GRNBoost2 and Arboreto: efficient and scalable inference of gene regulatory networks
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Summary: Inferring a Gene Regulatory Network (GRN) from gene expression data is a computationally expensive task, exacerbated by increasing data sizes due to advances in high-throughput gene profiling technology, such as single-cell RNA-seq. To equip researchers with a toolset to infer GRNs from large expression datasets, we propose GRNBoost2 and the Arboreto framework. GRNBoost2 is an efficient algorithm for regulatory network inference using gradient boosting, based on the GENIE3 architecture. Arboreto is a computational framework that scales up GRN inference algorithms complying with this architecture. Arboreto includes both GRNBoost2 and an improved implementation of GENIE3, as a user-friendly open source Python package. Availability and implementation: Arboreto is available under the 3-Clause BSD license at http://arboreto.readthedocs.io. Supplementary information: Supplementary data are available at Bioinformatics online.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Single-cell RNA sequencing (scRNA-seq) data enables cell type-specific trans-regulation inference through co-expression analysis such as PIDC and SCENIC21–30.”
From Inferring gene regulatory networks from single-cell multiome data using atlas-scale external data (2025) · cites this paper as [29]
In the citing paper
“In addition, most of the regulatory edges point in both directions, and the resulting GRNs contain too many edges in the range of 34,000 to 47,000 edges for networks with only 3,000 input genes for GRNBOOST2, making this approach impractical for datasets with thousands of cells and full transcriptomes.18”
From SCING: Inference of robust, interpretable gene regulatory networks from single cell and spatial transcriptomics (2023) · cites this paper as [18]
In the citing paper
“SCING not only offers robust and accurate GRN inference and improved gene coverage and speed compared to previous approaches,9,18 but also versatile GRN inference with scRNA-seq, snRNA-seq, and spatial transcriptomics data.”
From SCING: Inference of robust, interpretable gene regulatory networks from single cell and spatial transcriptomics (2023) · cites this paper as [18]
Citations
Cites
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731
Highly parallel genome-wide expression profiling of individual cells using nanoliter droplets.
Macosko, E. Z., Basu, A., Satija, R., Nemesh, J., Shekhar, K., Goldman, M., Tirosh, I., Bialas, A. R., Kamitaki, N., Martersteck, E. M., et al. (2015) · Cell · doi:10.1016/j.cell.2015.05.002 · Cited by 7,110
Scenic: single-cell regulatory network inference and clustering.
Aibar, S., González-Blas, C. B., Moerman, T., Huynh-Thu, V. A., Imrichova, H., Hulselmans, G., Rambow, F., Marine, J.-C., Geurts, P., Aerts, J., et al. (2017) · Nature Methods · doi:10.1038/nmeth.4463 · Cited by 6,520
Self-citationInferring Regulatory Networks from Expression Data Using Tree-Based Methods
Huynh-Thu, V. A., Irrthum, A., Wehenkel, L., & Geurts, P. (2010) · PLoS ONE · doi:10.1371/journal.pone.0012776 · Cited by 2,131
Wisdom of crowds for robust gene network inference
The DREAM5 Consortium, Marbach, D., Costello, J. C., Küffner, R., Vega, N. M., Prill, R. J., Camacho, D. M., Allison, K. R., Kellis, M., Collins, J. J., et al. (2012) · Nature Methods · doi:10.1038/nmeth.2016 · Cited by 1,667
Gene Regulatory Network Inference: An Introductory Survey
Huynh‐Thu, V. A., & Sanguinetti, G. (2018) · Methods in molecular biology · doi:10.1007/978-1-4939-8882-2_1 · Cited by 195
