"
Team:TU-Munich/AnnotatorCode.js
From 2013.igem.org
/**
* 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
// Extinction coefficients for Y(Tyr) and W(Trp), as well as Cystine (formed by disulfide bond of two Cysteine) var extinction = { Y:1490 , W:5500 , Cystine:125 };
// 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'];
/*from: * Varshavsky (1997). The N-end rule pathway of protein degradation.
* Varshavsky et al. (1989). Universality and structure of the N-end rule. */
var halflife_table_Mammalian = {A: "4.4", R: "1", N: "1.4", D: "1.1", C: "1.2", Q: "0.8", E: "1", G: "30", H: "3.5", I: "20", L: "5.5", K: "1.3", M: "30", F: "1.1", P: ">20", S: "1.9", T: "7.2", W: "2.8", Y: "2.8", V: "100"};
var halflife_table_Yeast = {A: ">20", R: "0.03", N: "0.05", D: "0.05", C: ">20", Q: "0.17", E: "0.5", G: ">20", H: "0.17", I: "0.5", L: "0.05", K: "0.05", M: ">20", F: "0.05", P: ">20", S: ">20", T: ">20", W: "0.05", Y: "0.17", V: ">20"};
var halflife_table_E_coli = {A: ">10", R: "0.03", N: ">10", D: ">10", C: ">10", Q: ">10", E: ">10", G: ">10", H: ">10", I: ">10", L: "0.03", K: "0.03", M: ">10", F: "0.03", P: "unknown", S: ">10", T: ">10", W: "0.03", Y: "0.03", V: ">10"};
var translation_table = { 'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S', 'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y', 'TGT': 'C', 'TGC': 'C', 'TGG': 'W', 'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L', 'CCT': 'P', 'CCC': 'P', 'CCA': 'P', 'CCG': 'P', 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q', 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R', 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M', 'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T', 'AAT': 'N', 'AAC': 'N', 'AAA': 'K', 'AAG': 'K', 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R', 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V', 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A', 'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E', 'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G', 'TAA': '*', //STOP CODONS, shouldn't appear and already be removed 'TAG': '*', 'TGA': '*' };
var stop_codons = {'TAA':0,'TAG':0, 'TGA' :0};
var non_synonymous_codons = { //these are excluded from the calculation of the CAI 'ATG':0, 'TGG':0 };
// weights for the calculation of the CAI (codon adaptation index), see e.g. http://www.ihes.fr/~carbone/papers/Bioinformatics.pdf // method based on: Sharp,P.M. and Li,W-H. (1987) The codon adaptation index—a measure of directional synonymous codon usage bias, and its potential applications var E_coli_codon_weights = { //from http://www.kazusa.or.jp/codon/cgi-bin/showcodon.cgi?species=37762&aa=1&style=N for E.coli & computing the weights for CAI calculation 'TTT': 1, 'TTC': 36/64, 'TTA': 18/38, 'TTG': 13/38, 'TCT': 18/20, 'TCC': 14/20, 'TCA': 18/20, 'TCG': 11/20, 'TAT': 1, 'TAC': 35/65, 'TGT': 1, 'TGC': 48/52, 'TGG': 1, 'CTT': 15/38, 'CTC': 10/38, 'CTA': 6/38, 'CTG': 1, 'CCT': 24/37, 'CCC': 16/37, 'CCA': 23/37, 'CCG': 1, 'CAT': 1, 'CAC': 37/63, 'CAA': 35/65, 'CAG': 1, 'CGT': 1, 'CGC': 26/30, 'CGA': 9/30, 'CGG': 15/30, 'ATT': 1, 'ATC': 31/47, 'ATA': 21/47, 'ATG': 1, 'ACT': 22/31, 'ACC': 1, 'ACA': 25/31, 'ACG': 22/31, 'AAT': 1, 'AAC': 41/59, 'AAA': 1, 'AAG': 29/71, 'AGT': 18/20, 'AGC': 1, 'AGA': 13/30, 'AGG': 7/30, 'GTT': 1, 'GTC': 19/32, 'GTA': 19/32, 'GTG': 29/32, 'GCT': 22/27, 'GCC': 26/27, 'GCA': 1, 'GCG': 25/27, 'GAT': 1, 'GAC': 35/65, 'GAA': 1, 'GAG': 36/64, 'GGT': 1, 'GGC': 29/34, 'GGA': 19/34, 'GGG': 18/34, 'TAA': 1, //STOP CODONS, shouldn't appear and already be removed 'TAG': 9/58, 'TGA': 33/58 };
