{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T11:06:40Z","timestamp":1780916800171,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":48,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819214648","type":"print"},{"value":"9789819214655","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-92-1465-5_28","type":"book-chapter","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T10:18:14Z","timestamp":1780913894000},"page":"355-368","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GlassMol: Interpretable Molecular Property Prediction with\u00a0Concept Bottleneck Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5742-1740","authenticated-orcid":false,"given":"Oscar","family":"Rivera","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8940-0461","authenticated-orcid":false,"given":"Ziqing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3260-6455","authenticated-orcid":false,"given":"Matthieu","family":"Dagommer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7905-5712","authenticated-orcid":false,"given":"Abhishek","family":"Pandey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6684-6752","authenticated-orcid":false,"given":"Kaize","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Belinkov, Y., Glass, J.: Analysis methods in neural language processing: a survey. In: TACL (2019)","DOI":"10.1162\/tacl_a_00254"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Blaschke, T., Ar\u00fas-Pous, J., Chen, H.: Reinvent 2.0: an ai tool for de novo drug design. In: JCIM (2020)","DOI":"10.26434\/chemrxiv.12058026.v3"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Cao, P.Y., He, Y., Cui, M.Y.: Group graph: a molecular graph representation with enhanced performance, efficiency and interpretability. J. Cheminform. (2024)","DOI":"10.1186\/s13321-024-00933-x"},{"key":"28_CR4","unstructured":"Chen, X., Liu, Y., Ma, X.: Self-explainable molecular property prediction via multi-view hypergraph learning. In: CIKM (2021)"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Dai, E., Wang, S.: Towards self-explainable graph neural network. In: CIKM (2021)","DOI":"10.1145\/3459637.3482306"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Yang, Z., Wang, H.: A systematic study of key elements underlying molecular property prediction. Nat. Commun. (2023)","DOI":"10.1038\/s41467-023-41948-6"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Ding, K., Xu, Z., Tong, H.: Data augmentation for deep graph learning: a survey. In: ACM SIGKDD Explorations Newsletter (2022)","DOI":"10.1145\/3575637.3575646"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Fan, Y., Wu, Y., French, R.H.: Hierarchical attention graph learning with LLM enhancement for molecular solubility prediction. Digital Discovery (2026)","DOI":"10.1039\/D5DD00407A"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Fung, V., Zhang, J., Juarez, E.: Benchmarking graph neural networks for materials chemistry. NPJ Comput. Materials (2021)","DOI":"10.26434\/chemrxiv.13615421.v2"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"G\u00f3mez-Bombarelli, R., Aguilera-Iparraguirre, J., Hirzel, T.D.: Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach. Nat. Mater. (2016)","DOI":"10.1038\/nmat4717"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Havasi, M., Parbhoo, S., Doshi-Velez, F.: Addressing leakage in concept bottleneck models. In: NeurIPS (2022)","DOI":"10.52202\/068431-1699"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Hu, F., Chen, D., Liu, Q.: Improving multi-task GNNs for molecular property prediction via missing label imputation. Mach. Intell. Res. (2025)","DOI":"10.1007\/s11633-023-1443-7"},{"key":"28_CR13","unstructured":"Hu, W., Liu, B., Gomes, J.: Strategies for pre-training graph neural networks, arXiv preprint (2019)"},{"key":"28_CR14","unstructured":"Huang, K., Fu, T., Gao, W.: Therapeutics data commons: Machine learning datasets and tasks for drug discovery and development (2021). arXiv preprint"},{"key":"28_CR15","unstructured":"Hurst, A., Lerer, A., Goucher, A.P.: GPT-4o system card. arXiv preprint (2024)"},{"key":"28_CR16","unstructured":"Ismail, A.A., Oikarinen, T., Wang, A.: Concept bottleneck language models for protein design (2024). arXiv preprint"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, T., Yao, Q., Wang, Z.: Expert-guided substructure information bottleneck for molecular property prediction. JCIM (2025)","DOI":"10.1021\/acs.jcim.5c00456"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Jim\u00e9nez-Luna, J., Grisoni, F., Schneider, G.: Drug discovery with explainable artificial intelligence. Nature Mach. Intell. (2020)","DOI":"10.1038\/s42256-020-00236-4"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Ju, J., Zheng, Y., Koh, H.Y., et\u00a0al.: M2LLM: Multi-view molecular representation learning with large language models. In: IJCAI (2025)","DOI":"10.24963\/ijcai.2025\/827"},{"key":"28_CR20","unstructured":"Kim, B., Wattenberg, M., Gilmer, J.: Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav). ICML (2018)"},{"key":"28_CR21","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks (2017). arXiv preprint"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Klucznik, T., Mikulak-Klucznik, B., McCormack, M.P., et\u00a0al.: Efficient syntheses of diverse, medicinally relevant targets planned by computer and executed in the laboratory. Chem (2018)","DOI":"10.1016\/j.chempr.2018.02.002"},{"key":"28_CR23","unstructured":"Koh, P.W., Nguyen, T., Tang, Y.S.: Concept bottleneck models. In: ICML (2020)"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Kumar, N., Berg, A.C., Belhumeur, P.N., et\u00a0al.: Attribute and simile classifiers for face verification. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459250"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Labadie-Tamayo, R., Slijep\u010devi\u0107, D., Chen, X., et\u00a0al.: Distilling knowledge from large language models: a concept bottleneck model for hate and counter speech recognition. IP&M (2026)","DOI":"10.1016\/j.ipm.2025.104309"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"28_CR27","unstructured":"Landrum, G.: others: Rdkit: Open-source cheminformatics software (2016)"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Leon, M., Perezhohin, Y., Peres, F.: Comparing smiles and selfies tokenization for enhanced chemical language modeling. Sci. Reports (2024)","DOI":"10.1038\/s41598-024-76440-8"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Li, H., Li, D., Zhang, J., et\u00a0al.: 3D-molgl: A multimodal framework for integrating 3D molecular graphs into language models. In: ESWA (2026)","DOI":"10.1016\/j.eswa.2026.131437"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Li, L., Zhang, Y., Wang, G.: Kolmogorov-arnold graph neural networks for molecular property prediction. Nature Mach. Intell. (2025)","DOI":"10.1038\/s42256-025-01087-7"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Y., Ding, K., Lu, Q.: Towards self-interpretable graph-level anomaly detection. In: NeurIPS (2023)","DOI":"10.52202\/075280-0394"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Madsen, A., Reddy, S., Chandar, S.: Post-hoc interpretability for neural NLP: a survey. ACM Comput. Surv. (2022)","DOI":"10.1145\/3546577"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Niyongabo Rubungo, A., Arnold, C., Rand, B.P.: LLM-prop: predicting the properties of crystalline materials using large language models. NPJ Comput. Materials (2025)","DOI":"10.1038\/s41524-025-01536-2"},{"key":"28_CR34","unstructured":"Oikarinen, T., Das, S., Nguyen, L.M.: Label-free concept bottleneck models (2023). arXiv preprint"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Qadri, Y.A., Shaikh, S., Ahmad, K.: Explainable artificial intelligence: a perspective on drug discovery. Pharmaceutics (2025)","DOI":"10.3390\/pharmaceutics17091119"},{"key":"28_CR36","unstructured":"Radhakrishnan, A., Nguyen, K., Chen, A.: Question decomposition improves the faithfulness of model-generated reasoning (2023). arXiv preprint"},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Ross, J., Belgodere, B., Chenthamarakshan, V.: Large-scale chemical language representations capture molecular structure and properties. Nature Mach. Intell. (2022)","DOI":"10.21203\/rs.3.rs-1570270\/v1"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Schneider, G., Fechner, U.: Computer-based de novo design of drug-like molecules. Nature Rev. Drug Discov. (2005)","DOI":"10.1038\/nrd1799"},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Tan, Z., Cheng, L., Wang, S.: Interpreting pretrained language models via concept bottlenecks. In: PAKDD (2024)","DOI":"10.24963\/ijcai.2024\/1221"},{"key":"28_CR40","unstructured":"Thieme, M., Hassan, M., Rupakheti, C.: Topopool: an adaptive graph pooling layer for extracting molecular and protein substructures. In: NeurIPS (2024)"},{"key":"28_CR41","unstructured":"Wang, Z., Wen, Y., Pattie, W.: Polo: Preference-guided multi-turn reinforcement learning for lead optimization (2025). arXiv preprint"},{"key":"28_CR42","unstructured":"Wang, Z., Zhang, K., Zhao, Z.: A survey of large language models for text-guided molecular discovery: from molecule generation to optimization (2025). arXiv preprint"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Wen, Y., Xu, C., Hu, J.Y.C.: Alignab: pareto-optimal energy alignment for designing nature-like antibodies (2024)","DOI":"10.32388\/OVBKGZ"},{"key":"28_CR44","doi-asserted-by":"crossref","unstructured":"Ye, X., Durrett, G.: The unreliability of explanations in few-shot prompting for textual reasoning (2022). arXiv preprint","DOI":"10.52202\/068431-2202"},{"key":"28_CR45","doi-asserted-by":"crossref","unstructured":"Yuan, H., Yu, H., Gui, S.: Explainability in graph neural networks: a taxonomic survey. In: TPAMI (2022)","DOI":"10.1109\/TPAMI.2022.3204236"},{"key":"28_CR46","unstructured":"Yuan, H., Yu, H., Wang, J., et\u00a0al.: On explainability of graph neural networks via subgraph explorations. In : ICML (2021)"},{"key":"28_CR47","doi-asserted-by":"crossref","unstructured":"Zhao, H., Chen, H., Yang, F.: Explainability for large language models: a survey. In: TIST (2024)","DOI":"10.1145\/3639372"},{"key":"28_CR48","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Koh, H.Y., Ju, J.: Large language models for scientific discovery in molecular property prediction. Nature Mach. Intell. (2025)","DOI":"10.1038\/s42256-025-00994-z"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-1465-5_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T10:18:49Z","timestamp":1780913929000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-1465-5_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819214648","9789819214655"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-1465-5_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pakdd2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}