{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T13:18:03Z","timestamp":1785417483863,"version":"3.56.0"},"posted":{"date-parts":[[2026,7,16]]},"group-title":"Systems Biology","reference-count":70,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nd\/4.0\/"}],"funder":[{"award":["R35CA220523"],"award-info":[{"award-number":["R35CA220523"]}],"id":[{"id":"https:\/\/ror.org\/040gcmg81","id-type":"ROR","asserted-by":"publisher"}]},{"award":["R01HG011393"],"award-info":[{"award-number":["R01HG011393"]}],"id":[{"id":"https:\/\/ror.org\/00baak391","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,7,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Gene regulatory networks (GRNs) provide a mechanistic framework for understanding how transcription factors coordinate gene expression to establish cellular identity and phenotype. Methods that integrate gene expression with motif-derived regulatory priors and other sources of biological information have substantially advanced gene regulatory network inference by reconstructing condition-specific regulatory architecture. These approaches estimate the evidence supporting regulatory interactions and have proven remarkably successful in a wide range of biological applications. A complementary view of regulatory networks, however, seeks to estimate the effect of those interactions on gene expression itself, providing a framework in which regulatory edges can be interpreted as activating or inhibitory influences on transcription.<\/jats:p>\n                <jats:p>We developed Giraffe, a biologically informed matrix factorization framework that jointly estimates transcription factor activities and gene regulatory networks by integrating gene expression, motif-based regulatory priors, and transcription factor protein-protein interactions. Giraffe estimates signed partial regulatory effects whose magnitude and sign can be interpreted as the strength and direction of transcriptional regulation. Building directly on the biological framework established by methods such as PANDA, Giraffe provides a complementary representation of gene regulatory networks that emphasizes mechanistic interpretation while remaining scalable, flexible, and computationally efficient.<\/jats:p>\n                <jats:p>Across synthetic benchmarks, six human tissues, yeast transcription factor perturbation experiments, and liver hepatocellular carcinoma, Giraffe accurately reconstructs regulatory interactions while distinguishing activating from inhibitory regulation with high accuracy. The inferred networks recover known features of tissue-specific regulation, correctly classify regulatory effects in transcription factor perturbation experiments, and identify biologically coherent changes in regulatory programs associated with liver cancer. Together, these results demonstrate that estimating the direction of transcriptional regulation provides a complementary perspective on gene regulatory networks that facilitates biological interpretation and hypothesis generation.<\/jats:p>","DOI":"10.64898\/2026.07.15.738791","type":"posted-content","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T13:40:23Z","timestamp":1784209223000},"source":"Crossref","is-referenced-by-count":0,"title":["Large-scale, interpretable gene regulatory network inference through biologically informed matrix factorization"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5402-9237","authenticated-orcid":false,"given":"Soel","family":"Micheletti","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA"},{"name":"Department of Computer Science, Zurich, ETH Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3852-6908","authenticated-orcid":false,"given":"Viola","family":"Fanfani","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julia","family":"Vogt","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Zurich, ETH Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2702-5879","authenticated-orcid":false,"given":"John","family":"Quackenbush","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA"},{"name":"Department of Data Science, Dana-Farber Cancer