def score2C(sim, data_df):
"""
this metric compares the sensitivity, specificity, precision of mutations
classified as clonal vs subclonal. We take the convention that the clone
with the largest phi is clonal and the rest is subclonal
we take also the convention that subclonal are the positive examples, and
clonal the negative ones.
"""
sim_att = sim.U
sim_clonal_idx = np.argmax(sim.phi)
sim_binary = (sim_att != sim_clonal_idx).astype(int)
return score2C_base(sim_binary, data_df.clonality_binary)
def score2C(sim, loci_table):
"""
this metric compares the sensitivity, specificity, precision of mutations
classified as clonal vs subclonal. We take the convention that the clone
with the largest phi is clonal and the rest is subclonal
we take also the convention that subclonal are the positive examples, and
clonal the negative ones.
"""
sim_att = sim.U
sim_clonal_idx = np.argmax(sim.phi)
sim_binary = (sim_att != sim_clonal_idx).astype(int)
est_att = loci_table.cluster_id
est_clonal_idx = np.argmax(pre_cluster_table.index.tolist())
est_binary = (est_att != est_clonal_idx).astype(int)
return score2C_base(sim_binary, est_binary)
def score2C(sim, data_df):
"""
this metric compares the sensitivity, specificity, precision of mutations
classified as clonal vs subclonal. We take the convention that the clone
with the largest phi is clonal and the rest is subclonal
we take also the convention that subclonal are the positive examples, and
clonal the negative ones.
"""
sim_att = sim.U
sim_clonal_idx = np.argmax(sim.phi)
sim_binary = (sim_att != sim_clonal_idx).astype(int)
true_df = sim._get_data_df()
ordered_loci_table = pd.merge(true_df, data_df, on='mutation_id')
est_att = ordered_loci_table.cluster_id
est_clonal_idx = data_df.groupby('cluster_id').vaf_purity.mean().idxmax()
est_binary = (est_att != est_clonal_idx).astype(int)
return score2C_base(sim_binary, est_binary)
def score2C(sim, loci_table, cluster_table):
"""
this metric compares the sensitivity, specificity, precision of mutations
classified as clonal vs subclonal. We take the convention that the clone
with the largest phi is clonal and the rest is subclonal
we take also the convention that subclonal are the positive examples, and
clonal the negative ones.
"""
sim_att = sim.U
sim_clonal_idx = np.argmax(sim.phi)
sim_binary = (sim_att != sim_clonal_idx).astype(int)
true_df = sim._get_data_df()
est_att = loci_table.Cluster_Assignment
est_clonal_idx = cluster_table.sort_values(
by='postDP_ccf_mean').iloc[-1]['Cluster_ID']
est_binary = (est_att != est_clonal_idx).astype(int)
return score2C_base(sim_binary, est_binary)
ordered_table = pd.merge(pred_cluster_assign,
true_cluster_assign,
on='mutation_id',
how='inner')
if len(true_cluster_assign) < 20000:
row_list.append(
score2A_base(ordered_table.true_cluster_id,
ordered_table.pred_cluster_id))
else:
row_list.append(np.nan)
ordered_table = pd.merge(pred_subclonal,
true_subclonal,
on='mutation_id',
how='inner')
auc, accuracy, sensitivity, specificity, precision = \
score2C_base(ordered_table.true_subclonal,
ordered_table.pred_subclonal)
for v in (auc, accuracy, sensitivity, specificity, precision):
row_list.append(v)
else:
for i in range(6):
row_list.append(np.nan)
if pred_profile is not None:
row_list.append(score_sig_1A_base(sig_profile_1A, pred_profile))
row_list.append(score_sig_1B_base(sig_profile_1B, pred_profile))
auc, accuracy, sensitivity, specificity, precision = \
score_sig_1C_base(true_signatures_1C, pred_signatures)
for v in (auc, accuracy, sensitivity, specificity, precision):
row_list.append(v)
if method == 'deconstructsigs':
nb_rows = min(est_dist.shape[0], true_profile_1E.shape[0])
score_sig_1D = score_sig_1D_base(
