{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T10:36:12Z","timestamp":1769423772608,"version":"3.49.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031653285","type":"print"},{"value":"9783031653292","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-65329-2_26","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T18:02:28Z","timestamp":1722535348000},"page":"387-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing Low-Cost Molecular Property Prediction with\u00a0Contrastive Learning on\u00a0SMILES Representations"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8147-554X","authenticated-orcid":false,"given":"Marcos G.","family":"Quiles","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5386-8751","authenticated-orcid":false,"given":"Piero A. L.","family":"Ribeiro","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8657-247X","authenticated-orcid":false,"given":"Gabriel A.","family":"Pinheiro","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8597-4987","authenticated-orcid":false,"given":"Ronaldo C.","family":"Prati","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0645-8760","authenticated-orcid":false,"given":"Juarez L. F. da","family":"Silva","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"key":"26_CR1","doi-asserted-by":"publisher","unstructured":"Shen, J., Nicolaou, C.A.: Molecular property prediction: recent trends in the era of artificial intelligence. Drug Discov. Today Technol. 32\u201333, 29\u201336 (2019). https:\/\/doi.org\/10.1016\/j.ddtec.2020.05.001, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1740674920300032","DOI":"10.1016\/j.ddtec.2020.05.001"},{"key":"26_CR2","doi-asserted-by":"publisher","unstructured":"G\u00f3mez-Bombarelli, R., et al.: Automatic chemical design using a data-driven continuous representation of molecules. ACS Central Sci. 4(2), 268\u2013276 (2018). https:\/\/doi.org\/10.1021\/acscentsci.7b00572, pMID: 29532027","DOI":"10.1021\/acscentsci.7b00572"},{"key":"26_CR3","doi-asserted-by":"publisher","unstructured":"Shen, C., Krenn, M., Eppel, S., Aspuru-Guzik, A.: Deep molecular dreaming: inverse machine learning for de-novo molecular design and interpretability with surjective representations. Mach. Learn. Sci. Technol. 2(3), 03LT02 (2021). https:\/\/doi.org\/10.1088\/2632-2153\/ac09d6","DOI":"10.1088\/2632-2153\/ac09d6"},{"key":"26_CR4","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1039\/D3DD00213F","volume":"3","author":"S Back","year":"2024","unstructured":"Back, S., et al.: Accelerated chemical science with AI. Digit. Disc. 3, 23\u201333 (2024). https:\/\/doi.org\/10.1039\/D3DD00213F","journal-title":"Digit. Disc."},{"issue":"7715","key":"26_CR5","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","volume":"559","author":"KT Butler","year":"2018","unstructured":"Butler, K.T., Davies, D.W., Cartwright, H., Isayev, O., Walsh, A.: Machine learning for molecular and materials science. Nature 559(7715), 547\u2013555 (2018). https:\/\/doi.org\/10.1038\/s41586-018-0337-2","journal-title":"Nature"},{"key":"26_CR6","doi-asserted-by":"publisher","unstructured":"Wei, J., et al.: Machine learning in materials science. InfoMat 1(3), 338\u2013358 (2019). https:\/\/doi.org\/10.1002\/inf2.12028, https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1002\/inf2.12028","DOI":"10.1002\/inf2.12028"},{"issue":"7019","key":"26_CR7","doi-asserted-by":"publisher","first-page":"823","DOI":"10.1038\/432823a","volume":"432","author":"P Kirkpatrick","year":"2004","unstructured":"Kirkpatrick, P., Ellis, C.: Chemical space. Nature 432(7019), 823\u2013823 (2004). https:\/\/doi.org\/10.1038\/432823a","journal-title":"Nature"},{"issue":"2","key":"26_CR8","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/j.trechm.2020.11.004","volume":"3","author":"CW Coley","year":"2021","unstructured":"Coley, C.W.: Defining and exploring chemical spaces. Trends Chem. 3(2), 133\u2013145 (2021). https:\/\/doi.org\/10.1016\/j.trechm.2020.11.004","journal-title":"Trends Chem."