ENNET: inferring large gene regulatory networks from expression data using gradient boosting
Sławek, J., & Arodź, T. (2013) · BMC Systems Biology · doi:10.1186/1752-0509-7-106 · Cited by 49
Cited by
Items 601–645 of 645
TRIAGE Toolkit: Streamlined Discovery of Regulatory Genes and Elements
Zhao, Q., Shen, S., Sun, Y., Sinniah, E., Bodén, M., Palpant, N. J., & Shim, W. J. (2026) · Current Protocols · doi:10.1002/cpz1.70413
“While considerable progress has been made in regulatory gene analysis with tools, such as GENIE3 (Huynh-Thu et al., 2010), GRNBoost2 (Moerman et al., 2019), Lisa (Qin et al., 2020), SCENIC (Aibar et al., 2017), and SCENIC + (Bravo Gonzalez-Blas et al., 2023), these methods primarily focus on TFs…”
Causal intervention validation of gene regulatory signals in scGPT
Kendiukhov, I. (2026) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2026.105080 · Cited by 2
Single-cell multiome profiling reveals neuronal bias of modulatory role of MeCP2 phosphorylation
Zhang, Z., Huang, X., Arachchilage, K. H., Chandrashekar, P. B., Dong, Q., Wang, R., Wang, D., & Chang, Q. (2026) · Neurobiology of Disease · doi:10.1016/j.nbd.2026.107521
“Log-normalized gene expression data were used to infer a co-expression network by linking transcription factors (TFs) to putative target genes (TGs) based on gene–gene correlations using GRNBoost2 (Moerman et al., 2019).”
Zhang, H., & Liu, Z. (2026) · Journal of the American Statistical Association · doi:10.1080/01621459.2026.2697050
Venter, M., & Naidoo, K. J. (2026) · Discover Chemistry. · doi:10.21203/rs.3.rs-10155568/v1
Emma Paul, M., Jereesh, A. S., & Kumar, G. S. (2026) · BMC Genomics · doi:10.1186/s12864-026-13185-w · Cited by 1
“By combining the strengths of tree-based and kernel-based models through optimized weighting, AGRN achieves more accurate GRN inference across benchmark datasets, outperforming many existing tree-based methods such as GENIE3 [17] and GRN-Boost2 [18] in evaluation metrics [10].”
GRNgen: A Generator of Gene Regulatory Networks Fitting Graph and Motif Properties
Tan-Lhernould, A., Dorval, T., & Fages, F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30870-2_14
Reconstructing Genetic Networks
Chetty, M., Gamage, H. N., & Hallinan, J. S. (2026) · Springer eBooks · doi:10.1007/978-3-032-11023-7_4
Evolution of withanolide biosynthesis in nightshades
Perez, S., Alseekh, S., Rojas-Contreras, S., Deanna, R., Smith, S. D., Knoch, E., Fernie, A. R., & Roda, F. (2026) · Taxon · doi:10.1002/tax.70191
SignifiKANTE: efficient P -value computation for gene regulatory networks
Woller, F., Martini, P., Sen, S. N., Blumenthal, D. B., & Hartebrodt, A. (2026) · Bioinformatics · doi:10.1093/bioinformatics/btag531
“SignifiKANTE is implemented in Python as an add-on for the widely used GRN inference package Arboreto (Moerman et al. 2019), with out-of-the-box support for GENIE3, GRNBoost2, as well as LASSO and ridge regression-based GRN inference as implemented in GReNaDIne (Schmitt et al. 2023).”
Zhang, C., Li, S., Jiang, R., Duan, H., Li, C., Qi, E., Wu, M., Li, X., Feng, S., & Zhou, H. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1014573
“The workflow encompasses three principal stages [68]: Co-expression Module Inference: GRNBoost2’s gradient boosting machine regression identified modules of co-expressed transcription factors and their potential target genes [69].”
scGraphVerse: a modular workflow for single-cell gene network inference
Cecere, F., Canditiis, D. D., Carissimo, A., & Angelini, C. (2026) · Bioinformatics Advances · doi:10.1093/bioadv/vbag208
“• GRNBoost2 (Moerman et al .”
