{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T05:46:24Z","timestamp":1743140784325,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":46,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819608133"},{"type":"electronic","value":"9789819608140"}],"license":[{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0814-0_11","type":"book-chapter","created":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T17:30:20Z","timestamp":1734024620000},"page":"160-174","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["When Molecular GAN Meets Byte-Pair Encoding"],"prefix":"10.1007","author":[{"given":"Huidong","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuhiko","family":"Morimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,13]]},"reference":[{"issue":"11","key":"11_CR1","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 Discov. Today 26(11), 2707\u20132715 (2021)","journal-title":"Drug Discov. Today"},{"key":"11_CR2","doi-asserted-by":"publisher","first-page":"105403","DOI":"10.1016\/j.compbiomed.2022.105403","volume":"145","author":"DD Martinelli","year":"2022","unstructured":"Martinelli, D.D., et al.: Generative machine learning for de novo drug discovery: a systematic review. Comput. Biol. Med. 145, 105403 (2022)","journal-title":"Comput. Biol. Med."},{"issue":"2","key":"11_CR3","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1517\/17460441.2014.872624","volume":"9","author":"JL Medina-Franco","year":"2014","unstructured":"Medina-Franco, J.L., Martinez-Mayorga, K., Meurice, N.: Balancing novelty with confined chemical space in modern drug discovery. Exp. Opin. Drug Discov. 9(2), 151\u2013165 (2014)","journal-title":"Exp. Opin. Drug Discov."},{"key":"11_CR4","doi-asserted-by":"publisher","first-page":"108311","DOI":"10.1016\/j.compbiomed.2024.108311","volume":"173","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Wang, S., Jiang, Z., Chen, Z., Bai, X.: CD-Net: cascaded 3D dilated convolutional neural network for pneumonia lesion segmentation. Comput. Biol. Med. 173, 108311 (2024)","journal-title":"Comput. Biol. Med."},{"issue":"2","key":"11_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11219-024-09671-7","volume":"32","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Wang, Z., Jiang, Z., Wu, M., Li, C., Yamanishi, Y.: Quantitative evaluation of molecular generation performance of graph-based GANs. Softw. Qual. J. 32(2), 1\u201329 (2024)","journal-title":"Softw. Qual. J."},{"key":"11_CR6","doi-asserted-by":"publisher","first-page":"101790","DOI":"10.1016\/j.datak.2020.101790","volume":"127","author":"J Zhang","year":"2020","unstructured":"Zhang, J., Jiang, Z., Du, Y., Li, T., Wang, Y., Hu, X.: Hierarchy construction and classification of heterogeneous information networks based on RSDAEF. Data Know. Eng. 127, 101790 (2020)","journal-title":"Data Know. Eng."},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, J., Hu, X., Jiang, Z., Song, B., Quan, W., Chen, Z.: Predicting disease-related RNA associations based on graph convolutional attention network. In: 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 177\u2013182. IEEE (2019)","DOI":"10.1109\/BIBM47256.2019.8983191"},{"key":"11_CR8","unstructured":"Kusner, M.J., Paige, B., Hern\u00e1ndez-Lobato, J.M.: Grammar variational autoencoder. In: International Conference on Machine Learning, pp. 1945\u20131954 (2017)"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Ma, C., Zhang, X.: GF-VAE: a flow-based variational autoencoder for molecule generation. In: Proceedings of the 30th ACM International Conference on Information and Knowledge Management, pp. 1181\u20131190 (2021)","DOI":"10.1145\/3459637.3482260"},{"key":"11_CR10","unstructured":"Vignac, C., Krawczuk, I., Siraudin, A., Wang, B., Cevher, V., Frossard, P.: DiGress: discrete denoising diffusion for graph generation. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"11_CR11","unstructured":"Xu, M., Powers, A.S., Dror, R.O., Ermon, S., Leskovec, J.: Geometric latent diffusion models for 3D molecule generation. In: International Conference on Machine Learning, pp. 38592\u201338610 (2023)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Li, C., Yamanaka, C., Kaitoh, K., Yamanishi, Y.: Transformer-based objective-reinforced generative adversarial network to generate desired molecules. In: IJCAI, pp. 3884\u20133890 (2022)","DOI":"10.24963\/ijcai.2022\/539"},{"key":"11_CR13","doi-asserted-by":"publisher","unstructured":"Li, C., Yamanishi, Y.: SpotGAN: a reverse-transformer GAN generates scaffold-constrained molecules with property optimization. In: Koutra, D., Plant, C., Gomez Rodriguez, M., Baralis, E., Bonchi, F. (eds.) Machine Learning and Knowledge Discovery in Databases: Research Track, ECML PKDD 2023. LNCS, vol. 14169, pp. 328\u2013338. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43412-9_19","DOI":"10.1007\/978-3-031-43412-9_19"},{"issue":"1","key":"11_CR14","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","volume":"28","author":"D Weininger","year":"1988","unstructured":"Weininger, D.: SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J. Chem. Info. Comput. Sci. 28(1), 31\u201336 (1988)","journal-title":"J. Chem. Info. Comput. Sci."},{"key":"11_CR15","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1007\/s10822-016-9938-8","volume":"30","author":"S Kearnes","year":"2016","unstructured":"Kearnes, S., McCloskey, K., Berndl, M., Pande, V., Riley, P.: Molecular graph convolutions: moving beyond fingerprints. J. Comput. Aided Mol. Des. 30, 595\u2013608 (2016)","journal-title":"J. Comput. Aided Mol. Des."},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Chowdhary, K.R.: Natural language processing. In: Fundamentals of Artificial Intelligence, pp. 603\u2013649 (2020)","DOI":"10.1007\/978-81-322-3972-7_19"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow B., Birch, A.: Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 (2015)","DOI":"10.18653\/v1\/P16-1162"},{"key":"11_CR18","unstructured":"Liu, Y.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"11_CR19","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)"},{"key":"11_CR20","unstructured":"Guimaraes, G.L., Sanchez-Lengeling, B., Outeiral, C., Farias, P.L.C., Aspuru-Guzik, A.: Objective-reinforced generative adversarial networks (ORGAN) for sequence generation models. arXiv preprint arXiv:1705.10843 (2017)"},{"key":"11_CR21","unstructured":"Li, C., Yamanishi, Y.: TenGAN: pure transformer encoders make an efficient discrete GAN for de novo molecular generation. In: International Conference on Artificial Intelligence and Statistics, pp. 361\u2013369 (2024)"},{"key":"11_CR22","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Graves, A., Graves, A.: Long short-term memory. In: Supervised Sequence Labelling with Recurrent Neural Networks, pp. 37\u201345 (2012)","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"11_CR24","first-page":"13455","volume":"38","author":"C Li","year":"2024","unstructured":"Li, C., Yamanishi, Y.: GxVAEs: two joint VAEs generate hit molecules from gene expression profiles. Proc. AAAI Conf. Artif. Intell. 38, 13455\u201313463 (2024)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"11_CR25","unstructured":"Dai, H., Tian, Y., Dai, B., Skiena, S., Song, L.: Syntax-directed variational autoencoder for structured data. In: International Conference on Learning Representations (2018)"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Tang, H., et al: MacGAN: a moment-actor-critic reinforcement learning-based generative adversarial network for molecular generation. In: APWeb-WAIM Joint International Conference on Web and Big Data, pp. 127\u2013141 (2023)","DOI":"10.1007\/978-981-97-2303-4_9"},{"issue":"1","key":"11_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCIAIG.2012.2186810","volume":"4","author":"CB Browne","year":"2012","unstructured":"Browne, C.B., et al.: A survey of Monte Carlo tree search methods. IEEE Trans. Comput. Intell. AI Games 4(1), 1\u201343 (2012)","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"11_CR28","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.patrec.2023.10.001","volume":"175","author":"H Tang","year":"2023","unstructured":"Tang, H., et al.: EarlGAN: an enhanced actor-critic reinforcement learning agent-driven GAN for de novo drug design. Pattern Recogn. Lett. 175, 45\u201351 (2023)","journal-title":"Pattern Recogn. Lett."},{"key":"11_CR29","unstructured":"Bahdanau, D., et al.: An actor-critic algorithm for sequence prediction. In: International Conference on Learning Representations (2022)"},{"issue":"4","key":"11_CR30","doi-asserted-by":"publisher","first-page":"045024","DOI":"10.1088\/2632-2153\/aba947","volume":"1","author":"M Krenn","year":"2020","unstructured":"Krenn, M., H\u00e4se, F., Nigam, A.K., Friederich, P., Aspuru-Guzik, A.: Self-referencing embedded strings (SELFIES): a 100% robust molecular string representation. Mach. Learn. Sci. Technol. 1(4), 045024 (2020)","journal-title":"Mach. Learn. Sci. Technol."},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Krenn, M., et\u00a0al.: SELFIES and the future of molecular string representations. Patterns 3(10) (2022)","DOI":"10.1016\/j.patter.2022.100588"},{"key":"11_CR32","unstructured":"De Cao, N., Kipf, T.: MolGAN: an implicit generative model for small molecular graphs. arXiv preprint arXiv:1805.11973 (2018)"},{"key":"11_CR33","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-030-67661-2_11","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"S P\u00f6lsterl","year":"2021","unstructured":"P\u00f6lsterl, S., Wachinger, C.: Adversarial learned molecular graph inference and generation. In: Hutter, F., Kersting, K., Lijffijt, J., Valera, I. (eds.) ECML PKDD 2020. LNCS (LNAI), vol. 12458, pp. 173\u2013189. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67661-2_11"},{"key":"11_CR34","unstructured":"Shi, C., Xu, M., Zhu, Z., Zhang, W., Zhang, M., Tang. J.: GraphAF: a flow-based autoregressive model for molecular graph generation. In: International Conference on Learning Representations (2020)"},{"key":"11_CR35","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. arXiv preprint arXiv:1605.08803 (2016)"},{"key":"11_CR36","unstructured":"You, J., Liu, B., Ying, Z., Pande, V., Leskovec, J.: Graph convolutional policy network for goal-directed molecular graph generation. Adv. Neural Info. Process. Syst. 31 (2018)"},{"key":"11_CR37","unstructured":"Popova, M., Shvets, M., Oliva, J., Isayev. O.: MolecularRNN: generating realistic molecular graphs with optimized properties. arXiv preprint arXiv:1905.13372 (2019)"},{"key":"11_CR38","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova. K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"11_CR39","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"issue":"4","key":"11_CR40","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1021\/acs.jcim.0c01127","volume":"61","author":"X Li","year":"2021","unstructured":"Li, X., Fourches, D.: Smiles pair encoding: a data-driven substructure tokenization algorithm for deep learning. J. Chem. Inf. Model. 61(4), 1560\u20131569 (2021)","journal-title":"J. Chem. Inf. Model."},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Ucak, U.V., Ashyrmamatov, I., Lee, J.: Improving the quality of chemical language model outcomes with atom-in-smiles tokenization. J. Cheminform. 15(1), 55, (2023)","DOI":"10.1186\/s13321-023-00725-9"},{"key":"11_CR42","unstructured":"Kida, T., Fukamachi, S., Takeda, M., Shinohara, A., Shinohara, T., Arikawa. S.: Byte pair encoding: a text compression scheme that accelerates pattern matching. Technical Report DOI-TR-161, Department of Informatics, Kyushu University (1999)"},{"issue":"7","key":"11_CR43","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1021\/ci3001277","volume":"52","author":"JJ Irwin","year":"2012","unstructured":"Irwin, J.J., Sterling, T., Mysinger, M.M., Bolstad, E.S., Coleman, R.G.: ZINC: a free tool to discover chemistry for biology. J. Chem. Info. Model. 52(7), 1757\u20131768 (2012)","journal-title":"J. Chem. Info. Model."},{"issue":"1","key":"11_CR44","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"11_CR45","unstructured":"Jin, W., Barzilay, R., Jaakkola, T.: Junction tree variational autoencoder for molecular graph generation. In: International Conference on Machine Learning, pp. 2323\u20132332 (2018)"},{"issue":"3","key":"11_CR46","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/0098-3004(93)90090-R","volume":"19","author":"A Ma\u0107kiewicz","year":"1993","unstructured":"Ma\u0107kiewicz, A., Ratajczak, W.: Principal components analysis (PCA). Comput. Geosci. 19(3), 303\u2013342 (1993)","journal-title":"Comput. Geosci."}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0814-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T18:05:54Z","timestamp":1734026754000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0814-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,13]]},"ISBN":["9789819608133","9789819608140"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0814-0_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,13]]},"assertion":[{"value":"13 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"3 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2024.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}