},{"key":"26_CR9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.108.058301","volume":"108","author":"M Rupp","year":"2012","unstructured":"Rupp, M., Tkatchenko, A., M\u00fcller, K.R., von Lilienfeld, O.A.: Fast and accurate modeling of molecular atomization energies with machine learning. Phys. Rev. Lett. 108, 058301 (2012). https:\/\/doi.org\/10.1103\/PhysRevLett.108.058301","journal-title":"Phys. Rev. Lett."},{"issue":"1","key":"26_CR10","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1038\/s41524-019-0189-9","volume":"5","author":"C Nyshadham","year":"2019","unstructured":"Nyshadham, C., et al.: Machine-learned multi-system surrogate models for materials prediction. NPJ Comput. Materials 5(1), 51 (2019). https:\/\/doi.org\/10.1038\/s41524-019-0189-9","journal-title":"NPJ Comput. Materials"},{"issue":"7","key":"26_CR11","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1038\/s41570-020-0189-9","volume":"4","author":"OA von Lilienfeld","year":"2020","unstructured":"von Lilienfeld, O.A., M\u00fcller, K.R., Tkatchenko, A.: Exploring chemical compound space with quantum-based machine learning. Nat. Rev. Chem. 4(7), 347\u2013358 (2020). https:\/\/doi.org\/10.1038\/s41570-020-0189-9","journal-title":"Nat. Rev. Chem."},{"key":"26_CR12","doi-asserted-by":"publisher","unstructured":"Pinheiro, G.A., Mucelini, J., Soares, M.D., Prati, R.C., Da\u00a0Silva, J.L.F., Quiles, M.G.: Machine learning prediction of nine molecular properties based on the SMILES representation of the QM9 quantum-chemistry dataset. J. Phys. Chem. A 124(47), 9854\u20139866 (2020). https:\/\/doi.org\/10.1021\/acs.jpca.0c05969, pMID: 33174750","DOI":"10.1021\/acs.jpca.0c05969"},{"key":"26_CR13","doi-asserted-by":"publisher","unstructured":"Cesar\u00a0de Azevedo, L., Pinheiro, G.A., Quiles, M.G., Da\u00a0Silva, J.L.F., Prati, R.C.: Systematic investigation of error distribution in machine learning algorithms applied to the quantum-chemistry qm9 data set using the bias and variance decomposition. J. Chem. Inf. Model. 61(9), 4210\u20134223 (2021). https:\/\/doi.org\/10.1021\/acs.jcim.1c00503","DOI":"10.1021\/acs.jcim.1c00503"},{"key":"26_CR14","doi-asserted-by":"publisher","unstructured":"Oliveira, A.F., Da\u00a0Silva, J.L.F., Quiles, M.G.: Molecular property prediction and molecular design using a supervised grammar variational autoencoder. J. Chem. Inform. Model. 62(4), 817\u2013828 (2022). https:\/\/doi.org\/10.1021\/acs.jcim.1c01573, pMID: 35174705","DOI":"10.1021\/acs.jcim.1c01573"},{"key":"26_CR15","doi-asserted-by":"publisher","unstructured":"Weininger, D.: Smiles, a chemical language and information system. 1. introduction to methodology and encoding rules. J. Chem. Inform. Comput. Sci. 28(1), 31\u201336 (1988). https:\/\/doi.org\/10.1021\/ci00057a005","DOI":"10.1021\/ci00057a005"},{"issue":"1","key":"26_CR16","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41524-022-00721-x","volume":"8","author":"MF Langer","year":"2022","unstructured":"Langer, M.F., Goe\u00dfmann, A., Rupp, M.: Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning. NPJ Comput. Mater. 8(1), 41 (2022). https:\/\/doi.org\/10.1038\/s41524-022-00721-x","journal-title":"NPJ Comput. Mater."