var Mouse_codon_weights = { //from http://www.kazusa.or.jp/codon/cgi-bin/showcodon.cgi?species=10090&aa=1&style=N for mus musculus & computing the weights for CAI calculation 'TTT': 44/56, 'TTC': 1, 'TTA': 7/39, 'TTG': 13/39, 'TCT': 20/24, 'TCC': 22/24, 'TCA': 14/24, 'TCG': 5/24, 'TAT': 43/57, 'TAC': 1, 'TGT': 48/52, 'TGC': 1, 'TGG': 1, 'CTT': 13/39, 'CTC': 20/39, 'CTA': 8/39, 'CTG': 1, 'CCT': 1, 'CCC': 30/31, 'CCA': 29/31, 'CCG': 10/31, 'CAT': 41/59, 'CAC': 1, 'CAA': 26/74, 'CAG': 1, 'CGT': 8/22, 'CGC': 17/22, 'CGA': 12/22, 'CGG': 19/22, 'ATT': 34/50, 'ATC': 1, 'ATA': 16/50, 'ATG': 1, 'ACT': 25/35, 'ACC': 1, 'ACA': 29/35, 'ACG': 10/35, 'AAT': 43/57, 'AAC': 1, 'AAA': 39/61, 'AAG': 1, 'AGT': 15/24, 'AGC': 1, 'AGA': 1, 'AGG': 1, 'GTT': 17/46, 'GTC': 25/46, 'GTA': 12/46, 'GTG': 1, 'GCT': 29/38, 'GCC': 1, 'GCA': 23/38, 'GCG': 9/38, 'GAT': 45/55, 'GAC': 1, 'GAA': 41/59, 'GAG': 1, 'GGT': 18/33, 'GGC': 1, 'GGA': 26/33, 'GGG': 23/33, 'TAA': 28/49, //STOP CODONS, shouldn't appear and already be removed 'TAG': 23/49, 'TGA': 1 };
var Yeast_codon_weights = { //from http://www.kazusa.or.jp/codon/cgi-bin/showcodon.cgi?species=4932&aa=1&style=N for Saccharomyces cerevisiae & computing the weights for CAI calculation 'TTT': 1, 'TTC': 41/59, 'TTA': 28/29, 'TTG': 1, 'TCT': 1, 'TCC': 16/26, 'TCA': 21/26, 'TCG': 10/26, 'TAT': 1, 'TAC': 44/56, 'TGT': 1, 'TGC': 37/63, 'TGG': 1, 'CTT': 13/29, 'CTC': 6/29, 'CTA': 14/29, 'CTG': 11/29, 'CCT': 31/42, 'CCC': 15/42, 'CCA': 1, 'CCG': 12/42, 'CAT': 1, 'CAC': 36/64, 'CAA': 1, 'CAG': 31/69, 'CGT': 14/48, 'CGC': 6/48, 'CGA': 7/48, 'CGG': 4/48, 'ATT': 1, 'ATC': 26/46, 'ATA': 27/46, 'ATG': 1, 'ACT': 1, 'ACC': 22/35, 'ACA': 30/35, 'ACG': 14/35, 'AAT': 1, 'AAC': 41/59, 'AAA': 1, 'AAG': 42/58, 'AGT': 16/26, 'AGC': 11/26, 'AGA': 1, 'AGG': 21/48, 'GTT': 1, 'GTC': 21/39, 'GTA': 21/39, 'GTG': 19/39, 'GCT': 1, 'GCC': 22/38, 'GCA': 29/38, 'GCG': 11/38, 'GAT': 1, 'GAC': 35/65, 'GAA': 1, 'GAG': 30/70, 'GGT': 1, 'GGC': 19/47, 'GGA': 22/47, 'GGG': 12/47, 'TAA': 1, //STOP CODONS, shouldn't appear and already be removed 'TAG': 23/47, 'TGA': 30/47 };
/**
* FUNCTIONS */
//The function called initially. This handles interaction with the registry server to obtain the sequence function get_sequence(){ try{
//---put together the url from which to get the sequence var entered_bb_number = document.getElementById("EnteredBioBrick").value; var numeric_start= entered_bb_number.search(/[0-9]/); if (numeric_start == 0){ throw "Not a valid BioBrick name nor a nucleotide sequence. The BioBrick name must contain one letter followed by digits"; } if (numeric_start == -1){ //so entered a sequence //interpret the entered bb number as sequence bb_number = ""; main_table_calc(entered_bb_number,bb_number); } else{ //entered a BioBrick number, so try to get the sequence from the Registry var bb_number = entered_bb_number.substr(numeric_start - 1); bb_number = bb_number.toUpperCase(); var bb_url = "http://parts.igem.org/das/parts/dna/?segment=BBa_" + bb_number;
try{ jQuery.ajax({ url: bb_url, type: 'GET', success: function(res) { try{
