Last active
March 3, 2017 15:34
-
-
Save elsherbini/625df7983f2c90c2580b8f44ccb51150 to your computer and use it in GitHub Desktop.
calculate parsimonious synonymous and nonsynonymous mutations for any two codons
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import networkx as nx | |
| def setup_codon_graph(): | |
| """create a networkx graph of codons as nodes and mutations as codon_edges. | |
| if the mutation is synonymous, the edgeweight is 0.01 | |
| if the mutation is non-synonymous, the edgeweight is 1.01 | |
| then, by calculating the shortest path length between two bases, | |
| you can get the most parsimonious path | |
| """ | |
| codon_table = { | |
| 'AAA': 'K', 'AAC': 'N', 'AAG': 'K', 'AAT': 'N', | |
| 'ACA': 'T', 'ACC': 'T', 'ACG': 'T', 'ACT': 'T', | |
| 'AGA': 'R', 'AGC': 'S', 'AGG': 'R', 'AGT': 'S', | |
| 'ATA': 'I', 'ATC': 'I', 'ATG': 'M', 'ATT': 'I', | |
| 'CAA': 'Q', 'CAC': 'H', 'CAG': 'Q', 'CAT': 'H', | |
| 'CCA': 'P', 'CCC': 'P', 'CCG': 'P', 'CCT': 'P', | |
| 'CGA': 'R', 'CGC': 'R', 'CGG': 'R', 'CGT': 'R', | |
| 'CTA': 'L', 'CTC': 'L', 'CTG': 'L', 'CTT': 'L', | |
| 'GAA': 'E', 'GAC': 'D', 'GAG': 'E', 'GAT': 'D', | |
| 'GCA': 'A', 'GCC': 'A', 'GCG': 'A', 'GCT': 'A', | |
| 'GGA': 'G', 'GGC': 'G', 'GGG': 'G', 'GGT': 'G', | |
| 'GTA': 'V', 'GTC': 'V', 'GTG': 'V', 'GTT': 'V', | |
| 'TAC': 'Y', 'TAT': 'Y', | |
| 'TCA': 'S', 'TCC': 'S', 'TCG': 'S', 'TCT': 'S', | |
| 'TGC': 'C', 'TGG': 'W', 'TGT': 'C', | |
| 'TTA': 'L', 'TTC': 'F', 'TTG': 'L', 'TTT': 'F'} | |
| def codon_edges(): | |
| for k in codon_table: | |
| one_aways = get_one_aways(k) | |
| for c in one_aways: | |
| if c in codon_table: | |
| if codon_table[k] == codon_table[c]: | |
| yield (k, c, 0.01) | |
| else: | |
| yield(k, c, 1.01) | |
| def get_one_aways(k): | |
| one_aways = [] | |
| l = list(k) | |
| for i, p in enumerate(l): | |
| for n in ["A", "C", "G", "T"]: | |
| if n != p: | |
| copy = l.copy() | |
| copy[i] = n | |
| one_aways.append("".join(copy)) | |
| return one_aways | |
| codon_graph = nx.Graph() | |
| codon_graph.add_nodes_from(codon_table.keys()) | |
| codon_graph.add_weighted_edges_from(codon_edges()) | |
| for k, v in codon_table.items(): | |
| codon_graph.node[k]['translation'] = v | |
| return codon_graph | |
| def get_ns_and_s(codon1, codon2, codon_graph): | |
| """get # of synonymous and non-synonymous mutations for a codon pair. | |
| this is kinda crappy. the edge weights are decimal numbers, | |
| with the integer part representing the non-synonymous mutations | |
| and the part after the decimal representing the total mutations. | |
| gross. | |
| """ | |
| distance = nx.shortest_path_length(codon_graph, "CTT", "TCC", weight="weight") | |
| ns = int(distance) | |
| s = round((distance - ns) * 100) | |
| return (s, ns) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment