{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T03:39:35Z","timestamp":1771299575000,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":81,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Pharmolix Inc."},{"name":"The National Key R&D Program of China","award":["2022YFF120300"],"award-info":[{"award-number":["2022YFF120300"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3672043","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:54:55Z","timestamp":1724561695000},"page":"2082-2093","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Learning Multi-view Molecular Representations with Structured and Unstructured Knowledge"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7107-378X","authenticated-orcid":false,"given":"Yizhen","family":"Luo","sequence":"first","affiliation":[{"name":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4961-2715","authenticated-orcid":false,"given":"Kai","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1598-5981","authenticated-orcid":false,"given":"Massimo","family":"Hong","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9452-7695","authenticated-orcid":false,"given":"Xing Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9005-9740","authenticated-orcid":false,"given":"Zikun","family":"Nie","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1458-1016","authenticated-orcid":false,"given":"Hao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1134-2343","authenticated-orcid":false,"given":"Zaiqing","family":"Nie","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research (AIR), Tsinghua University & Pharmolix Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72."},{"key":"e_1_3_2_2_2_1","volume-title":"Benoit Roux, and Masakatsu Watanabe.","author":"Becker Oren M","year":"2001","unstructured":"Oren M Becker, Alexander D MacKerell Jr, Benoit Roux, and Masakatsu Watanabe. 2001. Computational biochemistry and biophysics. Crc Press."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2016.06.004"},{"key":"e_1_3_2_2_4_1","volume-title":"Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review. arXiv preprint arXiv:2310.14735","author":"Chen Banghao","year":"2023","unstructured":"Banghao Chen, Zhaofeng Zhang, Nicolas Langren\u00e9, and Shengxin Zhu. 2023. Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review. arXiv preprint arXiv:2310.14735 (2023)."},{"key":"e_1_3_2_2_5_1","volume-title":"ChemBERTa: large-scale self-supervised pretraining for molecular property prediction. arXiv preprint arXiv:2010.09885","author":"Chithrananda Seyone","year":"2020","unstructured":"Seyone Chithrananda, Gabriel Grand, and Bharath Ramsundar. 2020. ChemBERTa: large-scale self-supervised pretraining for molecular property prediction. arXiv preprint arXiv:2010.09885 (2020)."},{"key":"e_1_3_2_2_6_1","volume-title":"Unifying molecular and textual representations via multi-task language modelling. arXiv preprint arXiv:2301.12586","author":"Christofidellis Dimitrios","year":"2023","unstructured":"Dimitrios Christofidellis, Giorgio Giannone, Jannis Born, Ole Winther, Teodoro Laino, and Matteo Manica. 2023. Unifying molecular and textual representations via multi-task language modelling. arXiv preprint arXiv:2301.12586 (2023)."},{"key":"e_1_3_2_2_7_1","volume-title":"Marcus Ennis, Janna Hastings, Martin Zbinden, Alan McNaught, Rafael Alc\u00e1ntara, Michael Darsow, Micka\u00ebl Guedj, and Michael Ashburner.","author":"Degtyarenko Kirill","year":"2007","unstructured":"Kirill Degtyarenko, Paula De Matos, Marcus Ennis, Janna Hastings, Martin Zbinden, Alan McNaught, Rafael Alc\u00e1ntara, Michael Darsow, Micka\u00ebl Guedj, and Michael Ashburner. 2007. ChEBI: a database and ontology for chemical entities of biological interest. Nucleic acids research, Vol. 36, suppl_1 (2007), D344--D350."