def map_variant_to_mean_full_relative_gamma(datadir,
*,
dose='sober',
filtered=True):
child_gammas = get_child_gammas(datadir)
parent_gammas = get_parent_gammas(datadir)
varcon = mapping_lib.get_mapping('variant', 'control', datadir)
vargamma = mapping_lib.get_mapping('variant', 'gamma', datadir, dose=dose)
conmask = vargamma.index.intersection(varcon.loc[varcon.control].index)
congamma = vargamma.loc[conmask]
sigma = congamma.std().gamma
z = -sigma # easier to read
unfiltered = (child_gammas / parent_gammas) - 1
if filtered:
geodelt_gammas = unfiltered.where(parent_gammas < (_Z_THRESHOLD * z))
else:
geodelt_gammas = unfiltered
relgammas = select_dose(geodelt_gammas, dose, datadir)
relgammas = relgammas.stack(level='sid', dropna=False)[['03']].unstack()
if filtered:
colname = 'relgamma'
else:
colname = 'unfiltered_relgamma'
relgammas = pd.DataFrame(relgammas.mean(axis=1), columns=[colname])
relgammas.reset_index(inplace=True)
mapping_lib.make_mapping(relgammas, 'variant', colname, datadir, dose=dose)
def map_variant_to_bin(datadir, dose='sober'):
varrg = mapping_lib.get_mapping('variant', 'relgamma', datadir, dose=dose)
bins = relgamma_bins()
rgbin = bin_relgammas(varrg.relgamma.values, bins)
rgbin = pd.DataFrame(rgbin.T, index=varrg.index,
columns=['rgbin']).reset_index()
mapping_lib.make_mapping(rgbin, 'variant', 'rgbin', datadir, dose=dose)
def map_variant_to_mean_full_gamma(datadir, dose='sober'):
allgammas = get_normed_gammas(datadir)
gammas = select_dose(allgammas, dose, datadir)
gammas = gammas.stack(level='sid', dropna=False)[['03']].unstack()
gammas = pd.DataFrame(gammas.mean(axis=1), columns=['gamma'])
gammas.reset_index(inplace=True)
mapping_lib.make_mapping(gammas, 'variant', 'gamma', datadir, dose=dose)
plt.legend(loc='lower left', fontsize='small')
plt.tight_layout()
plotfile = PLOTDIR / 'scatter.agg.png'.format(**locals())
plt.savefig(plotfile, dpi=_FIGDPI)
plt.close()
locusmap = mapping_lib.get_mapping('variant', 'locus_tag', UNGD)
genemap = mapping_lib.get_mapping('locus_tag', 'gene_name', UNGD)
geneids = genemap.loc[locusmap.loc[data.index].locus_tag]
geneids.index = data.index
data['y_meas'] = data.relgamma
data['y_pred'] = cross_predictions
data['gene_name'] = geneids
data['original'] = familymap.original
mapping_lib.make_mapping(data.reset_index(), 'variant', 'y_pred', UNGD)
rhos = list()
for gene, group in data.groupby('gene_name'):
predicted = group.y_pred
measured = group.y_meas
sprrho, _ = st.spearmanr(predicted, measured)
prsrho, _ = st.pearsonr(predicted, measured)
rhos.append(pd.Series({'gene':gene,
'sprrho_convnet':sprrho,
'prsrho_convnet':prsrho}))
plt.figure(figsize=(6,6))
template = 'Predictions vs. Measurements\n{gene}'
main_title_str = template.format(**locals())
plt.title(main_title_str)