Institute, Boston, MA, USA"},{"name":"Channing Division of Network Medicine, Brigham and Women\u2019s Hospital, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6459-5053","authenticated-orcid":false,"given":"Jonas","family":"Fischer","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1575-824X","authenticated-orcid":false,"given":"Alexander","family":"Marx","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Zurich, ETH Zurich, Switzerland"},{"name":"Department of Statistics, TU Dortmund University, Dortmund, Germany"},{"name":"Research Center Trustworthy Data Science and Security, University Alliance Ruhr, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9638-9722","authenticated-orcid":false,"given":"Panagiotis","family":"Mandros","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026072011001155000_2026.07.15.738791v1.1","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.74.47"},{"key":"2026072011001155000_2026.07.15.738791v1.2","doi-asserted-by":"publisher","DOI":"10.15252\/msb.20156236"},{"key":"2026072011001155000_2026.07.15.738791v1.3","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkab778"},{"key":"2026072011001155000_2026.07.15.738791v1.4","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-023-02877-1"},{"issue":"2","key":"2026072011001155000_2026.07.15.738791v1.5","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1038\/s41419-019-1385-8","article-title":"Neurotrophins and their involvement in digestive cancers","volume":"10","year":"2019","journal-title":"Cell death & disease"},{"issue":"1","key":"2026072011001155000_2026.07.15.738791v1.6","doi-asserted-by":"crossref","first-page":"e1006591","DOI":"10.1371\/journal.pcbi.1006591","article-title":"Multi-study inference of regulatory networks for more accurate models of gene regulation","volume":"15","year":"2019","journal-title":"PLoS computational biology"},{"issue":"1","key":"2026072011001155000_2026.07.15.738791v1.7","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1038\/s41540-024-00386-w","article-title":"Flexible modeling of regulatory networks improves transcription factor activity estimation","volume":"10","year":"2024","journal-title":"npj Systems Biology and Applications"},{"issue":"6","key":"2026072011001155000_2026.07.15.738791v1.8","first-page":"4940","article-title":"Examining the key genes and pathways in hepatocellular carcinoma development from hepatitis b virus-positive cirrhosis","volume":"18","year":"2018","journal-title":"Molecular medicine reports"},{"key":"2026072011001155000_2026.07.15.738791v1.9","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-018-2201-7"},{"key":"2026072011001155000_2026.07.15.738791v1.10","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkx1092"},{"key":"2026072011001155000_2026.07.15.738791v1.11","doi-asserted-by":"publisher","DOI":"10.1126\/science.282.5389.699"},{"key":"2026072011001155000_2026.07.15.738791v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.tig.2018.07.007"},{"key":"2026072011001155000_2026.07.15.738791v1.13","doi-asserted-by":"crossref","first-page":"101531","DOI":"10.1016\/j.tranon.2022.101531","article-title":"Unraveling the actin cytoskeleton in the malignant transformation of cholangiocyte biology","volume":"26","year":"2022","journal-title":"Translational Oncology"},{"issue":"3","key":"2026072011001155000_2026.07.15.738791v1.14","doi-asserted-by":"crossref","first-page":"e1000044","DOI":"10.1371\/journal.pcbi.1000044","article-title":"A semi-supervised method for predicting transcription factor\u2013gene interactions in escherichia coli","volume":"4","year":"2008","journal-title":"PLoS computational biology"},{"key":"2026072011001155000_2026.07.15.738791v1.15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.0050008"},{"key":"2026072011001155000_2026.07.15.738791v1.16","doi-asserted-by":"crossref","unstructured":"Fanfani, V. , Shutta, K. H. , Mandros, P. , Fischer, J. , Saha, E. , Micheletti, S. , Chen, C. , Guebila, M. B. , Lopes-Ramos, C. M. , and Quackenbush, J. (2024). Reproducible processing of tcga regulatory