def get_series():
n = 10
rng = np.random.RandomState(cfg.random_seed)
x = np.linspace(0, 100, n) + rng.normal(0, 0.1, size=n)
x.sort()
shape = Sigslope()
t1 = (-1, 40, 50, 0.2)
y1 = shape.f(t1, x)
t2 = (1, 30, 25, 0.5)
y2 = shape.f(t2, x)
c = -0.95
sigma = 100 * np.array([[1, c], [c, 1]])
noise = rng.multivariate_normal([0, 0], sigma, n)
y = np.c_[y1, y2] + noise
return SeveralGenesOneRegion(
expression=y,
ages=x,
gene_names=['A', 'B'],
region_name='THERE',
original_inds=np.arange(n),
age_scaler=None,
)
def analyze_paired_scores_with_and_without_priors(n_best=10):
nFitter = Fitter(Sigslope())
yFitter = Fitter(Sigslope(priors_name), 'normal')
nFits = get_all_fits(data, nFitter, allow_new_computation=False)
yFits = get_all_fits(data, yFitter, allow_new_computation=False)
score_pairs = [(f1.LOO_score, f2.LOO_score)
for f1, f2 in iterate_fits(nFits, yFits)]
nScores, yScores = zip(*score_pairs)
_, pval = scipy.stats.wilcoxon(nScores, yScores)
pval = pval / 2 # one sided p-value
print '*** wilcoxon signed rank p-value (one sided) = {:.3g}'.format(pval)
# find examples of best improvements
diffs = [(f2.LOO_score - f1.LOO_score, f1.LOO_score, f2.LOO_score, g, r)
for dsname, g, r, f1, f2 in iterate_fits(
nFits, yFits, R2_threshold=-1, return_keys=True)]
diffs.sort(reverse=True)
print 'Gene/Regions for which priors produce best R2 improvement:'
for i, (delta, R2_without, R2_with, g, r) in enumerate(diffs[:10]):
print '{i}) {g}@{r}, delta-R2={delta:.3g}. R2_without={R2_without:.3g}, R2_with={R2_with:.3g}'.format(
**locals())
def plot_theta_diff_scatter(show_title=False):
yFitter = Fitter(Sigslope(priors_name), 'normal')
nFitter = Fitter(Sigslope())
yFits = get_all_fits(data, yFitter)
nFits = get_all_fits(data, nFitter)
pairs = [(nFit.LOO_score, yFit.LOO_score)
for nFit, yFit in iterate_fits(nFits, yFits)]
diff_pairs = [(n, y - n) for n, y in pairs
if n is not None and y is not None]
n, d = zip(*diff_pairs)
fig = plt.figure()
ax = fig.add_axes([0.15, 0.12, 0.8, 0.8])
ax.scatter(n, d, alpha=0.5)
xlims = ax.get_xlim()
ax.plot(xlims, [0, 0], 'k--')
ax.set_xlim(*xlims)
if show_title:
ax.title(r'Improvement from prior on $\theta$ vs. baseline $R^2$',
fontsize=fontsize)
ax.set_xlabel(r'$R^2$(no priors)', fontsize=fontsize)
ax.set_ylabel(r'$R^2$($\theta$) - $R^2$(no priors)', fontsize=fontsize)
ax.tick_params(axis='both', labelsize=fontsize)
return fig
def get_series():
n = 10
rng = np.random.RandomState(cfg.random_seed)
x = np.linspace(0,100,n) + rng.normal(0,0.1,size=n)
x.sort()
shape = Sigslope()
t1 = (-1,40,50,0.2)
y1 = shape.f(t1,x)
t2 = (1,30,25,0.5)
y2 = shape.f(t2,x)
c = -0.95
sigma = 100*np.array([[1, c], [c, 1]])
noise = rng.multivariate_normal([0,0],sigma,n)
y = np.c_[y1,y2] + noise
return SeveralGenesOneRegion(
expression = y,
ages = x,
gene_names = ['A','B'],
region_name = 'THERE',
original_inds = np.arange(n),
age_scaler = None,
)
def analyze_variant(theta, sigma):
theta_priors = priors_name if theta else None
sigma_prior = 'normal' if sigma else None
shape = Sigslope(theta_priors)
fitter = Fitter(shape, sigma_prior)
fits = get_all_fits(data, fitter, allow_new_computation=False)
LOO_scores = [
f.LOO_score for f in iterate_fits(fits) if f.LOO_score is not None
]
mu, sem = bootstrap(LOO_scores, np.mean)
return Bunch(
theta=theta,
sigma=sigma,
LOO_scores=LOO_scores,
mu=mu,
sem=sem,
)
def get_fitter():
shape = Sigslope(priors='sigslope80')
fitter = Fitter(shape, sigma_prior='normal')
return fitter
ax.plot(xpos, h, linewidth=3, label=shape.cache_name())
ax.set_xlim(*zoom)
ax.set_ylim(0, zoom_max * 1.1)
ax.legend(loc='best', fontsize=fontsize, frameon=False)
ax.set_xlabel('test $R^2$ score', fontsize=fontsize)
ax.set_ylabel("probability density", fontsize=fontsize)
ax.tick_params(axis='both', labelsize=fontsize)
return fig
cfg.verbosity = 1
age_scaler = LogScaler()
data = GeneData.load('both').scale_ages(age_scaler)
sigmoid = Sigmoid(priors='sigmoid_wide')
sigslope = Sigslope(priors='sigslope80')
shapes = [sigmoid, sigslope]
fitters = [Fitter(shape, sigma_prior='normal') for shape in shapes]
#####################################################
# Example fits
#####################################################
GRs = [
('ABHD4', 'STC', (5, 8)),
]
for g, r, yrange in GRs:
for fitter in fitters:
print 'Doing {}@{}...'.format(g, r)
series = data.get_one_series(g, r)
theta, _, _, _ = fitter.fit(series.ages, series.single_expression)
fig = plot_one_series(series, fitter.shape, theta, yrange)
tuples = dct_tuples.values()
pairs = [(x[0], x[1]) for x in tuples]
fig = plot_comparison_scatter(pairs, pathway)
filename = join('RP', 'correlation-diff-scatter-{}.png'.format(pathway))
save_figure(fig, filename, b_close=True, under_results=True)
fig = plot_comparison_bar(tuples)
filename = join('RP', 'correlation-diff-bar-{}.png'.format(pathway))
save_figure(fig, filename, b_close=True, under_results=True)
fig = plot_comparison_bar(tuples, several_levels=True)
filename = join(
'RP', 'correlation-diff-bar-several-levels-{}.png'.format(pathway))
save_figure(fig, filename, b_close=True, under_results=True)
disable_all_warnings()
cfg.verbosity = 1
age_scaler = LogScaler()
shape = Sigslope('sigslope80')
fitter = Fitter(shape, sigma_prior='normal')
pathways = ['cannabinoids', 'serotonin']
for pathway in pathways:
data = GeneData.load('both').restrict_pathway(pathway).scale_ages(
age_scaler)
fits = get_all_fits(data,
fitter,
n_correlation_iterations=4,
allow_new_computation=False)
analyze_pathway(pathway, data, fitter, fits)