var a = res.responseText; var b=a.indexOf("<body>");
var c=a.indexOf("",b); var d=a.indexOf("
",c);var sequence = a.substr(c+3,d-c-3); } catch(err){ var txt = "Couldn't get the sequence from the registry. The BioBrick does not exist in the data base."; txt = txt + "\n"; txt = txt + "\nPlease restart and enter the nucleotide sequence manually instead of the BioBrick number!"; alert(txt); return; //to end program
}
//---call the main function with the sequence information--- if (sequence == ""){ alert("The sequence obtained from the registry is empty.\nPlease restart and enter the sequence manually instead of the BioBrick number!"); return; //to end the program //sequence = prompt(prompttxt,""); //if couldn't get the sequence in this way, ask user to enter it manually } main_table_calc(sequence,bb_number);
} }); } catch(error){ alert(error); } } } catch(err){ txt="There was an error on this page in get_sequence().\n\n"; txt=txt + "Error description: \n" + err + "\n\n"; txt=txt + "Click OK to continue. \n\n"; alert(txt); }; }
//the main function, which calls the necessary functions to compute the table entries and puts the table together
function main_table_calc(sequence,bb_number) {
try{
var entered_nuc_sequence = clean_sequence(sequence);
var reading_frame = find_reading_frame(entered_nuc_sequence);
var reading_frame_start = reading_frame[0]; //the A in the ATG start codon
var reading_frame_end = reading_frame[1]; //last nucleotide to be translated
//recall internal indexing starts at 0, external indexing at 1
var entered_nuc_length = entered_nuc_sequence.length; if (reading_frame_start == -9 && (reading_frame_end > entered_nuc_length - 1) ){ //so RFC25 var coding_nuc_sequence = "ATGGCCGGC" + entered_nuc_sequence + "ACCGGT"; //add prefix and suffix var RFC_standard = "RFC 25, so ATGGCCGGC and ACCGGT were added (in italics) to the 5' and 3' ends: (underlined part encodes the protein)"; var nuc_sequence_to_display = "<u>ATGGCCGGC" + entered_nuc_sequence.substr(0,9) + "..." + entered_nuc_sequence.substr(entered_nuc_length-9) +"ACCGGT</u>" ; var nuc_sequence_to_display_html = " " + "ATGGCCGGC" + entered_nuc_sequence.substr(0,9) + " ... " + entered_nuc_sequence.substr(entered_nuc_length-9) +"ACCGGT" ; } else if ( reading_frame_end > entered_nuc_length - 1 ){ //stop codon in RFC10 suffix var coding_nuc_sequence = entered_nuc_sequence.substr(reading_frame_start) + "TAC"; var RFC_standard = "RFC 10 using the stop codon in the suffix, so TAC was added (in italics) to the 3' end: (underlined part encodes the protein)"; var nuc_sequence_to_display = entered_nuc_sequence.substr(0,reading_frame_start) + "<u>" + entered_nuc_sequence.substr(reading_frame_start,9) + "..." + entered_nuc_sequence.substr(entered_nuc_length-9) +"TAC</u>" ; var nuc_sequence_to_display_html = " " + entered_nuc_sequence.substr(0,reading_frame_start) + "" + entered_nuc_sequence.substr(reading_frame_start,9) + " ... " + entered_nuc_sequence.substr(entered_nuc_length-9) +"TAC" ; } else { var coding_nuc_sequence = entered_nuc_sequence.substr( reading_frame_start , reading_frame_end - reading_frame_start + 1); var RFC_standard = "RFC 10: (underlined part encodes the protein)"; var nuc_sequence_to_display = entered_nuc_sequence.substr(0,reading_frame_start) + "<u>" + entered_nuc_sequence.substr(reading_frame_start,9) + "..." + entered_nuc_sequence.substr(reading_frame_end-8,9) +"</u>" + entered_nuc_sequence.substr(reading_frame_end+1) ; var nuc_sequence_to_display_html = " " + entered_nuc_sequence.substr(0,reading_frame_start) + "" + entered_nuc_sequence.substr(reading_frame_start,9) + " ... " + entered_nuc_sequence.substr(reading_frame_end-8,9) +"" + entered_nuc_sequence.substr(reading_frame_end+1) ; }
