{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T18:49:57Z","timestamp":1772218197295,"version":"3.50.1"},"reference-count":48,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T00:00:00Z","timestamp":1744243200000},"content-version":"vor","delay-in-days":40,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Invariant molecular representation models provide potential solutions to guarantee accurate prediction of molecular properties under distribution shifts out-of-distribution (OOD) by identifying and leveraging invariant substructures inherent to the molecules. However, due to the complex entanglement of molecular functional groups and the frequent display of activity cliffs by molecular properties, the separation of molecules becomes inaccurate and tricky. This results in inconsistent semantics among the invariant substructures identified by existing models, which means molecules sharing identical invariant structures may exhibit drastically different properties. Focusing on the aforementioned challenges, in the semantic space, this paper explores the potential correlation between the consistent semantic\u2013expressing the same information within different molecular representation forms\u2013and the molecular property prediction problem. To enhance the performance of OOD molecular property prediction, this paper proposes a consistent semantic representation learning (CSRL) framework without separating molecules, which comprises two modules: a semantic uni-code (SUC) module and a consistent semantic extractor (CSE). To address inconsistent mapping of semantic in different molecular representation forms, SUC adjusts incorrect embeddings into the correct embeddings of two molecular representation forms. Then, CSE leverages non-semantic information as training labels to guide the discriminator\u2019s learning, thereby suppressing the reliance of CSE on the non-semantic information in different molecular representation embeddings. Extensive experiments demonstrate that the consistent semantic can guarantee the performance of models. Overall, CSRL can improve the model\u2019s average Receiver Operating Characteristic - Area Under the Curve (ROC-AUC) by 6.43%, when comparing with 11 state-of-the-art models on 12 datasets.<\/jats:p>","DOI":"10.1093\/bib\/bbaf147","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T05:09:46Z","timestamp":1744261786000},"source":"Crossref","is-referenced-by-count":1,"title":["Consistent semantic representation learning for out-of-distribution molecular property prediction"],"prefix":"10.1093","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6740-5540","authenticated-orcid":false,"given":"Xinlong","family":"Wen","sequence":"first","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University , No.1 Shizishan Street, Hongshan District, Wuhan, 430070, Hubei ,","place":["People\u2019s Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University , No.1 Shizishan Street, Hongshan District, Wuhan, 430070, Hubei ,","place":["People\u2019s Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhan","family":"Long","sequence":"additional","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University , No.1 Shizishan Street, Hongshan District, Wuhan, 430070, Hubei ,","place":["People\u2019s Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuoying","family":"Wei","sequence":"additional","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University , No.1 Shizishan Street, Hongshan District, Wuhan, 430070, Hubei ,","place":["People\u2019s Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongbo","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University , No.1 Shizishan Street, Hongshan District, Wuhan, 430070, Hubei ,","place":["People\u2019s Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,4,10]]},"reference":[{"key":"2025041005093404600_ref1","first-page":"1452","article-title":"Uncovering neural scaling laws in molecular representation learning","volume-title":"Proceedings of the Neural Information Processing Systems (NIPS)","author":"Chen","year":"2024"},{"key":"2025041005093404600_ref2","doi-asserted-by":"publisher","first-page":"bbae298","DOI":"10.1093\/bib\/bbae298","article-title":"Mvmrl: a multi-view molecular representation learning method for molecular property prediction","volume":"25","author":"Zhang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025041005093404600_ref3","doi-asserted-by":"publisher","first-page":"bbae438","DOI":"10.1093\/bib\/bbae438","article-title":"Adapting differential molecular representation with hierarchical prompts for multi-label property prediction","volume":"25","author":"Kang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025041005093404600_ref4","first-page":"12964","article-title":"Learning substructure invariance for out-of-distribution molecular representations","volume-title":"Proceedings of the Neural Information Processing Systems (NIPS)","author":"Yang","year":"2022"},{"key":"2025041005093404600_ref5","first-page":"78435","article-title":"Learning invariant molecular representation in latent discrete space","volume-title":"Proceedings of the Neural Information Processing Systems (NIPS)","author":"Zhuang","year":"2023"},{"key":"2025041005093404600_ref6","first-page":"3945","article-title":"Joint learning of label and environment causal independence for graph out-of-distribution generalization","volume-title":"Proceedings of the Neural