Team:TU-Munich/AnnotatorCode.js

From 2013.igem.org

Revision as of 20:16, 16 July 2013 by ChristopherW (Talk | contribs)

/**

*  DATA VALUES
*/

var amino_acids = {A:0,R:0,N:0,D:0,C:0,Q:0,E:0,G:0,I:0,H:0,K:0,L:0,M:0,F:0,P:0,S:0,T:0,W:0,Y:0,V:0};

// amino acid weights - http://web.expasy.org/findmod/findmod_masses.html#AA var amino_weights = { "A": 71.0788, "C": 103.1388, "D": 115.0886, "E": 129.1155, "F": 147.1766, "G": 57.0519, "H": 137.1411, "I": 113.1594, "K": 128.1741, "L": 113.1594, "M": 131.1926, "N": 114.1038, "P": 97.1167, "Q": 128.1307, "R": 156.1875, "S": 87.0782, "T": 101.1051, "V": 99.1326, "W": 186.2132, "Y": 163.1760 }; var water_weight = 18.01528; //average molecular weight of one molecule of water

// Kyte & Doolittle index of hydrophobicity var kd = { 'A': 1.8, 'R':-4.5, 'N':-3.5, 'D':-3.5, 'C': 2.5,

     'Q':-3.5, 'E':-3.5, 'G':-0.4, 'H':-3.2, 'I': 4.5,
     'L': 3.8, 'K':-3.9, 'M': 1.9, 'F': 2.8, 'P':-1.6,
     'S':-0.8, 'T':-0.7, 'W':-0.9, 'Y':-1.3, 'V': 4.2 };

// Flexibility // Normalized flexibility parameters (B-values), average (Vihinen et al., 1994) var Flex= { 'A': 0.984, 'C': 0.906, 'E': 1.094, 'D': 1.068,

      'G': 1.031, 'F': 0.915, 'I': 0.927, 'H': 0.950,
      'K': 1.102, 'M': 0.952, 'L': 0.935, 'N': 1.048,
      'Q': 1.037, 'P': 1.049, 'S': 1.046, 'R': 1.008,
      'T': 0.997, 'W': 0.904, 'V': 0.931, 'Y': 0.929};

// Hydrophilicity // 1 Hopp & Wood // Proc. Natl. Acad. Sci. U.S.A. 78:3824-3828(1981). var hw = { 'A':-0.5, 'R': 3.0, 'N': 0.2, 'D': 3.0, 'C':-1.0,

     'Q': 0.2, 'E': 3.0, 'G': 0.0, 'H':-0.5, 'I':-1.8,
     'L':-1.8, 'K': 3.0, 'M':-1.3, 'F':-2.5, 'P': 0.0,
     'S': 0.3, 'T':-0.4, 'W':-3.4, 'Y':-2.3, 'V':-1.5 };

// Surface accessibility // 1 Emini Surface fractional probability var em = { 'A': 0.815, 'R': 1.475, 'N': 1.296, 'D': 1.283, 'C': 0.394,

     'Q': 1.348, 'E': 1.445, 'G': 0.714, 'H': 1.180, 'I': 0.603,
     'L': 0.603, 'K': 1.545, 'M': 0.714, 'F': 0.695, 'P': 1.236,
     'S': 1.115, 'T': 1.184, 'W': 0.808, 'Y': 1.089, 'V': 0.606 };

// 2 Janin Interior to surface transfer energy scale var ja = { 'A': 0.28, 'R':-1.14, 'N':-0.55, 'D':-0.52, 'C': 0.97,

     'Q':-0.69, 'E':-1.01, 'G': 0.43, 'H':-0.31, 'I': 0.60,
     'L': 0.60, 'K':-1.62, 'M': 0.43, 'F': 0.46, 'P':-0.42,
     'S':-0.19, 'T':-0.32, 'W': 0.29, 'Y':-0.15, 'V': 0.60 };

// A two dimentional dictionary for calculating the instability index. // Guruprasad K., Reddy B.V.B., Pandit M.W. Protein Engineering 4:155-161(1990). // It is based on dipeptide values therefore the vale for the dipeptide DG is DIWV['D']['G']. var DIWV = { 'A': {'A': 1.0, 'C': 44.94, 'E': 1.0, 'D': -7.49,

