Data-driven reverse engineering of signaling pathways using ensembles of dynamic models
Open accessThe DOI matches its Crossref record; 87 of the 88 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
Despite significant efforts and remarkable progress, the inference of signaling networks from experimental data remains very challenging. The problem is particularly difficult when the objective is to obtain a dynamic model capable of predicting the effect of novel perturbations not considered during model training. The problem is ill-posed due to the nonlinear nature of these systems, the fact that only a fraction of the involved proteins and their post-translational modifications can be measured, and limitations on the technologies used for growing cells in vitro, perturbing them, and measuring their variations. As a consequence, there is a pervasive lack of identifiability. To overcome these issues, we present a methodology called SELDOM (enSEmbLe of Dynamic lOgic-based Models), which builds an ensemble of logic-based dynamic models, trains them to experimental data, and combines their individual simulations into an ensemble prediction. It also includes a model reduction step to prune spurious interactions and mitigate overfitting. SELDOM is a data-driven method, in the sense that it does not require any prior knowledge of the system: the interaction networks that act as scaffolds for the dynamic models are inferred from data using mutual information. We have tested SELDOM on a number of experimental and in silico signal transduction case-studies, including the recent HPN-DREAM breast cancer challenge. We found that its performance is highly competitive compared to state-of-the-art methods for the purpose of recovering network topology. More importantly, the utility of SELDOM goes beyond basic network inference (i.e. uncovering static interaction networks): it builds dynamic (based on ordinary differential equation) models, which can be used for mechanistic interpretations and reliable dynamic predictions in new experimental conditions (i.e. not used in the training). For this task, SELDOM's ensemble prediction is not only consistently better than predictions from individual models, but also often outperforms the state of the art represented by the methods used in the HPN-DREAM challenge.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures

![Fig 2 MAPK signaling network. The model by Huang et al. [67] was used to generate pseudo-experimental data for two sub-problems. The first (MAPKp) partially observed (MAPK-PP, MAPKK-PP and MAPKKK), and the second fully observed MAPKf.](https://figures.cochat.ai/paper-figures/cd41259a0d7446309c192556b7b5130d/data-driven-reverse-engineering-of-signaling-pathways-using-ensembles-of-dynamic-figure-2.jpg)





Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
“First applications of this in the field of mechanistic modeling are available for models with dozens of biochemical species (Henriques et al., 2017).”
From Efficient Parameter Estimation Enables the Prediction of Drug Response Using a Mechanistic Pan-Cancer Pathway Model (2018) · cites this paper as Henriques et al., 2017
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb01338.x · Cited by 88,486
A Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb00917.x · Cited by 48,949
Model selection and multimodel inference: a practical information-theoretic approach.
Guthery, F. S., Burnham, K. P., & Anderson, D. R. (2003) · The Journal of Wildlife Management · doi:10.2307/3802723 · Cited by 41,495
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325
Ensemble methods in machine learning
Dietterich, T. G. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-45014-9_1 · Cited by 8,408
The relationship between Precision-Recall and ROC curves
Davis, J., & Goadrich, M. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143874 · Cited by 6,559
Mitogen-Activated Protein Kinase Pathways Mediated by ERK, JNK, and p38 Protein Kinases
Johnson, G. L., & Lapadat, R. (2002) · Science · doi:10.1126/science.1072682 · Cited by 4,295
OpenMP: an industry standard API for shared-memory programming
Dagum, L., & Menon, R. (1998) · IEEE Computational Science and Engineering · doi:10.1109/99.660313 · Cited by 3,343
Model selection and multimodel inference : a practical information-theoretic approach
Burnham, K. P., Anderson, D. R., & Burnham, K. P. (2002) · Thammasat University Digital Collections · Cited by 2,907
Modeling and Simulation of Genetic Regulatory Systems: A Literature Review
de Jong, H. (2002) · Journal of Computational Biology · doi:10.1089/10665270252833208 · Cited by 2,663
Research works printed but not linked: 2
- Breiman L. Arcing classifiers. Ann Stat. 1998; 26(3): 801– 824.
- De La Maza M, Yuret D. Dynamic hill climbing. AI expert. 1994; 9: 26– 26.
Cited by
Two new Later Stone Age sites from the Final Pleistocene in the Falémé Valley, eastern Senegal
Ndiaye, M., Lespez, L., Tribolo, C., Rassé, M., Hadjas, I., Davidoux, S., Huysecom, É., & Douze, K. (2024) · Monash University Research Portal (Monash University) · doi:10.3929/ethz-b-000667478 · Cited by 23,868
AlphaFold, Artificial Intelligence (AI), and Allostery
Nussinov, R., Zhang, M., Liu, Y., & Jang, H. (2022) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.2c04346 · Cited by 190
Machine Learning Methods for Analysis of Metabolic Data and Metabolic Pathway Modeling
Cuperlovic-Culf, M. (2018) · Metabolites · doi:10.3390/metabo8010004 · Cited by 163
“[78], attempting to help determine dynamic network models from experimental data.”
