arboreto

Name: arboreto
Author: K-Dense-AI

806installs3.1kforks

How to install arboreto?

k-dense-ai/scientific-agent-skills/arboreto

$npx -y skills add K-Dense-AI/scientific-agent-skills --skill arboreto

Installs into the current project.

Summary

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Suppo

Files · 1

View on GitHub

SKILL.md

1	# Arboreto
2
3	## Overview
4
5	Arboreto is a Python library from [Aerts Lab](https://github.com/aertslab/arboreto) for inferring gene regulatory networks (GRNs) from gene expression data. It parallelizes tree-based ensemble regression (GRNBoost2, GENIE3) with [Dask](https://distributed.dask.org/) across local cores or remote clusters.
6
7	Core capability: Identify which transcription factors (TFs) regulate which target genes based on expression patterns across observations (cells, samples, conditions).
8
9	Upstream: PyPI 0.1.6 (2021-02-09, latest). Docs: [arboreto.readthedocs.io](https://arboreto.readthedocs.io/en/latest/). Primary downstream consumer: [pySCENIC](https://github.com/aertslab/pySCENIC).
10
11	## Quick Start
12
13	Install arboreto:
14	```bash
15	uv pip install arboreto
16	```
17
18	Basic GRN inference:
19	```python
20	import pandas as pd
21	from arboreto.algo import grnboost2
22
23	if __name__ == '__main__':
24	# Load expression data (genes as columns)
25	expression_matrix = pd.read_csv('expression_data.tsv', sep='\t')
26
27	# Infer regulatory network
28	network = grnboost2(expression_data=expression_matrix)
29
30	# Save results (TF, target, importance)
31	network.to_csv('network.tsv', sep='\t', index=False, header=False)
32	```
33
34	Critical: Always use `if __name__ == '__main__':` guard because Dask spawns new processes.
35
36	## Core Capabilities
37
38	### 1. Basic GRN Inference
39
40	For standard GRN inference workflows including:
41	- Input data preparation (Pandas DataFrame or NumPy array)
42	- Running inference with GRNBoost2 or GENIE3
43	- Filtering by transcription factors
44	- Output format and interpretation
45
46	See: `references/basic_inference.md`
47
48	Use the ready-to-run script: `scripts/basic_grn_inference.py` for standard inference tasks:
49	```bash
50	python scripts/basic_grn_inference.py expression_data.tsv output_network.tsv --tf-file tfs.txt --seed 777 --limit 5000
51	```
52
53	### 2. Algorithm Selection
54
55	Arboreto provides two algorithms:
56
57	GRNBoost2 (Recommended):
58	- Fast gradient boosting-based inference
59	- Optimized for large datasets (10k+ observations)
60	- Default choice for most analyses
61
62	GENIE3:
63	- Random Forest-based inference
64	- Original multiple regression approach
65	- Use for comparison or validation
66
67	Quick comparison:
68	```python
69	from arboreto.algo import grnboost2, genie3
70
71	# Fast, recommended
72	network_grnboost = grnboost2(expression_data=matrix)
73
74	# Classic algorithm
75	network_genie3 = genie3(expression_data=matrix)
76	```
77
78	For detailed algorithm comparison, parameters, and selection guidance: `references/algorithms.md`
79
80	### 3. Distributed Computing
81
82	Scale inference from local multi-core to cluster environments:
83
84	Local (default) - Uses all available cores automatically:
85	```python
86	network = grnboost2(expression_data=matrix)
87	```
88
89	Custom local client - Control resources:
90	```python
91	from distributed import LocalCluster, Client
92
93	local_cluster = LocalCluster(n_workers=10, memory_limit='8GB')
94	client = Client(local_cluster)
95
96	network = grnboost2(expression_data=matrix, client_or_address=client)
97
98	client.close()
99	local_cluster.close()
100	```
101
102	Cluster computing - Connect to remote Dask scheduler:
103	```python
104	from distributed import Client
105
106	client = Client('tcp://scheduler:8786')
107	network = grnboost2(expression_data=matrix, client_or_address=client)
108	```
109
110	For cluster setup, performance optimization, and large-scale workflows: `references/distributed_computing.md`
111
112	## Installation
113
114	```bash
115	uv pip install arboreto
116	```
117
118	Conda (Bioconda):
119
120	```bash
121	conda install -c bioconda arboreto
122	```
123
124	Dependencies (from upstream `requirements.txt`): `dask[complete]`, `distributed`, `numpy`, `pandas`, `scikit-learn`, `scipy`
125
126	Input formats: pandas DataFrame, dense `numpy.ndarray`, or sparse `scipy.sparse.csc_matrix` (rows = observations, columns = genes). For array/matrix inputs, pass `gene_names` explicitly.
127
128	## Common Use Cases
129
130	### Single-Cell RNA-seq Analysis
131	```python
132	import pandas as pd
133	from arboreto.algo import grnboost2
134
135	if __name__ == '__main__':
136	# Load single-cell expression matrix (cells x genes)
137	sc_data = pd.read_csv('scrna_counts.tsv', sep='\t')
138
139	# Infer cell-type-specific regulatory network
140	network = grnboost2(expression_data=sc_data, seed=42)
141
142	# Filter high-confidence links
143	high_confidence = network[network['importance'] > 0.5]
144	high_confidence.to_csv('grn_high_confidence.tsv', sep='\t', index=False)
145	```
146
147	### Bulk RNA-seq with TF Filtering
148	```python
149	from arboreto.utils import load_tf_names
150	from arboreto.algo import grnboost2
151
152	if __name__ == '__main__':
153	# Load data