Xu, T.-F., Wang, X., Li, H., He, S., He, Y.-L., & Huang, X. (2026) · Discover Oncology · doi:10.1007/s12672-026-05644-3
“…regulatory programs, we employed the SCENIC workflow[41], which includes three core steps: (1) inference of gene regulatory networks using GRNBoost2[42]; (2) transcription factor binding motif enrichment analysis; and (3) calculation of cell-type-specific regulator activity scores using AUCell.”
Jiang, Y., Li, Y., Xie, Q., Li, Y., & Wang, H. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.28.738702
“Traditional GRN methods like GRNBoost2 infer a single global or population-level network from pooled cells [12– 14].”
Zhou, L., Luo, S., Huang, Z., Zhang, Z., Wang, Z., & Zhang, J. (2026) · Molecular Systems Biology · doi:10.1038/s44320-026-00235-4 · Cited by 3
Spatially varying gene regulation network inference from spatial transcriptomics
Li, Y., Chen, J. Y., Lu, T., Tsai, N., & Wang, H. (2026) · Bioinformatics Advances · doi:10.1093/bioadv/vbag230
“The baselines include CeSpGRN (Zhang et al. 2022) for spot-or cell-specific GRNs from spatial data, locCSN (Wang et al. 2021) for cell-specific GRNs, and GRNBoost2 (Moerman et al. 2019) for cell-type–level inference.”
AI-driven tri-typing in agriculture: Current advances, future frontiers
Hussain, S., Naureen, I., Habib, M., Awan, F. S., Ghuman, H. F., Sher, A., Riaz, M. W., Usman, H. M., Hussain, S., Kong, F., et al. (2026) · Molecular Breeding · doi:10.1007/s11032-026-01705-1
IAGRN: An Interleaved-Attention Graph Neural Network for Gene Regulatory Network Inference
Wang, Y., Tian, S., & Li, D. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27167300
“Early machine learning approaches, such as GENIE3 [6] and GRNBoost2 [7], primarily utilize ensemble learning strategies to infer regulatory relationships from gene expression data.”
A proteome-centered atlas links tissue specialization and phytohormone variation in rapeseed
Chen, Z., Hou, Z., Qian, X., Sun, F., Wen, J., Huang, S., Ke, Y., Xie, Y., Zhang, X., Zhang, M., et al. (2026) · Cell Reports · doi:10.1016/j.celrep.2026.117867
Zhao, F., Zhao, P., Chang, J., Yan, B., Guo, S., Sun, X., Zhou, C., Wang, X., Tong, J., Zhang, X., et al. (2026) · Research Square · doi:10.21203/rs.3.rs-10575957/v1
Leukemic Stem Cell Subtypes Drive Distinct Niche Remodeling in Acute Myeloid LeukemiaPreprint
Prummel, K. D., Mathioudaki, A., Berest, I., Sood, S., Rauchhaus, J., Richter, T., Baskan, Y., Rauchaus, J., Holitsch, C., Kamal, A., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.08.24.746513
BaghGolshani, M., Beheshti, A., Newton, M. A. H., & Alinejad-Rokny, H. (2026) · IEEE International Conference on Digital Health (ICDH) · doi:10.1109/icdh72779.2026.00041
“Data-driven baselines such as GRN-Boost2 [12] scale well, but they may blur direct regulation with correlation.”
Zhang, Y., Wang, Z., Ning, S., Li, D., Sheng, Z., Hu, S., Jiao, G., Shao, G., Xie, L., Wang, L., et al. (2026) · The Crop Journal · doi:10.1016/j.cj.2026.07.022
Mamba-GRN: A Mamba-inspired framework for no-overlap held-out regulatory edge prediction
Wu, H., Wu, Z., & Liu, X. (2026) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2026.109369
Spatially guided in vivo single-cell functional genomics of postnatal heart
Wang, H., Dong, Y., Song, Y., Colon, M., Grosso, C., Yapundich, N., Ricketts, S. N., Liu, X., Farber, G., Liu, S. L., et al. (2026) · Nature Cardiovascular Research · doi:10.1038/s44161-026-00861-z · Cited by 3
“79), identifying genes co-expressed with TFs and separating targets into positively and negatively correlated groups.”