BackgroundA protocol for dynamic model calibration
Villaverde, A. F., Pathirana, D., Fröhlich, F., Hasenauer, J., & Banga, J. R. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbab387 · Cited by 137
Self-citationFröhlich, F., Kessler, T., Weindl, D., Shadrin, A., Schmiester, L., Hache, H., Muradyan, A., Schütte, M., Lim, J.-H., Heinig, M., et al. (2018) · Cell Systems · doi:10.1016/j.cels.2018.10.013 · Cited by 143
“First applications of this in the field of mechanistic modeling are available for models with dozens of biochemical species (Henriques et al., 2017).”
BackgroundNexus between in silico and in vivo models to enhance clinical translation of nanomedicine
Moradi Kashkooli, F., Soltani, M., Souri, M., Meaney, C., & Kohandel, M. (2021) · Nano Today · doi:10.1016/j.nantod.2020.101057 · Cited by 120
Lee, D., Jayaraman, A., & Kwon, J. S. (2020) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1008472 · Cited by 113
How to deal with parameters for whole-cell modelling
Babtie, A. C., & Stumpf, M. P. H. (2017) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0237 · Cited by 83
Artificial intelligence and synthetic biology approaches for human gut microbiome
Kumar, P., Sinha, R., & Shukla, P. (2022) · Critical Reviews in Food Science and Nutrition · doi:10.1080/10408398.2020.1850415 · Cited by 71
“Further, as the method is data driven, it does not require prior knowledge either about the dynamics of reaction or the nature of the network (Henriques et al. 2017).”
MethodInferring dynamic topology for decoding spatiotemporal structures in complex heterogeneous networks
Wang, S., Herzog, E. D., Kiss, I. Z., Schwartz, W. J., Bloch, G., Sebek, M., Granados‐Fuentes, D., Wang, L. Y., & Li, J.-S. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1721286115 · Cited by 59
“, the interactions between nodes are binary values (11, 12), and the developed techniques are robust when the network is sparse and small (8, 13).”
BackgroundReconstructing phosphorylation signalling networks from quantitative phosphoproteomic data
Invergo, B. M., & Beltrão, P. (2018) · Essays in Biochemistry · doi:10.1042/ebc20180019 · Cited by 40
Barbosa, S., Niebel, B., Wolf, S., Mauch, K., & Takors, R. (2018) · Biosystems · doi:10.1016/j.biosystems.2018.10.008 · Cited by 39
Computational Approaches in Theranostics: Mining and Predicting Cancer Data
Cova, T. F. G. G., Bento, D. J., & Nunes, S. C. C. (2019) · Pharmaceutics · doi:10.3390/pharmaceutics11030119 · Cited by 32
“This can be improved using parameter optimization, onte Carlo, reverse engineering, and model reduction strategies [72,73], as well as artificial intelligence techniques (e.”
MethodContext-specific network modeling identifies new crosstalk in β-adrenergic cardiac hypertrophy
Khalilimeybodi, A., Paap, A., Christiansen, S. L. M., & Saucerman, J. J. (2020) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1008490 · Cited by 26
“Hence, recently, researchers prefer to utilize hybrid approaches for modeling large-scale networks [40,41].”
BackgroundMini-batch optimization enables training of ODE models on large-scale datasets
Stapor, P. L., Schmiester, L., Wierling, C., Merkt, S., Pathirana, D., Lange, B. M. H., Weindl, D., & Hasenauer, J. (2022) · Nature Communications · doi:10.1038/s41467-021-27374-6 · Cited by 36
Henriques, D., Alonso‐del‐Real, J., Querol, A., & Balsa‐Canto, E. (2018) · Frontiers in Microbiology · doi:10.3389/fmicb.2018.00088 · Cited by 31
“, we omitted the experimental data for each temperature and computed an ensemblemodel for each scenario (Henriques et al., 2017).”
Self-citationModels of Models: A Translational Route for Cancer Treatment and Drug Development
Ogilvie, L. A., Kovachev, A., Wierling, C., Lange, B. M. H., & Lehrach, H. (2017) · Frontiers in Oncology · doi:10.3389/fonc.2017.00219 · Cited by 30
“An alternative strategy is to reduce the number of parameters by simplifying the model using model reduction methods (32, 33).”
