/// <summary>
/// TotalFromAminoAcidChainCompositionList method.
/// </summary>
/// <param name="aminoAcidChainCompositionList"></param>
/// <returns></returns>
public static AminoAcidChainComposition TotalFromAminoAcidChainCompositionList(List <AminoAcidChainComposition> aminoAcidChainCompositionList)
{
var aminoAcidChainCompositionTotal = new AminoAcidChainComposition("Total", "-");
lock (aminoAcidChainCompositionList)
{
foreach (AminoAcidChainComposition aminoAcidChainComposition in aminoAcidChainCompositionList)
{
for (int x = 0; x < AminoAcidTotals.TotalAminoAcids(); x++)
{
// note 1: array is zero based, amino acid numbers are one based
// note 2: IncrementAminoAcidCount method also increments all groups so only one call is required
aminoAcidChainCompositionTotal.IncrementAminoAcidCount(x + 1, aminoAcidChainComposition.AminoAcidGroupsCount[(int)AminoAcidGroups.AminoAcidGroups.EnumAminoAcidGroups.AminoAcids][x]);
}
}
}
return(aminoAcidChainCompositionTotal);
}
public static SpreadsheetCell[] SpreadsheetTitleRow()
{
var titleRow = new List <SpreadsheetCell>();
titleRow.Add(new SpreadsheetCell("Protein ID"));
titleRow.Add(new SpreadsheetCell("Chain ID"));
int totalAminoAcids = AminoAcidTotals.TotalAminoAcids();
for (int index = 0; index < totalAminoAcids; index++)
{
titleRow.Add(new SpreadsheetCell(AminoAcidConversions.AminoAcidNumberToCode1L(index + 1)));
}
titleRow.Add(new SpreadsheetCell("Total"));
return(titleRow.ToArray());
}
/// <summary>
/// This method returns the entire UniProt database composition as a chain.
/// </summary>
/// <returns></returns>
public static AminoAcidChainComposition AminoAcidCompositionAsChain()
{
var result = new AminoAcidChainComposition();
int totalAminoAcids = AminoAcidTotals.TotalAminoAcids();
for (int x = 0; x < totalAminoAcids; x++)
{
var aaPercentage = AminoAcidCompositionInPercent(x + 1);
var aaOriginal = (aaPercentage / 100) * TotalAminoAcidsInDatabase;
result.IncrementAminoAcidCount(x + 1, aaOriginal);
}
result.NumberSamples = TotalSamplesInDatabase;
result = AminoAcidChainComposition.ConvertToPercentage(result);
return(result);
}
public static AminoAcidPairCompositionMatrix ConvertToMatrix(AminoAcidChainComposition chain)
{
if (chain == null)
{
return(null);
}
var result = new AminoAcidPairCompositionMatrix();
int totalAminoAcids = AminoAcidTotals.TotalAminoAcids();
for (int x = 0; x < totalAminoAcids; x++)
{
for (int y = 0; y < totalAminoAcids; y++)
{
result.IncrementAminoAcidCount(x + 1, y + 1, (chain.AminoAcidGroupsCount[(int)AminoAcidGroups.AminoAcidGroups.EnumAminoAcidGroups.AminoAcids][x] * chain.AminoAcidGroupsCount[(int)AminoAcidGroups.AminoAcidGroups.EnumAminoAcidGroups.AminoAcids][y]) / 100);
}
}
return(result);
}
/// <summary>
/// This method returns a spreadsheet heat map of the entire UniProt sequence database.
