{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T01:35:02Z","timestamp":1782524102756,"version":"3.54.5"},"reference-count":70,"publisher":"American Chemical Society (ACS)","issue":"15","license":[{"start":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T00:00:00Z","timestamp":1721952000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T00:00:00Z","timestamp":1721952000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T00:00:00Z","timestamp":1721952000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100007029","name":"State Committee of Science","doi-asserted-by":"publisher","award":["23LCG-1F002"],"award-info":[{"award-number":["23LCG-1F002"]}],"id":[{"id":"10.13039\/501100007029","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Chem. Inf. Model."],"published-print":{"date-parts":[[2024,8,12]]},"DOI":"10.1021\/acs.jcim.4c00512","type":"journal-article","created":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T06:05:42Z","timestamp":1721973942000},"page":"5832-5843","source":"Crossref","is-referenced-by-count":21,"title":["BartSmiles: Generative Masked Language Models for Molecular Representations"],"prefix":"10.1021","volume":"64","author":[{"given":"Gayane","family":"Chilingaryan","sequence":"first","affiliation":[{"name":"YerevaNN, Charents str. 20, 0025 Yerevan, Armenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hovhannes","family":"Tamoyan","sequence":"additional","affiliation":[{"name":"YerevaNN, Charents str. 20, 0025 Yerevan, Armenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ani","family":"Tevosyan","sequence":"additional","affiliation":[{"name":"YerevaNN, Charents str. 20, 0025 Yerevan, Armenia"},{"name":"Toxometris.ai, Sarmen str. 7, 0019 Yerevan, Armenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nelly","family":"Babayan","sequence":"additional","affiliation":[{"name":"Institute of Molecular Biology, NAS RA, Hasratyan 7, 0014 Yerevan, Armenia"},{"name":"Toxometris.ai, Sarmen str. 7, 0019 Yerevan, Armenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karen","family":"Hambardzumyan","sequence":"additional","affiliation":[{"name":"YerevaNN, Charents str. 20, 0025 Yerevan, Armenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zaven","family":"Navoyan","sequence":"additional","affiliation":[{"name":"Toxometris.ai, Sarmen str. 7, 0019 Yerevan, Armenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Armen","family":"Aghajanyan","sequence":"additional","affiliation":[{"name":"Meta AI Research, 1 Hacker Wy, Menlo Park, California 94025, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hrant","family":"Khachatrian","sequence":"additional","affiliation":[{"name":"YerevaNN, Charents str. 20, 0025 Yerevan, Armenia"},{"name":"Yerevan State University, Alex Manoogian str. 1, 0025 Yerevan, Armenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0578-0758","authenticated-orcid":true,"given":"Lusine","family":"Khondkaryan","sequence":"additional","affiliation":[{"name":"Institute of Molecular Biology, NAS RA, Hasratyan 7, 0014 Yerevan, Armenia"},{"name":"Toxometris.ai, Sarmen str. 7, 0019 Yerevan, Armenia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2024,7,26]]},"reference":[{"key":"ref1\/cit1","doi-asserted-by":"publisher","DOI":"10.1021\/c160017a018"},{"key":"ref2\/cit2","first-page":"199","volume":"9","author":"Glem R. C.","year":"2006","journal-title":"IDrugs"},{"key":"ref3\/cit3","doi-asserted-by":"publisher","DOI":"10.1021\/ci100050t"},{"key":"ref4\/cit4","unstructured":"Dahl, G. E.; Jaitly, N.; Salakhutdinov, R. Multi-task Neural Networks for QSAR Predictions. 2014, arXiv:1406.1231. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/14061231 (accessed Sept 09, 2020)."},{"key":"ref5\/cit5","doi-asserted-by":"publisher","DOI":"10.1021\/ci00057a005"},{"key":"ref6\/cit6","unstructured":"Duvenaud, D.; Maclaurin, D.; Aguilera-Iparraguirre, J.; Gomez-Bombarelli, R. H.; Aspuru-Guzik, A.; Ryan, P. In  Convolutional Networks on Graphs for Learning Molecular Fingerprints, Proceedings of the 28th International Conference on Neural Information Processing Systems, Monreal, Canada; MIT Press: Cambridge, MA, USA, 2015; pp 2224\u20132232."},{"key":"ref7\/cit7","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-016-9938-8"},{"key":"ref8\/cit8","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"ref9\/cit9","doi-asserted-by":"publisher","DOI":"10.1038\/432823a"},{"key":"ref10\/cit10","unstructured":"Aghajanyan, A. CM3: A Causal Masked Multimodal Model of the Internet. 