             'G': 1.0, 'F': 1.0, 'I': 1.0, 'H': -7.49,
             'K': 1.0, 'M': 1.0, 'L': 1.0, 'N': 1.0,
             'Q': 1.0, 'P': 20.26, 'S': 1.0, 'R': 1.0,
             'T': 1.0, 'W': 1.0, 'V': 1.0, 'Y': 1.0 },
       'C': {'A': 1.0, 'C': 1.0, 'E': 1.0, 'D': 20.26,
             'G': 1.0, 'F': 1.0, 'I': 1.0, 'H': 33.60,
             'K': 1.0, 'M': 33.60, 'L': 20.26, 'N': 1.0,
             'Q': -6.54, 'P': 20.26, 'S': 1.0, 'R': 1.0,
             'T': 33.60, 'W': 24.68, 'V': -6.54, 'Y': 1.0},
       'E': {'A': 1.0, 'C': 44.94, 'E': 33.60, 'D': 20.26,
             'G': 1.0, 'F': 1.0, 'I': 20.26, 'H': -6.54,
             'K': 1.0, 'M': 1.0, 'L': 1.0, 'N': 1.0,
             'Q': 20.26, 'P': 20.26, 'S': 20.26, 'R': 1.0,
             'T': 1.0, 'W': -14.03, 'V': 1.0, 'Y': 1.0},
       'D': {'A': 1.0, 'C': 1.0, 'E': 1.0, 'D': 1.0,
             'G': 1.0, 'F': -6.54, 'I': 1.0, 'H': 1.0,
             'K': -7.49, 'M': 1.0, 'L': 1.0, 'N': 1.0,
             'Q': 1.0, 'P': 1.0, 'S': 20.26, 'R': -6.54,
             'T': -14.03, 'W': 1.0, 'V': 1.0, 'Y': 1.0},
       'G': {'A': -7.49, 'C': 1.0, 'E': -6.54, 'D': 1.0,
             'G': 13.34, 'F': 1.0, 'I': -7.49, 'H': 1.0,
             'K': -7.49, 'M': 1.0, 'L': 1.0, 'N': -7.49,
             'Q': 1.0, 'P': 1.0, 'S': 1.0, 'R': 1.0,
             'T': -7.49, 'W': 13.34, 'V': 1.0, 'Y': -7.49},
       'F': {'A': 1.0, 'C': 1.0, 'E': 1.0, 'D': 13.34,
             'G': 1.0, 'F': 1.0, 'I': 1.0, 'H': 1.0,
             'K': -14.03, 'M': 1.0, 'L': 1.0, 'N': 1.0,
             'Q': 1.0, 'P': 20.26, 'S': 1.0, 'R': 1.0,
             'T': 1.0, 'W': 1.0, 'V': 1.0, 'Y': 33.601},
       'I': {'A': 1.0, 'C': 1.0, 'E': 44.94, 'D': 1.0,
             'G': 1.0, 'F': 1.0, 'I': 1.0, 'H': 13.34,
             'K': -7.49, 'M': 1.0, 'L': 20.26, 'N': 1.0,
             'Q': 1.0, 'P': -1.88, 'S': 1.0, 'R': 1.0,
             'T': 1.0, 'W': 1.0, 'V': -7.49, 'Y': 1.0},
       'H': {'A': 1.0, 'C': 1.0, 'E': 1.0, 'D': 1.0,
             'G': -9.37, 'F': -9.37, 'I': 44.94, 'H': 1.0,
             'K': 24.68, 'M': 1.0, 'L': 1.0, 'N': 24.68,
             'Q': 1.0, 'P': -1.88, 'S': 1.0, 'R': 1.0,
             'T': -6.54, 'W': -1.88, 'V': 1.0, 'Y': 44.94},
       'K': {'A': 1.0, 'C': 1.0, 'E': 1.0, 'D': 1.0,
             'G': -7.49, 'F': 1.0, 'I': -7.49, 'H': 1.0,
             'K': 1.0, 'M': 33.60, 'L': -7.49, 'N': 1.0,
             'Q': 24.64, 'P': -6.54, 'S': 1.0, 'R': 33.60,
             'T': 1.0, 'W': 1.0, 'V': -7.49, 'Y': 1.0},
       'M': {'A': 13.34, 'C': 1.0, 'E': 1.0, 'D': 1.0,
             'G': 1.0, 'F': 1.0, 'I': 1.0, 'H': 58.28,
             'K': 1.0, 'M': -1.88, 'L': 1.0, 'N': 1.0,
             'Q': -6.54, 'P': 44.94, 'S': 44.94, 'R': -6.54,
             'T': -1.88, 'W': 1.0, 'V': 1.0, 'Y': 24.68},
       'L': {'A': 1.0, 'C': 1.0, 'E': 1.0, 'D': 1.0,
