Interpretable machine learning uncovers structural determinants of Wnt-Wntless binding specificity from atomistic simulations

Machine Learning


  • Albrecht, L. V., Tejeda-Munoz, N. & De Robertis, E. M. Cell biology of canonical Wnt signaling. Annu. Rev. Cell Dev. Biol. 37, 369–389 (2021).

  • Mehta, S., Hingole, S. & Chaudhary, V. The emerging mechanisms of Wnt secretion and signaling in development. Front. Cell Dev. Biol. 9, 714746 (2021).

  • Hayat, R., Manzoor, M. & Hussain, A. Wnt signaling pathway: a comprehensive review. Cell Biol. Int. 46, 863–877 (2022).

  • Clevers, H. & Nusse, R. Wnt/β-catenin signaling and disease. Cell 8, 1192–1205 (2012).

    Google Scholar 

  • Nusse, R. & Clevers, H. Wnt/β-catenin signaling, disease, and emerging therapeutic modalities. Cell 169, 985–999 (2017).

    Google Scholar 

  • Niehrs, C. The complex world of WNT receptor signalling. Nat. Rev. Mol. Cell Biol. 13, 767–779 (2012).

    Google Scholar 

  • Xiao, Q., Chen, Z., Jin, X., Mao, R. & Chen, Z. The many postures of noncanonical Wnt signaling in development and diseases. Biomed. Pharmacother. 93, 360–366 (2017).

    Google Scholar 

  • Krausova, M. & Korinek, V. Wnt signaling in adult intestinal stem cells and cancer. Cell Signal. 26, 570–579 (2024).

    Google Scholar 

  • Zhan, T., Rindtorff, N. & Boutros, M. Wnt signaling in cancer. Oncogene 36, 1461–1473 (2017).

    Google Scholar 

  • You, M. et al. Signaling pathways in cancer metabolism: mechanisms and therapeutic targets. Signal Transduct. Target. Ther. 8, 196 (2023).

    Google Scholar 

  • Groenewald, W., Lund, A. H. & Michael, D. The role of WNT pathway mutations in cancer development and an overview of therapeutic options. Cells 12, 990 (2023).

    Google Scholar 

  • Zhang, Y. & Wang, X. Targeting the Wnt/β-catenin signaling pathway in cancer. J. Hematol. Oncol. 13, 165 (2020).

    Google Scholar 

  • Xue, C. et al. Wnt signaling pathways in biology and disease: mechanisms and therapeutic advances. Signal Transduct. Target. Ther. 10, 106 (2025).

    Google Scholar 

  • Anastas, J. N. & Moon, R. T. WNT signalling pathways as therapeutic targets in cancer. Nat. Rev. Cancer 13, 11–26 (2013).

  • Inestrosa, N. C. & Varela-Nallar, L. Wnt signaling in the nervous system and in Alzheimer’s disease. J. Mol. Cell Biol. 6, 64–74 (2014).

    Google Scholar 

  • Ramakrishna, K. et al. WNT-β catenin signaling as a potential therapeutic target for neurodegenerative diseases: current status and future perspective. Diseases 11, 89 (2023).

    Google Scholar 

  • Anand, A. A., Khan, M., V, M. & Kar, D. The molecular basis of Wnt/β-catenin signaling pathways in neurodegenerative diseases. Int. J. Cell Biol. 1, 9296092 (2023).

    Google Scholar 

  • Monroe, D. G., McGee-Lawrence, M. E., Oursler, M. J. & Westendorf, J. J. Update on Wnt signaling in bone cell biology and bone disease. Gene 492, 1–18 (2012).

    Google Scholar 

  • Hu, L., Chen, W., Qian, A. & Li, Y.-P. Wnt/β-catenin signaling components and mechanisms in bone formation, homeostasis, and disease. Bone Res. 12, 39 (2024).

    Google Scholar 

  • van Amerongen, R. & Nusse, R. Towards an integrated view of Wnt signaling in development. Development 136, 3205–3214 (2009).

    Google Scholar 

  • MacDonald, B. T., Tamai, K. & He, X. Wnt/β-catenin signaling: components, mechanisms, and diseases. Dev. Cell 17, 9–26 (2009).

    Google Scholar 

  • Janda, C. Y., Waghray, D., Levin, A. M., Thomas, C. & Garcia, K. C. Structural basis of Wnt recognition by frizzled. Science 337, 59–64 (2012).

    Google Scholar 

  • Janda, C. Y. et al. Surrogate Wnt agonists that phenocopy canonical Wnt and β-catenin signalling. Nature 545, 234–237 (2017).