2022, arXiv:2201.07520. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2201.07520 (accessed on Aug 20, 2022)."},{"key":"ref11\/cit11","unstructured":"Bao, H.; Dong, L.; Piao, S.; Wei, F. BEiT: BERT Pre-Training of Image Transformers. 2021, arXiv:2106.08254. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2106.08254 (accessed on Aug 20, 2022)."},{"key":"ref12\/cit12","doi-asserted-by":"crossref","unstructured":"He, K. In  Masked Autoencoders Are Scalable Vision Learners, IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 2022; pp 15979\u201315988.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref13\/cit13","unstructured":"Liu, Y.; Ott, M.; Goyal, N.; Du, J.; Joshi, M.; Chen, D.; Levy, O.; Lewis, M.; Zettlemoyer, L.; Stoyanov, V. RoBERTa: A Robustly Optimized BERT Pretraining Approach. 2019, arXiv:1907.11692. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1907.11692 (accessed on Sept 10, 2022)."},{"key":"ref14\/cit14","unstructured":"Lewis, M.; Ghazvininejad, M.; Ghosh, G.; Aghajanyan, A.; Wang, S.; Zettlemoyeret, L. Pre-training via Paraphrasing. 2020, arXiv:2006.15020. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2006.15020 (accessed on Oct 01, 2022)."},{"key":"ref15\/cit15","doi-asserted-by":"crossref","unstructured":"Conneau, A.; Baevski, A.; Collobert, R.; Mohamed, A.; Auli, M. Unsupervised Cross-lingual Representation Learning for Speech Recognition. 2020, arXiv:2006.13979. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2006.13979 (accessed on Sept 10, 2022).","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref16\/cit16","unstructured":"Radford, A.; Kim, J. W.; Xu, T.; Brockman, G.; McLeavey, C.; Sutskever, I. Robust Speech Recognition via Large-Scale Weak Supervision. 2022, arXiv:2212.04356. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2212.04356 (accessed on March 01, 2022)."},{"key":"ref17\/cit17","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.7b00616"},{"key":"ref18\/cit18","doi-asserted-by":"crossref","unstructured":"Wang, S.; Guo, Y.; Wang, Y.; Sun, H.; Huang, J. In  Smiles-bert: Large Scale Unsupervised Pre-training for Molecular Property Prediction, Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, New York, NY, USA. 2019; pp 429\u2013436","DOI":"10.1145\/3307339.3342186"},{"key":"ref19\/cit19","unstructured":"Chithrananda, S.; Grand, G.; Ramsundar, B. ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction. 2020, arXiv:2010.09885. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2010.09885 (accessed on Aug 03, 2022)."},{"key":"ref20\/cit20","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00580-7"},{"key":"ref21\/cit21","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac3ffb"},{"key":"ref22\/cit22","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00447-x"},{"key":"ref23\/cit23","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c00495"},{"key":"ref24\/cit24","unstructured":"Wang, H.; Wang, H.; Li, W.; Jin, X.; Cho, K.; Ji, H.; Han, J.; Burke, M. D. In  Chemical-Reaction-Aware Molecule Representation Learning, 10th International Conference on Learning Representations, 2022."},{"key":"ref25\/cit25","unstructured":"Stark, H.; Beaini, D.; Corso, G.; Tossou, P.; Dallago, C.; G\u00fcnnemann, S.; Li\u00f2et, P. In  3D Infomax Improves GNNs for Molecular Property Prediction, Proceedings of the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, 2022; pp 20479\u201320502."},{"key":"ref26\/cit26","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2022-jjm0j"},{"key":"ref27\/cit27","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c00675"},{"key":"ref28\/cit28","unstructured":"Sundararajan, M.; Taly, A.; Yan, Q. In  Axiomatic Attribution for Deep Networks, Proceedings of the 34th International Conference on Machine Learning, Sydney, NSW, Australia, 2017; pp 3319\u20133328."},{"key":"ref29\/cit29","unstructured":"Landrum, G. Rdkit: A Software Suite for Cheminformatics, Computational Chemistry, and Predictive Modeling, 2013."},{"key":"ref30\/cit30","unstructured":"Lewis, M.; Liu, Y.; Goyal, N.; Ghazvininejad, M.; Mohamed, A.; Levy, O.; Stoyanov, V.; Zettlemoyeret, L. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. 2019, arXiv:1910.13461. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1910.13461 (accessed on Aug 03, 2022)."