networks. bioRxiv.","DOI":"10.1101\/2024.11.05.622163"},{"key":"2026072011001155000_2026.07.15.738791v1.17","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-12-1"},{"key":"2026072011001155000_2026.07.15.738791v1.18","doi-asserted-by":"publisher","DOI":"10.1101\/gr.265595.120"},{"key":"2026072011001155000_2026.07.15.738791v1.19","doi-asserted-by":"publisher","DOI":"10.1016\/bs.acr.2020.10.002"},{"issue":"16","key":"2026072011001155000_2026.07.15.738791v1.20","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.3390\/cells11162507","article-title":"Constitutive occurrence of e: N-cadherin heterodimers in adherens junctions of hepatocytes and derived tumors","volume":"11","year":"2022","journal-title":"Cells"},{"key":"2026072011001155000_2026.07.15.738791v1.21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0064832"},{"key":"2026072011001155000_2026.07.15.738791v1.22","first-page":"280066","article-title":"The role of gonadotropin-releasing hormone in cancer cell proliferation and metastasis","volume":"8","year":"2017","journal-title":"Frontiers in endocrinology"},{"issue":"1","key":"2026072011001155000_2026.07.15.738791v1.23","first-page":"1","article-title":"Tigress: trustful inference of gene regulation using stability selection","volume":"6","year":"2012","journal-title":"BMC systems biology"},{"issue":"1","key":"2026072011001155000_2026.07.15.738791v1.24","doi-asserted-by":"crossref","first-page":"7923","DOI":"10.1038\/s41598-020-64870-z","article-title":"Correlation-centred variable selection of a gene expression signature to predict breast cancer metastasis","volume":"10","year":"2020","journal-title":"Scientific reports"},{"key":"2026072011001155000_2026.07.15.738791v1.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.tim.2017.04.009"},{"key":"2026072011001155000_2026.07.15.738791v1.26","doi-asserted-by":"crossref","unstructured":"Hossain, I. , Fanfani, V. , Quackenbush, J. , and Burkholz, R. (2023). Biologically informed neuralodes for genome-wide regulatory dynamics. bioRxiv, pages 2023\u201302.","DOI":"10.21203\/rs.3.rs-2675584\/v1"},{"key":"2026072011001155000_2026.07.15.738791v1.27","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0012776"},{"key":"2026072011001155000_2026.07.15.738791v1.28","unstructured":"Kingma, D. P. and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980."},{"issue":"8","key":"2026072011001155000_2026.07.15.738791v1.29","doi-asserted-by":"crossref","first-page":"1208","DOI":"10.3390\/biology11081208","article-title":"Data incompleteness may form a hard-to-overcome barrier to decoding life\u00e2s mechanism","volume":"11","year":"2022","journal-title":"Biology"},{"key":"2026072011001155000_2026.07.15.738791v1.30","doi-asserted-by":"publisher","DOI":"10.1109\/mc.2009.263"},{"key":"2026072011001155000_2026.07.15.738791v1.31","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-9-1"},{"issue":"5","key":"2026072011001155000_2026.07.15.738791v1.32","first-page":"417","article-title":"Transcription factors: an overview","volume":"74","year":"1993","journal-title":"International journal of experimental pathology"},{"key":"2026072011001155000_2026.07.15.738791v1.33","doi-asserted-by":"crossref","unstructured":"Lee, J.-H. and Kim, C.-S. (2020). Multi-loss rebalancing algorithm for monocular depth estimation. In European Conference on Computer Vision, pages 785\u2013801. Springer.","DOI":"10.1007\/978-3-030-58520-4_46"},{"issue":"3","key":"2026072011001155000_2026.07.15.738791v1.34","doi-asserted-by":"crossref","first-page":"289","DOI":"10.3748\/wjg.v16.i3.289","article-title":"Hepatic tight junctions: From viral entry to cancer metastasis","volume":"16","year":"2010","journal-title":"World Journal of Gastroenterology: WJG"},{"key":"2026072011001155000_2026.07.15.738791v1.35","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbp028"},{"issue":"12","key":"2026072011001155000_2026.07.15.738791v1.36","doi-asserted-by":"crossref","first-page":"107795","DOI":"10.1016\/j.celrep.2020.107795","article-title":"Sex differences in gene expression and regulatory networks across 29 human tissues","volume":"31","year":"2020","journal-title":"Cell reports"},{"key":"2026072011001155000_2026.07.15.738791v1.37","doi-asserted-by":"publisher","DOI":"10.1158\/1538-7445.AM2018-5538"},{"key":"2026072011001155000_2026.07.15.738791v1.38","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa947"},{"key":"2026072011001155000_2026.07.15.738791v1.39","unstructured":"Mahmood, O. , Skok Gibbs, C. , Bonneau, R. , and Cho, K. (2022). Probabilistic matrix factorization for gene regulatory network inference. bioRxiv, pages 2022\u201309."