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab627"},{"key":"e_1_3_2_2_9_1","volume-title":"A survey for in-context learning. arXiv preprint arXiv:2301.00234","author":"Dong Qingxiu","year":"2022","unstructured":"Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Zhiyong Wu, Baobao Chang, Xu Sun, Jingjing Xu, and Zhifang Sui. 2022. A survey for in-context learning. arXiv preprint arXiv:2301.00234 (2022)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.26"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.47"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00438-4"},{"key":"e_1_3_2_2_13_1","volume-title":"Mol-Instructions-A Large-Scale Biomolecular Instruction Dataset for Large Language Models. In The Twelfth International Conference on Learning Representations.","author":"Fang Yin","year":"2023","unstructured":"Yin Fang, Xiaozhuan Liang, Ningyu Zhang, Kangwei Liu, Rui Huang, Zhuo Chen, Xiaohui Fan, and Huajun Chen. 2023. Mol-Instructions-A Large-Scale Biomolecular Instruction Dataset for Large Language Models. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00654-0"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1039\/D0MH01451F"},{"key":"e_1_3_2_2_16_1","volume-title":"A survey of knowledge enhanced pre-trained language models","author":"Hu Linmei","year":"2023","unstructured":"Linmei Hu, Zeyi Liu, Ziwang Zhao, Lei Hou, Liqiang Nie, and Juanzi Li. 2023. A survey of knowledge enhanced pre-trained language models. IEEE Transactions on Knowledge and Data Engineering (2023)."},{"key":"e_1_3_2_2_17_1","volume-title":"Strategies For Pre-training Graph Neural Networks. In International Conference on Learning Representations (ICLR).","author":"Hu W","year":"2020","unstructured":"W Hu, B Liu, J Gomes, M Zitnik, P Liang, V Pande, and J Leskovec. 2020. Strategies For Pre-training Graph Neural Networks. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac3ffb"},{"key":"e_1_3_2_2_19_1","unstructured":"Pengcheng Jiang Cao Xiao Tianfan Fu and Jimeng Sun. 2023. Bi-level Contrastive Learning for Knowledge Enhanced Molecule Representations. (2023)."},{"key":"e_1_3_2_2_20_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_2_21_1","volume-title":"Proceedings of NAACL-HLT. 4171--4186","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Sunghwan Kim Paul A Thiessen Evan E Bolton Jie Chen Gang Fu Asta Gindulyte Lianyi Han Jane He Siqian He Benjamin A Shoemaker et al. 2016. PubChem substance and compound databases. Nucleic acids research Vol. 44 D1 (2016) D1202--D1213.","DOI":"10.1093\/nar\/gkv951"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K18-1050"},{"key":"e_1_3_2_2_24_1","first-page":"31","article-title":"RDKit: A software suite for cheminformatics, computational chemistry, and predictive modeling","volume":"8","author":"Greg Landrum","year":"2013","unstructured":"Greg Landrum et al. 2013. RDKit: A software suite for cheminformatics, computational chemistry, and predictive modeling. Greg Landrum, Vol. 8 (2013), 31.","journal-title":"Greg Landrum"},{"key":"e_1_3_2_2_25_1","unstructured":"Junnan Li Dongxu Li Silvio Savarese and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. (2023)."},{"key":"e_1_3_2_2_26_1","volume-title":"Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective. arXiv preprint arXiv:2306.06615","author":"Li Jiatong","year":"2023","unstructured":"Jiatong Li, Yunqing Liu, Wenqi Fan, Xiao-Yong Wei, Hui Liu, Jiliang Tang, and Qing Li. 2023. Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective. arXiv preprint arXiv:2306.06615 (2023)."},{"key":"e_1_3_2_2_27_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, Vol. 34 (2021), 9694--9705."},{"key":"e_1_3_2_2_28_1","volume-title":"Towards 3D Molecule-Text Interpretation in Language Models. arXiv preprint arXiv:2401.13923","author":"Li Sihang","year":"2024","unstructured":"Sihang Li, Zhiyuan Liu, Yanchen Luo, Xiang Wang, Xiangnan He, Kenji Kawaguchi, Tat-Seng Chua, and Qi Tian. 2024. Towards 3D Molecule-Text Interpretation in Language Models. arXiv preprint arXiv:2401.13923 (2024)."},{"key":"e_1_3_2_2_29_1","volume-title":"A survey of multi-view representation learning","author":"Li Yingming","year":"2018","unstructured":"Yingming Li, Ming Yang, and Zhongfei Zhang. 2018. A survey of multi-view representation learning. IEEE transactions on knowledge and data engineering, Vol. 31, 10 (2018), 1863--1883."},{"key":"e_1_3_2_2_30_1","volume-title":"Git-mol: A multi-modal large language model for molecular science with graph, image, and text. arXiv preprint arXiv:2308.06911","author":"Liu Pengfei","year":"2023","unstructured":"Pengfei Liu, Yiming Ren, and Zhixiang Ren. 2023. Git-mol: A multi-modal large language model for molecular science with graph, image, and text. arXiv preprint arXiv:2308.06911 (2023)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00759-6"},{"key":"e_1_3_2_2_32_1","volume-title":"International Conference on Learning Representations.","author":"Liu Shengchao","year":"2021","unstructured":"Shengchao Liu, Hanchen Wang, Weiyang Liu, Joan Lasenby, Hongyu Guo, and Jian Tang. 2021. Pre-training Molecular Graph Representation with 3D Geometry. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_33_1","volume-title":"Self-supervised learning: Generative or contrastive","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Fanjin Zhang, Zhenyu Hou, Li Mian, Zhaoyu Wang, Jing Zhang, and Jie Tang. 2021. Self-supervised learning: Generative or contrastive. IEEE transactions on knowledge and data engineering, Vol. 35, 1 (2021), 857--876."},{"key":"e_1_3_2_2_34_1","volume-title":"2023 e. GPT understands, too. AI Open","author":"Liu Xiao","year":"2023","unstructured":"Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2023 e. GPT understands, too. AI Open (2023)."},{"key":"e_1_3_2_2_35_1","volume-title":"MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter. In The 2023 Conference on Empirical Methods in Natural Language Processing.","author":"Liu Zhiyuan","year":"2023","unstructured":"Zhiyuan Liu, Sihang Li, Yanchen Luo, Hao Fei, Yixin Cao, Kenji Kawaguchi, Xiang Wang, and Tat-Seng Chua. 2023. MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter. In The 2023 Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_2_36_1","volume-title":"2023 d. MolXPT: Wrapping Molecules with Text for Generative Pre-training. arXiv preprint arXiv:2305.10688","author":"Liu Zequn","year":"2023","unstructured":"Zequn Liu, Wei Zhang, Yingce Xia, Lijun Wu, Shufang Xie, Tao Qin, Ming Zhang, and Tie-Yan Liu. 2023 d. MolXPT: Wrapping Molecules with Text for Generative Pre-training. arXiv preprint arXiv:2305.10688 (2023)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.447"},{"key":"e_1_3_2_2_38_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2018","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_39_1","volume-title":"Molfm: A multimodal molecular foundation model. arXiv preprint arXiv:2307.09484","author":"Luo Yizhen","year":"2023","unstructured":"Yizhen Luo, Kai Yang, Massimo Hong, Xingyi Liu, and Zaiqing Nie. 2023. Molfm: A multimodal molecular foundation model. arXiv preprint arXiv:2307.09484 (2023)."},{"key":"e_1_3_2_2_40_1","volume-title":"Biomedgpt: Open multimodal generative pre-trained transformer for biomedicine. arXiv preprint arXiv:2308.09442","author":"Luo Yizhen","year":"2023","unstructured":"Yizhen Luo, Jiahuan Zhang, Siqi Fan, Kai Yang, Yushuai Wu, Mu Qiao, and Zaiqing Nie. 2023. Biomedgpt: Open multimodal generative pre-trained transformer for biomedicine. arXiv preprint arXiv:2308.09442 (2023)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557401"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1075\/li.30.1.03nad"},{"key":"e_1_3_2_2_44_1","volume-title":"Improving few-shot performance of language models via nearest neighbor calibration. arXiv preprint arXiv:2212.02216","author":"Nie Feng","year":"2022","unstructured":"Feng Nie, Meixi Chen, Zhirui Zhang, and Xu Cheng. 2022. Improving few-shot performance of language models via nearest neighbor calibration. arXiv preprint arXiv:2212.02216 (2022)."},{"key":"e_1_3_2_2_45_1","unstructured":"OpenAI. 2022. Introducing chatgpt. https:\/\/doi.org\/blog\/chatgpt"},{"key":"e_1_3_2_2_47_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318."},{"key":"e_1_3_2_2_48_1","volume-title":"BioT5: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning. arXiv preprint arXiv:2402.17810","author":"Pei Qizhi","year":"2024","unstructured":"Qizhi Pei, Lijun Wu, Kaiyuan Gao, Xiaozhuan Liang, Yin Fang, Jinhua Zhu, Shufang Xie, Tao Qin, and Rui Yan. 2024. BioT5: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning. arXiv preprint arXiv:2402.17810 (2024)."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.70"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.260"},{"key":"e_1_3_2_2_51_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_52_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. [n. d.]. Improving language understanding by generative pre-training. ( [n. d.])."