def get_maxpvals(condition):
alldata = {}
allgroups = {}
maxpvals = {}
for i, gseid in enumerate([
gseid_ for gseid_ in listdir('../data/expression')
if gseid_.startswith('GSE')
]):
if not gseid.startswith('GSE'):
continue
maxpvals[gseid] = 0
alldata[gseid] = {}
groups = pd.read_csv(join('../data/expression', gseid,
'processed/group_labels.tsv'),
index_col='group_name',
sep='\t')
allgroups[gseid] = groups[groups.group_condition == condition]
if len(allgroups[gseid]):
for j, group in enumerate(allgroups[gseid].index.tolist()):
alldata[gseid][group] = {}
alldata[gseid][group]['fc'] = utils.non_nan(
np.loadtxt(
'../gendata/coexpression/{}/seqcorrs_{}_1000.dat'.
format(gseid, group)))
alldata[gseid][group]['rdma'] = utils.non_nan(
np.loadtxt(
'../gendata/coexpression/{}/seqcorrs_{}_rdm_a_1000.dat'
.format(gseid, group)))
alldata[gseid][group]['rdmb'] = utils.non_nan(
np.loadtxt(
'../gendata/coexpression/{}/seqcorrs_{}_rdm_b_1000.dat'
.format(gseid, group)))
pval_a = utils.mwpval(alldata[gseid][group]['fc'],
alldata[gseid][group]['rdma'])
pval_b = utils.mwpval(alldata[gseid][group]['fc'],
alldata[gseid][group]['rdmb'])
maxpvals[gseid] = max([maxpvals[gseid], pval_a, pval_b])
else:
maxpvals[gseid] = np.nan
return maxpvals
default=None,
help='Override output filepath')
args = parser.parse_args()
if args.out_file is None:
out_file = '../gendata/plots/go_asthma_copd_bp_mf_cc.pdf'
else:
out_file = args.out_file
if args.config is not None:
config = utils.read_config(args.config)
types = ['fc', 'rdm_a', 'rdm_b']
seqsims_cc = {
tp:
non_nan(np.loadtxt('../gendata/seqsim/seqsims_{}_cc_1000.dat'.format(tp)))
for tp in types
}
seqsims_mf = {
tp:
non_nan(np.loadtxt('../gendata/seqsim/seqsims_{}_mf_1000.dat'.format(tp)))
for tp in types
}
seqsims_bp = {
tp:
non_nan(np.loadtxt('../gendata/seqsim/seqsims_{}_bp_1000.dat'.format(tp)))
for tp in types
}
plt.figure(figsize=[8, 4])
data = [
maxpvals = {}
for i, gseid in enumerate([
gseid_ for gseid_ in listdir('../data/expression')
if gseid_.startswith('GSE')
]):
maxpvals[gseid] = 0
alldata[gseid] = {}
groups = pd.read_csv(join('../data/expression', gseid,
'processed/group_labels.tsv'),
index_col='group_name',
sep='\t')
allgroups[gseid] = groups[groups.group_condition == 'healthy']
for j, group in enumerate(allgroups[gseid].index.tolist()):
alldata[gseid][group] = {}
alldata[gseid][group]['fc'] = utils.non_nan(
np.loadtxt(
'../gendata/coexpression/{}/seqcorrs_{}_1000.dat'.format(
gseid, group)))
alldata[gseid][group]['rdma'] = utils.non_nan(
np.loadtxt(
'../gendata/coexpression/{}/seqcorrs_{}_rdm_a_1000.dat'.format(
gseid, group)))
alldata[gseid][group]['rdmb'] = utils.non_nan(
np.loadtxt(
'../gendata/coexpression/{}/seqcorrs_{}_rdm_b_1000.dat'.format(
gseid, group)))
pval_a = utils.mwpval(alldata[gseid][group]['fc'],
alldata[gseid][group]['rdma'])
pval_b = utils.mwpval(alldata[gseid][group]['fc'],
alldata[gseid][group]['rdmb'])
maxpvals[gseid] = max([maxpvals[gseid], pval_a, pval_b])
diseases = pd.read_csv(
'../data/disease_ontology/processed/diseases_size_min_50.tsv',
sep='\t',
index_col='diseaseId')
obs_dir = '../gendata/seqsim/disgenet_diseases/related'
N_samples = 100
pairs = [pair.split('_') for pair in listdir(obs_dir)]
obs_seqsims = []
typea_seqsims = []
typeb_seqsims = []
for pair in pairs:
pair = '_'.join(pair)
obs_seqsims.append(
non_nan(np.loadtxt(join(obs_dir, pair, 'seqsims_fc.dat'))))
typea_seqsims.append(
non_nan(np.loadtxt(join(obs_dir, pair, 'seqsims_rdm_a.dat'))))
typeb_seqsims.append(
non_nan(np.loadtxt(join(obs_dir, pair, 'seqsims_rdm_b.dat'))))
ylbl = [
diseases.loc[d0].diseaseName + '---' + diseases.loc[d1].diseaseName
for d0, d1 in pairs
]
ylbl_short = [
utils.trim_text(diseases.loc[d0].diseaseName, maxchar=15) + '---' +
