{"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/retrocomposer-discovering-novel-reactions-by","title":"RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction","arxiv_id":"2112.11225","date":"2021-12-20","proceeding":null,"authors":["Chaochao Yan","Peilin Zhao","Chan Lu","Yang Yu","Junzhou Huang"],"abstract":"The main target of retrosynthesis is to recursively decompose desired molecules into available building blocks. Existing template-based retrosynthesis methods follow a template selection stereotype and suffer from limited training templates, which prevents them from discovering novel reactions. To overcome this limitation, we propose an innovative retrosynthesis prediction framework that can compose novel templates beyond training templates. As far as we know, this is the first method that uses machine learning to compose reaction templates for retrosynthesis prediction. Besides, we propose an effective reactant candidate scoring model that can capture atom-level transformations, which helps our method outperform previous methods on the USPTO-50K dataset. Experimental results show that our method can produce novel templates for 15 USPTO-50K test reactions that are not covered by training templates. We have released our source implementation.","url_abs":"https://arxiv.org/abs/2112.11225v2","url_pdf":"https://arxiv.org/pdf/2112.11225v2.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":"retrocomposer-discovering-novel-reactions-by","repo_url":"https://github.com/uta-smile/retrocomposer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"retrosynthesis","task_name":"Retrosynthesis"},{"task_slug":"single-step-retrosynthesis","task_name":"Single-step retrosynthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/single-step-retrosynthesis-on-uspto-50k","task":"Single-step retrosynthesis","dataset":"USPTO-50k","model":"RetroComposer (reaction class as prior)","rank_in_archive_order":4,"of":35,"metrics":{"Top-1 accuracy":"65.9","Top-10 accuracy":"91.5","Top-3 accuracy":"85.8","Top-5 accuracy":"89.5"},"uses_additional_data":false},{"leaderboard":"/sota/single-step-retrosynthesis-on-uspto-50k","task":"Single-step retrosynthesis","dataset":"USPTO-50k","model":"RetroComposer (reaction class unknown)","rank_in_archive_order":16,"of":35,"metrics":{"Top-1 accuracy":"54.4","Top-10 accuracy":"87.7","Top-3 accuracy":"77.2","Top-5 accuracy":"83.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.11225","atlas_url":"https://app.syntology.ai/?focus=2112.11225","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}