var trans_result = translate_to_aa_and_codon_count(coding_nuc_sequence); var amino_sequence = trans_result[0]; var codon_count = trans_result[1];
var amino_output = " ";
for ( i=0 ; i < amino_sequence.length /100 ; i++){
amino_output = amino_output + (100*(i) + 1) + " " + amino_sequence.substr(i*100, 100) + "
";
}
amino_output = amino_output + "";
SequenceFeatures = find_sequence_features(coding_nuc_sequence,amino_sequence); var SequenceFeatureTable = "";
var codon_usage = analyze_codons(codon_count); // 0 -> E_coli, 1 -> Yeast, 2 -> Mammalian //translate numerical CAI value into categories: 1.00-0.80 -> excellent // 0.79-0.60 -> good // 0.59-0.40 -> acceptable // 0.39-0.20 -> bad // 0.19-0.00 -> very bad for (i=0;i<3;i++){ if (codon_usage[i] >= 0.80){ codon_usage[i] = "excellent (" + codon_usage[i].toFixed(2) + ")"; } else if (codon_usage[i] < 0.8 && codon_usage[i] >= 0.6){ codon_usage[i] = "good (" + codon_usage[i].toFixed(2) + ")"; } else if (codon_usage[i] < 0.6 && codon_usage[i] >= 0.4){ codon_usage[i] = "acceptable (" + codon_usage[i].toFixed(2) + ")"; } else if (codon_usage[i] < 0.4 && codon_usage[i] >= 0.2){ codon_usage[i] = "bad (" + codon_usage[i].toFixed(2) + ")"; } else{ codon_usage[i] = "very bad (" + codon_usage[i].toFixed(2) + ")"; } }
var counting_result = count_amino_acids(amino_sequence); var amino_content = counting_result[0]; var amino_freq = counting_result[1]; var total_aminos = amino_sequence.length; var molecular_weight = compute_molecular_weight(amino_content); var pI = compute_pI(amino_sequence,amino_content); var extinction_coeffs = compute_extinction_coeff(amino_content,molecular_weight); var nterm = amino_sequence[0];
// --- Create the output --- var htmlCode = "";
// Code to display the table htmlCode = htmlCode
+ "| Parameters for BioBrick <a href=\"http://parts.igem.org/wiki/index.php?title=Part:BBa_" + bb_number + "\">BBa_" + bb_number + "</a> automatically created by the <a href=\"https://2013.igem.org/Team:TU-Munich/Results/AutoAnnotator\">BioBrick-AutoAnnotator</a> version 1.0" + " | " + "|||||||||||||||||||||||||||||||||||||||||||||
| " + "Nucleotide sequence in " + RFC_standard + " " + nuc_sequence_to_display_html + "" + " " + " ORF from " + (reading_frame_start + 1) + " to " + (reading_frame_end + 1) + " (excluding stop-codon)" + " | "
+ "|||||||||||||||||||||||||||||||||||||||||||||
| Amino acid sequence: " + amino_output + " | "
+ "|||||||||||||||||||||||||||||||||||||||||||||
| Amino acid composition:"
//TABLE IN TABLE + "
| " // close the cell of Amino acid composition
+ "|||||||||||||||||||||||||||||||||||||||||||||
" + "Amino acid counting: "
+ "
| " //close Amino acid counting cell
+ "" + "Biochemical parameters:"
+ "
| " //close Biochemical parameters cell
+ "||||||||||||||||||||||||||||||||||||||||||||
Organism specific parameters"
+ "
| " //close Organism specific cell
+ "|||||||||||||||||||||||||||||||||||||||||||||
Organism specific parameters"
+ "
| " //close Organism specific cell