/// </summary>
/// <returns></returns>
public static List <SpreadsheetCell[]> UniProtHeatMapSpreadsheet()
{
var spreadsheet = new List <SpreadsheetCell[]>();
//spreadsheet.Add("HM Entire UniProt Database"); // filename / worksheet name
spreadsheet.Add(new[] { new SpreadsheetCell("Amino Acid Heat Map - Entire UniProt Database Composition (Converted To Matrix)") }); // spreadsheet title
//spreadsheet.Add(new[] {new SpreadsheetCell(string.Empty), });
//spreadsheet.Add(new[] {new SpreadsheetCell("Amino Acid Heat Map - Entire UniProt Database - A to Z") }); // section title
//spreadsheet.AddRange(AminoAcidCompositionAsMatrix().SpreadsheetAminoAcidColorGroupsHeatMap());
foreach (AminoAcidGroups.AminoAcidGroups.EnumAminoAcidGroups enumAminoAcidGroups in Enum.GetValues(typeof(AminoAcidGroups.AminoAcidGroups.EnumAminoAcidGroups)))
{
spreadsheet.Add(new[] { new SpreadsheetCell(string.Empty), });
spreadsheet.Add(new[] { new SpreadsheetCell("Amino Acid Heat Map - Entire UniProt Database - Acid Groups " + enumAminoAcidGroups) }); // section title
spreadsheet.AddRange(AminoAcidCompositionAsMatrix().SpreadsheetAminoAcidColorGroupsHeatMap(enumAminoAcidGroups));
}
spreadsheet.Add(new[] { new SpreadsheetCell(string.Empty), });
spreadsheet.Add(new[] { new SpreadsheetCell("Amino Acid Heat Map - Entire UniProt Database - Original Data - A to Z") }); // section title
AminoAcidChainComposition c = AminoAcidCompositionAsChain();
var chain = new List <SpreadsheetCell>();
chain.Add(new SpreadsheetCell(string.Empty));
for (int i = 0; i < AminoAcidTotals.TotalAminoAcids(); i++)
{
chain.Add(new SpreadsheetCell(AminoAcidConversions.AminoAcidNumberToCode1L(i + 1)));
}
spreadsheet.Add(chain.ToArray());
chain = new List <SpreadsheetCell>();
chain.Add(new SpreadsheetCell(string.Empty));
for (int i = 0; i < AminoAcidTotals.TotalAminoAcids(); i++)
{
chain.Add(new SpreadsheetCell(c.AminoAcidGroupsCount[(int)AminoAcidGroups.AminoAcidGroups.EnumAminoAcidGroups.AminoAcids][i]));
}
spreadsheet.Add(chain.ToArray());
foreach (AminoAcidGroups.AminoAcidGroups.EnumAminoAcidGroups enumAminoAcidGroups in Enum.GetValues(typeof(AminoAcidGroups.AminoAcidGroups.EnumAminoAcidGroups)))
{
spreadsheet.Add(new[] { new SpreadsheetCell(string.Empty), });
spreadsheet.Add(new[] { new SpreadsheetCell("Amino Acid Heat Map - Entire UniProt Database - Original Data - Acid Groups " + enumAminoAcidGroups) }); // section title
var chainGroups = new List <SpreadsheetCell>();
chainGroups.Add(new SpreadsheetCell(string.Empty));
for (int i = 0; i < AminoAcidGroups.AminoAcidGroups.GetTotalSubgroups(enumAminoAcidGroups); i++)
{
chainGroups.Add(new SpreadsheetCell((i + 1)));
}
spreadsheet.Add(chainGroups.ToArray());
chainGroups = new List <SpreadsheetCell>();
chainGroups.Add(new SpreadsheetCell(string.Empty));
for (int i = 0; i < AminoAcidGroups.AminoAcidGroups.GetTotalSubgroups(enumAminoAcidGroups); i++)
{
chainGroups.Add(new SpreadsheetCell(c.AminoAcidGroupsCount[(int)enumAminoAcidGroups][i]));
}
spreadsheet.Add(chainGroups.ToArray());
}
return(spreadsheet);
}
public void TestListAminoAcidsByProperty()
{
var x = new AminoAcidProperties<string>()
{
//Acidic = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() {Acidic = true}),
Aliphatic = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() {Aliphatic = true}),
Aromatic = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() {Aromatic = true}),
Charged = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() {Charged = true}),
Hydrophobic = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() {Hydrophobic = true}),
Hydroxylic = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() {Hydroxylic = true}),