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"crossref","unstructured":"Guillaume Richard Bernardo P de Almeida Hugo Dalla-Torre Christopher Blum Lorenz Hexemer Priyanka Pandey Stefan Laurent Marie P Lopez Alexander Laterre Maren Lang et al. 2024. ChatNT: A Multimodal Conversational Agent for DNA RNA and Protein Tasks. bioRxiv (2024) 2024--04.","DOI":"10.1101\/2024.04.30.591835"},{"key":"e_1_3_2_2_55_1","volume-title":"Enhancing activity prediction models in drug discovery with the ability to understand human language. arXiv preprint arXiv:2303.03363","author":"Seidl Philipp","year":"2023","unstructured":"Philipp Seidl, Andreu Vall, Sepp Hochreiter, and G\u00fcnter Klambauer. 2023. Enhancing activity prediction models in drug discovery with the ability to understand human language. arXiv preprint arXiv:2303.03363 (2023)."},{"key":"e_1_3_2_2_56_1","volume-title":"Computational methods in drug discovery. Pharmacological reviews","author":"Sliwoski Gregory","year":"2014","unstructured":"Gregory Sliwoski, Sandeepkumar Kothiwale, Jens Meiler, and Edward W Lowe. 2014. Computational methods in drug discovery. Pharmacological reviews, Vol. 66, 1 (2014), 334--395."},{"key":"e_1_3_2_2_57_1","volume-title":"International Conference on Machine Learning. PMLR","author":"St\u00e4rk Hannes","year":"2022","unstructured":"Hannes St\u00e4rk, Dominique Beaini, Gabriele Corso, Prudencio Tossou, Christian Dallago, Stephan G\u00fcnnemann, and Pietro Li\u00f2. 2022. 3d infomax improves gnns for molecular property prediction. In International Conference on Machine Learning. PMLR, 20479--20502."},{"key":"e_1_3_2_2_58_1","volume-title":"A molecular multimodal foundation model associating molecule graphs with natural language. arXiv preprint arXiv:2209.05481","author":"Su Bing","year":"2022","unstructured":"Bing Su, Dazhao Du, Zhao Yang, Yujie Zhou, Jiangmeng Li, Anyi Rao, Hao Sun, Zhiwu Lu, and Ji-Rong Wen. 2022. A molecular multimodal foundation model associating molecule graphs with natural language. arXiv preprint arXiv:2209.05481 (2022)."},{"key":"e_1_3_2_2_59_1","volume-title":"Generative pretraining in multimodality. arXiv preprint arXiv:2307.05222","author":"Sun Quan","year":"2023","unstructured":"Quan Sun, Qiying Yu, Yufeng Cui, Fan Zhang, Xiaosong Zhang, Yueze Wang, Hongcheng Gao, Jingjing Liu, Tiejun Huang, and Xinlong Wang. 2023. Generative pretraining in multimodality. arXiv preprint arXiv:2307.05222 (2023)."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-016-0123-9"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-014-0037-3"},{"key":"e_1_3_2_2_62_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.2174\/157489012799362377"},{"key":"e_1_3_2_2_64_1","volume-title":"From molecules to scaffolds to functional groups: building context-dependent molecular representation via multi-channel learning. arXiv preprint arXiv:2311.02798","author":"Wan Yue","year":"2023","unstructured":"Yue Wan, Jialu Wu, Tingjun Hou, Chang-Yu Hsieh, and Xiaowei Jia. 2023. From molecules to scaffolds to functional groups: building context-dependent molecular representation via multi-channel learning. arXiv preprint arXiv:2311.02798 (2023)."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00360"},{"key":"e_1_3_2_2_66_1","volume-title":"Language models as knowledge embeddings. arXiv preprint arXiv:2206.12617","author":"Wang Xintao","year":"2022","unstructured":"Xintao Wang, Qianyu He, Jiaqing Liang, and Yanghua Xiao. 2022. Language models as knowledge embeddings. arXiv preprint arXiv:2206.12617 (2022)."},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00447-x"},{"key":"e_1_3_2_2_68_1","volume-title":"A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382","author":"White Jules","year":"2023","unstructured":"Jules White, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, and Douglas C Schmidt. 2023. A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382 (2023)."},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"crossref","unstructured":"David S Wishart Yannick D Feunang An C Guo Elvis J Lo Ana Marcu Jason R Grant Tanvir Sajed Daniel Johnson Carin Li Zinat Sayeeda et al. 2018. DrugBank 5.0: a major update to the DrugBank database for 2018. Nucleic acids research Vol. 46 D1 (2018) D1074--D1082.","DOI":"10.1093\/nar\/gkx1037"},{"key":"e_1_3_2_2_70_1","volume-title":"MoleculeNet: a benchmark for molecular machine learning. Chemical science","author":"Wu Zhenqin","year":"2018","unstructured":"Zhenqin Wu, Bharath Ramsundar, Evan N Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S Pappu, Karl Leswing, and Vijay Pande. 