{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T12:19:18Z","timestamp":1786105158857,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,9,4]],"date-time":"2019-09-04T00:00:00Z","timestamp":1567555200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF CAREER grant","award":["IIS-1553687"],"award-info":[{"award-number":["IIS-1553687"]}]},{"name":"US National Science Foundation","award":["IIS-1718853"],"award-info":[{"award-number":["IIS-1718853"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,9,4]]},"DOI":"10.1145\/3307339.3342186","type":"proceedings-article","created":{"date-parts":[[2019,9,9]],"date-time":"2019-09-09T12:20:31Z","timestamp":1568031631000},"page":"429-436","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":387,"title":["SMILES-BERT"],"prefix":"10.1145","author":[{"given":"Sheng","family":"Wang","sequence":"first","affiliation":[{"name":"University of Texas at Arlington, Arlington, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuzhi","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhong","family":"Wang","sequence":"additional","affiliation":[{"name":"NIH, Rockville, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongmao","family":"Sun","sequence":"additional","affiliation":[{"name":"NIH, Rockville, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junzhou","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,9,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Youtube-8m: A large-scale video classification benchmark. arXiv preprint arXiv:1609.08675","author":"Abu-El-Haija Sami","year":"2016"},{"key":"e_1_3_2_1_2_1","volume-title":"Low Data Drug Discovery with One-shot Learning. arXiv preprint arXiv:1611.03199","author":"Altae-Tran Han","year":"2016"},{"key":"e_1_3_2_1_3_1","volume-title":"Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473","author":"Bahdanau Dzmitry","year":"2014"},{"key":"e_1_3_2_1_4_1","volume-title":"et almbox","author":"Ching Travers","year":"2018"},{"key":"e_1_3_2_1_5_1","unstructured":"Andrew M Dai and Quoc V Le. 2015. Semi-supervised sequence learning. In Advances in Neural Information Processing Systems. 3079--3087.   Andrew M Dai and Quoc V Le. 2015. Semi-supervised sequence learning. In Advances in Neural Information Processing Systems. 3079--3087."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305478"},{"key":"e_1_3_2_1_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018"},{"key":"e_1_3_2_1_8_1","unstructured":"David K Duvenaud Dougal Maclaurin Jorge Iparraguirre Rafael Bombarell Timothy Hirzel Al\u00e1n Aspuru-Guzik and Ryan P Adams. 2015. Convolutional networks on graphs for learning molecular fingerprints. In Advances in neural information processing systems. 2224--2232.   David K Duvenaud Dougal Maclaurin Jorge Iparraguirre Rafael Bombarell Timothy Hirzel Al\u00e1n Aspuru-Guzik and Ryan P Adams. 2015. Convolutional networks on graphs for learning molecular fingerprints. In Advances in neural information processing systems. 2224--2232."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305510"},{"key":"e_1_3_2_1_10_1","first-page":"199","article-title":"Circular fingerprints: flexible molecular descriptors with applications from physical chemistry to ADME","volume":"9","author":"Glen Robert C","year":"2006","journal-title":"IDrugs"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/cmdc.200800408"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci3001277"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-016-9938-8"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.02.010"},{"key":"e_1_3_2_1_16_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014"},{"key":"e_1_3_2_1_17_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016"},{"key":"e_1_3_2_1_18_1","volume-title":"Adaptive Graph Convolutional Neural Networks. arXiv preprint arXiv:1801.03226","author":"Li Ruoyu","year":"2018"},{"key":"e_1_3_2_1_19_1","volume-title":"Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025","author":"Luong Minh-Thang","year":"2015"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1021\/c160017a018"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/11530084_13"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1021\/jp202765c"},{"key":"e_1_3_2_1_23_1","volume-title":"fairseq: A fast, extensible toolkit for sequence modeling. arXiv preprint arXiv:1904.01038","author":"Ott Myle","year":"2019"},{"key":"e_1_3_2_1_24_1","volume-title":"Deep contextualized word representations. arXiv preprint arXiv:1802.05365","author":"Peters Matthew E","year":"2018"},{"key":"e_1_3_2_1_25_1","volume-title":"Improving language understanding by generative pre-training. URL https:\/\/s3-us-west-2. amazonaws. com\/openai-assets\/research-covers\/languageunsupervised\/language understanding paper. pdf","author":"Radford Alec","year":"2018"},{"key":"e_1_3_2_1_26_1","volume-title":"Massively multitask networks for drug discovery. arXiv preprint arXiv:1502.02072","author":"Ramsundar Bharath","year":"2015"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci100050t"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci500749q"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.6b00290"},{"key":"e_1_3_2_1_30_1","unstructured":"Ilya Sutskever Oriol Vinyals and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems. 3104--3112.   Ilya Sutskever Oriol Vinyals and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems. 3104--3112."},{"key":"e_1_3_2_1_31_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.   Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_1_32_1","volume-title":"AtomNet: a deep convolutional neural network for bioactivity prediction in structure-based drug discovery. arXiv preprint arXiv:1510.02855","author":"Wallach Izhar","year":"2015"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"e_1_3_2_1_34_1","volume-title":"Graph Convolutional Nets for Tool Presence Detection in Surgical Videos. In International Conference on Information Processing in Medical Imaging. Springer, 467--478","author":"Wang Sheng","year":"2019"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46723-8_74"},{"key":"e_1_3_2_1_36_1","volume-title":"et almbox","author":"Wang Yanli","year":"2011"},{"key":"e_1_3_2_1_37_1","first-page":"1","article-title":"SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"17","author":"Weininger David","year":"1970","journal-title":"Proc. Edinburgh Math. SOC"},{"key":"e_1_3_2_1_38_1","volume-title":"Sequence-to-sequence learning as beam-search optimization. arXiv preprint arXiv:1606.02960","author":"Wiseman Sam","year":"2016"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3107411.3107424"},{"key":"e_1_3_2_1_40_1","volume-title":"et almbox","author":"Yang Kevin","year":"2019"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3233547.3233548"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.725"}],"event":{"name":"BCB '19: 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","location":"Niagara Falls NY USA","acronym":"BCB '19","sponsor":["SIGBio ACM Special Interest Group on Bioinformatics"]},"container-title":["Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307339.3342186","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3307339.3342186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:09Z","timestamp":1750204389000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307339.3342186"}},"subtitle":["Large Scale Unsupervised Pre-Training for Molecular Property Prediction"],"short-title":[],"issued":{"date-parts":[[2019,9,4]]},"references-count":42,"alternative-id":["10.1145\/3307339.3342186","10.1145\/3307339"],"URL":"https:\/\/doi.org\/10.1145\/3307339.3342186","relation":{},"subject":[],"published":{"date-parts":[[2019,9,4]]},"assertion":[{"value":"2019-09-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}