},{"key":"2026072011001155000_2026.07.15.738791v1.40","doi-asserted-by":"crossref","unstructured":"Mandros, P. , Gallagher, I. , Fanfani, V. , Chen, C. , Fischer, J. , Ismail, A. , Hsu, L. , Saha, E. , DeConti, D. K. , and Quackenbush, J. (2024). node2vec2rank: Large scale and stable graph differential analysis via multi-layer node embeddings and ranking. bioRxiv.","DOI":"10.1101\/2024.06.16.599201"},{"issue":"1","key":"2026072011001155000_2026.07.15.738791v1.41","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1007\/s12551-018-0494-4","article-title":"The rise of the distributions: why non-normality is important for understanding the transcriptome and beyond","volume":"11","year":"2019","journal-title":"Biophysical reviews"},{"key":"2026072011001155000_2026.07.15.738791v1.42","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0913357107"},{"key":"2026072011001155000_2026.07.15.738791v1.43","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2010.00740.x"},{"key":"2026072011001155000_2026.07.15.738791v1.44","unstructured":"Melchior, P. , Joseph, R. , and Moolekamp, F. (2019). Proximal adam: robust adaptive update scheme for constrained optimization. arXiv preprint arXiv:1910.10094."},{"key":"2026072011001155000_2026.07.15.738791v1.45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2007\/79879","article-title":"Information-theoretic inference of large transcriptional regulatory networks","volume":"2007","year":"2007","journal-title":"EURASIP journal on bioinformatics and systems biology"},{"key":"2026072011001155000_2026.07.15.738791v1.46","unstructured":"Micheletti, S. (2023). Biologically informed matrix factorization for joint inference of gene regulatory networks and transcription factor activities. Master\u2019s thesis, ETH Zurich."},{"issue":"9","key":"2026072011001155000_2026.07.15.738791v1.47","doi-asserted-by":"crossref","first-page":"btae531","DOI":"10.1093\/bioinformatics\/btae531","article-title":"Higher-order correction of persistent batch effects in correlation networks","volume":"40","year":"2024","journal-title":"Bioinformatics"},{"key":"2026072011001155000_2026.07.15.738791v1.48","doi-asserted-by":"publisher","DOI":"10.1007\/s12038-015-9558-9"},{"issue":"5","key":"2026072011001155000_2026.07.15.738791v1.49","doi-asserted-by":"crossref","first-page":"e1004220","DOI":"10.1371\/journal.pcbi.1004220","article-title":"Sharing and specificity of co-expression networks across 35 human tissues","volume":"11","year":"2015","journal-title":"PLoS computational biology"},{"key":"2026072011001155000_2026.07.15.738791v1.50","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14010238"},{"issue":"4","key":"2026072011001155000_2026.07.15.738791v1.51","doi-asserted-by":"crossref","first-page":"347","DOI":"10.4161\/cam.3.4.9458","article-title":"The role of focal adhesion kinase in tumor initiation and progression","volume":"3","year":"2009","journal-title":"Cell adhesion & migration"},{"key":"2026072011001155000_2026.07.15.738791v1.52","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkv007"},{"key":"2026072011001155000_2026.07.15.738791v1.53","doi-asserted-by":"crossref","unstructured":"Saha, E. , Guebila, M. B. , Fanfani, V. , Fischer, J. , Shutta, K. H. , Mandros, P. , DeMeo, D. L. , Quackenbush, J. , and Lopes-Ramos, C. M. (2023). Gene regulatory networks reveal sex difference in lung adenocarcinoma. bioRxiv.","DOI":"10.1101\/2023.09.22.559001"},{"issue":"1","key":"2026072011001155000_2026.07.15.738791v1.54","doi-asserted-by":"crossref","first-page":"5387","DOI":"10.1038\/s41598-017-03299-3","article-title":"Role of insulin receptor substrates in the progression of hepatocellular carcinoma","volume":"7","year":"2017","journal-title":"Scientific