dmel_ids = [x["FBgn"] for x in obb]
hmel_ids = [x["locus"] for x in hpg]
mapped_hmel_ids = mapped(hmel_ids)
orthologues_with_data = [x for x in orthologues if x["Dmel_ID"] in dmel_ids and x["Hmel_ID"] in mapped_hmel_ids]
dmel_ids_with_orthologues = list()
for o in orthologues_with_data:
for l in obb:
if o["Dmel_ID"] == l["FBgn"]:
dmel_ids_with_orthologues.append(dict(l)) # use dict explicitly to force deep copy
hmel_ids_with_orthologues = list()
for o in orthologues_with_data:
for l in hpg:
if o["Hmel_ID"] == l["locus"]:
hmel_ids_with_orthologues.append(dict(l)) # use dict explicitly to force deep copy
# control_gene_names = getControlGenes([x['locus'] for x in hmel_ids_with_orthologues], 20)
control_gene_names = getControlGenes([y[0] for y in imm], 10)
control_genes = [x for x in hpg if x["locus"] in control_gene_names]
immunity_genes = [x for x in hpg if x["locus"] in [y[0] for y in imm]]
###
#
# Add class information to H. mel genes
#
for (g, d) in zip(hmel_ids_with_orthologues, dmel_ids_with_orthologues):
g["gene_name"] = d["Locus"]
g["Class"] = d["Class"]
g["Cell_Hum"] = d["Cell_Hum"]
for g in control_genes:
g["gene_name"] = ""
g["Class"] = "control"
# immunity genes by class
classes = {"humoral_recognition": "1", "cellular_recognition": "2", "RNAi": "3", "AMP": "4", "signaling": "5"}
# load results from HelPopGen run
with open("../results/results_thres0.1_150615052013.csv", "r") as f:
field_names = f.readline().rstrip().split(",")
rows = [x for x in csv.DictReader(f, fieldnames=field_names)]
# load list of immunity genes
with open("../data/hmel_dmel_orthologues.csv", "r") as f:
field_names = f.readline().rstrip().split(",")
immunity_genes = [x for x in csv.DictReader(f, fieldnames=field_names)]
mapped_immunity_genes = mapped([x["Hmel_ID"] for x in immunity_genes])
control_genes = getControlGenes(mapped_immunity_genes)
# load Obbard 2009 gene table
with open("../data/s027_all.csv", "r") as f:
field_names = f.readline().rstrip().split(",")
Obb_genes = [x for x in csv.DictReader(f, fieldnames=field_names)]
# get classes
for i in immunity_genes:
d = i["Dmel_ID"]
for g in Obb_genes:
if g["FBgn"] == d:
i["Class"] = g["Class"]
i["Cell_Hum"] = g["Cell_Hum"]
with open("../results/results_004314052013.csv", "r") as f:
results = [l.split(",") for l in f.readlines() if any([i in l for i in loci])]
P_N = [float(x[-6]) for x in results]
P_S = [float(x[-5]) for x in results]
D_N = [float(x[-2]) for x in results]
D_S = [float(x[-1]) for x in results]
return 1 - sum([P_N[i] / (P_S[i] + 1) for i in range(len(P_N))]) * sum(D_S) / (sum(D_N) * len(P_S))
# load list of immunity genes
with open("../data/hmel_dmel_orthologues.csv", "r") as f:
field_names = f.readline().rstrip().split(",")
immunity_genes = [x for x in csv.DictReader(f, fieldnames=field_names)]
mapped_immunity_genes = mapped([x["Hmel_ID"] for x in immunity_genes])
control_genes = getControlGenes(mapped_immunity_genes)
# load Obbard 2009 gene table
with open("../data/s027_all.csv", "r") as f:
field_names = f.readline().rstrip().split(",")
Obb_genes = [x for x in csv.DictReader(f, fieldnames=field_names)]
# get classes
for i in immunity_genes:
d = i["Dmel_ID"]
for g in Obb_genes:
if g["FBgn"] == d:
i["Class"] = g["Class"]
i["Cell_Hum"] = g["Cell_Hum"]
# with open("../data/ImmunityGenes.csv", 'r') as f:
