def export_sequence_json(T, path, prefix):
from Bio import SeqIO
plain_export = 0.99
indent = None
elems = {'root': {}}
for node in T.find_clades():
elems[node.clade] = {}
for gene, aln_fname in get_genes_and_alignments(path, tree=True):
seqs = {}
for seq in SeqIO.parse(aln_fname, 'fasta'):
seqs[seq.name] = seq
root_seq = seqs[T.root.name]
elems['root'][gene] = "".join(root_seq)
for node in T.find_clades():
nseq = seqs[node.name]
if hasattr(node, "clade"):
differences = {
pos: state
for pos, (
state,
ancstate) in enumerate(zip(nseq, elems['root'][gene]))
if state != ancstate
}
if len(differences) <= plain_export * len(seq):
elems[node.clade][gene] = differences
else:
elems[node.clade][gene] = seq
fname = sequence_json(path, prefix)
write_json(elems, fname, indent=indent)
def export_diversity(path, prefix, reference, indent=None):
'''
write the alignment entropy of each alignment (nucleotide and translations) to file
'''
genes = load_features(reference)
entropy_json = {}
for feat, aln_fname in get_genes_and_alignments(path, tree=False):
entropy = diversity_statistics(aln_fname, nuc=feat == 'nuc')
S = [max(0, round(x, 4)) for x in entropy]
n = len(S)
if feat == 'nuc':
entropy_json[feat] = {
'pos': range(0, n),
'codon': [x // 3 for x in range(0, n)],
'val': S
}
elif feat in genes:
entropy_json[feat] = {
'pos': [x for x in genes[feat]][::3],
'codon': range(n),
'val': S
}
write_json(entropy_json, diversity_json(path, prefix), indent=indent)
seqs[seq.name] = seq
muts = {}
muts[T.root.name]=''
for node in T.get_nonterminals():
pseq = seqs[node.name]
for c in node:
cseq = seqs[c.name]
muts[c.name]=','.join([anc+str(pos+1)+der
for pos, (anc, der) in enumerate(zip(pseq, cseq))
if anc!=der])
return muts
if __name__ == '__main__':
parser = generic_argparse("Assign amino acid mutations to the tree")
args = parser.parse_args()
path = args.path
tree_meta = read_tree_meta_data(path)
T = Phylo.read(tree_newick(path), 'newick')
for gene, aln_fname in get_genes_and_alignments(path, tree=True):
if gene!='nuc':
muts = get_amino_acid_mutations(T, aln_fname)
for node_name in tree_meta:
tree_meta[node_name][gene+'_mutations'] = muts[node_name]
write_tree_meta_data(path, tree_meta)
def export_metadata_json(T, path, prefix, reference, isvcf=False, indent=1):
print("Writing out metaprocess")
mjson = {}
mjson["virus_count"] = T.count_terminals()
from datetime import date
mjson["updated"] = date.today().strftime('%Y-%m-%d')
mjson["author_info"] = {
"?": {
"paper_url": "?",
"journal": "?",
"title": "?",
"n": 1
}
}
mjson["seq_author_map"] = {}
from collections import defaultdict
cmaps = defaultdict(list)
with open(color_maps(path), 'r') as cfile:
for line in cfile:
try:
trait, name, color = line.strip().split('\t')
except:
continue
cmaps[trait].append((name, color))
#if drug-resistance colours have been auto-generated, get these too
import os.path
if os.path.isfile(drm_color_maps(path)):
with open(drm_color_maps(path), 'r') as cfile:
for line in cfile:
try:
trait, name, color = line.strip().split('\t')
except:
continue
cmaps[trait].append((name, color))
mjson["color_options"] = {
"gt": {
"menuItem": "genotype",
"type": "discrete",
"legendTitle": "Genotype",
"key": "genotype"
},
"num_date": {
"menuItem": "date",
"type": "continuous",
"legendTitle": "Sampling date",
"key": "num_date"
}
}
for trait in cmaps:
mjson["color_options"][trait] = {
"menuItem": trait,
"type": "discrete",
"color_map": cmaps[trait],
"legendTitle": trait,
"key": trait
}
mjson["panels"] = ["tree", "map", "entropy"]
mjson["title"] = "NextTB"
mjson["maintainer"] = "Emma Hodcroft"
mjson["geo"] = {}
lat_long_defs = load_lat_long_defs()
for geo_trait in ['region', "country", 'division']:
mjson["geo"][geo_trait] = {}
for n in T.find_clades():
if geo_trait in n.attr:
place = n.attr[geo_trait]
if (place not in mjson["geo"][geo_trait]
and place in lat_long_defs):
mjson["geo"][geo_trait][place] = lat_long_defs[place]
mjson["commit"] = "unknown"
mjson["filters"] = ["country", "region", "division"]
genes = load_features(reference)
anno = {}
for feat, aln_fname in get_genes_and_alignments(path, tree=False):
if feat in genes:
anno[feat] = {
"start": int(genes[feat].location.start),
"end": int(genes[feat].location.end),
"strand": genes[feat].location.strand
}
if isvcf:
#if vcf, there is no 'gene' called 'nuc' that will be read in
#above, so manually include it here.
from filenames import ref_fasta
from Bio import SeqIO
refSeq = SeqIO.parse(ref_fasta(path), format='fasta').next()
anno['nuc'] = {"start": 1, "end": len(refSeq.seq), "strand": 1}
mjson["annotations"] = anno
write_json(mjson, meta_json(path, prefix), indent=indent)