def study_type(study):
ancestor_dict = {}
exps = v5.study_to_exps(study)
for exp in exps:
ancestors = v5.exp_to_celltypes(exp)
for celltype in v5.exp_to_celltypes(exp):
ancestors += co.get_ancestors(celltype)
ancestor_dict[exp] = ancestors
if len(exps) == 1:
ancestors = ancestor_dict[exps[0]]
else:
first = True
for exp in ancestor_dict:
if first:
ancestors = set(ancestor_dict[exp])
first = False
continue
ancestors = ancestors | set(ancestor_dict[exp])
ancestors = list(ancestors)
common = []
for term_id in co.get_terms_without_children(list(ancestors)):
common.append(co.get_term_name(term_id))
common = '; '.join(common)
return common
def is_type_available(celltype, study):
study = v5.study_to_exps(study)
for exp in v5.get_exps():
if exp in study:
continue
else:
if celltype in v5.exp_to_celltypes(exp):
return True
return False
def get_exp_proportion(exp):
study = v5.exp_to_study(exp)
nonzero = pd.read_csv(decon_temp + 'nonzero_Weight_'
+ study + '.tsv', sep = '\t',index_col=0)
exps = v5.study_to_exps(study)
if len(exps) == 1:
singleExp = True
else:
singleExp = False
return get_proportion(exp, nonzero,singleExp)
def get_study_proportion(study):
nonzero = pd.read_csv(decon_temp + 'nonzero_Weight_'
+ study + '.tsv', sep = '\t',index_col=0)
exps = v5.study_to_exps(study)
if study not in single_exp_list:
singleExp = False
else:
singleExp = True
proportion = []
for exp in exps:
proportion.append(get_proportion(exp, nonzero, singleExp))
avg = np.mean(np.array(proportion))
return avg
def scatterplot(ax, exp, celltype, remove_study = False):
study = v5.exp_to_study(exp)
if remove_study:
if not is_type_available(celltype, study):
print("Cell type ({}) not provided in reference ".format(celltype)
+ "matrix for this study.")
return
query = get_query_expression(exp)
exp_list = v5.study_to_exps(study)
reference = get_reference_expression(celltype, exp_list, remove_study)
ax.scatter(reference[0], query)
ax.set(xlim=(0, 450000), ylim=(0, 450000))
diag_line, = ax.plot(ax.get_xlim(), ax.get_ylim(), ls="--", c=".3")
xstick = np.arange(0, 450000 ,100000)
ax.set_xticks(xstick)
ax.set_yticks(xstick)
ax.set(xlabel = "{} ({} experiments)".format(co.get_term_name(celltype),
reference[1]), ylabel = exp)
def proportions_all():
"""
Returns a dictionary with experiment accession numbers as keys and
proportions correct as values.
"""
# update because that makes no sense
proportions = {}
studies = v5.get_studies()
for study in studies:
# try:
nonzero = pd.read_csv(decon_temp + 'nonzero_Normal_' + study + '.tsv',
sep='\t')
exps = v5.study_to_exps(study)
if len(exps) == 1:
singleExp = True
else:
singleExp = False
for exp in exps:
proportions[exp] = get_proportion(exp, nonzero, singleExp)
# for exp in exps:
# proportions[exp] = get_proportion(exp, nonzero)
# if len(exps) == 1:
# print(study)
# continue
# else:
# for exp in exps:
# proportions[exp] = get_proportion(exp, nonzero)
# except:
# print("Shit")
# pass
return proportions