public static string TransferTo(this Aminoacid from, Aminoacid to, out int mutationCount)
{
var fromCodes = from.Codes;
var toCodes = to.Codes;
if (fromCodes.Length == 0 || toCodes.Length == 0)
{
mutationCount = int.MaxValue;
return(string.Empty);
}
var lst = (from f in fromCodes
from t in toCodes
let m = TransferTo(f, t)
orderby m
select new { From = f, To = t, TransCost = m }).ToList();
var min = (from l in lst
where l.TransCost == lst[0].TransCost
select l).ToList();
mutationCount = min[0].TransCost;
return((from m in min
let r = MyConvert.Format("{0}->{1}", m.From, m.To)
select r).Merge(" ! "));
}
public void TestGetAtomMassPercent()
{
Aminoacid aa = new Aminoacid();
aa.Initialize('G', "Glydddddd", 57.02147, 57.05, "Glycine", "C2H3NO", true, "", 2.1);
double atomCPercent = aa.GetAtomMassPercent(Atom.C);
Assert.AreEqual(Atom.C.MonoMass * 2 / aa.MonoMass, atomCPercent, 0.0001);
}
private static bool DoIsRnaEditing(Aminoacid from, Aminoacid to, ref string mutationstr)
{
var fromCodes = from.Codes;
var toCodes = to.Codes;
var lst = (from f in fromCodes
from t in toCodes
let m = TransferTo(f, t)
where m == 1
select new { From = f, To = t, TransCost = m }).ToList();
foreach (var m in lst)
{
for (int i = 0; i < m.From.Length; i++)
{
//if (m.From[i] == 'T' && m.To[i] == 'C')
if (m.From[i] == 'A' && m.To[i] == 'G')
{
mutationstr = string.Format("{0}->{1}", m.From, m.To);
return(true);
}
}
}
return(false);
}
public ProteinCarbonRangePredictor()
{
var aas = new Aminoacids();
this.maxCarbonPercentAminoacid = aas.GetMaxCarbonPercentAminoacid();
this.minCarbonPercentAminoacid = aas.GetMinCarbonPercentAminoacid();
}
public void TestInitialize()
{
Aminoacid aa = new Aminoacid();
Assert.AreEqual(false, aa.Visible);
aa.Initialize('G', "Glydddddd", 57.02147, 57.05, "Glycine", "C2H3NO", true, "", 2.1);
Assert.AreEqual("Gly", aa.ThreeName);
Assert.AreEqual(57, aa.NominalMass);
Assert.AreEqual("G Gly 57.0215 57.05 Glycine C2H3NO", aa.ToString());
}
/// <summary>从本地加载氨基酸数据 </summary>
public static async Task LoadDataAsync()
{
if (loaded)
{
throw new PolymerModelException("PolymerModel has been loaded");
}
string aminoacidData = await IOUtil.ReadInStreamingAssetsAsync(string.Empty, "Aminoacid.csv");
AminoacidDt = CSVHelper.ReadCSVStr(aminoacidData);
string connectionData = await IOUtil.ReadInStreamingAssetsAsync(string.Empty, "Connection.csv");
ConnectionDt = CSVHelper.ReadCSVStr(connectionData);
//将Connection数据表转化为字典，有助于后续的数据查找
Dictionary <string, List <DataRow> > connectionDic = new Dictionary <string, List <DataRow> >();
foreach (DataRow connectionDataRow in ConnectionDt.Rows)
{
string type = connectionDataRow["Type"].ToString();
if (!connectionDic.ContainsKey(type))
{
connectionDic.Add(type, new List <DataRow>());
}
connectionDic[type].Add(connectionDataRow);
}
//遍历氨基酸数据表 + connectionDic 一起构建氨基酸数据结构
foreach (DataRow aminoacidDataRow in AminoacidDt.Rows)
{
string type = aminoacidDataRow["Type"].ToString();
AminoacidType aminoacidType = (AminoacidType)Enum.Parse(typeof(AminoacidType), type);
string chinese = aminoacidDataRow["Chinese"].ToString();
bool isStandard = aminoacidDataRow["IsStandard"].ToString() == "1";
string[] atomNames = aminoacidDataRow["Atoms"].ToString().Trim('[', ']').Split(' ');
Dictionary <KeyValuePair <string, string>, BondType> connection = new Dictionary <KeyValuePair <string, string>, BondType>();
if (connectionDic.ContainsKey(type))
{
//若该残基包含键
foreach (DataRow connectionDataRow in connectionDic[type])
{
string firstAtom = connectionDataRow["First"].ToString();
string secondAtom = connectionDataRow["Second"].ToString();
BondType bondType = (BondType)Enum.Parse(typeof(BondType), connectionDataRow["BondType"].ToString());
connection.Add(new KeyValuePair <string, string>(firstAtom, secondAtom), bondType);
}
}
Aminoacid aminoacid = new Aminoacid(aminoacidType, chinese, isStandard, atomNames, connection);
Aminoacid.Aminoacids.Add(aminoacid.Type, aminoacid);
}
loaded = true;
}
protected void WriteAtom(StreamWriter sw, Aminoacid samAA, Aminoacid refAA, Atom[] atoms, string atomName, bool outputZero = true)
{
foreach (var atom in atoms)
{
if (samAA.Composition.ContainsKey(atom) || refAA.Composition.ContainsKey(atom))
{
sw.WriteLine("{0}\t{1}\t{2}", atomName, samAA.Composition.ContainsKey(atom) ? samAA.Composition[atom] : 0, refAA.Composition.ContainsKey(atom) ? refAA.Composition[atom] : 0);
return;
}
}
if (outputZero)
{
sw.WriteLine("{0}\t0\t0", atomName);
}
}
public static bool IsRnaEditing(this Aminoacid from, Aminoacid to, out string mutationStr)
{
if (RnaEditingMap == null)
{
PrepareRnaEditingMap();
}
var pair = new Pair <char, char>(from.OneName, to.OneName);
if (RnaEditingMap.ContainsKey(pair))
{
mutationStr = RnaEditingMap[pair];
return(true);
}
mutationStr = string.Empty;
return(false);
}
/// <summary>解析Pdb文件数据</summary>
private void ParsePdbData(string str)
{
using (StringReader sr = new StringReader(str))
{
string record = null;//当前读取的记录
//蛋白质作用域***********/
string id = null;
string classification = null;
string publishDate = null;
Dictionary <string, Chain> chains = new Dictionary <string, Chain>();
Vector3 minPos = Vector3.zero;
Vector3 maxPos = Vector3.zero;
Vector3 centerPos = Vector3.zero; // 蛋白质的中心位置
//*************************/
//肽链作用域*************/
OXTAtom oxt = null;
Dictionary <int, AminoacidInProtein> seqAminoacids = new Dictionary <int, AminoacidInProtein>();
//*************************/
//氨基酸作用域***********/
char altloc = ' '; // 可替位置标示符
string resName = null;
string chainId = null;
int residueSeq = 0;
Dictionary <AtomInAminoacid, Vector3> atomInAminoacidPos = new Dictionary <AtomInAminoacid, Vector3>();
Dictionary <AtomInAminoacid, int> atomInAminoacidSerial = new Dictionary <AtomInAminoacid, int>();
//*************************/
AminoacidInProtein currentAminoacidInProtein = null;
bool completeLastAminoacid = true;//已完成上一个残基的读取
while ((record = sr.ReadLine()) != null)
{
//原子作用域
string title = record.Substring(0, 6);
if (title.StartsWith("HEADER"))
{