Information Processing Systems (NIPS)","author":"Gui","year":"2024"},{"key":"2025041005093404600_ref7","doi-asserted-by":"publisher","first-page":"8562","DOI":"10.1609\/aaai.v38i8.28700","article-title":"Graph invariant learning with subgraph co-mixup for out-of-distribution generalization","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","author":"Jia","year":"2024"},{"key":"2025041005093404600_ref8","first-page":"15524","article-title":"Interpretable and generalizable graph learning via stochastic attention mechanism","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Miao","year":"2022"},{"key":"2025041005093404600_ref9","doi-asserted-by":"crossref","first-page":"1696","DOI":"10.1145\/3534678.3539366","article-title":"Causal attention for interpretable and generalizable graph classification","volume-title":"Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","author":"Sui","year":"2022"},{"key":"2025041005093404600_ref10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3644392","article-title":"Enhancing out-of-distribution generalization on graphs via causal attention learning","volume":"18","author":"Sui","year":"2024","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"2025041005093404600_ref11","article-title":"Discovering invariant rationales for graph neural networks","author":"Wu","year":"2022"},{"key":"2025041005093404600_ref12","first-page":"71486","article-title":"Does invariant graph learning via environment augmentation learn invariance?","volume-title":"Proceedings of the Neural Information Processing Systems (NIPS)","author":"Chen","year":"2024"},{"key":"2025041005093404600_ref13","first-page":"22131","article-title":"Learning causally invariant representations for out-of-distribution generalization on graphs","volume-title":"Proceedings of the Neural Information Processing Systems (NIPS)","author":"Chen","year":"2022"},{"key":"2025041005093404600_ref14","doi-asserted-by":"publisher","first-page":"btae118","DOI":"10.1093\/bioinformatics\/btae118","article-title":"Molfescue: Enhancing molecular property prediction in data-limited and imbalanced contexts using few-shot and contrastive learning","volume":"40","author":"Zhang","year":"2024","journal-title":"Bioinformatics"},{"key":"2025041005093404600_ref15","doi-asserted-by":"publisher","first-page":"5938","DOI":"10.1021\/acs.jcim.2c01073","article-title":"Exposing the limitations of molecular machine learning with activity cliffs","volume":"62","author":"Van Tilborg","year":"2022","journal-title":"J Chem Inf Model"},{"key":"2025041005093404600_ref16","doi-asserted-by":"publisher","first-page":"2123","DOI":"10.1021\/j100659a011","article-title":"Calculation of the interaction energy of one molecule with its whole surrounding. i. Method and application to pure nonpolar compounds","volume":"76","author":"Huron","year":"1972","journal-title":"J Phys Chem"},{"key":"2025041005093404600_ref17","first-page":"24529","article-title":"Zin: When and how to learn invariance without environment partition?","volume-title":"Proceedings of the Neural Information Processing Systems (NIPS)","author":"Lin","year":"2022"},{"key":"2025041005093404600_ref18","doi-asserted-by":"publisher","first-page":"3125","DOI":"10.3390\/molecules26113125","article-title":"Graph neural networks with multiple feature extraction paths for chemical property estimation","volume":"26","author":"Ishida","year":"2021","journal-title":"Molecules"},{"key":"2025041005093404600_ref19","article-title":"From coarse to fine: enable comprehensive graph self-supervised learning with multi-granular semantic ensemble","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Wen","year":"2024"},{"key":"2025041005093404600_ref20","doi-asserted-by":"publisher","first-page":"109883","DOI":"10.1016\/j.isci.2024.109883","article-title":"Semantic similarity is not enough: a novel nlp-based semantic similarity measure in geospatial context","volume":"27","author":"Abbasi","year":"2024","journal-title":"IScience"},{"key":"2025041005093404600_ref21","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"2025041005093404600_ref22","doi-asserted-by":"publisher","first-page":"2570","DOI":"10.1609\/aaai.v38i3.28034","article-title":"Delving into multimodal prompting for fine-grained visual classification","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","author":"Jiang","year":"2024"},{"key":"2025041005093404600_ref23","doi-asserted-by":"publisher","first-page":"103373","DOI":"10.1016\/j.drudis.2022.103373","article-title":"Deep learning methods for molecular representation and property prediction","volume":"27","author":"Li","year":"2022","journal-title":"Drug Discov Today"},{"key":"2025041005093404600_ref24","doi-asserted-by":"publisher","first-page":"2663","DOI":"10.1109\/TSP.2021.3071210","article-title":"Deep learning enabled semantic communication systems","volume":"69","author":"Xie","year":"2021","journal-title":"IEEE Trans Signal Process"},{"key":"2025041005093404600_ref25","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1021\/ci010132r","article-title":"Reoptimization of mdl keys for use in drug discovery","volume":"42","author":"Durant","year":"2002","journal-title":"J Chem Inf Comput Sci"},{"key":"2025041005093404600_ref26","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1021\/c160017a018","article-title":"The generation of a unique machine description for chemical structures-a technique developed at chemical