def _export_labels(self) -> ReportOutput:
if self.dataset.encoded_data.labels is not None:
labels_df = pd.DataFrame(self.dataset.encoded_data.labels)
file_path = f"{self.result_path}labels.csv"
labels_df.to_csv(file_path, sep=",", index=False)
return ReportOutput(file_path, "exported labels")
def _write_results_table(self, data):
table_path = f"{self.result_path}{self.result_name}.csv"
data.to_csv(table_path, index=False)
return ReportOutput(table_path, "feature values")
def _export_matrix(self) -> ReportOutput:
data = self._get_data()
file_path = self._save_to_file(data,
f"{self.result_path}design_matrix")
return ReportOutput(file_path, "design matrix")
def export_receptorlist(self, receptors, result_path):
export_list = []
node_metadata_list = []
edge_metadata_list = []
for receptor in receptors:
first_chain = receptor.get_chain(self.chains[0])
second_chain = receptor.get_chain(self.chains[1])
first_chain_name = self.get_shared_name(first_chain)
second_chain_name = self.get_shared_name(second_chain)
export_list.append([first_chain_name, "pair", second_chain_name])
node_metadata_list.append(
[first_chain_name, self.chains[0]] +
self.get_formatted_node_metadata(first_chain))
node_metadata_list.append(
[second_chain_name, self.chains[1]] +
self.get_formatted_node_metadata(second_chain))
edge_metadata_list.append(
[f"{first_chain_name} (pair) {second_chain_name}"] +
self.get_formatted_edge_metadata(first_chain, second_chain))
full_df = pd.DataFrame(
export_list,
columns=[self.chains[0], "relationship", self.chains[1]])
node_meta_df = pd.DataFrame(
node_metadata_list,
columns=[
"shared_name", "chain", "sequence", "v_subgroup", "v_gene",
"j_subgroup", "j_gene"
] + self.additional_node_attributes)
edge_meta_df = pd.DataFrame(edge_metadata_list,
columns=["shared_name"] +
self.additional_edge_attributes)
node_cols = list(node_meta_df.columns)
node_meta_df["n_duplicates"] = 1
node_meta_df = node_meta_df.groupby(
node_cols, as_index=False)["n_duplicates"].sum()
edge_meta_df.drop_duplicates(inplace=True)
node_meta_df.to_csv(f"{result_path}node_metadata.tsv",
sep="\t",
index=0,
header=True)
edge_meta_df.to_csv(f"{result_path}edge_metadata.tsv",
sep="\t",
index=0,
header=True)
if self.drop_duplicates:
full_df.drop_duplicates(inplace=True)
full_df.to_csv(f"{result_path}all_chains.sif",
sep="\t",
index=0,
header=False)
shared_df = full_df[(full_df.duplicated(["alpha"], keep=False)) |
(full_df.duplicated(["beta"], keep=False))]
shared_df.to_csv(f"{result_path}shared_chains.sif",
sep="\t",
index=0,
header=False)
return [
ReportOutput(path=f"{result_path}node_metadata.tsv"),
ReportOutput(path=f"{result_path}edge_metadata.tsv"),
ReportOutput(path=f"{result_path}all_chains.sif"),
ReportOutput(path=f"{result_path}shared_chains.sif")
]