},{"key":"ref31\/cit31","doi-asserted-by":"crossref","unstructured":"Ott, M.; Edunov, S.; Baevski, A.; Fan, A.; Gross, S.; Ng, N.; Grangier, D.; Auli, M. In  fairseq: A Fast, Extensible Toolkit for Sequence Modeling, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations); Association for Computational Linguistics, USA: Minneapolis, Minnesota, USA, 2019; pp 48\u201353.","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref32\/cit32","unstructured":"Paszke, A.; Sam, G.; Massa, F.; Lerer, A.; Bradbury, J.; Chanan, G.; Killeen, T.; Lin, Z.; Gimelshein, N.; Antiga, L.; Desmaison, A.; Kopf, A.; Yang, E.; DeVito, Z.; Raison, M.; Tejani, A.; Chilamkurthy, S.; Steiner, B.; Fang, L.; Bai, J.; Chintala, S. In  PyTorch: An Imperative Style, High-Performance Deep Learning Library, Proceeding of the 33rd Conference on Neural Information Processing Systems; Curran Associates Inc.: NY, USA, 2019; pp 8026\u20138037."},{"key":"ref33\/cit33","unstructured":"Baines, M.; Bhosale, S.; Caggiano, V.; Goyal, N.; Goyal, S.; Ott, M.; Lefaudeux, B.; Liptchinsky, V.; Rabbat, M.; Sheiffer, S.; Sridhar, A.; Xu, M. Fairscale: A general purpose modular pytorch library for high performance and large-scale training. https:\/\/github.com\/facebookresearch\/fairscale. 2021. (accessed on March 01, 2022)."},{"key":"ref34\/cit34","unstructured":"Arakelyan, G.; Sofgomonyan, G.; the Aim team. Aim. https:\/\/github.com\/aimhubio\/aim. 2020. (accessed on April 13, 2022)."},{"key":"ref35\/cit35","unstructured":"Wang, T.; Roberts, A.; Hesslow, D.; Le Scao, T.; Chung, H. W.; Beltagy, I.; Launay, J.; Raffelet, C. What language model architecture and pretraining objective work best for zero-shot generalization? 2022, arXiv:2204.05832. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2204.05832 (accessed on Sept 10, 2022)."},{"key":"ref36\/cit36","unstructured":"Devlin, J.; Chang, M.W.; Lee, K.; Toutanova, K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. 2018, arXiv:1810.04805. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1810.04805 (accessed on Sept 10, 2022)."},{"key":"ref37\/cit37","doi-asserted-by":"publisher","DOI":"10.1021\/ci300124c"},{"key":"ref38\/cit38","doi-asserted-by":"crossref","unstructured":"Kudo, T.; Richardson, J. SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing. 2018, arXiv:1808.06226. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1808.06226 (accessed on March 10, 2022).","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref39\/cit39","doi-asserted-by":"publisher","DOI":"10.1021\/jm9602928"},{"key":"ref40\/cit40","doi-asserted-by":"publisher","DOI":"10.1021\/ci900161g"},{"key":"ref41\/cit41","doi-asserted-by":"publisher","DOI":"10.1039\/C7TX00259A"},{"key":"ref42\/cit42","unstructured":"Extraction of Chemical Structures and Reactions from the Literature. PhD Thesis, University of Cambridge, 2012."},{"key":"ref43\/cit43","doi-asserted-by":"crossref","unstructured":"Wang, A.; Singh, A.; Michael, J.; Hill, F.; Levy, O.; Bowman, S. In  GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding, Proceedings of the 2018 EMNLP Workshop NLP: Analyzing and Interpreting Neural Networks for NLP; Association for Computational Linguistics, Belgium: Brussels, Belgium, 2018; pp 353\u2013355.","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref44\/cit44","unstructured":"Izmailov, P.; Podoprikhin, D.; Garipov, T.; Vetrov, D.; Wilson, A. G. Averaging Weights Leads to Wider Optima and Better Generalization. 2018, arXiv:1803.05407. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1803.05407 (accessed on April 11, 2022)."},{"key":"ref45\/cit45","unstructured":"Aghajanyan, A.; Shrivastava, A.; Gupta, A.; Goyal, N.; Zettlemoyer, L.; Gupta, S. Better Fine-Tuning by Reducing Representational Collapse. 2020, arXiv:2008.03156. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2008.03156 (accessed on April 02, 2022)."},{"key":"ref46\/cit46","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00237"},{"key":"ref47\/cit47","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.9b00959"},{"key":"ref48\/cit48","unstructured":"Hu, W.; Liu, B.; Gomes, J.; Zitnik, M.; Liang, P.; Pande, V.; Leskovec, J. In  Strategies for Pre-training Graph Neural Networks, International Conference on Learning Representations; Addis ababa, Ethopia, 2020."