def score1C(sim, data_df):
sim_w = np.unique(sim.U, return_counts=True)[1] / sim.N
est_w = data_df.groupby('cluster_id').vaf_purity.count().values / len(
data_df)
est_phi = data_df.groupby('cluster_id').vaf_purity.mean().values
return score1C_base(sim.phi, est_phi, sim_w, est_w)
def score1C(sim, cluster_table):
sim_w = np.unique(sim.U, return_counts=True)[1] / sim.N
est_w = cluster_table['Cluster_Assignment'] / cluster_table[
'Cluster_Assignment'].sum()
est_phi = cluster_table['postDP_ccf_mean']
return score1C_base(sim.phi, est_phi, sim_w, est_w)
def score1C(sim, est):
sim_w = np.unique(sim.U, return_counts=True)[1] / sim.N
pre_est_w = np.zeros(est.J)
pre_counts = np.unique(np.argmax(est.qun, axis=1), return_counts=True)
pre_est_w[pre_counts[0]] = pre_counts[1]
est_w = pre_est_w / len(sim.U)
return score1C_base(sim.phi, est.phi, sim_w, est_w)
def score1C(sim, loci_table):
sim_w = np.unique(sim.U, return_counts=True)[1] / sim.N
est_w = loci_table[loci_table.cluster > 0].groupby(
'cluster')['tumor.vaf'].count() / len(loci_table)
est_phi = loci_table[loci_table.cluster > 0].groupby(
'cluster')['tumor.vaf'].mean() / 100
return score1C_base(sim.phi, est_phi, sim_w, est_w)
def score1C(sim, cluster_table):
sim_w = np.unique(sim.U, return_counts=True)[1] / sim.N
est_w = cluster_table['no.of.mutations'] / cluster_table[
'no.of.mutations'].sum()
est_phi = cluster_table['location']
return score1C_base(sim.phi, est_phi, sim_w, est_w)
def score1C(sim, loci_table):
sim_w = np.unique(sim.U, return_counts=True)[1]/sim.N
pre_cluster_table = loci_table.groupby('ccube_ccf_mean').rough_mult.count()
est_w = pre_cluster_table.values/len(loci_table)
est_phi = pre_cluster_table.index.values
return score1C_base(sim.phi, est_phi, sim_w, est_w)
row_list.append(folder_path.split('_')[-1])
row_list.append(info_df.median_depth.mean())
(ll_ratio, pval, J_pred, phi_pred_values, weights_pred,
pred_cluster_assign, pred_subclonal, pred_profile, pred_signatures,
pred_signatures_mut, est_dist, runtime) = \
method_function_dict[method](folder_path)
row_list.append(J_pred)
row_list.append(ll_ratio)
row_list.append(pval)
if J_pred is not None:
row_list.append(score1B_base(J_true, J_pred))
else:
row_list.append(np.nan)
if phi_pred_values is not None:
row_list.append(
score1C_base(phi_true_values, phi_pred_values, weights_true,
weights_pred))
else:
row_list.append(np.nan)
if pred_cluster_assign is not None:
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,
def score1C(sim, cluster_table):
sim_w = np.unique(sim.U, return_counts=True)[1] / sim.N
est_w = cluster_table['size'] / cluster_table['size'].sum()
est_phi = cluster_table['mean']
return score1C_base(sim.phi, est_phi, sim_w, est_w)
def score1C(sim, data_df):
sim_w = np.unique(sim.U, return_counts=True)[1]/sim.N
est_w = data_df.groupby('Clonality').CCF.count().values/len(data_df)
est_phi = data_df.groupby('Clonality').CCF.mean().values
return score1C_base(sim.phi, est_phi, sim_w, est_w)
row_list.append(info_df.perc_dip.mean())
row_list.append(folder_path.split('_')[-1])
row_list.append(info_df.median_depth.mean())
(ll_ratio, pval, J_pred, phi_pred_values, weights_pred,
pred_cluster_assign, pred_subclonal, pred_profile, pred_signatures,
pred_signatures_mut, est_dist, runtime) = \
method_function_dict[method](folder_path)
row_list.append(J_pred)
row_list.append(ll_ratio)
row_list.append(pval)
if J_pred is not None:
row_list.append(score1B_base(J_true, J_pred))
else:
row_list.append(np.nan)
if phi_pred_values is not None:
row_list.append(score1C_base(phi_true_values, phi_pred_values,
weights_true, weights_pred))
else:
row_list.append(np.nan)
if pred_cluster_assign is not None:
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)
