meta_windows = pd.concat(meta_windows)
meta_windows.reset_index(drop=True,
inplace=True)
meta_windows.worm_gene.replace({'C43B7.2':'figo-1'},
inplace=True)
feat_windows = pd.concat(feat_windows)
feat_windows.reset_index(drop=True,
inplace=True)
#%% N2 analysis only
if N2_analysis:
feat_df, meta_df, idx, gene_list = select_strains(['N2'],
CONTROL_STRAIN,
feat_df=feat,
meta_df=meta)
feat_df.drop_duplicates(inplace=True)
meta_df.drop_duplicates(inplace=True)
# filter features
feat_df, meta_df, featsets = filter_features(feat_df,
meta_df)
stim_cmap = sns.color_palette('Pastel1',3)
stim_lut = dict(zip(STIMULI_ORDER.keys(), stim_cmap))
feat_lut = {f:v for f in featsets['all'] for k,v in stim_lut.items() if k in f}
feat_nonan = impute_nan_inf(feat_df)
window_files = list(WINDOW_FILES.rglob('*_window_*'))
window_feat_files = [f for f in window_files if 'features' in str(f)]
window_feat_files.sort(key=find_window)
window_fname_files = [f for f in window_files if 'filenames' in str(f)]
window_fname_files.sort(key=find_window)
assert (find_window(f[0]) == find_window(f[1])
for f in list(zip(window_feat_files, window_fname_files)))
genes = [g for g in meta.worm_gene.unique() if g != CONTROL_STRAIN]
# genes = [g.replace('C43B7.2', 'figo-1') for g in genes]
genes = [g for g in genes if 'myo' not in g and 'unc-54' not in g]
#%%
feat_df, meta_df, idx, gene_list = select_strains(STRAINS,
CONTROL_STRAIN,
feat_df=feat,
meta_df=meta)
# filter features
feat_df, meta_df, featsets = filter_features(feat_df, meta_df)
strain_lut, stim_lut, feat_lut = make_colormaps(gene_list,
featlist=featsets['all'],
idx=idx,
candidate_gene=STRAINS)
# colorbars to map colors to strains
plot_colormap(strain_lut)
plt.savefig(saveto / 'strain_cmap.png')
plot_cmap_text(strain_lut)
plt.savefig(saveto / 'strain_cmap_text.png')
genes = [g for g in meta_ts.worm_gene.unique() if g != CONTROL_STRAIN]
genes = [g for g in genes if 'myo' not in g and 'unc-54' not in g]
#%%
for g in genes:
print('making ts stimuli plots for {}'.format(g))
candidate_gene = g
timeseries_fname = RAW_DATA_DIR / 'Results' / '{}_timeseries.hdf5'.format(
candidate_gene)
(saveto / candidate_gene).mkdir(exist_ok=True)
# only select strains of interest
meta, idx, gene_list = select_strains(candidate_gene,
CONTROL_STRAIN,
meta_df=meta_ts)
strain_lut, stim_lut = make_colormaps(gene_list, [], idx,
candidate_gene)
if g == 'figo-1':
strain_lut['C43B7.2'] = strain_lut['figo-1']
timeseries_df = pd.read_hdf(timeseries_fname, 'timeseries_df')
# hires_df = pd.read_hdf(timeseries_fname, 'hires_df')
# test_feats = [f for f in timeseries_df.columns if 'radial_velocity' in f]
# t = ['d_relative_to_neck_radial_velocity_head_tip',
# 'relative_to_neck_radial_velocity_head_tip']
meta = pd.read_csv(METADATA_FILE, index_col=None)
assert meta.worm_strain.unique().shape[0] == meta.worm_gene.unique().shape[0]
meta.loc[:,'date_yyyymmdd'] = meta['date_yyyymmdd'].apply(lambda x: str(int(x)))
#drop nan wells
meta.dropna(axis=0,
subset=['worm_gene'],
inplace=True)
# remove data from dates to exclude
good_date = meta.query('@DATES_TO_DROP not in imaging_date_yyyymmdd').index
# bad wells
good_wells_from_gui = meta.query('is_bad_well == False').index
meta = meta.loc[good_wells_from_gui & good_date,:]
# only select strains of interest
meta, idx, gene_list = select_strains(CANDIDATE_GENE,
CONTROL_STRAIN,
meta_df=meta,
feat_df=None)
strain_lut, stim_lut = make_colormaps(gene_list,
idx,
CANDIDATE_GENE,
CONTROL_STRAIN,
featlist=[])
#strain to gene dictionary
strain_dict = strain_gene_dict(meta)
gene_dict = {v:k for k,v in strain_dict.items()}
meta = align_bluelight_meta(meta)
if is_reload_timeseries_from_results:
# this uses tierpytools under the hood
timeseries_df, hires_df = load_bluelight_timeseries_from_results(