+ "|||||||||||||||||||||||||||||||||||||||||||||
| Sequence features:"
+ SequenceFeatureTable //created in find_sequence_features(a,b) below + " | "
+ "|||||||||||||||||||||||||||||||||||||||||||||
| The BioBrick-AutoAnnotator was created by <a href=\"https://2013.igem.org/Team:TU-Munich\">TU-Munich 2013</a> iGEM team. For more information please see the <a href=\"https://2013.igem.org/Team:TU-Munich/Results/Software\">documentation</a>. If you have any questions, comments or suggestions, please email us at <a href=\"mailto:igem@wzw.tum.de?Subject=AutoAnnotator\" target=\"_top\">igem@wzw.tum.de</a>." + " | "
+ "
+ "
";
$("#htmlTable").html(htmlCode); $("#htmlExplanation").html("The generated table giving various computed parameters: (The wiki-code producing this table is below)");
$("#wikiTable").text("" + htmlCode + ""); $("#wikiExplanation").html("Copy the following into the wiki to get the protein-data-table:");
} catch(err){ txt="There was an error on this page.\n\n"; if ((err.toString()).substr(0,16) == "An error occured"){ txt = txt + "This error originated at a lower level: \n\n" + err.toString(); } else{ txt=txt + "The originating error is: \n" + err + "\n\n"; } alert(txt); return; //to end execution }
};
function find_sequence_features(coding_nuc_sequence,amino_sequence){ try{ //first look for RFC25 scars var RFC25_scars = []; for ( i = 0 ; i < coding_nuc_sequence.length ; i = i + 3){ var codonpair = coding_nuc_sequence.substr(i,6); if (codonpair == "ACCGGC"){ RFC25_scars = [RFC25_scars,i]; } }
//find forbidden restriction sites
//find His5 var Features = [RFC25_scars,]; return Features; } catch(err){ txt = "An error occured while finding sequence features and preparing the output.\n"; if ((err.toString()).substr(0,16) == "An error occured"){ txt = txt + "This error originated at a lower level: \n\n" + err.toString(); } else{ txt=txt + "The originating error is: \n" + err + "\n\n"; } throw txt; } }
function clean_sequence(sequence){ try{ var cleanSequence = sequence.replace(/ /g, ""); // remove spaces var cleanSequence2= cleanSequence.toUpperCase(); // convert to upper case var cleanSequence3= cleanSequence2.replace(/\r?\n|\r/g, ""); // remove line breaks var wrongLetter = cleanSequence3.search(/[^ATGC]/); // check for wrong nucleotides if (wrongLetter > -1){ throw "Unknown nucleotide in the entered sequence. Only use A, T, G, C!"; } return cleanSequence3; } catch(err){ txt = "An error occured while checking and cleaning up the provided sequence.\n"; if ((err.toString()).substr(0,16) == "An error occured"){ txt = txt + "This error originated at a lower level: \n\n" + err.toString(); } else{ txt=txt + "The originating error is: \n" + err + "\n\n"; } throw 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,I:0,L: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,I:0,L: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 = "An error occured while counting the amino acids.\n"; if ((err.toString()).substr(0,16) == "An error occured"){ txt = txt + "This error originated at a lower level: \n\n" + err.toString(); } else{ txt=txt + "The originating error is: \n" + err + "\n\n"; } throw 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 = "An error occured while computing the molecular weight of the protein.