utils.trim_text(diseases.loc[d1].diseaseName, maxchar=15)
for d0, d1 in pairs
]
if args.out_file is None:
out_file = '../gendata/plots/asthma_pneumonia_ipf.pdf'
else:
out_file = args.out_file
if args.config is not None:
config = utils.read_config(args.config)
def non_nan(arr):
arr = np.asarray(arr)
return arr[~np.isnan(arr)]
asthma_copd_disease_4302 = non_nan(
np.loadtxt(
'../gendata/coexpression/GSE4302/seqcorrs_disease_gsms_1000.dat'))
asthma_pneumonia_disease = non_nan(
np.loadtxt(
'../gendata/coexpression/asthma_pneumonia/seqcorrs_disease_gsms.dat'))
asthma_ipf_disease = non_nan(
np.loadtxt('../gendata/coexpression/asthma_ipf/seqcorrs_disease_gsms.dat'))
boxprops = {'linewidth': 1, 'zorder': 3}
whiskerprops = {'linewidth': 1, 'zorder': 3}
capprops = {'linewidth': 1, 'zorder': 3}
medianprops = {'color': 'red', 'linewidth': 1.5, 'zorder': 6}
flierprops = {'marker': 'o', 'markeredgecolor': 'lightgray', 'zorder': 1}
labels = ['Ast.-pneumonia', 'Ast.-IPF', 'Asthma-COPD']
if args.out_file is None:
out_file = '../gendata/plots/asthma_pneumonia_ipf.pdf'
else:
out_file = args.out_file
if args.config is not None:
config = utils.read_config(args.config)
def non_nan(arr):
arr = np.asarray(arr)
return arr[~np.isnan(arr)]
asthma_copd_disease_57148 = non_nan(
np.loadtxt(
'../gendata/coexpression/GSE57148/seqcorrs_disease_gsms_1000.dat'))
copd_pneumonia_disease = non_nan(
np.loadtxt(
'../gendata/coexpression/copd_pneumonia/seqcorrs_disease_gsms.dat'))
copd_ipf_disease = non_nan(
np.loadtxt('../gendata/coexpression/copd_ipf/seqcorrs_disease_gsms.dat'))
boxprops = {'linewidth': 1, 'zorder': 3}
whiskerprops = {'linewidth': 1, 'zorder': 3}
capprops = {'linewidth': 1, 'zorder': 3}
medianprops = {'color': 'red', 'linewidth': 1.5, 'zorder': 6}
flierprops = {'marker': 'o', 'markeredgecolor': 'lightgray', 'zorder': 1}
labels = ['Pneumonia-COPD', 'IPF-COPD', 'Asthma-COPD']
pos = [1, 2, 3]
parser.add_argument('--no_show', action='store_true', help='Do not show plots')
parser.add_argument('--out_file',
default=None,
help='Override output filepath')
args = parser.parse_args()
if args.out_file is None:
out_file = '../gendata/plots/asthma_copd_random_diseases_gse57148_boxplot.pdf'
else:
out_file = args.out_file
if args.config is not None:
config = utils.read_config(args.config)
obs_disease = non_nan(
np.loadtxt(
'../gendata/coexpression/GSE57148/seqcorrs_disease_gsms_1000.dat'))
dis = pd.read_csv(
'../gendata/coexpression/rdm_disgenet/diseases_size_min_24_max_36.tsv',
sep='\t',
index_col='diseaseId')
chronic = dis[dis.diseaseName.str.lower().str.contains(
'chronic')].index.tolist()
datadir = '../gendata/coexpression/rdm_disgenet/copd'
filenames = [
filename for filename in listdir(datadir)
if filename.split('_')[1] not in chronic and '_disease' in filename
] # we want unrelated diseases
parser.add_argument('--out_file',
default=None,
help='Override output filepath')
args = parser.parse_args()
if args.out_file is None:
out_file = '../gendata/plots/go_asthma_copd.pdf'
else:
out_file = args.out_file
if args.config is not None:
config = utils.read_config(args.config)
types = ['fc', 'rdm_a', 'rdm_b']
seqsims = {
tp: non_nan(np.loadtxt('../gendata/seqsim/seqsims_{}_1000.dat'.format(tp)))
for tp in types
}
print(utils.mwpval(seqsims['fc'], seqsims['rdm_a']))
print(utils.mwpval(seqsims['fc'], seqsims['rdm_b']))
plt.figure(figsize=[5, 5])
pos = [0, 1, 2]
boxprops = {'linewidth': 1, 'zorder': 3}
whiskerprops = {'linewidth': 1, 'zorder': 3}
capprops = {'linewidth': 1, 'zorder': 3}
medianprops = {'color': 'red', 'linewidth': 1.5, 'zorder': 6}
flierprops = {'marker': 'o', 'markeredgecolor': 'lightgray', 'zorder': 1}
plt.gca().yaxis.grid(True, zorder=0, linestyle=':')
bplot = plt.boxplot([seqsims['rdm_a'], seqsims['rdm_b'], seqsims['fc']],