},{"key":"ref49\/cit49","unstructured":"Rong, Y.; Bian, Y.; Xu, T.; Xie, W.; Wei, Y.; Huang, W.; Huanget, J. In  Self-Supervised Graph Transformer on Large-Scale Molecular Data, Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, 2020; pp 12559\u201312571."},{"key":"ref50\/cit50","unstructured":"Scikit-learn:\nMachine Learning in Python. https:\/\/scikit-learn.org\/ (accessed\non April 04, 2022)."},{"key":"ref51\/cit51","doi-asserted-by":"publisher","DOI":"10.1038\/s41570-018-0152"},{"key":"ref52\/cit52","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-018-0323-6"},{"key":"ref53\/cit53","unstructured":"Yan, C.; Zhao, P.; Lu, C.; Yu, Y.; Huang, J. RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction. 2021, arXiv:2112.11225. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2112.11225 (accessed on Sept 10, 2022)."},{"key":"ref54\/cit54","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-19266-y"},{"key":"ref55\/cit55","unstructured":"Somnath, V. R.; Bunne, C.; Coley, C. W.; Krause, A.; Barzilay, R. Learning Graph Models for Retrosynthesis Prediction. 2020, arXiv:2006.07038. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2006.07038 (accessed on Sept 10, 2022)."},{"key":"ref56\/cit56","unstructured":"Sun, R.; Dai, H.; Li, L.; Kearnes, S.; Dai, B. Energy-based View of Retrosynthesis. 2020, arXiv:2007.13437. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2007.13437 (accessed on Sept 10, 2022)."},{"key":"ref57\/cit57","doi-asserted-by":"publisher","DOI":"10.1039\/C8SC02339E"},{"key":"ref58\/cit58","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.9b00576"},{"key":"ref59\/cit59","unstructured":"Jin, W.; Coley, C. W.; Barzilay, R.; Jaakkola, T. In  Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network, Proceedings of the 31st International Conference on Neural Information Processing Systems; Long Beach: California, USA, 2017; pp 2604\u20132613."},{"key":"ref60\/cit60","unstructured":"Bradshaw, J.; Kusner, M. J.; Paige, B.; Segler, M. H. S.; Hern\u00e1ndez-Lobato, J. M. A Generative Model For Electron Paths. 2018, arXiv:1805.10970. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1805.10970 (accessed on Sept 08, 2022)."},{"key":"ref61\/cit61","doi-asserted-by":"crossref","unstructured":"Do, K.; Tran, T.; Venkatesh, S. In  Graph Transformation Policy Network for Chemical Reaction Prediction, Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; Anchorage: AK, USA, 2018; pp 750\u2013760.","DOI":"10.1145\/3292500.3330958"},{"key":"ref62\/cit62","doi-asserted-by":"publisher","DOI":"10.1039\/C8SC04228D"},{"key":"ref63\/cit63","unstructured":"Radford, A.; Jozefowicz, R.; Sutskever, I. Learning to Generate Reviews and Discovering Sentiment. 2017, arXiv:1704.01444. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1704.01444 (accessed on Sept 10, 2022)."},{"key":"ref64\/cit64","unstructured":"Aghajanyan, A.; Zettlemoyer, L.; Gupta, S. Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning. 2020, arXiv:2012.13255. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2012.13255 (accessed on Sept 09, 2022)."},{"key":"ref65\/cit65","unstructured":"Kokhlikyan, N.; Miglani, V.; Martin, M.; Wang, E.; Alsallakh, B.; Reynolds, J.; Melnikov, A.; Kliushkina, N.; Araya, C.; Yan, S.; Reblitz-Richardson, O. Captum: A unified and generic model interpretability library for PyTorch. 2020, arXiv:2009.07896. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2009.07896 (accessed on May 05, 2020)."},{"key":"ref66\/cit66","doi-asserted-by":"publisher","DOI":"10.1515\/aiht-2016-67-2801"},{"key":"ref67\/cit67","doi-asserted-by":"publisher","DOI":"10.1021\/ci300245q"},{"key":"ref68\/cit68","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00479-8"},{"key":"ref69\/cit69","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.8b00234"},{"key":"ref70\/cit70","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-19594-z"}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.4c00512","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.4c00512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T08:17:38Z","timestamp":1723450658000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/doi\/10.1021\/acs.jcim.4c00512"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,26]]},"references-count":70,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2024,8,12]]}},"alternative-id":["10.1021\/acs.jcim.4c00512"],"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.4c00512","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,26]]}}}