reports"},{"key":"2026072011001155000_2026.07.15.738791v1.55","doi-asserted-by":"crossref","unstructured":"Salleh, F. H. M. , Zainudin, S. , and Arif, S. M. (2017). Multiple linear regression for reconstruction of gene regulatory networks in solving cascade error problems. Advances in bioinformatics, 2017.","DOI":"10.1155\/2017\/4827171"},{"key":"2026072011001155000_2026.07.15.738791v1.56","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0090481"},{"issue":"19","key":"2026072011001155000_2026.07.15.738791v1.57","doi-asserted-by":"crossref","first-page":"10260","DOI":"10.3390\/ijms221910260","article-title":"Growth factors, pi3k\/akt\/mtor and mapk signaling pathways in colorectal cancer pathogenesis: where are we now?","volume":"22","year":"2021","journal-title":"International Journal of Molecular Sciences"},{"key":"2026072011001155000_2026.07.15.738791v1.58","doi-asserted-by":"crossref","unstructured":"Szklarczyk, D. , Morris, J. H. , Cook, H. , Kuhn, M. , Wyder, S. , Simonovic, M. , Santos, A. , Doncheva, N. T. , Roth, A. , Bork, P. , et al. (2016). The string database in 2017: quality-controlled protein\u2013protein association networks, made broadly accessible. Nucleic acids research, page gkw937.","DOI":"10.1093\/nar\/gkw937"},{"key":"2026072011001155000_2026.07.15.738791v1.59","doi-asserted-by":"publisher","DOI":"10.1111\/J.2517-6161.1996.TB02080.X"},{"issue":"8","key":"2026072011001155000_2026.07.15.738791v1.60","doi-asserted-by":"crossref","first-page":"2385","DOI":"10.3390\/cancers15082385","article-title":"The ubiquitin\u2013proteasome system in tumor metabolism","volume":"15","year":"2023","journal-title":"Cancers"},{"issue":"1","key":"2026072011001155000_2026.07.15.738791v1.61","doi-asserted-by":"crossref","first-page":"1282","DOI":"10.1038\/s42003-022-04226-7","article-title":"Netrex-cf integrates incomplete transcription factor data with gene expression to reconstruct gene regulatory networks","volume":"5","year":"2022","journal-title":"Communications Biology"},{"key":"2026072011001155000_2026.07.15.738791v1.62","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp674"},{"key":"2026072011001155000_2026.07.15.738791v1.63","doi-asserted-by":"publisher","DOI":"10.1101\/gr.275107.120"},{"key":"2026072011001155000_2026.07.15.738791v1.64","doi-asserted-by":"crossref","first-page":"10263","DOI":"10.1609\/aaai.v35i11.17230","article-title":"Gene regulatory network inference as relaxed graph matching","volume":"35","year":"2021","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2026072011001155000_2026.07.15.738791v1.65","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2014.08.009"},{"key":"2026072011001155000_2026.07.15.738791v1.66","doi-asserted-by":"crossref","unstructured":"Wu, K. and Lin, F. (2024). Lipid metabolism as a potential target of liver cancer. Journal of Hepatocellular Carcinoma, pages 327\u2013346.","DOI":"10.2147\/JHC.S450423"},{"key":"2026072011001155000_2026.07.15.738791v1.67","doi-asserted-by":"crossref","unstructured":"Wuchty, S. , Ravasz, E. , and Barab\u00e1si, A.-L. (2006). The architecture of biological networks. Complex systems science in biomedicine, pages 165\u2013181.","DOI":"10.1007\/978-0-387-33532-2_5"},{"key":"2026072011001155000_2026.07.15.738791v1.68","doi-asserted-by":"publisher","DOI":"10.1016\/J.GPB.2019.09.006"},{"key":"2026072011001155000_2026.07.15.738791v1.69","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab009"},{"issue":"10","key":"2026072011001155000_2026.07.15.738791v1.70","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.2217\/fon.11.95","article-title":"Targeting the pi3k\/akt\/mtor pathway in hepatocellular carcinoma","volume":"7","year":"2011","journal-title":"Future oncology"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.07.15.738791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T18:00:25Z","timestamp":1784570425000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.07.15.738791"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":70,"URL":"https:\/\/doi.org\/10.64898\/2026.07.15.738791","relation":{},"subject":[],"published":{"date-parts":[[2026,7,16]]},"subtype":"preprint"}}