def test_present_for_all_same_seq():
yaml_file = load_yaml_file(os.path.join(base_dir,"mdl_dir","project.yaml"))
aligned_dict={}
for protein in yaml_file["protein_list"]:
t = load_random_traj(yaml_file, protein)
aligned_dict[protein] = t.top.to_fasta(chain=0)
for protein in yaml_file["protein_list"]:
aligned_seq = aligned_dict[protein]
prt_mapping, prt_seq =_map_residue_ind_seq_ind(yaml_file, protein, aligned_seq)
assert(len(_present_for_all(protein, prt_mapping, prt_seq, aligned_dict))==len(prt_seq))
return
def test_map_residue_seq_with_insert():
yaml_file = load_yaml_file(os.path.join(base_dir,"mdl_dir","project.yaml"))
aligned_dict={}
for protein in yaml_file["protein_list"]:
expected = {}
t = load_random_traj(yaml_file, protein)
expected[protein] = [i.index+3 for i in t.top.residues if i.is_protein]
aligned_dict[protein] = "---"+ t.top.to_fasta(chain=0)
aligned_seq = aligned_dict[protein]
actual,_ =_map_residue_ind_seq_ind(yaml_file, protein, aligned_seq)
assert expected[protein] == list(actual.values())
return
def test_map_residue_seq_with_insert_at_end():
yaml_file = load_yaml_file(os.path.join(base_dir,"mdl_dir","project.yaml"))
aligned_dict={}
for protein in yaml_file["protein_list"]:
expected = {}
t = load_random_traj(yaml_file, protein)
#add an insertion AFTER 10 residues. We expect all but the 10 have
expected[protein] = [i for i in range(t.n_residues) if t.top.residue(i).code is not None]
aligned_dict[protein] = t.top.to_fasta(chain=0)+"---"
aligned_seq = aligned_dict[protein]
actual,_ =_map_residue_ind_seq_ind(yaml_file, protein, aligned_seq)
assert expected[protein] == list(actual.values())
return
def test_map_residue_seq_with_two_inserts():
yaml_file = load_yaml_file(os.path.join(base_dir,"mdl_dir","project.yaml"))
aligned_dict={}
for protein in yaml_file["protein_list"]:
expected = {}
t = load_random_traj(yaml_file, protein)
#add an insertion AFTER 10 residues. and then again at 20
expected[protein] = [i for i in range(10) if t.top.residue(i).code is not None] + \
[i+3 for i in range(10, 20) if t.top.residue(i).code is not None]+\
[i+5 for i in range(20, t.n_residues) if t.top.residue(i).code is not None]
prt_code = t.top.to_fasta(chain=0)
aligned_dict[protein] = prt_code[:10]+\
"---"+ \
prt_code[10:20]+\
"--"+ \
prt_code[20:]
aligned_seq = aligned_dict[protein]
actual,_ =_map_residue_ind_seq_ind(yaml_file, protein, aligned_seq)
assert expected[protein] == list(actual.values())
return
