def peptide_fdr(psms, peptide_fdr_threshold, pi0_lambda, plot_path, nofdr):
pi0_method = 'bootstrap'
pi0_smooth_df = 3
pi0_smooth_log_pi0 = False
pfdr = False
if nofdr:
peptides = psms.groupby(['modified_peptide', 'decoy',
'q_value'])['pp'].max().reset_index()
targets = peptides[~peptides['decoy']].copy()
decoys = peptides[peptides['decoy']].copy()
else:
peptides = psms.groupby(['modified_peptide',
'decoy'])['pp'].max().reset_index()
targets = peptides[~peptides['decoy']].copy()
decoys = peptides[peptides['decoy']].copy()
targets['p_value'] = pemp(targets['pp'], decoys['pp'])
targets['q_value'] = qvalue(
targets['p_value'],
pi0est(targets['p_value'], pi0_lambda, pi0_method, pi0_smooth_df,
pi0_smooth_log_pi0)['pi0'], pfdr)
plot(plot_path, "global peptide scores", targets['pp'], decoys['pp'])
return targets[targets['q_value'] < peptide_fdr_threshold][
'modified_peptide'], np.min(
targets[targets['q_value'] < peptide_fdr_threshold]['pp'])
def test_random(regtest):
np.random.seed(1)
for i in (1, 2, 5, 10, 100):
for j in (1, 2, 5, 10, 100):
stat = np.random.random((i, ))
stat0 = np.random.random((j, ))
print(i, j, file=regtest)
print(pemp(stat, stat0), file=regtest)
def test_random(regtest):
np.random.seed(1)
for i in (1, 2, 5, 10, 100):
for j in (1, 2, 5, 10, 100):
stat = np.random.random((i,))
stat0 = np.random.random((j,))
print(i, j, file=regtest)
print(pemp(stat, stat0), file=regtest)
def test_1():
stat = np.array([0, 1, 3, 2, 0.1, 0.5, 0.6, 0.3, 0.5, 0.6, 0.2, 0.5])
stat0 = np.array([0.4, 0.2, 0.5, 1, 0.5, 0.7, 0.2, 0.4])
np.testing.assert_almost_equal(
pemp(stat, stat0),
np.array([
1.0, 0.125, 0.125, 0.125, 1.0, 0.25, 0.25, 0.75, 0.25, 0.25, 0.75,
0.25
]))
def protein_fdr(psms, protein_fdr_threshold, pi0_lambda, plot_path):
pi0_method = 'bootstrap'
pi0_smooth_df = 3
pi0_smooth_log_pi0 = False
pfdr = False
proteins = psms.groupby(['protein_id', 'decoy'])['pp'].max().reset_index()
targets = proteins[~proteins['decoy']].copy()
decoys = proteins[proteins['decoy']].copy()
targets['p_value'] = pemp(targets['pp'], decoys['pp'])
targets['q_value'] = qvalue(
targets['p_value'],
pi0est(targets['p_value'], pi0_lambda, pi0_method, pi0_smooth_df,
pi0_smooth_log_pi0)['pi0'], pfdr)
plot(plot_path, "global protein scores", targets['pp'], decoys['pp'])
return targets[
targets['q_value'] < protein_fdr_threshold]['protein_id'], np.min(
targets[targets['q_value'] < protein_fdr_threshold]['pp'])
def test_1():
stat = np.array([0, 1, 3, 2, 0.1, 0.5, 0.6, 0.3, 0.5, 0.6, 0.2, 0.5])
stat0 = np.array([0.4, 0.2, 0.5, 1, 0.5, 0.7, 0.2, 0.4])
np.testing.assert_almost_equal(pemp(stat, stat0),
np.array([1.0, 0.125, 0.125, 0.125, 1.0, 0.25, 0.25, 0.75, 0.25, 0.25, 0.75, 0.25]))
def combine_scores(self, scores):
combined_scores = scores.groupby(
['condition_id', 'bait_id', 'prey_id', 'decoy',
'confidence_bin'])['score'].mean().reset_index()
combined_scores.loc[combined_scores['decoy'] == 0, 'pvalue'] = pemp(
combined_scores[combined_scores['decoy'] == 0]['score'],
combined_scores[combined_scores['decoy'] == 1]['score'])
pi0_combined = pi0est(
combined_scores[combined_scores['decoy'] == 0]['pvalue'],
self.pi0_lambda, self.pi0_method, self.pi0_smooth_df,
self.pi0_smooth_log_pi0)['pi0']
combined_scores.loc[combined_scores['decoy'] == 0, 'qvalue'] = qvalue(
combined_scores[combined_scores['decoy'] == 0]['pvalue'],
pi0_combined, self.pfdr)
click.echo("Info: Unique interactions detected before integration:")
click.echo(
"%s (at q-value < 0.01)" %
(scores[(scores['decoy'] == 0) & (scores['qvalue'] < 0.01)][[
'bait_id', 'prey_id'
]].drop_duplicates().shape[0]))
click.echo(
"%s (at q-value < 0.05)" %
(scores[(scores['decoy'] == 0) & (scores['qvalue'] < 0.05)][[
'bait_id', 'prey_id'
]].drop_duplicates().shape[0]))
click.echo("%s (at q-value < 0.1)" %
(scores[(scores['decoy'] == 0) & (scores['qvalue'] < 0.1)][[
'bait_id', 'prey_id'
]].drop_duplicates().shape[0]))
click.echo("%s (at q-value < 0.2)" %
(scores[(scores['decoy'] == 0) & (scores['qvalue'] < 0.2)][[
'bait_id', 'prey_id'
]].drop_duplicates().shape[0]))
click.echo("%s (at q-value < 0.5)" %
(scores[(scores['decoy'] == 0) & (scores['qvalue'] < 0.5)][[
'bait_id', 'prey_id'
]].drop_duplicates().shape[0]))
click.echo("Info: Unique interactions detected after integration:")
click.echo("%s (at q-value < 0.01)" %
(combined_scores[(combined_scores['decoy'] == 0)
& (combined_scores['qvalue'] < 0.01)][[
'bait_id', 'prey_id'
]].drop_duplicates().shape[0]))
click.echo("%s (at q-value < 0.05)" %
(combined_scores[(combined_scores['decoy'] == 0)
& (combined_scores['qvalue'] < 0.05)][[
'bait_id', 'prey_id'
]].drop_duplicates().shape[0]))
click.echo("%s (at q-value < 0.1)" %
(combined_scores[(combined_scores['decoy'] == 0)
& (combined_scores['qvalue'] < 0.1)][[
'bait_id', 'prey_id'
]].drop_duplicates().shape[0]))
click.echo("%s (at q-value < 0.2)" %
(combined_scores[(combined_scores['decoy'] == 0)
& (combined_scores['qvalue'] < 0.2)][[
'bait_id', 'prey_id'
]].drop_duplicates().shape[0]))
click.echo("%s (at q-value < 0.5)" %
(combined_scores[(combined_scores['decoy'] == 0)
& (combined_scores['qvalue'] < 0.5)][[
'bait_id', 'prey_id'
]].drop_duplicates().shape[0]))
click.echo("Info: Combined pi0: %s." % pi0_combined)
return combined_scores