abstracts service","volume":"5","author":"Morgan","year":"1965","journal-title":"J Chem Doc"},{"key":"2025041005093404600_ref27","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J Chem Inf Model"},{"key":"2025041005093404600_ref28","article-title":"Deconfounding to explanation evaluation in graph neural networks","author":"Wu","year":"2022"},{"key":"2025041005093404600_ref29","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.1109\/LSP.2021.3092227","article-title":"A semantic encoding out-of-distribution classifier for generalized zero-shot learning","volume":"28","author":"Ding","year":"2021","journal-title":"IEEE Signal Process Lett"},{"key":"2025041005093404600_ref30","doi-asserted-by":"crossref","DOI":"10.36227\/techrxiv.170775117.72309088\/v1","article-title":"A mathematical theory of semantic communication","author":"Niu","year":"2024"},{"key":"2025041005093404600_ref31","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1109\/JSAIT.2023.3336538","article-title":"Causal semantic communication for digital twins: a generalizable imitation learning approach","volume":"4","author":"Thomas","year":"2023","journal-title":"IEEE J Select Areas Inform Theory"},{"key":"2025041005093404600_ref32","first-page":"63529","article-title":"Achieving cross modal generalization with multimodal unified representation","volume-title":"Proceedings of the Neural Information Processing Systems (NIPS)","author":"Xia","year":"2024"},{"key":"2025041005093404600_ref33","first-page":"9096","article-title":"Classification-oriented semantic wireless communications","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Kutay","year":"2024"},{"key":"2025041005093404600_ref34","first-page":"60661","article-title":"Transitivity recovering decompositions: Interpretable and robust fine-grained relationships","volume-title":"Proceedings of the Neural Information Processing Systems (NIPS)","author":"Chaudhuri","year":"2024"},{"key":"2025041005093404600_ref35","doi-asserted-by":"crossref","DOI":"10.1109\/TCOMM.2024.3400912","article-title":"Contrastive learning based semantic communications","volume":"72","author":"Tang","year":"2024","journal-title":"IEEE Trans Commun"},{"key":"2025041005093404600_ref36","article-title":"Towards out-of-distribution generalization: a survey","author":"Liu","year":"2021"},{"key":"2025041005093404600_ref37","doi-asserted-by":"crossref","DOI":"10.1145\/3626772.3657927","article-title":"Negative as positive: enhancing out-of-distribution generalization for graph contrastive learning","author":"Wang","year":"2024"},{"key":"2025041005093404600_ref38","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Ganin","year":"2015"},{"key":"2025041005093404600_ref39","first-page":"387","article-title":"Admeood: Out-of-distribution benchmark for drug property prediction","volume-title":"Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Wei","year":"2023"},{"key":"2025041005093404600_ref40","doi-asserted-by":"publisher","first-page":"8023","DOI":"10.1609\/aaai.v37i7.25970","article-title":"Drugood: Out-of-distribution dataset curator and benchmark for ai-aided drug discovery-a focus on affinity prediction problems with noise annotations","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","author":"Ji","year":"2023"},{"key":"2025041005093404600_ref41","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"Moleculenet: a benchmark for molecular machine learning","volume":"9","author":"Zhenqin","year":"2018","journal-title":"Chem Sci"},{"key":"2025041005093404600_ref42","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2025041005093404600_ref43","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1109\/TNN.1997.641482","article-title":"The nature of statistical learning theory","volume":"8","author":"Cherkassky","year":"1997","journal-title":"IEEE Trans Neural Netw"},{"key":"2025041005093404600_ref44","article-title":"Invariant risk minimization.","author":"Arjovsky","year":"2019"},{"key":"2025041005093404600_ref45","first-page":"5815","article-title":"Out-of-distribution generalization via risk extrapolation (rex)","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Krueger","year":"2021"},{"key":"2025041005093404600_ref46","doi-asserted-by":"publisher","first-page":"183904","DOI":"10.1007\/s11704-023-2640-9","article-title":"Protein acetylation sites with complex-valued polynomial model","volume":"18","author":"Bao","year":"2024","journal-title":"Front Comp Sci"},{"key":"2025041005093404600_ref47","doi-asserted-by":"publisher","first-page":"1277121","DOI":"10.3389\/fmicb.2023.1277121","article-title":"Oral_voting_transfer: classification of oral microorganisms\u2019 function proteins with voting transfer model","volume":"14","author":"Bao","year":"2024","journal-title":"Front Microbiol"},{"key":"2025041005093404600_ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71050-9","volume-title":"Optimal Transport: Old and New","author":"Villani","year":"2009"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf147\/62900871\/bbaf147.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf147\/62900871\/bbaf147.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T05:09:53Z","timestamp":1744261793000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf147\/8109670"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf147","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,3]]},"published":{"date-parts":[[2025,3]]},"article-number":"bbaf147"}}