def _generate_distances_long_format(self):
genome = Genome.regions()
panel_analyser = PanelAnalyser()
frames = [panel_analyser.snp_distances_per_chromosome(panel, genome)
for panel in Panel.all_panels()]
distances = pd.concat(frames).T
return pd.melt(distances)
def read_ancestry_files(self, only_optimal_Ks=False):
dataframes = []
datasets = Dataset.all_datasets()
Ks = self.available_Ks()
panels = Panel.all_panels() + Panel.all_control_panels()
for dataset, K, panel in product(datasets, Ks, panels):
if only_optimal_Ks and self.optimal_Ks()[dataset.label] != K:
continue
# Results are sorted in directories named like DATASET_PANEL
tag = "{}_{}".format(dataset.label, panel.label)
basedir = join(ADMIXTURE_DIR, tag)
if not isdir(basedir):
continue
# Read the .Q file for ratios of ancestry per sample
fname = "{}.{}.Q".format(tag, K)
ancestries_df = pd.read_csv(join(basedir, fname), sep="\s+",
names=list(range(K)))
# Read the .fam file for the sample IDs (they're in the same order)
fname = "{}.fam".format(tag)
samples = pd.read_csv(join(basedir, fname), sep="\s+", index_col=0,
usecols=[0], names=["sample"])
ancestries_df.index = samples.index
# Add population data to the sample IDs
samples_df = ThousandGenomes().all_samples()
ancestries_df = samples_df.join(ancestries_df).dropna()
continents_present = len(ancestries_df["superpopulation"].unique())
if continents_present >= 3:
self.infer_ancestral_components_from_samples_origin(ancestries_df)
self.infer_ancestral_components_from_reference_pop(ancestries_df)
# Arrange the hierarchical index
ancestries_df.reset_index(inplace=True)
ancestries_df["dataset"] = dataset.label
ancestries_df["K"] = K
ancestries_df["panel"] = panel.label
ancestries_df.set_index(["dataset", "K", "panel"], inplace=True)
dataframes.append(ancestries_df)
return pd.concat(dataframes)