Negative = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() {Negative = true}),
Polar = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() {Polar = true}),
Positive = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() {Positive = true}),
Small = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() {Small = true}),
Sulphur = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() {Sulphur = true}),
Tiny = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() { Tiny = true }),
};
var uncommon = AminoAcidConversions.ListAminoAcidsByProperty(new AminoAcidProperties<bool>() {}, AminoAcidPropertyMatchType.AllMatch);
var y = new AminoAcidProperties<string>()
{
};
for (var i = 0; i < AminoAcidTotals.TotalAminoAcids(); i++)
{
var aa = AminoAcidConversions.AminoAcidNumberToAminoAcidObject(i + 1);
//if (aa.Acidic) y.Acidic += aa.Code1L;
if (aa.Aliphatic) y.Aliphatic += aa.Code1L;
if (aa.Aromatic) y.Aromatic += aa.Code1L;
if (aa.Charged) y.Charged += aa.Code1L;
if (aa.Hydrophobic) y.Hydrophobic += aa.Code1L;
if (aa.Hydroxylic) y.Hydroxylic += aa.Code1L;
if (aa.Negative) y.Negative += aa.Code1L;
if (aa.Polar) y.Polar += aa.Code1L;
if (aa.Positive) y.Positive += aa.Code1L;
if (aa.Small) y.Small += aa.Code1L;
if (aa.Sulphur) y.Sulphur += aa.Code1L;
if (aa.Tiny) y.Tiny += aa.Code1L;
}
//Console.WriteLine("Acidic: " + x.Acidic);
Console.WriteLine("Aliphatic: " + x.Aliphatic);
Console.WriteLine("Aromatic: " + x.Aromatic);
Console.WriteLine("Charged: " + x.Charged);
Console.WriteLine("Hydrophobic: " + x.Hydrophobic);
Console.WriteLine("Hydroxylic: " + x.Hydroxylic);
Console.WriteLine("Negative: " + x.Negative);
Console.WriteLine("Polar: " + x.Polar);
Console.WriteLine("Positive: " + x.Positive);
Console.WriteLine("Small: " + x.Small);
Console.WriteLine("Sulphur: " + x.Sulphur);
Console.WriteLine("Tiny: " + x.Tiny);
Console.WriteLine("Others: " + uncommon);
//Assert.AreEqual(string.Join(" ", y.Acidic.OrderBy(a=>a).ToArray()), string.Join(" ", x.Acidic.OrderBy(a=>a).ToArray()));
Assert.AreEqual(string.Join(" ", y.Aliphatic.OrderBy(a=>a).ToArray()), string.Join(" ", x.Aliphatic.OrderBy(a=>a).ToArray()));
Assert.AreEqual(string.Join(" ", y.Aromatic.OrderBy(a=>a).ToArray()), string.Join(" ", x.Aromatic.OrderBy(a=>a).ToArray()));
Assert.AreEqual(string.Join(" ", y.Charged.OrderBy(a=>a).ToArray()), string.Join(" ", x.Charged.OrderBy(a=>a).ToArray()));
Assert.AreEqual(string.Join(" ", y.Hydrophobic.OrderBy(a=>a).ToArray()), string.Join(" ", x.Hydrophobic.OrderBy(a=>a).ToArray()));
Assert.AreEqual(string.Join(" ", y.Hydroxylic.OrderBy(a=>a).ToArray()), string.Join(" ", x.Hydroxylic.OrderBy(a=>a).ToArray()));
Assert.AreEqual(string.Join(" ", y.Negative.OrderBy(a=>a).ToArray()), string.Join(" ", x.Negative.OrderBy(a=>a).ToArray()));
Assert.AreEqual(string.Join(" ", y.Polar.OrderBy(a=>a).ToArray()), string.Join(" ", x.Polar.OrderBy(a=>a).ToArray()));
Assert.AreEqual(string.Join(" ", y.Positive.OrderBy(a=>a).ToArray()), string.Join(" ", x.Positive.OrderBy(a=>a).ToArray()));
Assert.AreEqual(string.Join(" ", y.Small.OrderBy(a=>a).ToArray()), string.Join(" ", x.Small.OrderBy(a=>a).ToArray()));
Assert.AreEqual(string.Join(" ", y.Sulphur.OrderBy(a=>a).ToArray()), string.Join(" ", x.Sulphur.OrderBy(a=>a).ToArray()));
Assert.AreEqual(string.Join(" ", y.Tiny.OrderBy(a=>a).ToArray()), string.Join(" ", x.Tiny.OrderBy(a=>a).ToArray()));
}
public static MotifProfileSpreadsheetRecord Record(List <VectorProteinInterfaceWhole> vectorProteinInterfaceWholeList)
{
if (vectorProteinInterfaceWholeList == null || vectorProteinInterfaceWholeList.Count == 0)
{
return(null);
}
var maxProteinInterfaceLength = vectorProteinInterfaceWholeList.Select(a => a.ProteinInterfaceAminoAcids1L().Length).Max();