MethodMeier‐Schellersheim, M., Varma, R., & Angermann, B. (2019) · Frontiers in Immunology · doi:10.3389/fimmu.2019.02268 · Cited by 27
“…problem is frequently taken as a motivation to resort to models that incorporate pathway structure but not kinetics [for instance in Boolean models (18)] or abandon prior pathway knowledge altogether in favor of extracting only as much information as the data being modeled provide directly (19).”
BackgroundChallenges in the calibration of large-scale ordinary differential equation models
Kapfer, E.-M., Stapor, P. L., & Hasenauer, J. (2019) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2019.12.236 · Cited by 18
Incorporating Pathway Information into Feature Selection towards Better Performed Gene Signatures
Tian, S., Wang, C., & Wang, B. (2019) · BioMed Research International · doi:10.1155/2019/2497509 · Cited by 18
“Here, “data-driven” means that specific data of a specific condition/disease are used to build up pathways [47, 48].”
BackgroundMultiobjective Identification of a Feedback Synthetic Gene Circuit
Boada, Y., Vignoni, A., & Picó, J. (2019) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2018.2885694 · Cited by 19
Penas, D. R., Henriques, D., González, P., Doallo, R., Saez-Rodriguez, J., & Banga, J. R. (2017) · PLOS ONE · doi:10.1371/journal.pone.0182186 · Cited by 16
Self-citationPalma, A., Iannuccelli, M., Rozzo, I., Licata, L., Perfetto, L., Massacci, G., Castagnoli, L., Cesareni, G., & Sacco, F. (2021) · Journal of Personalized Medicine · doi:10.3390/jpm11020117 · Cited by 19
“The predictions of the model ensemble are finally combined into an ensemble prediction [24,30].”
MethodMachine learning for control of (bio)chemical manufacturing systems
Himmel, A., Matschek, J., Kok, R. L., Morabito, B., Nguyen, H. H., & Findeisen, R. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-99134-6.00009-8 · Cited by 16
Network inference from perturbation time course data
Sarmah, D., Smith, G. R., Bouhaddou, M., Stern, A. D., Erskine, J., & Birtwistle, M. R. (2022) · npj Systems Biology and Applications · doi:10.1038/s41540-022-00253-6 · Cited by 17
“4b) 37,39,41,46,52,62 .”
MethodFAMoS: A Flexible and dynamic Algorithm for Model Selection to analyse complex systems dynamics
Gabel, M., Hohl, T., Imle, A., Fackler, O., & Graw, F. (2019) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1007230 · Cited by 11
“Several existing model selection algorithms already provide advanced fitting methods for the challenging analyses of dynamical systems while relying on model comparisons across the whole model space [2, 14, 17, 18, 46].”
Boolean function metrics can assist modelers to check and choose logical rules
Zobolas, J., Monteiro, P. T., Kuiper, M. T. R., & Flobak, Å. (2022) · Journal of Theoretical Biology · doi:10.1016/j.jtbi.2022.111025 · Cited by 10
Mathematical basis and toolchain for hierarchical optimization of biochemical networks
Viswan, N. A., Tribut, A., Gasparyan, M. D., Radulescu, O., & Bhalla, U. S. (2024) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1012624 · Cited by 8
TopoFilter: a MATLAB package for mechanistic model identification in systems biology
Rybiński, M., Möller, S., Sunnåker, M., Lormeau, C., & Stelling, J. (2020) · BMC Bioinformatics · doi:10.1186/s12859-020-3343-y · Cited by 7
Characterization of multiscale logic operations in the neural circuits
Woo, J., Choi, K., Kim, S. H., Han, K., & Choi, M. Y. (2021) · Frontiers in Bioscience-Landmark · doi:10.52586/4983 · Cited by 6
“There are also various information-theoretic approaches [79] using an ensemble of logic models [ 80], regression approaches [81], other heuristic, meta-heuristic, and hybrid methods [82–85], and many more.”
MethodFeng, J., Zhang, X., & Tian, T. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms251810204 · Cited by 5
“• Dynamic logical network models, which use Boolean variables for MAPK modules and the AKT and P53 pathways [160,161].”
BackgroundHan, Y., & Styczynski, M. P. (2024) · npj Systems Biology and Applications · doi:10.1038/s41540-024-00412-x · Cited by 7
“For example, ensemble models for signaling network structures have been developed using logic-based models to accountfor structural uncertainty 24 .”