Bayesian Network Modeling for Gene Regulatory System Analysis in Precision Biotechnology
Quispe-Carita, A.-J., Flores, B. C., Vargas, J. C. J., Lipa, J. P. T., Paredes-Quispe, J. R., López-Cueva, M. A., & Coyla-Idme, L. (2026) · Journal Of Biochemical Technology · doi:10.51847/x02xsqnrtf
A single-nucleus transcriptomic atlas of human inner ear development
van der Valk, W. H., Udayappan, S. D., van Beelen, E. S. A., Goveia, J., Beatovic, A., Moisse, M., Menafra, R., de Groot, J. C. M. J., Koehler, K. R., van Benthem, P. P. G., et al. (2026) · Nature Neuroscience · doi:10.1038/s41593-026-02432-8 · Cited by 1
“Gene regulatory networks were reconstructed using the GRNboost2 method from the arboreto package (version 0.1.6) 91 .”
InfluentialCausal assessment of Bayesian gene regulatory networks from single-cell transcriptomics
Sato, N., Scutari, M., & Imoto, S. (2026) · Cell Reports Methods · doi:10.1016/j.crmeth.2026.101580
Decoding gene regulation in plant genomes with artificial intelligence
Rayamajhi, N., Xu, T., Liu, T., Gao, J., Varala, K., & Li, Y. (2026) · Journal of Experimental Botany · doi:10.1093/jxb/erag323
Chen, X., Zhang, T., Lv, J., & Li, C. (2026) · CSIAM transactions on life sciences. · doi:10.4208/csiam-ls.so-2026-0518
Inferring Gene Regulatory Networks in Stem Cells: Methods and Applications
Solano-Galarza, D., Roeh, S., & Walzthoeni, T. (2026) · Methods in molecular biology · doi:10.1007/978-1-0716-5539-9_1
Puhaleva, B., Kotzev, K., Делчев, К., Metodiev, N., & Abadjieva, D. V. (2026) · Animal Reproduction Science · doi:10.1016/j.anireprosci.2026.108317
Zhu, Y., Han, D., & Wang, Z. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag513
“…inference methods in this field and has consequently become the most widely adopted [ 14, 15]. pySCENIC employs a gradient boosting machine-based algorithm, GRNboost2 (previously GENIE3) [ 53], for GRN construction, and subsequently filters the GRNs using TFBS information within promoter regions.”
Song, X., Lv, J., Ge, S., Xu, S., Wu, Y., Zheng, Y., Zhou, W., Li, L., Zhang, Y., Zhang, J., et al. (2026) · Science Advances · doi:10.1126/sciadv.aeh0260
“GRNBoost was used to identify TF-target gene coexpression modules, which were then refined against the cisTarget database to retain only genes with relevant TF-binding motifs ( 95 ).”
Glial Dysfunction and Memory Impairments in a Model of Pediatric Obstructive Sleep Apnea
Williamson, M. R., Botas, J., Hedayatpour, M. J., Zlatkov, T., Harmancı, A. S., Yates, C. M., Nobleza, K. J., Ailani, R., Adler, A. C., Kheradmand, F., et al. (2026) · Glia · doi:10.1002/glia.70230
“In the first stage, gene regulatory networks were inferred using GRNBoost2 (Moerman et al. 2019), which identifies putative transcription factor–target gene relationships based on expression co-variation.”
