{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:49:23Z","timestamp":1782312563886,"version":"3.54.5"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032061058","type":"print"},{"value":"9783032061065","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"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\/978-3-032-06106-5_6","type":"book-chapter","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T10:08:16Z","timestamp":1759399696000},"page":"95-111","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["De Novo Molecular Design Enabled by\u00a0Direct Preference Optimization and\u00a0Curriculum Learning"],"prefix":"10.1007","author":[{"given":"Junyu","family":"Hou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"key":"6_CR1","first-page":"12008","volume":"33","author":"S Ahn","year":"2020","unstructured":"Ahn, S., Kim, J., Lee, H., Shin, J.: Guiding deep molecular optimization with genetic exploration. Adv. Neural. Inf. Process. Syst. 33, 12008\u201312021 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the 26th Annual International Conference On Machine Learning, pp. 41\u201348 (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Blaschke, T., et al.: Reinvent 2.0: an AI tool for de novo drug design. J. Chemical Inf. Modeling 60(12), 5918\u20135922 (2020)","DOI":"10.1021\/acs.jcim.0c00915"},{"issue":"1","key":"6_CR4","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1002\/(SICI)1098-1128(199601)16:1<3::AID-MED1>3.0.CO;2-6","volume":"16","author":"RS Bohacek","year":"1996","unstructured":"Bohacek, R.S., McMartin, C., Guida, W.C.: The art and practice of structure-based drug design: a molecular modeling perspective. Med. Res. Rev. 16(1), 3\u201350 (1996)","journal-title":"Med. Res. Rev."},{"issue":"3","key":"6_CR5","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1021\/acs.jcim.8b00839","volume":"59","author":"N Brown","year":"2019","unstructured":"Brown, N., Fiscato, M., Segler, M.H., Vaucher, A.C.: Guacamol: benchmarking models for de novo molecular design. J. Chemical Inf. Modeling 59(3), 1096\u20131108 (2019)","journal-title":"J. Chemical Inf. Modeling"},{"key":"6_CR6","unstructured":"Cheng, X., Zhou, X., Yang, Y., Bao, Y., Gu, Q.: Decomposed direct preference optimization for structure-based drug design. arXiv preprint arXiv:2407.13981 (2024)"},{"key":"6_CR7","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.jhealeco.2016.01.012","volume":"47","author":"JA DiMasi","year":"2016","unstructured":"DiMasi, J.A., Grabowski, H.G., Hansen, R.W.: Innovation in the pharmaceutical industry: new estimates of r &d costs. J. Health Econ. 47, 20\u201333 (2016)","journal-title":"J. Health Econ."},{"issue":"2","key":"6_CR8","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","volume":"4","author":"R G\u00f3mez-Bombarelli","year":"2018","unstructured":"G\u00f3mez-Bombarelli, R., et al.: Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent. Sci. 4(2), 268\u2013276 (2018)","journal-title":"ACS Cent. Sci."},{"key":"6_CR9","first-page":"44040","volume":"37","author":"S Gu","year":"2025","unstructured":"Gu, S., et al.: Aligning target-aware molecule diffusion models with exact energy optimization. Adv. Neural. Inf. Process. Syst. 37, 44040\u201344063 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"6","key":"6_CR10","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s42256-022-00494-4","volume":"4","author":"J Guo","year":"2022","unstructured":"Guo, J., et al.: Improving de novo molecular design with curriculum learning. Nat. Mach. Intell. 4(6), 555\u2013563 (2022)","journal-title":"Nat. Mach. Intell."},{"key":"6_CR11","unstructured":"Hacohen, G., Weinshall, D.: On the power of curriculum learning in training deep networks. In: International Conference On Machine Learning, pp. 2535\u20132544. PMLR (2019)"},{"key":"6_CR12","doi-asserted-by":"publisher","first-page":"7405","DOI":"10.52202\/075280-0325","volume":"36","author":"X Hu","year":"2023","unstructured":"Hu, X., Liu, G., Zhao, Y., Zhang, H.: De novo drug design using reinforcement learning with multiple gpt agents. Adv. Neural. Inf. Process. Syst. 36, 7405\u20137418 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"6_CR13","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1021\/ci049714+","volume":"45","author":"JJ Irwin","year":"2005","unstructured":"Irwin, J.J., Shoichet, B.K.: Zinc- a free database of commercially available compounds for virtual screening. J. Chemical Inf. Modeling 45(1), 177\u2013182 (2005)","journal-title":"J. Chemical Inf. Modeling"},{"issue":"12","key":"6_CR14","doi-asserted-by":"publisher","first-page":"3567","DOI":"10.1039\/C8SC05372C","volume":"10","author":"JH Jensen","year":"2019","unstructured":"Jensen, J.H.: A graph-based genetic algorithm and generative model\/monte carlo tree search for the exploration of chemical space. Chem. Sci. 10(12), 3567\u20133572 (2019)","journal-title":"Chem. Sci."},{"key":"6_CR15","unstructured":"Jin, W., Barzilay, R., Jaakkola, T.: Junction tree variational autoencoder for molecular graph generation. In: International Conference On Machine Learning, pp. 2323\u20132332. PMLR (2018)"},{"key":"6_CR16","unstructured":"Jin, W., Barzilay, R., Jaakkola, T.: Multi-objective molecule generation using interpretable substructures. In: International Conference On Machine Learning, pp. 4849\u20134859. PMLR (2020)"},{"key":"6_CR17","unstructured":"Liu, S., Wang, J., Yang, Y., Wang, C., Liu, L., Guo, H., Xiao, C.: Chatgpt-powered conversational drug editing using retrieval and domain feedback. arXiv preprint arXiv:2305.18090 (2023)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Liu, X., Ye, K., van Vlijmen, H.W., Emmerich, M.T., IJzerman, A.P., van Westen, G.J.: Drugex v2: de novo design of drug molecules by pareto-based multi-objective reinforcement learning in polypharmacology. J. Cheminf. 