def plot_correlations(self):
# Figure that calculates the Euclidean distance between each EFM and
# the "experimental" flow, and overlays that information on the
# standard "Pareto" plot
exp_flux_df = self.fluxes_df.copy()
# remove the exchange reactions (xchg_*)
exp_flux_df = exp_flux_df.loc[
exp_flux_df.reaction_id.str.find('xchg') != 0, :]
exp_flux_df.reaction_id = exp_flux_df.reaction_id.apply(
D.FIX_REACTION_ID)
fig0, axs0 = plt.subplots(1, 2, figsize=(15, 7))
rates_df, params_df, km_df, enzyme_abundance_df = \
get_concatenated_raw_data('standard')
CORR_FLUX_L = 'correlation with exp fluxes'
LOG_LIKELIHOOD_L = 'log likelihood of flow'
figure_data = D.get_figure_data()
data = figure_data['standard']
data[CORR_FLUX_L] = rates_df.transpose().corr().loc[9999]
# calculate the likelihood of each EFM according to the measured flux
# distribution
data[LOG_LIKELIHOOD_L] = 0
joined_rates = rates_df.T
joined_rates['std'] = exp_flux_df[D.MEAS_STDEV_L]
joined_rates['std'] = joined_rates['std'].fillna(
0) + 1.0 # add a baseline stdev of 10%
for efm in data.index:
x = (joined_rates[efm] - joined_rates[9999]) / joined_rates['std']
log_likelihood = -(x**2).sum() / 2
data.loc[efm, LOG_LIKELIHOOD_L] = log_likelihood
data.loc[data[D.STRICTLY_ANAEROBIC_L],
D.GROWTH_RATE_L] = 0 # remove oxygen-sensitive EFMs
cmap = D.pareto_cmap(0.88)
D.plot_basic_pareto(data,
axs0[0],
x=D.YIELD_L,
y=D.GROWTH_RATE_L,
c=CORR_FLUX_L,
cmap=cmap,
vmin=0,
vmax=1,
linewidth=0,
s=20)
D.plot_basic_pareto(data,
axs0[1],
x=D.YIELD_L,
y=D.GROWTH_RATE_L,
c=LOG_LIKELIHOOD_L,
cmap=cmap,
linewidth=0,
s=20,
vmin=-100000,
vmax=0)
for ax in axs0:
for efm in D.efm_dict.keys():
xy = np.array(data.loc[efm,
[D.YIELD_L, D.GROWTH_RATE_L]].tolist())
xytext = xy + np.array((-1, 0.025))
ax.annotate(xy=xy,
s=D.efm_dict[efm]['label'],
xycoords='data',
xytext=xytext,
arrowprops=dict(facecolor='black',
shrink=0.05,
width=2,
headwidth=4))
ax.set_xlim(-1e-3, 1.1 * data[D.YIELD_L].max())
ax.set_ylim(-1e-3, 1.15 * data[D.GROWTH_RATE_L].max())
axs0[0].set_title('distance from measured fluxes (correlation)')
axs0[1].set_title('distance from measured fluxes (likelihood)')
fig0.tight_layout()
fig0.savefig(os.path.join(D.OUTPUT_DIR, 'Fig_flux_correlation.pdf'))
# -*- coding: utf-8 -*-
"""
Created on Tue Dec 8 10:38:03 2015
@author: noore
"""
import zipfile, os
import pandas as pd
import definitions as D
TSNE_DIM_1 = 't-SNE dim1'
TSNE_DIM_2 = 't-SNE dim2'
if __name__ == '__main__':
figure_data = D.get_figure_data()
for fig_name in ['monod_glucose_aero', 'monod_glucose_anae']:
zip_fname = D.DATA_FILES[fig_name][0][0]
prefix, ext = os.path.splitext(os.path.basename(zip_fname))
with zipfile.ZipFile(zip_fname, 'r') as z:
rates_df = pd.read_csv(z.open('%s/rates.csv' % prefix, 'r'),
header=0,
index_col=0)
stoich_df = pd.read_csv(z.open('%s/stoich.csv' % prefix, 'r'),
header=None,
index_col=None)
kcat_df = pd.read_csv(z.open('%s/kcats.csv' % prefix, 'r'),
header=None,