},{"issue":"1","key":"26_CR17","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s13321-018-0258-y","volume":"10","author":"H Moriwaki","year":"2018","unstructured":"Moriwaki, H., Tian, Y.S., Kawashita, N., Takagi, T.: Mordred: a molecular descriptor calculator. J. Cheminformatics 10(1), 4 (2018). https:\/\/doi.org\/10.1186\/s13321-018-0258-y","journal-title":"J. Cheminformatics"},{"issue":"1","key":"26_CR18","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1109\/TKDE.2021.3090866","volume":"35","author":"X Liu","year":"2021","unstructured":"Liu, X., et al.: Self-supervised learning: generative or contrastive. IEEE Trans. Knowl. Data Eng. 35(1), 857\u2013876 (2021). https:\/\/doi.org\/10.1109\/TKDE.2021.3090866","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Pinheiro, G.A., Da\u00a0Silva, J.L.F., Quiles, M.G.: SMICLR: contrastive learning on multiple molecular representations for semi-supervised and unsupervised representation learning. J. Chem. Inform. Model. 62, 3948\u20133960 (2022). Under Review","DOI":"10.1021\/acs.jcim.2c00521"},{"key":"26_CR20","doi-asserted-by":"publisher","unstructured":"Xie, J., Wang, Y., Rao, J., Zheng, S., Yang, Y.: Self-supervised contrastive molecular representation learning with a chemical synthesis knowledge graph. J. Chem. Inf. Model. (2024). https:\/\/doi.org\/10.1021\/acs.jcim.4c00157","DOI":"10.1021\/acs.jcim.4c00157"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, R., Shen, C., Kong, T., Li, L.: Dense contrastive learning for self-supervised visual pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3024\u20133033 (2021)","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Vision-language pre-training with triple contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15671\u201315680 (June 2022)","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"26_CR23","doi-asserted-by":"publisher","first-page":"193907","DOI":"10.1109\/ACCESS.2020.3031549","volume":"8","author":"PH Le-Khac","year":"2020","unstructured":"Le-Khac, P.H., Healy, G., Smeaton, A.F.: Contrastive representation learning: a framework and review. IEEE Access 8, 193907\u2013193934 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3031549","journal-title":"IEEE Access"},{"key":"26_CR24","doi-asserted-by":"publisher","unstructured":"Rethmeier, N., Augenstein, I.: A primer on contrastive pretraining in language processing: methods, lessons learned, and perspectives. ACM Comput. Surv. 55(10) (2023). https:\/\/doi.org\/10.1145\/3561970","DOI":"10.1145\/3561970"},{"issue":"3","key":"26_CR25","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. Nature Mach. Intell. 4(3), 279\u2013287 (2022). https:\/\/doi.org\/10.1038\/s42256-022-00447-x","journal-title":"Nature Mach. Intell."},{"key":"26_CR26","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1039\/C9ME00039A","volume":"4","author":"DC Elton","year":"2019","unstructured":"Elton, D.C., Boukouvalas, Z., Fuge, M.D., Chung, P.W.: Deep learning for molecular design-a review of the state of the art. Mol. Syst. Des. Eng. 4, 828\u2013849 (2019). https:\/\/doi.org\/10.1039\/C9ME00039A","journal-title":"Mol. Syst. Des. Eng."},{"key":"26_CR27","unstructured":"Bjerrum, E.J.: Smiles enumeration as data augmentation for neural network modeling of molecules (2017)"},{"issue":"9","key":"26_CR28","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1038\/s42256-021-00368-1","volume":"3","author":"MA Skinnider","year":"2021","unstructured":"Skinnider, M.A., Stacey, R.G., Wishart, D.S., Foster, L.J.: Chemical language models enable navigation in sparsely populated chemical space. Nature Mach. Intell. 3(9), 759\u2013770 (2021). https:\/\/doi.org\/10.1038\/s42256-021-00368-1","journal-title":"Nature Mach. Intell."},{"issue":"1","key":"26_CR29","doi-asserted-by":"publisher","first-page":"3293","DOI":"10.1038\/s41467-022-30839-x","volume":"13","author":"D Flam-Shepherd","year":"2022","unstructured":"Flam-Shepherd, D., Zhu, K., Aspuru-Guzik, A.: Language models can learn complex molecular distributions. Nature Commun. 13(1), 3293 (2022). https:\/\/doi.org\/10.1038\/s41467-022-30839-x","journal-title":"Nature Commun."