    Google Scholar 

  • Liu, J. et al. Wnt/β-catenin signalling: function, biological mechanisms, and therapeutic opportunities. Signal Transduct. Target. Ther. 7, 3 (2022).

    Google Scholar 

  • Zhong, Q. et al. Cryo-EM structure of human Wntless in complex with Wnt3a. Nat. Commun. 12, 4541 (2021).

    Google Scholar 

  • Das, S., Yu, S., Sakamori, R., Stypulkowski, E. & Gao, N. Wntless in Wnt secretion: molecular, cellular and genetic aspects. Front. Biol. 7, 587–593 (2012).

    Google Scholar 

  • Nygaard, R. et al. Structural basis of WLS/Evi-mediated Wnt transport and secretion. Cell 184, 194–206 (2021).

  • Wolf, L. & M. Boutros. The role of Evi/Wntless in exporting Wnt proteins. Development 150, dev201352 (2023).

  • Capponi, S., Wang, S., Navarro, E. J. & Bianco, S. AI-driven prediction of SARS-CoV-2 variant binding trends from atomistic simulations. Eur. Phys. J. E 44, 123 (2021).

    Google Scholar 

  • Pavlova, A. et al. Machine learning reveals the critical interactions for SARS-CoV-2 spike protein binding to ACE2. J. Phys. Chem. Lett. 12, 5494–5502 (2021).

  • Ovchinnikov, S. et al. Protein structure determination using metagenome sequence data. Science 355, 294–298 (2017).

    Google Scholar 

  • Marks, D. S. et al. Protein 3D structure computed from evolutionary sequence variation. PloS ONE 6, e28766 (2011).

    Google Scholar 

  • Brownless, A.-L. R., Rheaume, E., Kuo, K. M., Kamerlin, S. C. L. & Gumbart, J. C. Using machine learning to analyze molecular dynamics simulations of biomolecules. J. Phys. Chem. B 129, 5375–5385 (2025).

  • Mustali, J. et al. Unsupervised deep learning for molecular dynamics simulations: a novel analysis of protein–ligand interactions in SARS-CoV-2 Mpro. RSC Adv. 13, 34249–34261 (2023).

    Google Scholar 

  • Casalino, L. et al. AI-driven multiscale simulations illuminate mechanisms of SARS-CoV-2 spike dynamics. Int. J. High. Perform. Comput. Appl. 35, 432–451 (2021).

    Google Scholar 

  • Casadio, R., Martelli, P. L. & Savojardo, C. Machine learning solutions for predicting protein–protein interactions. Wiley Interdiscip. Rev. Comput. Mol. Sci. 12, e1618 (2022).

    Google Scholar 

  • Cunningham, J. M., Koytiger, G., Sorger, P. K. & AlQuraishi, M. Biophysical prediction of protein–peptide interactions and signaling networks using machine learning. Nat. Methods 17, 175–183 (2020).

    Google Scholar 

  • Das, S. & Chakrabarti, S. Classification and prediction of protein–protein interaction interface using machine learning algorithm. Sci. Rep. 11, 1761 (2021).

    Google Scholar 

  • Zhang, J., Durham, J. & Cong, Q. Revolutionizing protein–protein interaction prediction with deep learning. Curr. Opin. Struct. Biol. 85, 102774 (2024).

    Google Scholar 

  • Weber, J. K. et al. Unsupervised and supervised AI on molecular dynamics simulations reveals complex characteristics of HLA-A2-peptide immunogenicity. Brief. Bioinform. 25, bbad504 (2023).

  • Frasnetti, E. et al. Integrating molecular dynamics and machine learning algorithms to predict the functional profile of kinase ligands. J. Chem. Theory Comput. 20, 9209–9229 (2024).

    Google Scholar 

  • Pavlova, A., Fan, Z., Lynch, D. L. & Gumbart, J. C. Machine learning of molecular dynamics simulations provides insights into the modulation of viral capsid assembly. J. Chem. Inf. Model. 65, 4844–4853 (2025).

    Google Scholar 

  • Fleetwood, O., Kasimova, M. A., Westerlund, A. M. & Delemotte, L. Molecular insights from conformational ensembles via machine learning. Biophys. J. 118, 765–780 (2020).

    Google Scholar 

  • Ljungberg, J. K., Kling, J. C., Tran, T. T. & Blumenthal, A. Functions of the WNT Signaling Network in Shaping Host Responses to Infection. Front. Immunol. 10, 2521 (2019).

