{"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-modal-molecule-structure-text-model-for","title":"Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing","arxiv_id":"2212.10789","date":"2022-12-21","proceeding":null,"authors":["Shengchao Liu","Weili Nie","Chengpeng Wang","Jiarui Lu","Zhuoran Qiao","Ling Liu","Jian Tang","Chaowei Xiao","Anima Anandkumar"],"abstract":"There is increasing adoption of artificial intelligence in drug discovery. However, existing studies use machine learning to mainly utilize the chemical structures of molecules but ignore the vast textual knowledge available in chemistry. Incorporating textual knowledge enables us to realize new drug design objectives, adapt to text-based instructions and predict complex biological activities. Here we present a multi-modal molecule structure-text model, MoleculeSTM, by jointly learning molecules' chemical structures and textual descriptions via a contrastive learning strategy. To train MoleculeSTM, we construct a large multi-modal dataset, namely, PubChemSTM, with over 280,000 chemical structure-text pairs. To demonstrate the effectiveness and utility of MoleculeSTM, we design two challenging zero-shot tasks based on text instructions, including structure-text retrieval and molecule editing. MoleculeSTM has two main properties: open vocabulary and compositionality via natural language. In experiments, MoleculeSTM obtains the state-of-the-art generalization ability to novel biochemical concepts across various benchmarks.","url_abs":"https://arxiv.org/abs/2212.10789v3","url_pdf":"https://arxiv.org/pdf/2212.10789v3.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-modal-molecule-structure-text-model-for","repo_url":"https://github.com/chao1224/moleculestm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"drug-design","task_name":"Drug Design"},{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.10789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10789"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chao1224/moleculestm","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"b822dd00427403bf","entry":"cycle_index","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b822dd00427403bf"}},{"code_sha256_prefix":"f85c5a6e56afd7f0","entry":"do_CL","repo":"chao1224/moleculestm","repo_kind":"official","path":"scripts/pretrain.py","file_url":"https://github.com/chao1224/moleculestm/blob/HEAD/scripts/pretrain.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f85c5a6e56afd7f0"}},{"code_sha256_prefix":"c8d7df8385819994","entry":"do_CL_eval","repo":"chao1224/moleculestm","repo_kind":"official","path":"scripts/downstream_01_retrieval_ATC.py","file_url":"https://github.com/chao1224/moleculestm/blob/HEAD/scripts/downstream_01_retrieval_ATC.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c8d7df8385819994"}},{"code_sha256_prefix":"eb6e3f5f75df6140","entry":"use_model_module","repo":"chao1224/moleculestm","repo_kind":"official","path":"MoleculeSTM/models/mega_molbart/mega_mol_bart.py","file_url":"https://github.com/chao1224/moleculestm/blob/HEAD/MoleculeSTM/models/mega_molbart/mega_mol_bart.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"eb6e3f5f75df6140"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}