\n"; if ((err.toString()).substr(0,16) == "An error occured"){ txt = txt + "This error originated at a lower level: \n\n" + err.toString(); } else{ txt=txt + "The originating error is: \n" + err + "\n\n"; } throw 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 = "An error occured while computing the theoretical pI.\n"; if ((err.toString()).substr(0,16) == "An error occured"){ txt = txt + "This error originated at a lower level: \n\n" + err.toString(); } else{ txt=txt + "The originating error is: \n" + err + "\n\n"; } throw 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 = "An error occured while computing the charge of the protein at a certain pH.\n"; if ((err.toString()).substr(0,16) == "An error occured"){ txt = txt + "This error originated at a lower level: \n\n" + err.toString(); } else{ txt=txt + "The originating error is: \n" + err + "\n\n"; } throw txt; } };
function compute_extinction_coeff(amino_acid_content,molecular_weight){ try{ var E_allCystine = amino_acid_content.Y * extinction.Y + amino_acid_content.W * extinction.W + (amino_acid_content.C /2)*extinction.Cystine; var E_noCystine = amino_acid_content.Y * extinction.Y + amino_acid_content.W * extinction.W ; return [E_allCystine,E_noCystine]; } catch(err){ txt = "An error occured while computing the extinction coefficient of the protein.\n"; if ((err.toString()).substr(0,16) == "An error occured"){ txt = txt + "This error originated at a lower level: \n\n" + err.toString(); } else{ txt=txt + "The originating error is: \n" + err + "\n\n"; } throw txt; } };
function find_reading_frame(nuc_sequence){ try{ // atg_position is the first nucleotide in the ATG (start codon) // stop_position is the first nucleotide in the stop codon var isRFC25=false; // check for RFC 25 var ideal_stop = nuc_sequence.length - 3; if (nuc_sequence.length%3 == 0 && !(nuc_sequence.substr(ideal_stop,3) in stop_codons)){ isRFC25 = confirm("Is this part in RFC25, i.e. the start codon is part of the prefix?\n If it is RFC25, press 'OK', otherwise 'Cancel'"); }
if ( !isRFC25 ){ //so not RFC25
var atg_position = nuc_sequence.indexOf("ATG"); if ( atg_position > -1){ var stop_position = -1; for ( i = atg_position + 3 ; i < nuc_sequence.length ; i = i + 3){ var codon = nuc_sequence.substr(i,3); if ( codon in stop_codons ){ stop_position = i; break; } } if (stop_position == -1){ if ((nuc_sequence.length - atg_position)%3 == 0){
stop_position = nuc_sequence.length + 3; //so RFC10 using stop codon in suffix alert("Using stop codon in suffix of RFC10"); } else { throw "No stop codon found in frame & can't use stop codon in suffix of RFC10"; } } } else { throw "No ATG found, something is wrong! Might be RFC25?"; } reading_length = stop_position - atg_position + 3; if ( (reading_length / nuc_sequence.length) < 0.6){ real_atg_position = prompt("The reading length is small compared to the length of the sequence, please enter the position of the start codon (start of sequence is 1)",atg_position + 1); atg_position = real_atg_position - 1; stop_position= -1; for ( i = atg_position + 3 ; i < nuc_sequence.length ; i = i + 3){ if (nuc_sequence.substr(i,3) == ("TAA"|"TAG"|"TGA") ){ stop_position = i; break; } } if (stop_position == -1 && atg_position > -1){ if ((nuc_sequence.length - atg_position)%3 == 0){
stop_position = nuc_sequence.length + 3; //so RFC10 using stop codon in suffix alert("Using stop codon in suffix of RFC10"); } else { throw "No stop codon found in frame & can't use stop codon in suffix of RFC10"; } }