Tang, B., Feng, Y., Gao, X., Mao, M., & Zhang, Y. (2026) · Journal of Zhejiang University SCIENCE B · doi:10.1631/jzus.b2500424
“For instance, GEne Net ‐ work Inference with Ensemble of trees (GENIE3), Gene Regulatory Network Boosting 2 (GRNBoost2), and SINgle CEll Regularized Inference using TIme-stamped Expression profileS (SINCERITIES) for ‐ mulate GRN inference as a regression problem, em ‐ ploying statistical or machine learning techniques…”
InfluentialBiologically grounded cell profiling across microscopy modalitiesPreprint
Ye, E., Wu, X., Peng, R., Hu, W., Li, X., Zhang, X., Niu, M., Guo, Y., Sheng, X., Wang, J., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.09.23.753678
Artificial Intelligence for Plant Gene Regulatory Networks
Yu, H. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27198819
“Directed, ranked, genome-wide; Level 2; top-ranked method in the DREAM5 benchmark [16] GRNBoost2 [30] Single-cell expression Gradient-boosting implementation of the GENIE3 design with an order-of-magnitude gain in runtime Directed, ranked; Level 2; inference engine within SCENIC-type pipelines…”
Decoding epithelial–mesenchymal transitions with multi-omics
Narwade, N. P., & Nieto, M. A. (2026) · Nature Reviews Genetics · doi:10.1038/s41576-026-01015-4
Wang, L., Zhipeng, W., 王昌松, Zhai, P., Xu, X., Liu, Z., Feng, H., Liu, H., Hou, Q., & Guo, M. (2026) · Research Square · doi:10.21203/rs.3.rs-10935749/v1
gsGNA: A Universal Pipeline for Mining Plant Stress-Resistance RegulatorsPreprint
Chen, Z., Zan, Z., Lu, Q., Wang, J., Zhu, J., Zhao, Q., Wang, P., Hu, Z., Fan, S., Xuemei, W., et al. (2026) · Research Square · doi:10.21203/rs.3.rs-11125843/v1
Emma Paul, M., Jereesh, A. S., & Kumar, G. S. (2026) · Discover Computing · doi:10.1007/s10791-026-10713-w
“GRNBoost2 [13] follows a similar idea but uses stochastic gradient boosting and early stopping to make the method more scalable for large expression datasets.”
Emerging frontiers for AI in single-cell genomics
Mitra, S., Li, J., & Leslie, C. S. (2026) · Molecular Cell · doi:10.1016/j.molcel.2026.09.014 · Cited by 1
Acinar‐Derived Organoids Reveal Stage‐Specific Control of Acinar Plasticity
Hou, Y., Li, S., Li, C., Lin, Z., He, D., Yang, L., Fu, L., Zhang, Q., Zhou, T., Yao, Y., et al. (2026) · Advanced Science · doi:10.1002/advs.78350
Metadata
- Authors
- Moerman, T., Aibar Santos, S., Bravo González-Blas, C., Simm, J., Moreau, Y., Aerts, J., & Aerts, S.
- Affiliations
- IMEC (BE)
- Laboratory of Computational Biology, VIB Center for Brain & Disease Research
- VIB-KU Leuven Center for Brain & Disease Research (BE)
- Corresponding author
- Aerts, Stein
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2018-11-15
- Volume
- 35
- Issue
- 12
- Pages
- 2159-2161
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- OpenAlex
- W2901292166
- Cited by
- 621
- References
- 7
- Citations by year
- 2026: 128 · 2025: 114 · 2024: 112 · 2023: 103 · 2022: 65 · 2021: 63 · 2020: 29 · 2019: 5
- FWCI
- 9.42
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model (vor)
- Locations
- Bioinformatics (publishedVersion)
- PubMed (publishedVersion)
- Document Server@UHasselt (UHasselt) (submittedVersion)
- Lirias (submittedVersion)
- Funders
- IMEC Strategic Funding
- IWT Exaptation
- FWO 06260
- Special Research Fund (PF/10/016)
- ERC Consolidator (724226_cis-CONTROL)
- Foundation Against Cancer (2016-070)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene Regulatory Network Analysis
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Microbial Metabolic Engineering and Bioproduction
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Keywords
- gene regulatory network inference, gradient boosting, GENIE3, gene expression data, single-cell RNA sequencing, scalable inference, open-source Python package
- MeSH terms
- Algorithms, Software, Gene Expression, Computational Biology, Gene Regulatory Networks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.