classification = record.Substring(10, 40).Trim(); //11-50
publishDate = record.Substring(50, 9); //51-59
id = record.Substring(62, 4); //63-66
}
else if (title.StartsWith("ATOM"))
{
//氨基酸残基相关部分
int lastResidueSeq = residueSeq;
residueSeq = int.Parse(record.Substring(22, 4).Trim()); //23-26列：残基序列号作为判断标志
if (lastResidueSeq != residueSeq && !completeLastAminoacid)
{
//若当前record为新的氨基酸残基的第一条记录(或记录为TER)
currentAminoacidInProtein = new AminoacidInProtein(altloc, resName, chainId, lastResidueSeq, atomInAminoacidPos, atomInAminoacidSerial);
seqAminoacids.Add(lastResidueSeq, currentAminoacidInProtein);
atomInAminoacidPos = new Dictionary <AtomInAminoacid, Vector3>();
atomInAminoacidSerial = new Dictionary <AtomInAminoacid, int>();
completeLastAminoacid = true;
}
else
{
completeLastAminoacid = false;
//record[16]是第17列，是用来标记同分异构体的，同分异构体的数据所在的行 在PDB文件里是挨在一起的，只需要显示同一种氨基酸的
//同分异构体里的一种异构体氨基酸就可以了，所以只需要PDB文件里的一种异构体氨基酸数据行。
if (record[16] != altloc)
{
continue; //若当前可替换标识符不是默认则跳过当前记录行
}
}
chainId = record.Substring(21, 1); //22
altloc = record[16]; //17
resName = record.Substring(17, 3); //18-20
//原子相关部分
string atomName = record.Substring(12, 4).Trim(); //13-16
int atomSerial = int.Parse(record.Substring(6, 5).Trim()); //7-11
float x = float.Parse(record.Substring(30, 8).Trim()); //31-38
float y = float.Parse(record.Substring(38, 8).Trim()); //39-46
float z = float.Parse(record.Substring(46, 8).Trim()); //47-54
Vector3 pos = new Vector3(x, y, z);
if (minPos == Vector3.zero)
{
minPos = pos;
}
if (maxPos == Vector3.zero)
{
maxPos = pos;
}
if (x > maxPos.x)
{
maxPos.x = x;
}
if (y > maxPos.y)
{
maxPos.y = y;
}
if (z > maxPos.z)
{
maxPos.z = z;
}
if (x < minPos.x)
{
minPos.x = x;
}
if (y < minPos.y)
{
minPos.y = y;
}
if (z < minPos.z)
{
minPos.z = z;
}
if (atomName == "OXT")
{
oxt = new OXTAtom(atomSerial, pos);
}
else
{
atomInAminoacidPos.Add(Aminoacid.Generate(resName)[atomName], pos);
atomInAminoacidSerial.Add(Aminoacid.Generate(resName)[atomName], atomSerial);
}
}
else if (title.StartsWith("TER"))
{ //链结束，TER是判断链是否结束的标志位
//氨基酸残基结算
residueSeq = int.Parse(record.Substring(22, 4).Trim()); //23-26列：残基序列号用来记录当前氨基酸残基的序列号
currentAminoacidInProtein = new AminoacidInProtein(altloc, resName, chainId, residueSeq, atomInAminoacidPos, atomInAminoacidSerial);
seqAminoacids.Add(residueSeq, currentAminoacidInProtein);
atomInAminoacidPos = new Dictionary <AtomInAminoacid, Vector3>();
atomInAminoacidSerial = new Dictionary <AtomInAminoacid, int>();
completeLastAminoacid = true;
//肽链结算
Chain chain = new Chain(chainId, seqAminoacids, oxt);
oxt = null;
seqAminoacids = new Dictionary <int, AminoacidInProtein>();
chains.Add(chain.ID, chain);
}
else if (title.StartsWith("HETATM"))
{ //非标准残基
}
else if (title.StartsWith("CONECT"))
{ //非标准残基间的原子连接关系
}
}
centerPos = new Vector3((minPos.x + maxPos.x) / 2, (minPos.y + maxPos.y) / 2, (minPos.z + maxPos.z) / 2);
Protein protein = new Protein(id, classification, publishDate, chains, centerPos);
GetModel <PdbLoaderModel>().ProteinData = protein;
Debug.Log("读取pdb完成");
}
}