} } else { // so RFC25 atg_position = -9; stop_position = nuc_sequence.length + 6; }
var reading_frame_start = atg_position; var reading_frame_end = stop_position - 1; //the last nucleotide to be translated
return [reading_frame_start,reading_frame_end]; } catch(err){ txt = "An error occured while determining the appropriate open reading frame (ORF) of the provided sequence.\n"; if ((err.toString()).substr(0,16) == "An error occured"){ txt = txt + "This error originated at a lower level: \n\n" + err.toString(); } else{ txt=txt + "The originating error is: \n" + err + "\n\n"; } throw txt; } };
function translate_to_aa_and_codon_count(nuc_sequence){ try{ var amino_sequence = ""; var codon_count = { 'TTT': 0, 'TTC': 0, 'TTA': 0, 'TTG': 0, 'TCT': 0, 'TCC': 0, 'TCA': 0, 'TCG': 0, 'TAT': 0, 'TAC': 0, 'TGT': 0, 'TGC': 0, 'TGG': 0, 'CTT': 0, 'CTC': 0, 'CTA': 0, 'CTG': 0, 'CCT': 0, 'CCC': 0, 'CCA': 0, 'CCG': 0, 'CAT': 0, 'CAC': 0, 'CAA': 0, 'CAG': 0, 'CGT': 0, 'CGC': 0, 'CGA': 0, 'CGG': 0, 'ATT': 0, 'ATC': 0, 'ATA': 0, 'ATG': 0, 'ACT': 0, 'ACC': 0, 'ACA': 0, 'ACG': 0, 'AAT': 0, 'AAC': 0, 'AAA': 0, 'AAG': 0, 'AGT': 0, 'AGC': 0, 'AGA': 0, 'AGG': 0, 'GTT': 0, 'GTC': 0, 'GTA': 0, 'GTG': 0, 'GCT': 0, 'GCC': 0, 'GCA': 0, 'GCG': 0, 'GAT': 0, 'GAC': 0, 'GAA': 0, 'GAG': 0, 'GGT': 0, 'GGC': 0, 'GGA': 0, 'GGG': 0, 'TAA': 0, //STOP CODONS, shouldn't appear and already be removed 'TAG': 0, 'TGA': 0 }; for ( i = 0 ; i < nuc_sequence.length ; i = i + 3){ var codon = nuc_sequence.substr(i,3); codon_count[codon] ++; //count the number of each codon appearing amino_sequence = amino_sequence + translation_table[codon]; } return [amino_sequence,codon_count]; } catch(err){ txt = "An error occured while translating the nucleotide sequence into the amino acid sequence.\n"; if ((err.toString()).substr(0,16) == "An error occured"){ txt = txt + "This error originated at a lower level: \n\n" + err.toString(); } else{ txt=txt + "The originating error is: \n" + err + "\n\n"; } throw txt; }
};
function analyze_codons(codon_count){ try{ var total_synon_codons = 0; var E_coli_prod = 1; var Yeast_prod = 1; var Mammalian_prod = 1;
for (codon in codon_count){ if (codon in non_synonymous_codons){ //ignore the non-synonimous codons continue; }
total_synon_codons = total_synon_codons + codon_count[codon]; //should give the total number of codons (excluding stop codons) E_coli_prod = E_coli_prod * Math.pow( E_coli_codon_weights[codon], codon_count[codon]); Yeast_prod = Yeast_prod * Math.pow( Yeast_codon_weights[codon], codon_count[codon]); Mammalian_prod = Mammalian_prod * Math.pow( Mouse_codon_weights[codon], codon_count[codon]);
//could count weak codons };
var E_coli_CAI = Math.pow( E_coli_prod, 1/total_synon_codons); var Yeast_CAI = Math.pow( Yeast_prod, 1/total_synon_codons); var Mammalian_CAI = Math.pow( Mammalian_prod, 1/total_synon_codons);
var usageOutput = [ E_coli_CAI , Yeast_CAI , Mammalian_CAI ]; return usageOutput; } catch(err){ txt = "An error occured while analyzing the codon usage of the provided sequence.\n"; if ((err.toString()).substr(0,16) == "An error occured"){ txt = txt + "This error originated at a lower level: \n\n" + err.toString(); } else{ txt=txt + "The originating error is: \n" + err + "\n\n"; } throw txt; } }