var totalAminoAcids = AminoAcidTotals.TotalAminoAcids();
var result = new MotifProfileSpreadsheetRecord
{
AminoAcidProfile = new decimal[maxProteinInterfaceLength][],
AverageProfile = new decimal[totalAminoAcids],
TotalFound = "" + vectorProteinInterfaceWholeList.Count,
};
var directionFwd = vectorProteinInterfaceWholeList.Count(a => !a.ReversedSequence);
var directionRev = vectorProteinInterfaceWholeList.Count - directionFwd;
if (directionFwd > 0 && directionRev == 0)
{
result.Direction = "Fwd";
}
else if (directionFwd == 0 && directionRev > 0)
{
result.Direction = "Rev";
}
else
{
result.Direction = "Mix";
}
for (var positionIndex = 0; positionIndex < result.AminoAcidProfile.Length; positionIndex++)
{
result.AminoAcidProfile[positionIndex] = new decimal[totalAminoAcids];
}
foreach (var record in vectorProteinInterfaceWholeList)
{
var aminoAcidCode1L = record.ProteinInterfaceAminoAcids1L();
for (int positionIndex = 0; positionIndex < aminoAcidCode1L.Length; positionIndex++)
{
var aa = aminoAcidCode1L[positionIndex];
var aaIndex = AminoAcidConversions.AminoAcidNameToNumber(aa) - 1;
result.AminoAcidProfile[positionIndex][aaIndex]++;
result.AverageProfile[aaIndex]++;
}
}
for (var positionIndex = 0; positionIndex < result.AminoAcidProfile.Length; positionIndex++)
{
var positionTotal = result.AminoAcidProfile[positionIndex].Sum();
for (var aaIndex = 0; aaIndex < totalAminoAcids; aaIndex++)
{
result.AminoAcidProfile[positionIndex][aaIndex] = (result.AminoAcidProfile[positionIndex][aaIndex] / positionTotal) * 100;
}
}
var averageTotal = result.AverageProfile.Sum();
for (var aaIndex = 0; aaIndex < totalAminoAcids; aaIndex++)
{
result.AverageProfile[aaIndex] = averageTotal != 0 ? (result.AverageProfile[aaIndex] / averageTotal) * 100 : 0;
}
return(result);
}
public static string[,] Spreadsheet(List <MotifProfileSpreadsheetRecord> motifProfileSpreadsheetRecordList)
{
if (motifProfileSpreadsheetRecordList == null)
{
throw new ArgumentNullException(nameof(motifProfileSpreadsheetRecordList));
}
var result = new List <string[]>();
var totalAminoAcids = AminoAcidTotals.TotalAminoAcids();
var sheetHeader = new List <string>()
{
"Motif Name",
"Motif Source",
"Direction",
"Total Found",
//"Total Found In Heterodimers",
//"Total Found In Homodimers",
"Profile Position",
};
sheetHeader.AddRange(AminoAcidConversions.AminoAcidCodeArray1L());
result.Add(sheetHeader.ToArray());
foreach (var record in motifProfileSpreadsheetRecordList.OrderByDescending(a => ProteinDataBankFileOperations.NullableTryParseInt32(a.TotalFound)))
{
result.Add(new string[] { });
var recordHeader = new List <string>()
{
record.MotifName,
record.MotifSource,
record.Direction,
record.TotalFound,
//record.TotalFoundInHeterodimers,
//record.TotalFoundInHomodimers,
"",
};
recordHeader.AddRange(AminoAcidConversions.AminoAcidCodeArray1L());
result.Add(recordHeader.ToArray());
for (var positionIndex = 0; positionIndex < record.AminoAcidProfile.Length; positionIndex++)
{
var row = new string[sheetHeader.Count];
row[sheetHeader.IndexOf("Profile Position")] = "" + (positionIndex + 1);
for (var aaIndex = 0; aaIndex < record.AminoAcidProfile[positionIndex].Length; aaIndex++)
{
row[aaIndex + sheetHeader.IndexOf("Profile Position") + 1] = $"{record.AminoAcidProfile[positionIndex][aaIndex]:0.00}";
}
result.Add(row);
}
var rowAverage = new string[sheetHeader.Count];
rowAverage[sheetHeader.IndexOf("Profile Position")] = "Average";
for (var aaIndex = 0; aaIndex < record.AverageProfile.Length; aaIndex++)
{
rowAverage[aaIndex + sheetHeader.IndexOf("Profile Position") + 1] = $"{record.AverageProfile[aaIndex]:0.00}";
}
result.Add(rowAverage);
}
return(ConvertTypes.StringJagged2DArrayTo2DArray(result.ToArray()));
}