},{"issue":"8","key":"26_CR30","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"issue":"10","key":"26_CR31","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1162\/089976600300015015","volume":"12","author":"FA Gers","year":"2000","unstructured":"Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM. Neural Comput. 12(10), 2451\u20132471 (2000). https:\/\/doi.org\/10.1162\/089976600300015015","journal-title":"Neural Comput."},{"key":"26_CR32","doi-asserted-by":"publisher","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020). https:\/\/doi.org\/10.48550\/ARXIV.2002.05709","DOI":"10.48550\/ARXIV.2002.05709"},{"issue":"1","key":"26_CR33","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3390\/technologies9010002","volume":"9","author":"A Jaiswal","year":"2021","unstructured":"Jaiswal, A., Babu, A.R., Zadeh, M.Z., Banerjee, D., Makedon, F.: A survey on contrastive self-supervised learning. Technologies 9(1), 2 (2021)","journal-title":"Technologies"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: A unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"26_CR35","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"26_CR36","doi-asserted-by":"publisher","unstructured":"Irwin, J.J., Shoichet, B.K.: Zinc - a free database of commercially available compounds for virtual screening. J. Chem. Inf. Model. 45(1), 177\u2013182 (2005). https:\/\/doi.org\/10.1021\/ci049714","DOI":"10.1021\/ci049714"},{"key":"26_CR37","doi-asserted-by":"publisher","unstructured":"Ruddigkeit, L., van Deursen, R., Blum, L.C., Reymond, J.L.: Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17. J. Chem. Inform. Model. 52(11), 2864\u20132875 (2012). https:\/\/doi.org\/10.1021\/ci300415d, pMID: 23088335","DOI":"10.1021\/ci300415d"},{"issue":"1","key":"26_CR38","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2014.22","volume":"1","author":"R Ramakrishnan","year":"2014","unstructured":"Ramakrishnan, R., Dral, P.O., Rupp, M., von Lilienfeld, O.A.: Quantum chemistry structures and properties of 134 kilo molecules. Sci. Data 1(1), 140022 (2014). https:\/\/doi.org\/10.1038\/sdata.2014.22","journal-title":"Sci. Data"},{"issue":"19","key":"26_CR39","doi-asserted-by":"publisher","first-page":"4702","DOI":"10.1021\/acs.jcim.2c00748","volume":"62","author":"AS Moraes","year":"2022","unstructured":"Moraes, A.S., et al.: Screening of the role of the chemical structure in the electrochemical stability window of ionic liquids: DFT calculations combined with data mining. J. Chem. Inf. Model. 62(19), 4702\u20134712 (2022). https:\/\/doi.org\/10.1021\/acs.jcim.2c00748","journal-title":"J. Chem. Inf. Model."},{"key":"26_CR40","unstructured":"Landrum, G.: RDKit: open-source cheminformatics software (2016). https:\/\/github.com\/rdkit\/rdkit\/"},{"key":"26_CR41","unstructured":"Ramsundar, B., Eastman, P., Walters, P., Pande, V., Leswing, K., Wu, Z.: Deep Learning for the Life Sciences. O\u2019Reilly Media (2019). https:\/\/www.amazon.com\/Deep-Learning-Life-Sciences-Microscopy\/dp\/1492039837"}],"container-title":["Lecture Notes in Computer Science","Computational Science and Its Applications \u2013 ICCSA 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-65329-2_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T18:14:31Z","timestamp":1722536071000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-65329-2_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031653285","9783031653292"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-65329-2_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCSA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science and Its Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccsa2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}