def _create_mapping(r):
_, query_start, query_end = parse_header(ali.ids[0])
# create mapping from query into PDB Uniprot sequence
# A_i will be query sequence indices, A_j Uniprot sequence indices
m = map_indices(ali[0], query_start, query_end,
ali[r["alignment_id"]], r["alignment_start"],
r["alignment_end"])
# create mapping from PDB Uniprot into seqres numbering
# j will be Uniprot sequence index, k seqres index
n = pd.DataFrame({
"j":
list(range(r["uniprot_start"], r["uniprot_end"] + 1)),
"k":
list(range(r["resseq_start"], r["resseq_end"] + 1)),
})
# need to convert to strings since other mapping has indices as strings
n.loc[:, "j"] = n.j.astype(str)
n.loc[:, "k"] = n.k.astype(str)
# join over Uniprot indices (i.e. j);
# get rid of any position that is not aligned
mn = m.merge(n, on="j", how="inner").dropna()
# extract final mapping from seqres (k) to query (i)
map_ = dict(zip(mn.k, mn.i))
return map_, mn
def align_dca2pdb(msa_name, pdbseq, msaseq):
"""
Some code taken from
https://github.com/bsir/dca-frustratometer/blob/master/dca_frustratometer.py
:param msa_name:
:param pdbseq: PDB seq string
:param msaseq: MSA seq string
:return:
"""
import numpy as np
from Bio import pairwise2
from evcouplings.compare import mapping as evmp
print("(map_dca2pdb)\taligning dca sequence to pdb coord sequence...")
# need to penalize for opening and adding gaps otherwise mapping is off (s param {-.5,-.1})
alignments_1 = pairwise2.align.globalxs(pdbseq[0], msaseq[0], -.5, -.1)
alignments_2 = pairwise2.align.globalxs(pdbseq[1], msaseq[1], -.5, -.1)
print(pairwise2.format_alignment(*alignments_1[0], full_sequences=True))
print(pairwise2.format_alignment(*alignments_2[0], full_sequences=True))
map_1 = evmp.map_indices(alignments_1[0][0], 1, 0, alignments_1[0][1], 1,
0)
map_2 = evmp.map_indices(alignments_2[0][0], 1 + len(pdbseq[0]), 0,
alignments_2[0][1], 1 + len(msaseq[0]), 0)
map_pdb_dca = map_1.append(map_2)
map_pdb_dca = map_pdb_dca.rename(columns={
"i": "pdb_i",
"A_i": "pdb_res",
"j": "dca_i",
"A_j": "dca_res"
})
outfile = "results\\reference_maps\\ref_map_{}.txt".format(
msa_name.strip(".fas"))
np.savetxt(outfile,
map_pdb_dca,
header="pdb_i\tpdb_res\tdca_i\tdca_res",
fmt="%s\t%s\t%s\t%s",
comments='')
print("(map_dca2pdb)\tWrote {}".format(outfile))
map_pdb_dca = map_pdb_dca.dropna()
map_dca2pdb_dict = dict(zip(map_pdb_dca["dca_i"], map_pdb_dca["pdb_i"]))
return map_dca2pdb_dict