Inferring signaling pathways with probabilistic programming
Merrell, D., & Gitter, A. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa861 · Cited by 5
Mechano-immunology in microgravity
Murali, A., & Sarkar, R. R. (2023) · Life Sciences in Space Research · doi:10.1016/j.lssr.2023.03.001 · Cited by 7
Deep Neural Networks for Predicting Single-Cell Responses and Probability Landscapes
Klumpe, H. E., Lugagne, J., Khalil, A. S., & Dunlop, M. J. (2023) · ACS Synthetic Biology · doi:10.1021/acssynbio.3c00203 · Cited by 7
Utility of constraints reflecting system stability on analyses for biological models
Kariya, Y., Honma, M., Tokuda, K., Konagaya, A., & Suzuki, H. (2022) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1010441 · Cited by 4
“does not require individual parameter determination [38].”
Design decisions for incorporating spatial and mechanical aspects in models of signaling networks
Bell, M. K., & Rangamani, P. (2021) · Current Opinion in Systems Biology · doi:10.1016/j.coisb.2021.03.004 · Cited by 4
Literature and data-driven based inference of signalling interactions using time-course data
Gjerga, E., Trairatphisan, P., Gábor, A., & Sáez-Rodríguez, J. (2019) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2019.12.235 · Cited by 3
Program Synthesis for Systems Biology
Köksal, A. S. (2018) · eScholarship (California Digital Library) · Cited by 4
Robust Approaches to Generating Reliable Predictive Models in Systems Biology
Choi, K. (2018) · RNA technologies · doi:10.1007/978-3-319-92967-5_15 · Cited by 3
Modelling techniques for biomolecular networksPreprint
Mayer, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00327 · Cited by 2
EDGE: Evolutionary Directed Graph Ensembles
Fontes, X., & Silva, D. C. (2019) · International Journal of Hybrid Intelligent Systems · doi:10.3233/his-190273 · Cited by 1
“Currently we see prediction and classification problems being tackled in almost every scientific field, from cancer prediction [21] to credit scoring [1], classification of fake news headlines [30] and even predicting the effect of new combinations of drugs [19].”
Synthesizing Signaling Pathways from Temporal Phosphoproteomic DataPreprint
Köksal, A. S., Beck, K., Cronin, D. R., McKenna, A., Camp, N. D., Srivastava, S., MacGilvray, M. E., Bodík, R., Wolf-Yadlin, A., Fraenkel, E., et al. (2017) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/209676 · Cited by 3
An improved framework for grey-box identification of biological processesPreprint
Jagadeesan, P., Raman, K., & Tangirala, A. K. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.02.14.638382 · Cited by 1
“Data-driven process Modeling (System Identification) has a wide range of applications in medicine and life sciences, such as in pharmacometrics or Quantitative Systems Pharmacology (QSP) [1], discovering drug targets [2], and uncovering the underlying mechanisms of a biological process [3, 4].”
Petritis, B. O. (2018) · Arizona State University Library Digital Repository (Arizona State University)
gitter-lab/ssps: July 2020 Release
Merrell, D., & Gitter, A. (2020) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.3939288
Metadata
- Authors
- Henriques, D., Villaverde, A. F., Rocha, M., Saez-Rodriguez, J., & Banga, J. R.
- Affiliations
- Consejo Superior de Investigaciones Científicas (ES)
- University of Minho (PT)
- Corresponding author
- Banga, Julio R.
- Venue
- PLOS Computational Biology
- Publisher
- Public Library of Science (PLoS)
- Published
- 2017-02-06
- Volume
- 13
- Issue
- 2
- Pages
- e1005379
- ISSN
- 1553-734X (ISSN-L)
- 1553-7358
- PMC
- PMC5319798
- OpenAlex
- W2586633795
- Cited by
- 44
- References
- 83
- Citations by year
- 2025: 1 · 2024: 5 · 2023: 2 · 2022: 5 · 2021: 4 · 2020: 8 · 2019: 8 · 2018: 7 · 2017: 4
- FWCI
- 3.02
- Type
- journal article
- Language
- en
- Update notices
- new_version (2017-02-21)
- Open access
- gold
- doi.org
- Licence
- Locations
- PLoS Computational Biology (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DIGITAL.CSIC (Spanish National Research Council (CSIC)) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Figshare (submittedVersion, cc-by)
- RWTH Publications (RWTH Aachen) (submittedVersion, other-oa)
- Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) (submittedVersion, other-oa)
- RWTH Publications (RWTH Aachen)
- Funders
- Galician government (Xunta de Galiza) I2C (ED481B2014/133-0)
- EU FP7 (ITN Grant number 289384)
- Spanish MINECO (DPI2014-55276-C5-2-R)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene Regulatory Network Analysis
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Microbial Metabolic Engineering and Bioproduction
- Keywords
- signaling pathway inference, ensemble forecasting, model reduction, network identifiability, signal transduction, ordinary differential equation model
- MeSH terms
- Algorithms, Animals, Computer Simulation, Humans, Models, Biological, Signal Transduction, Proteome, Metabolic Engineering, Metabolic Flux Analysis
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.