People who liked this also viewed

6 picks

Type

arboreto

806installs3.1kforks

View on GitHub

How to install arboreto?

k-dense-ai/scientific-agent-skills/arboreto

$npx -y skills add K-Dense-AI/scientific-agent-skills --skill arboreto

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Arboreto
2
3	## Overview
4
5	Arboreto is a Python library from [Aerts Lab](https://github.com/aertslab/arboreto) for inferring gene regulatory networks (GRNs) from gene expression data. It parallelizes tree-based ensemble regression (GRNBoost2, GENIE3) with [Dask](https://distributed.dask.org/) across local cores or remote clusters.
6
7	Core capability: Identify which transcription factors (TFs) regulate which target genes based on expression patterns across observations (cells, samples, conditions).
8
9	Upstream: PyPI 0.1.6 (2021-02-09, latest). Docs: [arboreto.readthedocs.io](https://arboreto.readthedocs.io/en/latest/). Primary downstream consumer: [pySCENIC](https://github.com/aertslab/pySCENIC).
10
11	## Quick Start
12
13	Install arboreto:
14	```bash
15	uv pip install arboreto
16	```
17
18	Basic GRN inference:
19	```python
20	import pandas as pd
21	from arboreto.algo import grnboost2
22
23	if __name__ == '__main__':
24	# Load expression data (genes as columns)
25	expression_matrix = pd.read_csv('expression_data.tsv', sep='\t')
26
27	# Infer regulatory network
28	network = grnboost2(expression_data=expression_matrix)
29
30	# Save results (TF, target, importance)
31	network.to_csv('network.tsv', sep='\t', index=False, header=False)
32	```
33
34	Critical: Always use `if __name__ == '__main__':` guard because Dask spawns new processes.
35
36	## Core Capabilities
37
38	### 1. Basic GRN Inference
39
40	For standard GRN inference workflows including:
41	- Input data preparation (Pandas DataFrame or NumPy array)
42	- Running inference with GRNBoost2 or GENIE3
43	- Filtering by transcription factors
44	- Output format and interpretation
45
46	See: `references/basic_inference.md`
47
48	Use the ready-to-run script: `scripts/basic_grn_inference.py` for standard inference tasks:
49	```bash
50	python scripts/basic_grn_inference.py expression_data.tsv output_network.tsv --tf-file tfs.txt --seed 777 --limit 5000
51	```
52
53	### 2. Algorithm Selection
54
55	Arboreto provides two algorithms:
56
57	GRNBoost2 (Recommended):
58	- Fast gradient boosting-based inference
59	- Optimized for large datasets (10k+ observations)
60	- Default choice for most analyses
61
62	GENIE3:
63	- Random Forest-based inference
64	- Original multiple regression approach
65	- Use for comparison or validation
66
67	Quick comparison:
68	```python
69	from arboreto.algo import grnboost2, genie3
70
71	# Fast, recommended
72	network_grnboost = grnboost2(expression_data=matrix)
73
74	# Classic algorithm
75	network_genie3 = genie3(expression_data=matrix)
76	```
77
78	For detailed algorithm comparison, parameters, and selection guidance: `references/algorithms.md`
79
80	### 3. Distributed Computing
81
82	Scale inference from local multi-core to cluster environments:
83
84	Local (default) - Uses all available cores automatically:
85	```python
86	network = grnboost2(expression_data=matrix)
87	```
88
89	Custom local client - Control resources:
90	```python
91	from distributed import LocalCluster, Client
92
93	local_cluster = LocalCluster(n_workers=10, memory_limit='8GB')
94	client = Client(local_cluster)
95
96	network = grnboost2(expression_data=matrix, client_or_address=client)
97
98	client.close()
99	local_cluster.close()
100	```
101
102	Cluster computing - Connect to remote Dask scheduler:
103	```python
104	from distributed import Client
105
106	client = Client('tcp://scheduler:8786')
107	network = grnboost2(expression_data=matrix, client_or_address=client)
108	```
109
110	For cluster setup, performance optimization, and large-scale workflows: `references/distributed_computing.md`
111
112	## Installation
113
114	```bash
115	uv pip install arboreto
116	```
117
118	Conda (Bioconda):
119
120	```bash
121	conda install -c bioconda arboreto
122	```
123
124	Dependencies (from upstream `requirements.txt`): `dask[complete]`, `distributed`, `numpy`, `pandas`, `scikit-learn`, `scipy`
125
126	Input formats: pandas DataFrame, dense `numpy.ndarray`, or sparse `scipy.sparse.csc_matrix` (rows = observations, columns = genes). For array/matrix inputs, pass `gene_names` explicitly.
127
128	## Common Use Cases
129
130	### Single-Cell RNA-seq Analysis
131	```python
132	import pandas as pd
133	from arboreto.algo import grnboost2
134
135	if __name__ == '__main__':
136	# Load single-cell expression matrix (cells x genes)
137	sc_data = pd.read_csv('scrna_counts.tsv', sep='\t')
138
139	# Infer cell-type-specific regulatory network
140	network = grnboost2(expression_data=sc_data, seed=42)
141
142	# Filter high-confidence links
143	high_confidence = network[network['importance'] > 0.5]
144	high_confidence.to_csv('grn_high_confidence.tsv', sep='\t', index=False)
145	```
146
147	### Bulk RNA-seq with TF Filtering
148	```python
149	from arboreto.utils import load_tf_names
150	from arboreto.algo import grnboost2
151
152	if __name__ == '__main__':
153	# Load data

People who liked this also viewed

6 picks

Type