{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T16:19:02Z","timestamp":1792253942582,"version":"4.4.0"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:00:00Z","timestamp":1788307200000},"content-version":"vor","delay-in-days":33,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"DOI":"10.1038\/s41467-026-75713-2","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T17:44:45Z","timestamp":1785519885000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Activity-cliff awareness enables robust graph learning for molecular property prediction"],"prefix":"10.1038","volume":"17","author":[{"given":"Chao","family":"Cui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaorui","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0380-6558","authenticated-orcid":false,"given":"Zaixi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2303-6114","authenticated-orcid":false,"given":"Alejandro","family":"Velez-Arce","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8910-0929","authenticated-orcid":false,"given":"Jianmin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangcheng","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4087-420X","authenticated-orcid":false,"given":"Yanbin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9865-180X","authenticated-orcid":false,"given":"Jie","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5473-8022","authenticated-orcid":false,"given":"Yu Zong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8530-7228","authenticated-orcid":false,"given":"Marinka","family":"Zitnik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7114-3664","authenticated-orcid":false,"given":"Wanxiang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"75713_CR1","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1038\/s41586-023-05905-z","volume":"616","author":"AV Sadybekov","year":"2023","unstructured":"Sadybekov, A. V. & Katritch, V. Computational approaches streamlining drug discovery. Nature 616, 673\u2013685 (2023).","journal-title":"Nature"},{"key":"75713_CR2","doi-asserted-by":"publisher","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","volume":"59","author":"K Yang","year":"2019","unstructured":"Yang, K. et al. Analyzing learned molecular representations for property prediction. J. Chem. Inf. Model. 59, 3370\u20133388 (2019).","journal-title":"J. Chem. Inf. Model."},{"key":"75713_CR3","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","volume":"4","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Wang, J., Cao, Z. & Barati Farimani, A. Molecular contrastive learning of representations via graph neural networks. Nat. Mach. Intell. 4, 279\u2013287 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"75713_CR4","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-23720-w","volume":"12","author":"D Chen","year":"2021","unstructured":"Chen, D. et al. Algebraic graph-assisted bidirectional transformers for molecular property prediction. Nat. Commun. 12, 3521 (2021).","journal-title":"Nat. Commun."},{"key":"75713_CR5","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1038\/s42256-022-00501-8","volume":"4","author":"Y Li","year":"2022","unstructured":"Li, Y. et al. An adaptive graph learning method for automated molecular interactions and properties predictions. Nat. Mach. Intell. 4, 645\u2013651 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"75713_CR6","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1039\/D2DD00077F","volume":"1","author":"H Chen","year":"2022","unstructured":"Chen, H., Vogt, M. & Bajorath, J. Deepac\u2013conditional transformer-based chemical language model for the prediction of activity cliffs formed by bioactive compounds. Digit. Discov. 1, 898\u2013909 (2022).","journal-title":"Digit. Discov."},{"key":"75713_CR7","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-35692-6","volume":"14","author":"M Moret","year":"2023","unstructured":"Moret, M. et al. Leveraging molecular structure and bioactivity with chemical language models for de novo drug design. Nat. Commun. 14, 114 (2023).","journal-title":"Nat. Commun."},{"key":"75713_CR8","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1186\/s13321-024-00848-7","volume":"16","author":"X Zheng","year":"2024","unstructured":"Zheng, X. & Tomiura, Y. A BERT-based pretraining model for extracting molecular structural information from a SMILES sequence. J. Cheminform. 16, 71 (2024).","journal-title":"J. Cheminform."},{"key":"75713_CR9","doi-asserted-by":"crossref","unstructured":"Pei, Q. et al. BioT5: enriching cross-modal integration in biology with chemical knowledge and natural language associations. In Proc. 2023 Conference on Empirical Methods in Natural Language Processing, (eds Bouamor, H., Pino, J. & Bali, K.) 1102\u20131123 (Association for Computational Linguistics, 2023).","DOI":"10.18653\/v1\/2023.emnlp-main.70"},{"key":"75713_CR10","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1038\/s42256-022-00557-6","volume":"4","author":"X Zeng","year":"2022","unstructured":"Zeng, X. et al. Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework. Nat. Mach. Intell. 4, 1004\u20131016 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"75713_CR11","doi-asserted-by":"publisher","first-page":"bbad404","DOI":"10.1093\/bib\/bbad404","volume":"24","author":"H Xiang","year":"2023","unstructured":"Xiang, H., Jin, S., Liu, X., Zeng, X. & Zeng, L. Chemical structure-aware molecular image representation learning. Brief. Bioinform. 24, bbad404 (2023).","journal-title":"Brief. Bioinform."},{"key":"75713_CR12","doi-asserted-by":"publisher","first-page":"4562","DOI":"10.1093\/bioinformatics\/btac545","volume":"38","author":"J Yi","year":"2022","unstructured":"Yi, J. et al. MICER: A pre-trained encoder\u2013decoder architecture for molecular image captioning. Bioinformatics 38, 4562\u20134572 (2022).","journal-title":"Bioinformatics"},{"key":"75713_CR13","doi-asserted-by":"crossref","unstructured":"Iqbal, J., Vogt, M. & Bajorath, J. Prediction of activity cliffs on the basis of images using convolutional neural networks. J. Comput. Aided Mol. Des. 35, 1\u20138 (2021).","DOI":"10.1007\/s10822-021-00380-y"},{"key":"75713_CR14","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1038\/s42256-021-00301-6","volume":"3","author":"WX Shen","year":"2021","unstructured":"Shen, W. X. et al. Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations. Nat. Mach. Intell. 3, 334\u2013343 (2021).","journal-title":"Nat. Mach. Intell."},{"key":"75713_CR15","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1186\/s13321-022-00650-3","volume":"14","author":"N Wen","year":"2022","unstructured":"Wen, N. et al. A fingerprints based molecular property prediction method using the BERT model. J. Cheminform. 14, 71 (2022).","journal-title":"J. Cheminform."},{"key":"75713_CR16","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-43214-1","volume":"14","author":"H Li","year":"2023","unstructured":"Li, H. et al. A knowledge-guided pre-training framework for improving molecular representation learning. Nat. Commun. 14, 7568 (2023).","journal-title":"Nat. Commun."},{"key":"75713_CR17","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","volume":"180","author":"JM Stokes","year":"2020","unstructured":"Stokes, J. M. et al. A deep learning approach to antibiotic discovery. Cell 180, 688\u2013702 (2020).","journal-title":"Cell"},{"key":"75713_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-020-00479-8","volume":"13","author":"D Jiang","year":"2021","unstructured":"Jiang, D. et al. Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models. J. Cheminform. 13, 1\u201323 (2021).","journal-title":"J. Cheminform."},{"key":"75713_CR19","doi-asserted-by":"publisher","first-page":"5938","DOI":"10.1021\/acs.jcim.2c01073","volume":"62","author":"D van Tilborg","year":"2022","unstructured":"van Tilborg, D., Alenicheva, A. & Grisoni, F. Exposing the limitations of molecular machine learning with activity cliffs. J. Chem. Inf. Model. 62, 5938\u20135951 (2022).","journal-title":"J. Chem. Inf. Model."},{"key":"75713_CR20","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1021\/acs.jcim.1c01163","volume":"62","author":"J Jime\u00b4nez-Luna","year":"2022","unstructured":"Jime\u00b4nez-Luna, J., Skalic, M. & Weskamp, N. Benchmarking molecular feature attribution methods with activity cliffs. J. Chem. Inf. Model. 62, 274\u2013283 (2022).","journal-title":"J. Chem. Inf. Model."},{"key":"75713_CR21","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1186\/s13321-023-00708-w","volume":"15","author":"M Dablander","year":"2023","unstructured":"Dablander, M., Hanser, T., Lambiotte, R. & Morris, G. M. Exploring QSAR models for activity-cliff prediction. J. Cheminform. 15, 47 (2023).","journal-title":"J. Cheminform."},{"key":"75713_CR22","doi-asserted-by":"crossref","unstructured":"Xia, J. et al. Understanding the limitations of deep models for molecular property prediction: insights and solutions. Adv. Neural Inf. Process. Syst. 36, 2827 (2024).","DOI":"10.52202\/075280-2827"},{"key":"75713_CR23","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-41948-6","volume":"14","author":"J Deng","year":"2023","unstructured":"Deng, J. et al. A systematic study of key elements underlying molecular property prediction. Nat. Commun. 14, 6395 (2023).","journal-title":"Nat. Commun."},{"key":"75713_CR24","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-41967-3","volume":"14","author":"AL Dias","year":"2023","unstructured":"Dias, A. L., Bustillo, L. & Rodrigues, T. Limitations of representation learning in small molecule property prediction. Nat. Commun. 14, 6394 (2023).","journal-title":"Nat. Commun."},{"key":"75713_CR25","doi-asserted-by":"publisher","first-page":"3525","DOI":"10.1039\/D0CS00098A","volume":"49","author":"EN Muratov","year":"2020","unstructured":"Muratov, E. N. et al. QSAR without borders. Chem. Soc. Rev. 49, 3525\u20133564 (2020).","journal-title":"Chem. Soc. Rev."},{"key":"75713_CR26","doi-asserted-by":"publisher","first-page":"14360","DOI":"10.1021\/acsomega.9b02221","volume":"4","author":"D Stumpfe","year":"2019","unstructured":"Stumpfe, D., Hu, H. & Bajorath, J. Evolving concept of activity cliffs. ACS Omega 4, 14360\u201314368 (2019).","journal-title":"ACS Omega"},{"key":"75713_CR27","doi-asserted-by":"publisher","first-page":"2932","DOI":"10.1021\/jm201706b","volume":"55","author":"D Stumpfe","year":"2012","unstructured":"Stumpfe, D. & Bajorath, J. Exploring activity cliffs in medicinal chemistry: miniperspective. J. Med. Chem. 55, 2932\u20132942 (2012).","journal-title":"J. Med. Chem."},{"key":"75713_CR28","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-71696-2","volume":"10","author":"Y Asawa","year":"2020","unstructured":"Asawa, Y., Yoshimori, A., Bajorath, J. & Nakamura, H. Prediction of an mmp-1 inhibitor activity cliff using the SAR matrix approach and its experimental validation. Sci. Rep. 10, 14710 (2020).","journal-title":"Sci. Rep."},{"key":"75713_CR29","doi-asserted-by":"publisher","first-page":"3131","DOI":"10.1021\/ci400597d","volume":"53","author":"V Namasivayam","year":"2013","unstructured":"Namasivayam, V., Iyer, P. & Bajorath, J. Prediction of individual compounds forming activity cliffs using emerging chemical patterns. J. Chem. Inf. Model. 53, 3131\u20133139 (2013).","journal-title":"J. Chem. Inf. Model."},{"key":"75713_CR30","doi-asserted-by":"publisher","first-page":"4034","DOI":"10.1021\/acs.jcim.9b00631","volume":"59","author":"C Kramer","year":"2019","unstructured":"Kramer, C. Nonadditivity analysis. J. Chem. Inf. Model. 59, 4034\u20134042 (2019).","journal-title":"J. Chem. Inf. Model."},{"key":"75713_CR31","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1186\/s13321-021-00525-z","volume":"13","author":"D Gogishvili","year":"2021","unstructured":"Gogishvili, D., Nittinger, E., Margreitter, C. & Tyrchan, C. Nonadditivity in public and in-house data: Implications for drug design. J. Cheminform. 13, 47 (2021).","journal-title":"J. Cheminform."},{"key":"75713_CR32","doi-asserted-by":"publisher","first-page":"26573","DOI":"10.1021\/acsomega.2c02738","volume":"7","author":"K Kwapien","year":"2022","unstructured":"Kwapien, K. et al. Implications of additivity and nonadditivity for machine learning and deep learning models in drug design. ACS Omega 7, 26573\u201326581 (2022).","journal-title":"ACS Omega"},{"key":"75713_CR33","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s10822-024-00566-0","volume":"38","author":"L Guasch","year":"2024","unstructured":"Guasch, L., Maeder, N., Cumming, J. G. & Kramer, C. From mundane to surprising nonadditivity: Drivers and impact on ML models. J. Comput. Aided Mol. Des. 38, 26 (2024).","journal-title":"J. Comput. Aided Mol. Des."},{"key":"75713_CR34","doi-asserted-by":"publisher","first-page":"1616","DOI":"10.1021\/ja01062a035","volume":"86","author":"C Hansch","year":"1964","unstructured":"Hansch, C. & Fujita, T. p-\u03c3-\u03c0 analysis. a method for the correlation of biological activity and chemical structure. J. Am. Chem. Soc. 86, 1616\u20131626 (1964).","journal-title":"J. Am. Chem. Soc."},{"key":"75713_CR35","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1021\/jm00334a001","volume":"7","author":"SM Free","year":"1964","unstructured":"Free, S. M. & Wilson, J. W. A mathematical contribution to structure-activity studies. J. Med. Chem. 7, 395\u2013399 (1964).","journal-title":"J. Med. Chem."},{"key":"75713_CR36","doi-asserted-by":"publisher","first-page":"2354","DOI":"10.1021\/ci300306a","volume":"52","author":"K Heikamp","year":"2012","unstructured":"Heikamp, K., Hu, X., Yan, A. & Bajorath, J. Prediction of activity cliffs using support vector machines. J. Chem. Inf. Model. 52, 2354\u20132365 (2012).","journal-title":"J. Chem. Inf. Model."},{"key":"75713_CR37","doi-asserted-by":"crossref","unstructured":"Zha, K., Cao, P., Son, J., Yang, Y. & Katabi, D. Rank-n-contrast: learning continuous representations for regression. Adv. Neural Inf. Process. Syst. 36, 786 (2024).","DOI":"10.52202\/075280-0786"},{"key":"75713_CR38","unstructured":"Huang, J.-J., Liao, C.-B. & Chen, P.-N. Quinazoline compounds as kinase inhibitors (2014). US Patent 8,785,459."},{"key":"75713_CR39","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1038\/nrd1467","volume":"3","author":"DC Rees","year":"2004","unstructured":"Rees, D. C., Congreve, M., Murray, C. W. & Carr, R. Fragment-based lead discovery. Nat. Rev. Drug Discov. 3, 660\u2013672 (2004).","journal-title":"Nat. Rev. Drug Discov."},{"key":"75713_CR40","doi-asserted-by":"crossref","unstructured":"Jahnke, W. et al. Fragment-to-lead medicinal chemistry publications in 2019. J. Med. Chem. 63, 15494\u201315507 (2020).","DOI":"10.1021\/acs.jmedchem.0c01608"},{"key":"75713_CR41","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1038\/nrd1086","volume":"2","author":"KH Bleicher","year":"2003","unstructured":"Bleicher, K. H., B\u00f6 hm, H.-J., M\u00fcller, K. & Alanine, A. I. Hit and lead generation: beyond high-throughput screening. Nat. Rev. Drug Discov. 2, 369\u2013378 (2003).","journal-title":"Nat. Rev. Drug Discov."},{"key":"75713_CR42","doi-asserted-by":"publisher","first-page":"7032","DOI":"10.1021\/acs.jcim.3c01530","volume":"63","author":"T Janela","year":"2023","unstructured":"Janela, T. & Bajorath, J. Anatomy of potency predictions focusing on structural analogues with increasing potency differences including activity cliffs. J. Chem. Inf. Model. 63, 7032\u20137044 (2023).","journal-title":"J. Chem. Inf. Model."},{"key":"75713_CR43","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1021\/acs.jcim.2c00327","volume":"62","author":"J Park","year":"2022","unstructured":"Park, J., Sung, G., Lee, S., Kang, S. & Park, C. ACGCN: Graph convolutional networks for activity cliff prediction between matched molecular pairs. J. Chem. Inf. Model. 62, 2341\u20132351 (2022).","journal-title":"J. Chem. Inf. Model."},{"key":"75713_CR44","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s13321-022-00676-7","volume":"15","author":"S Tamura","year":"2023","unstructured":"Tamura, S., Miyao, T. & Bajorath, J. Large-scale prediction of activity cliffs using machine and deep learning methods of increasing complexity. J. Cheminform. 15, 4 (2023).","journal-title":"J. Cheminform."},{"key":"75713_CR45","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1186\/s13321-023-00769-x","volume":"15","author":"Z Fralish","year":"2023","unstructured":"Fralish, Z., Chen, A., Skaluba, P. & Reker, D. DeepDelta: predicting ADMET improvements of molecular derivatives with deep learning. J. Cheminform. 15, 101 (2023).","journal-title":"J. Cheminform."},{"key":"75713_CR46","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1002\/wics.51","volume":"2","author":"H Abdi","year":"2010","unstructured":"Abdi, H. Partial least squares regression and projection on latent structure regression (PLS regression). Wiley Interdiscip. Rev. Comput. Stat. 2, 97\u2013106 (2010).","journal-title":"Wiley Interdiscip. Rev. Comput. Stat."},{"key":"75713_CR47","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","volume":"64","author":"E Heid","year":"2023","unstructured":"Heid, E. et al. Chemprop: a machine learning package for chemical property prediction. J. Chem. Inf. Model. 64, 9\u201317 (2023).","journal-title":"J. Chem. Inf. Model."},{"key":"75713_CR48","doi-asserted-by":"crossref","unstructured":"Maggiora, G. M. On outliers and activity cliffs why QSAR often disappoints. J. Chem. Inf. Model. 46, 1535 (2006).","DOI":"10.1021\/ci060117s"},{"key":"75713_CR49","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","volume":"40","author":"A Gaulton","year":"2012","unstructured":"Gaulton, A. et al. ChEMBL: A large-scale bioactivity database for drug discovery. Nucleic Acids Res. 40, D1100\u2013D1107 (2012).","journal-title":"Nucleic Acids Res."},{"key":"75713_CR50","doi-asserted-by":"publisher","first-page":"D1083","DOI":"10.1093\/nar\/gkt1031","volume":"42","author":"AP Bento","year":"2014","unstructured":"Bento, A. P. et al. The ChEMBL bioactivity database: an update. Nucleic Acids Res. 42, D1083\u2013D1090 (2014).","journal-title":"Nucleic Acids Res."},{"key":"75713_CR51","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1080\/17460441.2019.1593371","volume":"14","author":"J Bajorath","year":"2019","unstructured":"Bajorath, J. Duality of activity cliffs in drug discovery. Expert Opin. Drug Discov. 14, 517\u2013520 (2019).","journal-title":"Expert Opin. Drug Discov."},{"key":"75713_CR52","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D. & Philbin, J. FaceNet: a unified embedding for face recognition and clustering. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 815\u2013823 (IEEE, 2015).","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"75713_CR53","unstructured":"Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks. In Proc. 5th International Conference on Learning Representations (ICLR, 2017)."},{"key":"75713_CR54","unstructured":"Xu, K., Hu, W., Leskovec, J. & Jegelka, S. How powerful are graph neural networks? In Proc. 7th International Conference on Learning Representations (ICLR, 2019)."},{"key":"75713_CR55","unstructured":"Veli\u010dkovi\u0107, P. et al. Graph attention networks. In Proc. 6th International Conference on Learning Representations (ICLR, 2018)."},{"key":"75713_CR56","unstructured":"Corso, G., Cavalleri, L., Beaini, D., Lio\u2018, P. & Veli\u010dkovi\u0107, P. Principal neighbourhood aggregation for graph nets. Adv. Neural Inf. Process. Syst. 33, 13260\u201313271 (2020)."},{"key":"75713_CR57","unstructured":"Fey, M. & Lenssen, J. E. Fast graph representation learning with PyTorch Geometric. In Proc. ICLR 2019 Workshop on Representation Learning on Graphs and Manifolds (ICLR, 2019)."},{"key":"75713_CR58","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13321-020-0416-x","volume":"12","author":"D Probst","year":"2020","unstructured":"Probst, D. & Reymond, J.-L. Visualization of very large high-dimensional data sets as mini-mum spanning trees. J. Cheminform. 12, 12 (2020).","journal-title":"J. Cheminform."},{"key":"75713_CR59","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1021\/ci900450m","volume":"50","author":"J Hussain","year":"2010","unstructured":"Hussain, J. & Rea, C. Computationally efficient algorithm to identify matched molecular pairs (MMPs) in large data sets. J. Chem. Inf. Model. 50, 339\u2013348 (2010).","journal-title":"J. Chem. Inf. Model."},{"key":"75713_CR60","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.20608055","author":"C Cui","year":"2026","unstructured":"Cui, C. et al. Benchmark datasets of molecular property cliff (MPC) in ACANet. Zenodo https:\/\/doi.org\/10.5281\/zenodo.20608055 (2026).","journal-title":"Zenodo"},{"key":"75713_CR61","doi-asserted-by":"crossref","unstructured":"Velez-Arce, A. et al. Signals in the cells: multimodal and contextualized machine learning foundations for therapeutics. In NeurIPS 2024 Workshop on AI for New Drug Modalities (2024).","DOI":"10.1101\/2024.06.12.598655"},{"key":"75713_CR62","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.20607015","author":"C Cui","year":"2026","unstructured":"Cui, C. et al. Source code for activity cliff-informed contrastive learning for molecular property prediction. Zenodo https:\/\/doi.org\/10.5281\/zenodo.20607015 (2026).","journal-title":"Zenodo"}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-75713-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-75713-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-75713-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T22:39:24Z","timestamp":1788302364000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-75713-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":62,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["75713"],"URL":"https:\/\/doi.org\/10.1038\/s41467-026-75713-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv-2023-5cz7s\/v4","asserted-by":"object"}]},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]},"assertion":[{"value":"9 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"9376"}}