             'G': 1.0, 'F': 1.0, 'I': 1.0, 'H': 1.0,
             'K': -7.49, 'M': 1.0, 'L': 1.0, 'N': 1.0,
             'Q': 33.60, 'P': 20.26, 'S': 1.0, 'R': 20.26,
             'T': 1.0, 'W': 24.68, 'V': 1.0, 'Y': 1.0},
       'N': {'A': 1.0, 'C': -1.88, 'E': 1.0, 'D': 1.0,
             'G': -14.03, 'F': -14.03, 'I': 44.94, 'H': 1.0,
             'K': 24.68, 'M': 1.0, 'L': 1.0, 'N': 1.0,
             'Q': -6.54, 'P': -1.88, 'S': 1.0, 'R': 1.0,
             'T': -7.49, 'W': -9.37, 'V': 1.0, 'Y': 1.0},
       'Q': {'A': 1.0, 'C': -6.54, 'E': 20.26, 'D': 20.26,
             'G': 1.0, 'F': -6.54, 'I': 1.0, 'H': 1.0,
             'K': 1.0, 'M': 1.0, 'L': 1.0, 'N': 1.0,
             'Q': 20.26, 'P': 20.26, 'S': 44.94, 'R': 1.0,
             'T': 1.0, 'W': 1.0, 'V': -6.54, 'Y': -6.54},
       'P': {'A': 20.26, 'C': -6.54, 'E': 18.38, 'D': -6.54,
             'G': 1.0, 'F': 20.26, 'I': 1.0, 'H': 1.0,
             'K': 1.0, 'M': -6.54, 'L': 1.0, 'N': 1.0,
             'Q': 20.26, 'P': 20.26, 'S': 20.26, 'R': -6.54,
             'T': 1.0, 'W': -1.88, 'V': 20.26, 'Y': 1.0},
       'S': {'A': 1.0, 'C': 33.60, 'E': 20.26, 'D': 1.0,
             'G': 1.0, 'F': 1.0, 'I': 1.0, 'H': 1.0,
             'K': 1.0, 'M': 1.0, 'L': 1.0, 'N': 1.0,
             'Q': 20.26, 'P': 44.94, 'S': 20.26, 'R': 20.26,
             'T': 1.0, 'W': 1.0, 'V': 1.0, 'Y': 1.0},
       'R': {'A': 1.0, 'C': 1.0, 'E': 1.0, 'D': 1.0,
             'G': -7.49, 'F': 1.0, 'I': 1.0, 'H': 20.26,
             'K': 1.0, 'M': 1.0, 'L': 1.0, 'N': 13.34,
             'Q': 20.26, 'P': 20.26, 'S': 44.94, 'R': 58.28,
             'T': 1.0, 'W': 58.28, 'V': 1.0, 'Y': -6.54},
       'T': {'A': 1.0, 'C': 1.0, 'E': 20.26, 'D': 1.0,
             'G': -7.49, 'F': 13.34, 'I': 1.0, 'H': 1.0,
             'K': 1.0, 'M': 1.0, 'L': 1.0, 'N': -14.03,
             'Q': -6.54, 'P': 1.0, 'S': 1.0, 'R': 1.0,
             'T': 1.0, 'W': -14.03, 'V': 1.0, 'Y': 1.0},
       'W': {'A': -14.03, 'C': 1.0, 'E': 1.0, 'D': 1.0,
             'G': -9.37, 'F': 1.0, 'I': 1.0, 'H': 24.68,
             'K': 1.0, 'M': 24.68, 'L': 13.34, 'N': 13.34,
             'Q': 1.0, 'P': 1.0, 'S': 1.0, 'R': 1.0,
             'T': -14.03, 'W': 1.0, 'V': -7.49, 'Y': 1.0},
       'V': {'A': 1.0, 'C': 1.0, 'E': 1.0, 'D': -14.03,
             'G': -7.49, 'F': 1.0, 'I': 1.0, 'H': 1.0,
             'K': -1.88, 'M': 1.0, 'L': 1.0, 'N': 1.0,
             'Q': 1.0, 'P': 20.26, 'S': 1.0, 'R': 1.0,
             'T': -7.49, 'W': 1.0, 'V': 1.0, 'Y': -6.54},
       'Y': {'A': 24.68, 'C': 1.0, 'E': -6.54, 'D': 24.68,
             'G': -7.49, 'F': 1.0, 'I': 1.0, 'H': 13.34,
             'K': 1.0, 'M': 44.94, 'L': 1.0, 'N': 1.0,
             'Q': 1.0, 'P': 13.34, 'S': 1.0, 'R': -15.91,
             'T': -7.49, 'W': -9.37, 'V': 1.0, 'Y': 13.34}
       };

