{"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/multi-objective-de-novo-drug-design-with","title":"Multi-Objective De Novo Drug Design with Conditional Graph Generative Model","arxiv_id":"1801.07299","date":"2018-01-18","proceeding":null,"authors":["Yibo Li","Liangren Zhang","Zhenming Liu"],"abstract":"Recently, deep generative models have revealed itself as a promising way of\nperforming de novo molecule design. However, previous research has focused\nmainly on generating SMILES strings instead of molecular graphs. Although\ncurrent graph generative models are available, they are often too general and\ncomputationally expensive, which restricts their application to molecules with\nsmall sizes. In this work, a new de novo molecular design framework is proposed\nbased on a type sequential graph generators that do not use atom level\nrecurrent units. Compared with previous graph generative models, the proposed\nmethod is much more tuned for molecule generation and have been scaled up to\ncover significantly larger molecules in the ChEMBL database. It is shown that\nthe graph-based model outperforms SMILES based models in a variety of metrics,\nespecially in the rate of valid outputs. For the application of drug design\ntasks, conditional graph generative model is employed. This method offers\nhigher flexibility compared to previous fine-tuning based approach and is\nsuitable for generation based on multiple objectives. This approach is applied\nto solve several drug design problems, including the generation of compounds\ncontaining a given scaffold, generation of compounds with specific\ndrug-likeness and synthetic accessibility requirements, as well as generating\ndual inhibitors against JNK3 and GSK3$\\beta$. Results show high enrichment\nrates for outputs satisfying the given requirements.","url_abs":"http://arxiv.org/abs/1801.07299v3","url_pdf":"http://arxiv.org/pdf/1801.07299v3.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":"multi-objective-de-novo-drug-design-with","repo_url":"https://github.com/kevinid/molecule_generator","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"drug-design","task_name":"Drug Design"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.07299","atlas_url":"https://app.syntology.ai/?focus=1801.07299","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}