Arboreto

uv pip install arboreto

import pandas as pd
from arboreto.algo import grnboost2

if __name__ == '__main__':
    # Load expression data (genes as columns)
    expression_matrix = pd.read_csv('expression_data.tsv', sep='\t')

    # Infer regulatory network
    network = grnboost2(expression_data=expression_matrix)

    # Save results (TF, target, importance)
    network.to_csv('network.tsv', sep='\t', index=False, header=False)

python scripts/basic_grn_inference.py expression_data.tsv output_network.tsv --tf-file tfs.txt --seed 777

from arboreto.algo import grnboost2, genie3

# Fast, recommended
network_grnboost = grnboost2(expression_data=matrix)

# Classic algorithm
network_genie3 = genie3(expression_data=matrix)

network = grnboost2(expression_data=matrix)

from distributed import LocalCluster, Client

local_cluster = LocalCluster(n_workers=10, memory_limit='8GB')
client = Client(local_cluster)

network = grnboost2(expression_data=matrix, client_or_address=client)

client.close()
local_cluster.close()

from distributed import Client

client = Client('tcp://scheduler:8786')
network = grnboost2(expression_data=matrix, client_or_address=client)

uv pip install arboreto

import pandas as pd
from arboreto.algo import grnboost2

if __name__ == '__main__':
    # Load single-cell expression matrix (cells x genes)
    sc_data = pd.read_csv('scrna_counts.tsv', sep='\t')

    # Infer cell-type-specific regulatory network
    network = grnboost2(expression_data=sc_data, seed=42)

    # Filter high-confidence links
    high_confidence = network[network['importance'] > 0.5]
    high_confidence.to_csv('grn_high_confidence.tsv', sep='\t', index=False)

from arboreto.utils import load_tf_names
from arboreto.algo import grnboost2

if __name__ == '__main__':
    # Load data
    expression_data = pd.read_csv('rnaseq_tpm.tsv', sep='\t')
    tf_names = load_tf_names('human_tfs.txt')

    # Infer with TF restriction
    network = grnboost2(
        expression_data=expression_data,
        tf_names=tf_names,
        seed=123
    )

    network.to_csv('tf_target_network.tsv', sep='\t', index=False)

from arboreto.algo import grnboost2

if __name__ == '__main__':
    # Infer networks for different conditions
    conditions = ['control', 'treatment_24h', 'treatment_48h']

    for condition in conditions:
        data = pd.read_csv(f'{condition}_expression.tsv', sep='\t')
        network = grnboost2(expression_data=data, seed=42)
        network.to_csv(f'{condition}_network.tsv', sep='\t', index=False)

# Step 1: Use arboreto for GRN inference
from arboreto.algo import grnboost2
network = grnboost2(expression_data=sc_data, tf_names=tf_list)

# Step 2: Use pySCENIC for regulon identification and activity scoring
# (See pySCENIC documentation for downstream analysis)

network = grnboost2(expression_data=matrix, seed=777)

from distributed import LocalCluster, Client

if __name__ == '__main__':
    client = Client(LocalCluster())

    seeds = [42, 123, 777]
    networks = []

    for seed in seeds:
        net = grnboost2(expression_data=matrix, client_or_address=client, seed=seed)
        networks.append(net)

    # Combine networks and filter consensus links
    consensus = analyze_consensus(networks)