/// <summary>
/// This method returns the percentage of the given Amino Acid in the entire UniProt database.
/// </summary>
/// <param name="aminoAcidCode"></param>
/// <returns></returns>
public static decimal AminoAcidCompositionInPercent(string aminoAcidCode)
{
if (aminoAcidCode == null)
{
throw new ArgumentNullException(nameof(aminoAcidCode));
}
return(AminoAcidCompositionInPercent(AminoAcidConversions.AminoAcidNameToNumber(aminoAcidCode)));
}
public void IncrementAminoAcidCount(string aminoAcidCode, decimal incrementValue = 1)
{
if (string.IsNullOrEmpty(aminoAcidCode))
{
throw new ArgumentOutOfRangeException(nameof(aminoAcidCode));
}
IncrementAminoAcidCount(AminoAcidConversions.AminoAcidNameToNumber(aminoAcidCode), incrementValue);
}
public void IncrementAminoAcidCount(char aminoAcidCode, decimal incrementValue = 1)
{
if (!ParameterValidation.IsAminoAcidCodeValid(aminoAcidCode))
{
throw new ArgumentOutOfRangeException(nameof(aminoAcidCode));
}
IncrementAminoAcidCount(AminoAcidConversions.AminoAcidNameToNumber(aminoAcidCode), incrementValue);
}
public static string FindProteinInterfaceAminoAcidCommonPropertiesMotif(List <string> proteinInterfaceSequenceList, AminoAcidPropertyMatchType aminoAcidPropertyMatchType, double matchValue = 0)
{
if (proteinInterfaceSequenceList == null)
{
throw new ArgumentNullException(nameof(proteinInterfaceSequenceList));
}
var totalProteinInterfaces = proteinInterfaceSequenceList.Count;
var proteinInterfaceLength = proteinInterfaceSequenceList.Select(a => a.Length).Max();
var aminoAcidObjects = new AminoAcidProperties <bool> [TotalAminoAcids];
for (var aaIndex = 0; aaIndex < aminoAcidObjects.Length; aaIndex++)
{
aminoAcidObjects[aaIndex] = AminoAcidConversions.AminoAcidNumberToAminoAcidObject(aaIndex + 1);
}
var aminoAcidPositionCount = new AminoAcidProperties <int> [proteinInterfaceLength];
for (var position = 0; position < aminoAcidPositionCount.Length; position++)
{
aminoAcidPositionCount[position] = new AminoAcidProperties <int>();
}
var motifs = new List <string>();
for (int positionIndex = 0; positionIndex < proteinInterfaceLength; positionIndex++)
{
string positionMotif = "";
foreach (var aaCode in proteinInterfaceSequenceList.Where(a => a.Length > positionIndex).Select(a => a[positionIndex]).Distinct().ToArray())
{
if (!char.IsLetterOrDigit(aaCode) || NonStandardAminoAcids.Contains(aaCode))
{
continue;
}
var aminoAcid = aminoAcidObjects[AminoAcidConversions.AminoAcidNameToNumber(aaCode) - 1];
var matches = AminoAcidConversions.ListAminoAcidsByProperty(aminoAcid, aminoAcidPropertyMatchType, matchValue);
positionMotif += string.Join("", matches.Where(a => !positionMotif.Contains(a) && !NonStandardAminoAcids.Contains(a)).ToArray());
}
motifs.Add(positionMotif);
}
return(MotifFormatter(motifs));
}
public static int[] ConvertAminoAcidNameCodeToSubgroupNumbers(EnumAminoAcidGroups enumAminoAcidGroups, char aminoAcidNameCode)
{
return(ConvertAminoAcidNumberToSubgroupNumbers(enumAminoAcidGroups, AminoAcidConversions.AminoAcidNameToNumber(aminoAcidNameCode)));
}
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);
}
/// <summary>
/// IncrementAminoAcidCount
/// </summary>
/// <param name="aminoAcidCodeA"></param>
/// <param name="aminoAcidCodeB"></param>
/// <param name="incrementValue"></param>
public void IncrementAminoAcidCount(string aminoAcidCodeA, string aminoAcidCodeB, decimal incrementValue = 1.0m)
{
IncrementAminoAcidCount(AminoAcidConversions.AminoAcidNameToNumber(aminoAcidCodeA), AminoAcidConversions.AminoAcidNameToNumber(aminoAcidCodeB), incrementValue);
}
public static bool IsAminoAcidCodeValid(string aminoAcidNameOrCode)
{
int aminoAcidNumber = AminoAcidConversions.AminoAcidNameToNumber(aminoAcidNameOrCode);
return(IsAminoAcidNumberValid(aminoAcidNumber));
}
