627,
3.90255,
3.94637,
3.96881,
3.99722,
4.01619,
4.00553,
3.98141,
3.95254,
3.91177,
3.89293,
3.90277,
3.85827,
3.76256,
3.70522,
3.65271,
3.58838,
3.51878,
3.45647,
3.40999,
3.37829,
3.35271,
3.34001,
3.34441,
3.30962,
3.26256,
3.22453,
3.16822,
2.77531,
2.21383,
2.44192,
2.65645,
2.5645,
2.39322,
2.26306,
2.13443,
2.00384,
1.87456,
1.76221,
1.66783,
1.59939,
1.54273,
1.47008,
1.41341,
1.4354,
1.43696,
1.39685,
1.34782,
1.30362,
1.26077,
1.22248,
1.18638,
1.14808,
1.11094,
1.11799,
1.11113,
1.03607,
0.96056,
0.935,
0.95218,
0.95174,
0.92821,
0.90443,
0.87775,
0.80971,
0.72396,
0.72258,
0.74405,
0.669,
0.57887,
0.54087,
0.51708,
0.49078,
0.46682,
0.44668,
0.43057,
0.41281,
0.39397,
0.37357,
0.35218,
0.33123,
0.31164,
0.29456,
0.27949,
0.26638,
0.25576,
0.24709,
0.23974,
0.23362,
0.22827,
0.22338,
0.21878,
0.21436,
0.21001,
0.20563,
0.20107,
0.19675,
0.19276,
0.18892,
0.18502,
0.18077,
0.17552,
0.16389,
0.14573,
0.19372,
0.2433,
0.22274,
0.18939,
0.15281,
0.11896,
0.09803,
0.08244,
0.06956,
0.05915,
0.05214
};
#endregion
double[][] dataPoints = new double[2][];
dataPoints[0] = xExperimental;
dataPoints[1] = yExperimental;
Net.Kniaz.LMA.LMA algorithm = new Net.Kniaz.LMA.LMA(f, parametrosEstimados,
dataPoints, null, new GeneralMatrix(parametrosEstimados.Length, parametrosEstimados.Length), 1d - 30, 100);
algorithm.Fit();
for (int i = 0; i < parametrosEstimados.Length; i++)
{
Trace.WriteLine("Parameter" + i.ToString() + " " + algorithm.Parameters[i].ToString());
}
}
