{"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/conditional-molecular-design-with-deep","title":"Conditional molecular design with deep generative models","arxiv_id":"1805.00108","date":"2018-04-30","proceeding":null,"authors":["Seokho Kang","Kyunghyun Cho"],"abstract":"Although machine learning has been successfully used to propose novel\nmolecules that satisfy desired properties, it is still challenging to explore a\nlarge chemical space efficiently. In this paper, we present a conditional\nmolecular design method that facilitates generating new molecules with desired\nproperties. The proposed model, which simultaneously performs both property\nprediction and molecule generation, is built as a semi-supervised variational\nautoencoder trained on a set of existing molecules with only a partial\nannotation. We generate new molecules with desired properties by sampling from\nthe generative distribution estimated by the model. We demonstrate the\neffectiveness of the proposed model by evaluating it on drug-like molecules.\nThe model improves the performance of property prediction by exploiting\nunlabeled molecules, and efficiently generates novel molecules fulfilling\nvarious target conditions.","url_abs":"http://arxiv.org/abs/1805.00108v3","url_pdf":"http://arxiv.org/pdf/1805.00108v3.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":"conditional-molecular-design-with-deep","repo_url":"https://github.com/nyu-dl/conditional-molecular-design-ssvae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"conditional-molecular-design-with-deep","repo_url":"https://github.com/AustinApple/SSVAE-for-electrolyte-molecule-design","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"conditional-molecular-design-with-deep","repo_url":"https://github.com/gcolmenarejo/cmd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"conditional-molecular-design-with-deep","repo_url":"https://github.com/sraghavan0610/SSVAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"property-prediction","task_name":"Property Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.00108","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}