// Data for the calculation of the Isoelectric Point /* pK values are from:

	* Bjellqvist, B.,Hughes, G.J., Pasquali, Ch., Paquet, N., Ravier, F., Sanchez,

J.-Ch., Frutiger, S. & Hochstrasser, D.F. The focusing positions of polypeptides in immobilized pH gradients can be predicted from their amino acid sequences. Electrophoresis 1993, 14, 1023-1031. * Bjellqvist, B., Basse, B., Olsen, E. and Celis, J.E. Reference points for comparisons of two-dimensional maps of proteins from different human cell types defined in a pH scale where isoelectric points correlate with polypeptide compositions. Electrophoresis 1994, 15, 529-539.

  • /

var positive_pKs = {'Nterm': 7.5 , 'K': 10.0, 'R': 12.0, 'H': 5.98 }; var negative_pKs = {'Cterm': 3.55, 'D': 4.05, 'E': 4.45, 'C': 9.0 , 'Y': 10.0}; // For some amino acids at the n-terminus the pK value is changed: var pKnterminal = {'A': 7.59, 'M': 7.0, 'S': 6.93, 'P': 8.36, 'T': 6.82, 'V': 7.44, 'E': 7.7}; //if one of these is N-terminal, this replaces the usual 7.5 for Nterm

var charged_aas = ['K', 'R', 'H', 'D', 'E', 'C', 'Y']; // or ProMost?


/**

*  FUNCTIONS
*/

function go_countingFun() { try{ var input = readSequence(); var counting_result = count_amino_acids(input); var amino_content = counting_result[0]; var amino_freq = counting_result[1]; var total_aminos = input.length; var molecular_weight = compute_molecular_weight(amino_content); var pI = compute_pI(input,amino_content);

