{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/predicting-organic-reaction-outcomes-with","title":"Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network","arxiv_id":"1709.04555","date":"2017-09-13","proceeding":"NeurIPS 2017 12","authors":["Wengong Jin","Connor W. Coley","Regina Barzilay","Tommi Jaakkola"],"abstract":"The prediction of organic reaction outcomes is a fundamental problem in\ncomputational chemistry. Since a reaction may involve hundreds of atoms, fully\nexploring the space of possible transformations is intractable. The current\nsolution utilizes reaction templates to limit the space, but it suffers from\ncoverage and efficiency issues. In this paper, we propose a template-free\napproach to efficiently explore the space of product molecules by first\npinpointing the reaction center -- the set of nodes and edges where graph edits\noccur. Since only a small number of atoms contribute to reaction center, we can\ndirectly enumerate candidate products. The generated candidates are scored by a\nWeisfeiler-Lehman Difference Network that models high-order interactions\nbetween changes occurring at nodes across the molecule. Our framework\noutperforms the top-performing template-based approach with a 10\\% margin,\nwhile running orders of magnitude faster. Finally, we demonstrate that the\nmodel accuracy rivals the performance of domain experts.","url_abs":"http://arxiv.org/abs/1709.04555v3","url_pdf":"http://arxiv.org/pdf/1709.04555v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"predicting-organic-reaction-outcomes-with","repo_url":"https://github.com/wengong-jin/nips17-rexgen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"computational-chemistry","task_name":"Computational chemistry"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.04555","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}