{"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/chemformer-a-pre-trained-transformer-for","title":"Chemformer: a pre-trained transformer for computational chemistry","arxiv_id":null,"date":"2022-01-31","proceeding":"Machine Learning: Science and Technology 2022 1","authors":["Ross Irwin","Spyridon Dimitriadis","Jiazhen He","Esben Jannik Bjerrum"],"abstract":"Transformer models coupled with a simplified molecular line entry system (SMILES) have recently proven to be a powerful combination for solving challenges in cheminformatics. These models, however, are often developed specifically for a single application and can be very resource-intensive to train. In this work we present the Chemformer model—a Transformer-based model which can be quickly applied to both sequence-to-sequence and discriminative cheminformatics tasks. Additionally, we show that self-supervised pre-training can improve performance and significantly speed up convergence on downstream tasks. On direct synthesis and retrosynthesis prediction benchmark datasets we publish state-of-the-art results for top-1 accuracy. We also improve on existing approaches for a molecular optimisation task and show that Chemformer can optimise on multiple discriminative tasks simultaneously. Models, datasets and code will be made available after publication.","url_abs":"https://iopscience.iop.org/article/10.1088/2632-2153/ac3ffb","url_pdf":"https://iopscience.iop.org/article/10.1088/2632-2153/ac3ffb/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":"chemformer-a-pre-trained-transformer-for","repo_url":"https://github.com/MolecularAI/Chemformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"computational-chemistry","task_name":"Computational chemistry"},{"task_slug":"retrosynthesis","task_name":"Retrosynthesis"},{"task_slug":"single-step-retrosynthesis","task_name":"Single-step retrosynthesis"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/single-step-retrosynthesis-on-uspto-50k","task":"Single-step retrosynthesis","dataset":"USPTO-50k","model":"Chemformer-Large (reaction class unknown)","rank_in_archive_order":17,"of":35,"metrics":{"Top-1 accuracy":"54.3","Top-10 accuracy":"63.0","Top-5 accuracy":"62.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}