GRNBoost2 benchmark on toy GRN

Notebook benchmarks GRN inference using GRNBoost2 on toy GRN data.

Library imports

from tqdm import tqdm

import pandas as pd

from arboreto.algo import grnboost2

from rgv_tools import DATA_DIR
from rgv_tools.benchmarking import get_data_subset, get_grn_auroc
from rgv_tools.core import read_as_dask

General settings

"""
from dask import config as cfg

cfg.set({"distributed.scheduler.worker-ttl": None})
"""

Constants

DATASET = "toy_grn"

SAVE_DATA = True
if SAVE_DATA:
    (DATA_DIR / DATASET / "results").mkdir(parents=True, exist_ok=True)

Function definitions

Data loading

adata = read_as_dask(store=DATA_DIR / DATASET / "raw" / "adata.zarr", layers=[])
adata

Velocity pipeline

grn_correlation = []

for dataset in tqdm(adata.obs["dataset"].cat.categories):
    adata_subset = get_data_subset(adata=adata, column="dataset", group=dataset, uns_keys=["true_K"])

    network = grnboost2(expression_data=adata_subset.to_df(), tf_names=adata.var_names.to_list())
    grn_estimate = pd.pivot(network, index="target", columns="TF").fillna(0).values

    grn_correlation.append(get_grn_auroc(ground_truth=adata_subset.uns["true_K"], estimated=grn_estimate))

Data saving

if SAVE_DATA:
    pd.DataFrame({"grn": grn_correlation}).to_parquet(
        path=DATA_DIR / DATASET / "results" / "grnboost2_correlation.parquet"
    )