    Google Scholar 

  • Kikuchi, A., Yamamoto, H. Sato, A. & Matsumoto, S. New insights into the mechanism of Wnt signaling pathway activation. Int. Rev. Cell Mol. Biol. 291, 21–71 (2011).

  • Powell, H. R., Islam, S. A., David, A. & Sternberg, M. J. E. Phyre2.2: a community resource for template-based protein structure prediction. J. Mol. Biol. 437, 168960 (2025).

    Google Scholar 

  • Chen, Y. et al. YidC insertase of Escherichia coli: water accessibility and membrane shaping. Structure 25, P1403–1414 (2017).

    Google Scholar 

  • Capponi, S., Freites, J. A., Tobias, D. J. & White, S. H. Interleaflet mixing and coupling in liquid-disordered phospholipid bilayers. Biochim. Biophys. Acta 1858, 354–362 (2016).

    Google Scholar 

  • Takada, R. et al. Monounsaturated fatty acid modification of Wnt protein: its role in Wnt secretion. Dev. Cell 11, 791–801 (2006).

    Google Scholar 

  • Jo, S., Kim, T., Iyer, V. G. & Im, W. CHARMM-GUI: a web-based graphical user interface for CHARMM. J. Comput. Chem. 29, 1859–1865 (2008).

    Google Scholar 

  • Lee, J. et al. CHARMM-GUI input generator for NAMD, GROMACS, AMBER, OpenMM, and CHARMM/OpenMM simulations using the CHARMM36 additive force field. J. Chem. Theory Comput. 12, 405–413 (2015).

  • Wu, E. L. et al. CHARMM‐GUI membrane builder toward realistic biological membrane simulations. J. Comput. Chem. 35, 1997–2004 (2014).

  • Jorgensen, W. L., Chandrasekhar, J., Madura, J. D., Impey, R. W. & Klein, M. L. Comparison of simple potential functions for simulating liquid water. J. Chem. Phys. 79, 926–935 (1983).

    Google Scholar 

  • Phillips, J. C. et al. Scalable molecular dynamics on CPU and GPU architectures with NAMD. J. Chem. Phys. 153, 044130 (2020).

    Google Scholar 

  • Feller, S. E., Zhang, Y., Pastor, R. W. & Brooks, B. R. Constant pressure molecular dynamics simulation: the Langevin Piston method. J. Chem. Phys. 103, 4613–4621 (1995).

    Google Scholar 

  • Darden, T., York, D. & Pedersen, L. Particle Mesh Ewald: an N · log(N) method for Ewald Sums in large systems. J. Chem. Phys. 98, 10089–10092 (1993).

    Google Scholar 

  • Miyamoto, S. & Kollman, P. A. Settle: an analytical version of the SHAKE and RATTLE algorithm for rigid water models. J. Comput. Chem. https://doi.org/10.1002/jcc.540130805 (1992).

  • Huang, J. et al. CHARMM36m: an improved force field for folded and intrinsically disordered proteins. Nat. Methods 14, 71–73 (2017).

  • Croitoru, A. et al. Additive CHARMM36 force field for nonstandard amino acids. J. Chem. Theory Comput. 17, 3554–3570 (2017).

    Google Scholar 

  • Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).

    Google Scholar 

  • Miller, J. R. The Wnts. Genome Biol. 3, reviews3001.1 (2001).

    Google Scholar 

  • MacDonald, B. T. et al. Disulfide bond requirements for active Wnt ligands. J. Biol. Chem. 289, 18122–18136 (2014).

    Google Scholar 

  • Roe, D. R. & Cheatham III, T. E. PTRAJ and CPPTRAJ: software for processing and analysis of molecular dynamics trajectory data. J. Chem. Theory Comput. 9, 3084–3095 (2013).

    Google Scholar 

  • Gowers, R. J. et al. MDAnalysis: a Python package for the rapid analysis of molecular dynamics simulations (SciPy, 2016).

  • Cheng, K. J., Shi, J., Pogorelov, T. V. & Capponi, S. Investigating the bromoform membrane interactions using atomistic simulations and machine learning: implications for climate change mitigation. J. Phys. Chem. B 128, 12493–12506 (2024).

  • Homayouni, H. et al. An autocorrelation-based LSTM-autoencoder for anomaly detection on time-series data. https://doi.org/10.1109/BigData50022.2020.9378192 (2020).

  • AgglomerativeClustering. https://scikit-learn.org/stable/modules/generated/sklearn.cluster.AgglomerativeClustering.html.



  • Source link