// --- Create the output --- var outputText = ""; /* for (aa in amino_acids) { outputText = outputText + " " +aa +" "+ amino_content[aa] + " " + amino_freq[aa].toFixed(2) + "%" + "
"; }; */ outputText = outputText + "{|cellspacing=\"0\" border=\"1\" " + "
|colspan=\"20\"|Automatically determined parameters using the [http://www.mediawiki.org/wiki/Table BioBrick-AutoAnnotator]" + "
|-" + "
|colspan=\"10\"|BioBrick: <partinfo>BBa_K1159000</partinfo>" + "
|colspan=\"10\"|Used open reading frame from position ?x? to ?y?." + "
|-" + "
|A (Ala)" + "
|" + amino_content.A + " (" + amino_freq.A.toFixed(2) + "%)" + "
|R (Arg)" + "
|" + amino_content.R + " (" + amino_freq.R.toFixed(2) + "%)" + "
|N (Asn)" + "
|" + amino_content.N + " (" + amino_freq.N.toFixed(2) + "%)" + "
|D (Asp)" + "
|" + amino_content.D + " (" + amino_freq.D.toFixed(2) + "%)" + "
|C (Cys)" + "
|" + amino_content.C + " (" + amino_freq.C.toFixed(2) + "%)" + "
|Q (Gln)" + "
|" + amino_content.Q + " (" + amino_freq.Q.toFixed(2) + "%)" + "
|E (Glu)" + "
|" + amino_content.E + " (" + amino_freq.E.toFixed(2) + "%)" + "
|G (Gly)" + "
|" + amino_content.G + " (" + amino_freq.G.toFixed(2) + "%)" + "
|H (His)" + "
|" + amino_content.H + " (" + amino_freq.H.toFixed(2) + "%)" + "
|-" + "
|K (Lys):" + "
|" + amino_content.K + " (" + amino_freq.K.toFixed(2) + "%)" + "
|M (Met)" + "
|" + amino_content.M + " (" + amino_freq.M.toFixed(2) + "%)" + "
|F (Phe)" + "
|" + amino_content.F + " (" + amino_freq.F.toFixed(2) + "%)" + "
|P (Pro)" + "
|" + amino_content.P + " (" + amino_freq.P.toFixed(2) + "%)" + "
|S (Ser)" + "
|" + amino_content.S + " (" + amino_freq.S.toFixed(2) + "%)" + "
|T (Thr)" + "
|" + amino_content.T + " (" + amino_freq.T.toFixed(2) + "%)" + "
|W (Trp)" + "
|" + amino_content.W + " (" + amino_freq.W.toFixed(2) + "%)" + "
|Y (Tyr)" + "
|" + amino_content.Y + " (" + amino_freq.Y.toFixed(2) + "%)" + "
|V (Val)" + "
|" + amino_content.V + " (" + amino_freq.V.toFixed(2) + "%)" + "
|-" + "
|colspan=\"3\"|Amino acid counting:" + "
|colspan=\"3\"|Total number of amino acids (aa):" + "
|colspan=\"2\"|" + total_aminos + "
|colspan=\"3\"|Number of positively charged aa (Arg + Lys):" + "
|colspan=\"2\"|" + (amino_content.R + amino_content.K) + "
|colspan=\"3\"|Number of negatively charged aa (Asp + Glu):" + "
|colspan=\"2\"|" + (amino_content.D + amino_content.E) + "
|-" + "
|colspan=\"3\"|Biochemical parameters:" + "
|colspan=\"3\"|Molecular weight [Da]:" + "
|colspan=\"2\"|" + molecular_weight.toFixed(2) + "
|colspan=\"3\"|Theoretical pI:" + "
|colspan=\"2\"|" + pI.toFixed(2) + "
|colspan=\"3\"|Extinction coefficient:" + "
|colspan=\"2\"|?4?" + "
|-" + "
|colspan=\"3\"|Estimated half-life:" + "
|colspan=\"3\"|Mammals:" + "
|colspan=\"2\"|?4 h?" + "
|colspan=\"3\"|Yeast:" + "
|colspan=\"2\"|?4?" + "
|colspan=\"3\"|E. coli:" + "
|colspan=\"2\"|?4?" + "
|-" + "
|colspan=\"3\"|Codon usage:" + "
|colspan=\"3\"|Mammals:" + "
|colspan=\"2\"|?good?" + "
|colspan=\"3\"|Yeast:" + "
|colspan=\"2\"|?Ok?" + "
|colspan=\"3\"|E. coli:" + "
|colspan=\"2\"|?bad ?" + "
|-" + "
|colspan=\"3\"|RFC standard:" + "
|colspan=\"17\"|This is a RFC 25 BioBrick, thus ATGGCCGGC and ACCGGT were added to the 5' and 3' ends." + "
|-" + "
|colspan=\"20\"| The BioBrick-AutoAnnotator was created by TU-Munich 2013 iGEM team. For information please read the description." + "
|}" + "

";

$("#newoutput").html(outputText); $("#CountingResult").html("Copy the following into the wiki to get the protein-data-table:");

} catch(err){ txt="There was an error on this page in go_countingFun().\n\n"; txt=txt + "Error description: " + err.message + "\n\n"; txt=txt + "Click OK to continue.\n\n"; alert(txt); }