13(1), 85 (2021)","DOI":"10.1186\/s13321-021-00561-9"},{"key":"6_CR19","unstructured":"Liu, X., Ye, K., van Vlijmen, H.W., IJzerman, A.P., van Westen, G.J.: Drugex v3: scaffold-constrained drug design with graph transformer-based reinforcement learning. J. Cheminf. 15(1), 24 (2023)"},{"issue":"1","key":"6_CR20","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13321-024-00812-5","volume":"16","author":"HH Loeffler","year":"2024","unstructured":"Loeffler, H.H., He, J., Tibo, A., Janet, J.P., Voronov, A., Mervin, L.H., Engkvist, O.: Reinvent 4: modern ai-driven generative molecule design. J. Cheminform 16(1), 20 (2024)","journal-title":"J. Cheminform"},{"issue":"1\u20133","key":"6_CR21","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.ejphar.2009.06.065","volume":"625","author":"S Mandal","year":"2009","unstructured":"Mandal, S., Mandal, S.K., et al.: Rational drug design. Eur. J. Pharmacol. 625(1\u20133), 90\u2013100 (2009)","journal-title":"Eur. J. Pharmacol."},{"issue":"11","key":"6_CR22","doi-asserted-by":"publisher","first-page":"2707","DOI":"10.1016\/j.drudis.2021.05.019","volume":"26","author":"J Meyers","year":"2021","unstructured":"Meyers, J., Fabian, B., Brown, N.: De novo molecular design and generative models. Drug Discovery Today 26(11), 2707\u20132715 (2021)","journal-title":"Drug Discovery Today"},{"issue":"181","key":"6_CR23","first-page":"1","volume":"21","author":"S Narvekar","year":"2020","unstructured":"Narvekar, S., Peng, B., Leonetti, M., Sinapov, J., Taylor, M.E., Stone, P.: Curriculum learning for reinforcement learning domains: a framework and survey. J. Mach. Learn. Res. 21(181), 1\u201350 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-017-0235-x","volume":"9","author":"M Olivecrona","year":"2017","unstructured":"Olivecrona, M., Blaschke, T., Engkvist, O., Chen, H.: Molecular de-novo design through deep reinforcement learning. J. Cheminform. 9, 1\u201314 (2017)","journal-title":"J. Cheminform."},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Popova, M., Isayev, O., Tropsha, A.: Deep reinforcement learning for de novo drug design. Sci. Adv. 4(7), eaap7885 (2018)","DOI":"10.1126\/sciadv.aap7885"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: your language model is secretly a reward model. Adv. Neural Inform. Process. Syst. 36 (2024)","DOI":"10.52202\/075280-2338"},{"issue":"6400","key":"6_CR27","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1126\/science.aat2663","volume":"361","author":"B Sanchez-Lengeling","year":"2018","unstructured":"Sanchez-Lengeling, B., Aspuru-Guzik, A.: Inverse molecular design using machine learning: generative models for matter engineering. Science 361(6400), 360\u2013365 (2018)","journal-title":"Science"},{"issue":"8","key":"6_CR28","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1038\/nrd1799","volume":"4","author":"G Schneider","year":"2005","unstructured":"Schneider, G., Fechner, U.: Computer-based de novo design of drug-like molecules. Nat. Rev. Drug Discovery 4(8), 649\u2013663 (2005)","journal-title":"Nat. Rev. Drug Discovery"},{"issue":"1","key":"6_CR29","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1021\/acscentsci.7b00512","volume":"4","author":"MH Segler","year":"2018","unstructured":"Segler, M.H., Kogej, T., Tyrchan, C., Waller, M.P.: Generating focused molecule libraries for drug discovery with recurrent neural networks. ACS Cent. Sci. 4(1), 120\u2013131 (2018)","journal-title":"ACS Cent. Sci."},{"key":"6_CR30","unstructured":"Simm, G., Pinsler, R., Hern\u00e1ndez-Lobato, J.M.: Reinforcement learning for molecular design guided by quantum mechanics. In: International Conference on Machine Learning, pp. 8959\u20138969. PMLR (2020)"},{"issue":"4","key":"6_CR31","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(4), 688\u2013702 (2020)","journal-title":"Cell"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Widatalla, T., Rafailov, R., Hie, B.: Aligning protein generative models with experimental fitness via direct preference optimization. bioRxiv, pp. 2024\u201305 (2024)","DOI":"10.1101\/2024.05.20.595026"},{"issue":"9","key":"6_CR33","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1038\/s41587-019-0224-x","volume":"37","author":"A Zhavoronkov","year":"2019","unstructured":"Zhavoronkov, A., et al.: Deep learning enables rapid identification of potent ddr1 kinase inhibitors. Nat. Biotechnol. 37(9), 1038\u20131040 (2019)","journal-title":"Nat. Biotechnol."},{"issue":"1","key":"6_CR34","doi-asserted-by":"publisher","first-page":"10752","DOI":"10.1038\/s41598-019-47148-x","volume":"9","author":"Z Zhou","year":"2019","unstructured":"Zhou, Z., Kearnes, S., Li, L., Zare, R.N., Riley, P.: Optimization of molecules via deep reinforcement learning. Sci. Rep. 9(1), 10752 (2019)","journal-title":"Sci. Rep."}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06106-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:18:25Z","timestamp":1782310705000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06106-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"ISBN":["9783032061058","9783032061065"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06106-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"3 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}