2018. MoleculeNet: a benchmark for molecular machine learning. Chemical science, Vol. 9, 2 (2018), 513--530."},{"key":"e_1_3_2_2_71_1","volume-title":"International Conference on Learning Representations.","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How Powerful are Graph Neural Networks?. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_72_1","volume-title":"International Conference on Machine Learning. PMLR, 38749--38767","author":"Xu Minghao","year":"2023","unstructured":"Minghao Xu, Xinyu Yuan, Santiago Miret, and Jian Tang. 2023. Protst: Multi-modality learning of protein sequences and biomedical texts. In International Conference on Machine Learning. PMLR, 38749--38767."},{"key":"e_1_3_2_2_73_1","volume-title":"Graph contrastive learning with augmentations. Advances in neural information processing systems","author":"You Yuning","year":"2020","unstructured":"Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. 2020. Graph contrastive learning with augmentations. Advances in neural information processing systems, Vol. 33 (2020), 5812--5823."},{"key":"e_1_3_2_2_74_1","volume-title":"A deep-learning system bridging molecule structure and biomedical text with comprehension comparable to human professionals. Nature communications","author":"Zeng Zheni","year":"2022","unstructured":"Zheni Zeng, Yuan Yao, Zhiyuan Liu, and Maosong Sun. 2022. A deep-learning system bridging molecule structure and biomedical text with comprehension comparable to human professionals. Nature communications, Vol. 13, 1 (2022), 862."},{"key":"e_1_3_2_2_75_1","volume-title":"Interactive Molecular Discovery with Natural Language. arXiv preprint arXiv:2306.11976","author":"Zeng Zheni","year":"2023","unstructured":"Zheni Zeng, Bangchen Yin, Shipeng Wang, Jiarui Liu, Cheng Yang, Haishen Yao, Xingzhi Sun, Maosong Sun, Guotong Xie, and Zhiyuan Liu. 2023. Interactive Molecular Discovery with Natural Language. arXiv preprint arXiv:2306.11976 (2023)."},{"key":"e_1_3_2_2_76_1","volume-title":"OntoProtein: Protein Pretraining With Gene Ontology Embedding. In International Conference on Learning Representations.","author":"Zhang Ningyu","year":"2021","unstructured":"Ningyu Zhang, Zhen Bi, Xiaozhuan Liang, Siyuan Cheng, Haosen Hong, Shumin Deng, Qiang Zhang, Jiazhang Lian, and Huajun Chen. 2021. OntoProtein: Protein Pretraining With Gene Ontology Embedding. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_77_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zhao Haiteng","year":"2024","unstructured":"Haiteng Zhao, Shengchao Liu, Ma Chang, Hannan Xu, Jie Fu, Zhihong Deng, Lingpeng Kong, and Qi Liu. 2024. Gimlet: A unified graph-text model for instruction-based molecule zero-shot learning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_78_1","volume-title":"LangCell: Language-Cell Pre-training for Cell Identity Understanding. arXiv preprint arXiv:2405.06708","author":"Zhao Suyuan","year":"2024","unstructured":"Suyuan Zhao, Jiahuan Zhang, Yizhen Luo, Yushuai Wu, and Zaiqing Nie. 2024. LangCell: Language-Cell Pre-training for Cell Identity Understanding. arXiv preprint arXiv:2405.06708 (2024)."},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.08.014"},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"crossref","unstructured":"Gengmo Zhou Zhifeng Gao Qiankun Ding Hang Zheng Hongteng Xu Zhewei Wei Linfeng Zhang and Guolin Ke. 2023. Uni-Mol: a universal 3D molecular representation learning framework. (2023).","DOI":"10.26434\/chemrxiv-2022-jjm0j-v4"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539368"},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599317"}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3672043","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3672043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:23Z","timestamp":1750291463000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3672043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":81,"alternative-id":["10.1145\/3637528.3672043","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3672043","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}