};

function readSequence() { try{ var sequence = document.getElementById("EnteredSequence").value; var cleanSequence = sequence.replace(/ /g, ""); return cleanSequence; } catch(err){ txt="There was an error on this page in readSequence().\n\n"; txt=txt + "Error description: " + err.message + "\n\n"; txt=txt + "Click OK to continue. \n\n"; alert(txt); } };

function count_amino_acids(sequence){ try{ //Counts standard amino acids, returns an array {AminoAcid:Number} var amino_acids_content = {A:0,R:0,N:0,D:0,C:0,Q:0,E:0,G:0,H:0,K:0,M:0,F:0,P:0,S:0,T:0,W:0,Y:0,V:0}; var amino_acids_freq = {A:0,R:0,N:0,D:0,C:0,Q:0,E:0,G:0,H:0,K:0,M:0,F:0,P:0,S:0,T:0,W:0,Y:0,V:0}; for (i=0; i<sequence.length; i++){ amino_acids_content[sequence[i]]++; } var total=sequence.length; for (aa in amino_acids){ amino_acids_freq[aa] = amino_acids_content[aa] * (100 / total); }; return [amino_acids_content,amino_acids_freq]; } catch(err){ txt="There was an error on this page in count_amino_acids(sequence).\n\n"; txt=txt + "Error description: " + err.message + "\n\n"; txt=txt + "Click OK to continue. \n\n"; alert(txt); } };

function compute_molecular_weight(amino_acids_content){ try{ var molec_weight = water_weight; for (aa in amino_acids){ molec_weight = molec_weight + amino_acids_content[aa] * amino_weights[aa]; } return molec_weight; } catch(err){ txt="There was an error on this page in compute_molecular_weight(amino_acids_content).\n\n"; txt=txt + "Error description: " + err.message + "\n\n"; txt=txt + "Click OK to continue. \n\n"; alert(txt); } }

function compute_pI(sequence,amino_acids_content){ try{ var nterm = sequence[0]; //the first aa var composition = {Nterm:1,Cterm:1, K:amino_acids_content.K, R:amino_acids_content.R, H:amino_acids_content.H, D:amino_acids_content.D, E:amino_acids_content.E, C:amino_acids_content.C, Y:amino_acids_content.Y}; var pos_pKs = jQuery.extend(true, {}, positive_pKs); //to clone positive_pKs, otherwise just passes reference if ( nterm in pKnterminal ){ pos_pKs.Nterm = pKnterminal[nterm]; }

var pHOld = 0.0; //just to set off the while loop var pHNew = 7.0; var step = 3.5; var charge = charge_at_pH(pHNew,composition,pos_pKs); while ( Math.abs(pHOld - pHNew) > 0.0001 && Math.abs(charge)!=0 ){ pHOld = pHNew; //store the now old pH if (charge >0){ pHNew = pHNew + step; } else { //so charge < 0 pHNew = pHNew - step; } step = step/2; charge = charge_at_pH(pHNew,composition,pos_pKs); } var pH = pHNew; return pH; } catch(err){ txt="There was an error on this page in compute_pI(sequence,amino_acids_content).\n\n"; txt=txt + "Error description: " + err.message + "\n\n"; txt=txt + "Click OK to continue. \n\n"; alert(txt); } }

function charge_at_pH(pH, compo, pos_pKs){ try{ var charge = 0; for (aa in positive_pKs){ charge = charge + compo[aa] * (1/(1+Math.pow(10, pH - pos_pKs[aa]))); } for (aa in negative_pKs){ charge = charge - compo[aa] * (1/(1+Math.pow(10, negative_pKs[aa] - pH))); } return charge; } catch(err){ txt="There was an error on this page in charge_at_pH(), which is used in calculating the pI.\n\n"; txt=txt + "Error description: " + err.message + "\n\n"; txt=txt + "Click OK to continue. \n\n"; alert(txt); } }

function findReadingFrame(sequence){ try{ var a = 0; return a; } catch(err){ txt="There was an error on this page in findReadingFrame().\n\n"; txt=txt + "Error description: " + err.message + "\n\n"; txt=txt + "Click OK to continue. \n\n"; alert(txt); } }